Network Video Recorders

The new AIE-VN34/44 and AIE-VO24/34 combine up to 100 TOPS of AI performance, four GMSL2 camera connections, and fanless rugged operation for transportation, AMR, and industrial automation applications. Aetina Corporation, a pioneer AI solution provider and an accelerator of edge AI infrastructure, announces the DeviceEdge AIE-VN34/44 and AIE-VO24/34, Aetina’s first palm-sized in-vehicle edge AI systems, powered by NVIDIA Jetson Orin NX and NVIDIA Jetson Orin Nano modules. Delivering up to 100 TOPS of AI performance and supporting up to four GMSL2 cameras in an ultra-compact, rugged form factor, the new systems are ready for mass production and target smart transportation, autonomous mobile robots (AMR), and industrial automation deployments where space and reliability are equally critical. Industrial automation deployments As AI-powered vision systems become increasingly essential across smart cities, intelligent transportation, and industrial automation, real-time processing of high-quality, multi-camera video streams within space-constrained environments remains a persistent challenge. The AIE-VN34/44 and AIE-VO24/34 address this directly: powered by NVIDIA Jetson Orin NX (8GB/16GB) and NVIDIA Jetson Orin Nano with Super Mode (4GB/8GB), the systems deliver up to 100 TOPS and 67 TOPS of AI performance respectively, packed into a palm-sized 136.3 x 132 x 63 mm chassis. Each system features four GMSL2 (Fakra-Z) ports, enabling long-distance, low-latency multi-camera streaming, real-time AI inference, and 360-degree environmental perception for surround-view monitoring, blind-spot detection, and situational awareness. Long-distance image transmission To accelerate system integration, the AIE-VN34/44 and AIE-VO24/34 can be flexibly expanded with Aetina validated GMSL2 adapter boards and camera modules, which support with plug-and-play driver-ready for long-distance image transmission of up to 15 meters. This bundle offering brings together camera sensing, high-speed visual data transmission, and NVIDIA Jetson Orin–powered edge inference, helping customers simplify system integration, shorten development and validation cycles, and achieve highly scalable, customisable AI deployment. Automotive electronic equipment Engineered for demanding mobile and industrial applications, the AIE-VN34/44 and AIE-VO24/34 pair rugged reliability with flexible connectivity. Both systems have passed MIL-STD-810H shock and vibration testing and carry E-Mark (E24) certification for automotive electronic equipment, streamlining integration into global vehicle markets. A fanless architecture supports stable, throttle-free operation from -25°C to +55°C, while a 9–36V DC wide-voltage input and integrated Ignition Power Control protect against voltage fluctuations and enable safe startup and shutdown. Isolated CAN FD and GPIO/RS-232 interfaces connect vehicle signals, controllers, sensors, and industrial peripherals, complemented by Gigabit Ethernet (GbE), USB 3.2, HDMI, M.2 M-Key storage, and optional M.2 E-Key wireless expansion. Actionable intelligence for AI agents The convergence of V2X and edge computing continues to drive demand for compact, rugged in-vehicle computing platforms that capable of processing multi-camera vision data locally and in real time. The AIE-VN34/44 and AIE-VO24/34 turn visual data into actionable intelligence for AI agents and autonomous systems, supporting surround-view monitoring and blind-spot detection for commercial vehicles, obstacle avoidance and path planning for AMRs, real-time defect inspection on production lines, and people tracking and security monitoring across smart retail and building environments. AI computing portfolio James Ho, Manager of Edge Computing Product Division at Aetina, stated: “As real-time, multi-camera perception becomes the sensing layer for AI agents operating in vehicles, AMRs, and industrial equipment, customers need edge compute that is rugged enough for the field and ready for mass production from day one, Aetina’s palm-sized in-vehicle edge AI systems bring four-camera GMSL2 support, automotive-grade certification, and NVIDIA Elite Partner-backed BSP support together in one rugged multi-vision platform, helping customers simplify integration and accelerate the deployment of intelligent vision at the edge.” The AIE-VN34/44 and AIE-VO24/34 are available now for mass production, supporting BSP built on NVIDIA JetPack 6.2, with NVIDIA JetPack 7.2 support to be added soon. 

Modern buildings are placing ever-increasing demands on door communication systems. Property owners, operators, and residents require intelligent solutions that accommodate different user groups, support flexible access methods, and meet high standards for security, connectivity, and integration. With the new D22x series, DoorBird introduces a new generation of IP video door intercoms. Developed based on specific customer requirements, the series combines cutting-edge technology, exceptional flexibility, premium design, and Made in Germany quality. As part of the ASSA ABLOY Group, the global pioneer in access solutions, DoorBird combines innovative IP-based door communication with extensive expertise in modern building security. Challenging lighting conditions The D22x series comprises more than 30 models and is the direct successor to the globally successful D21x Series. New additions to the portfolio include versions with digital nameplates, which can be managed centrally and remotely, offering significant advantages for property managers, housing associations, and operators of larger buildings. All models feature a 5 MP HDR camera with a Sony image sensor and a 180° ultra-wide-angle lens, providing excellent visibility of the entrance area even under challenging lighting conditions. Video transmission is available in HD quality via the local network or through DoorBird Cloud Pro. Outstanding audio performance ensures clear and intelligible communication between visitors and residents, even in demanding environments. Depending on the model, a variety of authentication methods are available, including the app, dual-frequency RFID, Bluetooth, PIN code, QR code, and fingerprint recognition. The security concept is further enhanced by a radar-based 4D motion sensor and an integrated tamper sensor. Comprehensively documented LAN With the D22x series, DoorBird also simplifies installation. Thanks to the integrated power output for electric door openers, many installations no longer require a separate power supply for the door release mechanism. This reduces cabling complexity, saves installation time, and lowers overall system costs. Open interfaces such as SIP, OSDP, RS485, and Wiegand, along with a comprehensively documented LAN and Cloud API, enable integration with more than 100 smart homes, access control, video surveillance, and building management systems. Building management systems The door station supports installations with up to 3,000 residential or office units. In addition to traditional call buttons, digital nameplates and displays with resident directories are available. Accessibility features can be added to every model, including an integrated hearing loop, pictograms, and acoustic door-opening confirmation signals. As an ISO/IEC 27001-certified company, DoorBird incorporates privacy and information security throughout the development process in accordance with the Security by Design principle. The D22x series offers a particularly cost-effective way to modernise existing DoorBird D21x installations. When upgrading, only the main electronic unit needs to be replaced. Existing housings, front panels, and other components can continue to be used, while all existing settings can be retained. This significantly reduces installation effort and contributes to environmental sustainability. Prestigious commercial properties In addition to technology, design plays a central role. More than 50 finishes and color options allow seamless integration into a wide variety of architectural concepts, from private residences to prestigious commercial properties. Using the DoorBird 3D Configurator, customers can customise the D22x series to their individual requirements. Front panel size and shape, engravings, mailboxes, and the integration of reader units from leading manufacturers can all be configured with maximum flexibility. “Modern buildings require solutions that can adapt flexibly while remaining easy to integrate,” says Sascha Keller, Founder and CEO of DoorBird. “With the D22x series, we provide a future-proof platform that combines powerful door communication, flexible access solutions, and sophisticated design Made in Germany.”

March Networks®, a pioneer in video surveillance and business intelligence, announces its 2026 mid-year product release, introducing expanded AI-powered search, new cloud video intelligence, broader VIVOTEK camera support and integration with C•CURE access control. The release is the first since the April 2026 merger of VIVOTEK’s branded business with March Networks. It marks the introduction of Connected Intelligence for Modern Security, the company's strategic approach to connecting video, data and AI across every system and site. Cloud video intelligence Organisations already capture vast amounts of video, operational data and security information. The challenge is making those systems work together. When information remains isolated, important patterns, risks, and opportunities can go unseen. March Networks connects video, data and AI to reveal what matters, helping customers investigate faster, uncover hidden patterns and act with greater confidence. “Customers do not need more disconnected systems or more data. They need the intelligence that comes when video, data and AI work together,” said Peter Strom, President and CEO of the combined March Networks and VIVOTEK organisation. “This release advances the March Networks solutions our customers use today, and creates more ways to connect cameras, access control, business systems and VIVOTEK technologies. It is an important step in our broader vision for connected, intelligent businesses.” Patterns and opportunities Connected Intelligence for Modern Security defines how March Networks and VIVOTEK bring video, data and AI together to surface what matters across every system, sensor and site. At the center of this approach is a clear promise: Connecting cameras, operational data, AI and workflows through one intelligence layer helps organisations uncover risks, patterns and opportunities that isolated systems often miss. The strategic approach is built on three pillars: Connect the Ecosystem - Every camera. Every system. Every site.               Connect cameras, access control, third-party systems, devices, data sources and workflows to reduce fragmentation across the environments customers already manage. Turn Sight into Insight - AI that reveals hidden patterns. AI-powered search, analytics and reporting help businesses find, validate and act on critical evidence and operational insights faster. Extend Intelligence Everywhere - From one site to thousands. On-Premise. Hybrid. Cloud. Connected solutions make intelligence accessible across roles, sites, devices and operating environments, allowing customers to deploy and scale technology based on their security, operational and infrastructure needs. Together, these pillars connect physical security, operations and intelligence at enterprise scale, helping customers move from sight to insight, faster action and better business results. The 2026 mid-year release expands March Networks and VIVOTEK's end-to-end portfolio across enterprise video management, business intelligence, AI-powered investigation, cloud services and third-party system integration. These capabilities put Connected Intelligence for Modern Security into action today and set the direction for what comes next. Enterprise video management “We have seen firsthand what's possible when customers connect video, AI, transactions and operational data,” said Strom. “For example, these connections helped a large retail organisation uncover nearly $1 million in organised retail fraud that traditional reporting and manual video review had missed. When intelligence is connected and systems work together, hidden losses become visible, investigations become faster and data becomes decisive.” Get faster answers at no extra cost with Searchlight AI, now included for all Searchlight Cloud users. Spot trends and act sooner with AI-powered, on-demand analysis of business data tied to video. Find critical evidence faster with expanded face and license plate search across compatible devices. Expand camera choice and flexibility with broader VIVOTEK support across March Networks environments. Unlock business intelligence for direct-to-cloud video with the new VIVOTEK VORTEX and Searchlight Cloud integration. Investigate access events faster by connecting C•CURE access control with March Networks Command Enterprise Software. Demonstrating product capabilities Together, these capabilities expand the devices, systems, data sources, deployment models and workflows customers can connect across their security environments. March Networks will bring Connected Intelligence for Modern Security to life by showcasing its newest solutions with VIVOTEK at Global Security Exchange, GSX 2026, taking place September 14–16 in Atlanta, Georgia. March Networks and VIVOTEK will also demonstrate product capabilities, connected workflows and ongoing technology integration at the 2026 Security Exhibition & Conference, taking place September 2–4 in Sydney, Australia. Attendees will see how connected video, data and AI help operators act on what matters across retail, banking and enterprise environments, from a single location to thousands of sites.

A critical infrastructure security system unifies high-assurance access control, scalable intrusion detection including video verification, perimeter protection, and lone worker safety into a single platform, helping operators of electricity, water, and gas networks protect distributed sites, support regulatory compliance, and maintain the uninterrupted delivery of essential services.  A loss of these services disrupts economies and endangers communities, which makes protecting them a national priority. It's also uniquely difficult, because critical infrastructure is rarely a single site. It's a distributed network of substations, treatment plants, and pipelines, often spread across vast and remote geographies.  Most demanding environments That challenge is now backed by strict regulations across in all sectors including energy, water, and sewerage. Responsible entities must maintain a Critical Infrastructure Risk Management Program that addresses physical security alongside cyber, personnel, and supply chain hazards. For operators, strong physical security systems have become a compliance necessity. For over 38 years, Inner Range has purpose-built security solutions alongside critical infrastructure experts, protecting these vital assets with a multi-layered approach designed for the most demanding environments.  Multi-factor authentication Access control is the foundation. Inner Range ensures only authorised personnel reach a site, using access cards, mobile credentials, PINs, or biometric authentication. Multi-factor authentication combines these methods for stronger protection, while video surveillance, granular scheduling, and real-time logging give operators complete visibility over every access point.  The highest-risk zones demand more. Inner Range's High-Security solution has attained Class 5 accreditation which is the highest classification for intruder alarm systems under the Australian and New Zealand standard AS/NZS 2201.1, built for Zone 3 high security environments. Where traditional alarms focus only on external intruders, Class 5 also defends against insider tampering, through two-factor disarming, faster polling, and end-to-end encryption. Inner Range’s High Security solution has also been deployed to secure defence sites and critical infrastructure throughout Europe, the Middle East and the America’s. Advanced video analytics For operators, this means genuine assurance. Every detector, cable, and message is encrypted, from the edge device right through to the control panel, so the system can be trusted to detect and report a breach even when someone is actively trying to defeat it.  For most sites, the perimeter is the first line of defence. Inner Range provides advanced video analytics for intruder detection that can scale across thousands of locations. Integrations with perimeter devices such as electric fences, beams, and other detection technologies provide the physical additional layers of perimeter security for large areas. Whether the protected area is an open expanse or a small building, smart analytics enable instant, automated threat responses. Distance is no barrier. The Multipath IP Cellular communication platform uses the internet and 4G cellular networks to transmit encrypted alarm messages to monitoring center's, ensuring first responders can act quickly no matter how remote the site.  Video surveillance systems Critical infrastructure work often happens at remote and dangerous sites where, sometimes, people work alone. Protecting these workers is both an operational and a duty-of-care priority. Inner Range supports duress alarms from fixed or mobile systems that integrate with lone worker systems featuring man-down detection and personal tracking. When an alarm is raised, guards and staff are notified instantly through the Communicator messaging application via SMS and email, while Real-Time Location Systems pinpoint personnel on site for a faster response and video surveillance systems provide the eyes and ears on the situation. Specialised key locking A single utility can span hundreds of sites and dozens of subsystems. Inner Range's Enterprise platform unifies access control, video surveillance, building management, intercom, environmental monitoring, and specialised key locking, all into one interface. Operators get a single platform to monitor people, assets, machinery, and site conditions, and to respond to incidents in real time. This centralised oversight is what turns a sprawling, complex estate into something manageable, visible, and defensible.  Unifying access control The real strength is in how the layers work together. Access control, video surveillance, intruder detection, perimeter sensors, facial recognition, location tracking, and lone worker safety operate as one coordinated system through a single pane of glass to detect, locate, and respond to threats automatically. Alerting the right people the moment an incident occurs.  Every deployment is backed by professional support, from software maintenance and cyber security updates to remote assistance and custom integration. With over 130 native integrations and more than 170,000 systems deployed globally, the platform scales from a single facility to a national network.  The infrastructure a nation relies on cannot afford gaps or guesswork. By unifying access control, video surveillance, intrusion detection, perimeter protection, and worker safety into one coordinated platform, Inner Range helps operators protect what matters most, and keep essential services running, from the core to the edge. 

IQSIGHT, formerly Bosch Video Systems and a pioneer in intelligence-first video security, today announced the release of the AUTODOME 7100s and AUTODOME 7100s IR. Designed for outdoor environments, the new pan-tilt-zoom (PTZ) cameras deliver clear images in all lighting conditions and built-in video analytics to secure critical assets day or night. The AUTODOME 7100s series addresses complex surveillance challenges across smart cities, transportation networks, critical infrastructure, and government facilities. Built on IQSIGHT’s intelligence-first platform, both models offer AI-enabled video analytics for precise detection while reducing false positives and are ready for context-aware GenAI capabilities available later this year. Real-world conditions Built for consistent results in real-world conditions and intelligence at the edge, key features of the AUTODOME 7100s series include: Detailed 4MP Video: Capture high-resolution images with a 30x optical zoom lens for reliable object identification up to 919 feet (280 meters). Motion-optimised HDR X technology prevents motion blur and trailing artifacts on fast-moving vehicles and people, even while the camera is actively panning or tracking. Visibility in challenging light conditions: Dynamic IR illumination synchronises beam angle and intensity with the optical zoom level to deliver balanced, glare-free exposure in total darkness up to 1,804 feet (550 meters). Built-in Intelligent Video Analytics Pro (IVA Pro): Comes standard for reliable intrusion detection, alerts, and operational insights in and around buildings and along perimeters. Additional licenses support object classification and counts for a range of security and safety uses.  Robust Design for Reliable Operation: Brushless positioning motors deliver precise accuracy and Kevlar-reinforced drive belts are engineered for long-term performance.  Positional encoders ensure the camera never loses track of its position, even following power losses or exposure to excessive force. Intelligent Power Modes: Adaptive PoE Management automatically detects available power levels and scales functions, including heaters, IR operation, and pan speeds, for continuous operation on low-power infrastructure. Secure by Design: Features an onboard Secure Element 3.0 certified to Common Criteria EAL6+ and FIPS 140-3 Level 3 to protect sensitive video data.

3xLOGIC, the foremost provider of integrated and intelligent security solutions, has launched VIGIL 13.5, the latest update to its VIGIL Video Management System (VMS). The new release introduces AI Bridge and Face Recognition, allowing organisations to deploy advanced AI-powered video analytics and security intelligence without replacing existing camera infrastructure. VIGIL 13.5 has been designed to support users who wish to improve operational awareness, automate security workflows, and modernise surveillance capabilities while maximising their existing investment. AI Bridge brings AI analytics to legacy ecosystems AI Bridge is a hardware layer that runs deep learning analytics on video from existing IP cameras. It applies edge-based deep learning analytics to existing IP camera deployments, enabling standard cameras to deliver intelligent detection and real-time alerts without the cost and disruption of a complete hardware refresh. For dealers and integrators, AI Bridge creates new opportunities to bring AI capabilities into existing customer environments while reducing barriers to adoption. Organisations can extend the life of their current camera infrastructure, accelerate AI adoption, and build a future-ready surveillance strategy without undertaking costly rip-and-replace projects. AI Bridge supports a broad range of AI-powered analytics, including person, vehicle, object, perimeter and loitering detection, dwell time, people counting, and fall detection. This makes it particularly attractive to retailers, educational institutions, healthcare, hospitality and entertainment, warehouses, and smart city leaders. Object detection, for example, can help operators track unexpected vehicles on an academic campus or warehouse yard.  Fall detection ensures a quick response if a person in a clinic or resident in a care home falls, while entry and exit detection will alert to possible absconding. This ensures individuals remain safe while staff can continue their duties with peace of mind that the system will alert them to any unusual behaviour or emergencies.  In retail settings, people-counting can improve wait times and queue management in a store, ensuring a good customer experience. Intrusion detection can secure back offices and stockrooms, and dwell times can tell leaders what areas of a store are most popular.  Vendor-neutral offers greater flexibility The platform is vendor-neutral, supports mixed camera environments, and can be centrally configured through the VIGIL Server Management Utility (VSMU). Customers can also combine AI Bridge along with 3xLOGIC's Edge-Based Deep Learning cameras within a single VIGIL deployment, providing a flexible approach to modernisation across hybrid environments. Supporting proactive security VIGIL 13.5 also introduces Face Recognition capabilities to the VIGIL platform, helping security teams move beyond passive video monitoring to responsible, proactive awareness. Using edge-based AI processing, the feature allows organisations to create secure local watchlists, receive real-time alerts when persons of interest are detected, rapidly search recorded footage, and automate workflows based on facial recognition events. Designed with privacy in mind, facial recognition processing takes place at the edge, helping organisations maintain control of sensitive data while improving investigation speed, situational awareness, and employee efficiency. Part of the wider ecosystem The latest release integrates seamlessly with the wider 3xLOGIC ecosystem, including VIGIL CLOUD, PACOM VIGIL CORE and SONITROL CORE, inviting users to deploy AI analytics across on-premises, cloud and hybrid environments. AI Bridge is available as either a perpetual license for on-premise deployment or as a subscription through VIGIL CLOUD, giving customers the flexibility to align deployment with operation and budget requirements. Mike Poe, Director of Product Management at 3xLOGIC said: "AI is helping organisations unlock more value from the infrastructure they already own. Now, with VIGIL 13.5, customers can add powerful AI analytics and facial recognition to existing camera deployments without the cost and disruption of replacing their entire surveillance estate. Whether they're looking to improve security, increase efficiency or begin their AI journey, VIGIL 13.5 provides a practical and scalable path forward."

The eagerness to adopt AI in physical security is increasing as teams want to implement technology solutions for faster, smarter operations. At the same time, the conversations surrounding AI have changed. The focus now includes not only efficiency gains but also concerns about accountability and trust. According to the Genetec 2026 State of Physical Security report, AI ranked alongside access control and video surveillance as a key priority. However, approximately 40% of the over 7,000 physical security leaders surveyed expressed concern about how AI systems use their data. The potential for malicious purposes followed close behind at 36%. You may recognise this tension in your own organisation. There is an expectation that AI can help operations and an understanding that AI entails risks. Balancing the two includes careful deployment and policies. Higher stakes demand a higher standard AI can quickly spot the difference and elevate the event to the security team Most AI applications in physical security revolve around automation. Basic examples include triggering events, filtering and classifying alarms, and enabling faster searches across video and event data. These applications tackle the persistent security challenges of too much noise and too little context. AI takes on some of the lifting, cutting the false positives that overwhelm operators and adding context to the events that remain. For example, someone loitering near an entrance may not be a notable event. While someone loitering and trying door handles is a priority. AI can quickly spot the difference and elevate the event to the security team. From there, the human operator can confirm the issue and next steps. AI narrows the operator's focus rather than replacing their judgment. Higher standard of supervision While these uses improve operator efficiency, they need to be implemented responsibly. Irresponsible AI usage in physical security is more than a simple inconvenience. The outputs affect safety and security. AI applications within physical security demand a higher standard of supervision. This oversight is often referred to as “human in the loop,” but perhaps a better phrase is "expert in the loop." The person validating an output needs the knowledge to question it, contextualise it, and overrule it if needed. How to deploy responsible AI Deploying responsible AI starts by defining where AI can add value to your specific organisation Deploying responsible AI starts by defining where AI can add value to your specific organisation. AI works best as a tool with a defined job. What is the problem that needs to be solved? What challenges are holding back the team? Start by identifying the problems, then work backward to a solution. Otherwise, you may be implementing technology that doesn’t fully meet your needs. Next, define parameters around AI usage within your team. Document exactly what AI is permitted to do and not allowed to do within your operations. Information should include which use cases you've approved, what data the system can access, and how issues escalate. By defining these elements, your team has clear guidelines on when AI tools are part of your security procedures and for what purposes. Cross-functional monthly meetings Because AI can behave unpredictably, it’s good to prepare for when something does go wrong. Even a well-built model will eventually drift from its thresholds. This is where governance comes in. Governance is what keeps responsible AI holding up over time. It sets the review cycles that catch an issue before an incident does. Governance related to AI entails data privacy, liability, and regulation. Input from legal, compliance, cybersecurity, and IT teams is important. Getting these groups together starts with something as simple as cross-functional monthly meetings to review use cases and emerging challenges. Consider also working with other manufacturers, integrators, and end users across your ecosystem. In doing so, you create shared standards that make issues diagnosable. Responsible AI as a practice, not a project The goal is to protect individual rights and build trust without hampering technological advancement Responsible AI usage in security is not a box to check or a project to complete. It's an ongoing practice, especially as the compliance bar rises. As more AI security risks surface, governments are drafting legislation to regulate how organisations can develop and implement AI-enabled technology. The goal is to protect individual rights and build trust without hampering technological advancement. Identified risk category For example, the 2024 AI Act in the European Union (EU) sets obligations for various AI applications based on their identified risk category. These requirements include creating adequate risk assessments and mitigation practices, using high-quality training datasets to reduce bias, and sharing detailed documentation on models with governing authorities as needed. In the US, multiple states have implemented legislation on AI use, and national legislation has been discussed. Organisations can begin by implementing documented processes for guidelines and governance: Conduct risk assessments: Evaluate how automating a specific process may impact critical systems or safety protocols Identify non-critical applications: Start by implementing AI into processes that aren’t central to your most critical operations to curb major business disruptions Prioritise human-centred design: Ensure that AI applications always empower humans with the information they need to make the best decisions Design for explainability: Ensure AI decisions can be explained and traced, so the expert in the loop can question, verify, or overrule them when needed. Broaden data protection strategies: Apply cybersecurity measures and best practices to AI-enabled solutions, including regular audits and system updates Choose trusted vendors: Work with vendors who follow responsible AI principles, considering biases, data protection, and cybersecurity Core pillar of physical security The industry is slowly converging on shared standards for AI governance. This is good news for early adopters who wish to shape the industry rather than react to it. The potential applications of AI in security are exciting. But as this technology evolves, so do the risks. Strong governance builds trust, a core pillar of physical security. Responsible AI protects that trust and earns more of it. Start by defining your outcomes, building guardrails, and creating accountability structures to support your organisation’s responsible use of AI technology.

For years, innovation in physical security has focused on what systems can do: higher-resolution cameras, AI-driven analytics, smarter access control, and cloud-based management. But across deployments, from residential systems to enterprise campuses, a more fundamental issue continues to undermine performance: Connectivity. It is increasingly clear that the effectiveness of modern security systems is not limited by sensors or software, but by the reliability, reach, and architecture of the networks that connect them. As security systems evolve toward real-time detection, automated response, and distributed intelligence, connectivity is no longer a supporting layer. It is the foundation and, too often, the weakest link. When security design is constrained by connectivity In theory, security systems are designed to maximise visibility, coverage, and response time. In practice, they are often designed around the limitations of network infrastructure. Nowhere is this more visible than in video surveillance. Cameras are frequently positioned not where risk is highest, but where connectivity is available. Dead zones in garages, basements, or perimeter edges force compromises in placement, reducing the effectiveness of the system. In some real-world deployments, traditional Wi-Fi has been shown to fail at a meaningful percentage of intended installation points, particularly in challenging environments or at the edges of coverage. This creates a disconnect between security intent and system reality. Instead of enabling proactive deterrence, such as detecting activity at the perimeter, systems are often relegated to recording events after they occur. The same pattern appears in access control. Many deployments rely on fragmented connectivity stacks, combinations of wired links, proprietary wireless protocols, and gateways, each optimised for a specific constraint such as range or power. While functional, these architectures introduce complexity, increase deployment costs, and create additional points of failure. Over time, these workarounds have become normalised. But as systems scale and expectations rise, their limitations are becoming harder to ignore. The hidden cost of fragmentation The consequences of unreliable or overly complex connectivity extend beyond performance. They impact the entire lifecycle of a security system. Advanced security features need consistent, reliable connectivity—not just bandwidthFor integrators, poor connectivity can mean longer installation times, more troubleshooting, and increased reliance on workarounds such as mesh networks or additional infrastructure. For vendors, it can translate into higher product return rates, increased support costs, and reduced customer satisfaction. For end users, the impact is more direct: systems that fail to connect reliably are systems that fail to deliver security. This is particularly critical as security solutions move toward more advanced use cases, including real-time alerts, remote management, and edge-based analytics. These capabilities depend not just on bandwidth, but on consistent, predictable connectivity across the entire deployment environment. Why traditional approaches are reaching their limits The industry has historically relied on a mix of connectivity options, each with its own strengths and tradeoffs. Wired infrastructure, such as Ethernet and PoE, offers reliability and performance but comes with higher installation costs and limited flexibility, particularly in large or distributed environments. Conventional Wi-Fi provides high throughput and seamless integration with IP networks but is optimised for short-range indoor use, where walls, distance, and interference can quickly degrade performance. Low-Power Wide-Area Networks (LPWAN) and cellular solutions extend range and coverage but often sacrifice throughput, increase latency, or introduce recurring operational costs. To compensate, many systems combine multiple technologies—layering gateways, protocol translation, and mesh architectures to bridge gaps. While effective in the short term, this approach increases system complexity and reduces long-term scalability. A shift toward simpler, more unified architectures In response, the industry is beginning to rethink connectivity, not as a patchwork of solutions, but as a unified foundation for modern security systems. The goal is straightforward: deliver long-range, reliable, and secure connectivity without adding architectural complexity. An example of this shift: Extending Wi-Fi beyond traditional limits One example of this shift can be seen in emerging Wi-Fi technologies designed specifically for long-range, low-power environments. Rather than replacing existing wireless approaches, these solutions aim to extend the familiar Wi-Fi model into new deployment scenarios where traditional networks struggle. Wi-Fi HaLow, based on the IEEE 802.11ah standard, is one such approach. Operating in sub-GHz spectrum, it enables significantly greater range and signal penetration compared to conventional 2.4 GHz and 5 GHz Wi-Fi, while maintaining native IP networking and established security frameworks. Wi-Fi trends reduce fragmentation and support data-heavy security systemsIn practical terms, this allows security devices, such as cameras and access control systems, to connect reliably across large properties, multi-building campuses, and outdoor environments without requiring dense access-point deployments or complex mesh configurations. It also supports higher data rates than many low-power wide-area technologies, enabling capabilities such as over-the-air updates, diagnostics, and increasingly, edge-based intelligence. At the same time, no single connectivity approach is universally optimal. Cellular remains essential for mobility, while LPWAN technologies continue to serve ultra-low-power sensing applications. Emerging Wi-Fi-based approaches highlight a broader industry direction: reducing fragmentation while supporting more demanding, data-rich security systems. From coverage to deterrence: A new security model One of the most significant implications of improved connectivity is the ability to rethink how security systems are deployed in the first place. Historically, limitations in wireless performance have pushed devices inward, closer to access points, inside buildings, and away from the perimeter. As a result, many systems are optimised for detection after the fact, rather than prevention at the edge. With more reliable long-range connectivity, this model begins to shift. Cameras and sensors can be placed where they are most effective—at entry points, along property boundaries, and in previously hard-to-reach areas. Combined with edge-based analytics, this enables earlier detection, faster response, and more effective deterrence. In this context, connectivity is not just an enabler of performance, it is a driver of fundamentally different security outcomes. Designing for the next generation of security systems As the industry moves forward, organisations deploying security systems should reassess how connectivity is factored into system design. Several principles are emerging: Prioritise reliability over peak performance Design for the perimeter, not just the interior Reduce architectural complexity Validate real-world performance, not just lab specifications The next wave of innovation in security will not be defined solely by smarter devices or more advanced analytics. It will be defined by whether those systems can connect, reliably, consistently, and at scale. Connectivity has long been treated as an invisible layer in security architecture. Today, it is becoming clear that it deserves far greater attention. As the industry rethinks its approach, one thing is certain: solving the connectivity challenge is not just a technical upgrade. It is a prerequisite for delivering on the full promise of modern security systems.

A security camera installed today has more AI processing power than the systems that guided early autonomous vehicle prototypes. And yet the operator who mounts that camera on a wall will, in all likelihood, never use most of that capability.  Industry surveys bear this out: a wide gap persists between the number of security professionals who believe AI can improve outcomes and the much smaller share who have adopted it operationally. The reason has nothing to do with the silicon and everything to do with how the industry has asked people to configure these systems. The problem is not that the industry lacks algorithms. The problem is that physical security has never found a scalable way to personalise systems for each site. The personalisation dilemma hiding in plain sight The problem is that physical security has never found a scalable way to personalise systems for each site A surveillance deployment at an airport, a retail chain, a school campus, and a logistics yard can look strikingly similar in hardware terms. Each installation uses image sensors, edge processors, network connectivity, and a management layer. What changes is what the operator cares about. At a school entrance, the priority might be perimeter approach after hours and controlled access during the day. At a loading dock, the concern is tailgating, vehicle dwell time, and safety incidents near forklifts. At an airport, the operator may need queue-flow analytics one moment, unattended-item detection the next, and then a search for a specific person of interest carrying a particular bag. At a retail store, loss prevention teams want to correlate customer flow patterns with point-of-sale data and identify suspicious behaviour near high-value merchandise. This range of needs forces a reality that the industry has acknowledged in principle but never resolved in practice: the application pool across the market is vast, yet each individual site typically requires only a narrow set of outcomes. Each deployment needs personalisation once, at commissioning, and then again whenever the environment or the risk profile shifts. The app store that never became a market For the better part of a decade, the industry’s most visible answer to the personalisation problem was the “app store” model. The logic was straightforward: curate a marketplace of trained neural network algorithms, let integrators browse a catalogue, and download the right analytic for each job. Queue counting for a passport control hall. License plate recognition for a parking structure. Occupancy monitoring for a conference room. The concept borrowed directly from the consumer smartphone approach. In practice, it never matched physical security’s purchasing and operating rhythm. A phone owner discovers and downloads new apps continuously. A physical security deployment selects one or two analytics functions at installation and rarely revisits them. Another maintenance burden A queue-counting algorithm trained on airport data is excellent at queue counting The economic incentive to maintain, curate, and update a broad catalogue across a fragmented ecosystem of camera OEMs, VMS platforms, and system integrators never materialised when the average buyer drew from only a thin slice of it. And the question of who would operate such a marketplace across that fragmented landscape was never satisfactorily answered. The deeper issue is that distribution was not the hard part. Personalisation was. A queue-counting algorithm trained on airport data is excellent at queue counting. It does not naturally become a general-purpose security tool for whatever the operator needs next. Once a model is trained for a narrow task, adaptation requires another project, another integration cycle, and another maintenance burden. AI-enabled cameras The examples that do exist are instructive. Schiphol Airport in the Netherlands has used trained camera systems for over a decade to measure queue length at passport control and alert staff when additional counters should open. Rome trailed AI-enabled cameras to track pedestrian wait times at crosswalks, measure bus queue length, and monitor parking occupancy to support active transport and reduce vehicle emissions. These are effective, well-regarded deployments. They also illustrate the limitation: each required its own trained model, its own integration effort, and its own maintenance cycle. The queue-counting camera at Schiphol cannot be redeployed to detect an abandoned bag. That is a separate algorithm, a separate procurement, and a separate project. What changes with agentic AI Applied to physical security, this translates into a simpler commissioning experience Agentic AI points to a fundamentally different approach. An agentic system can receive goals expressed in natural language, determine the appropriate actions to fulfil those goals, execute those actions using available tools, and verify the results. Applied to physical security, this translates into a simpler commissioning experience: the operator expresses intent in plain language, and the system configures itself to achieve that intent. Consider the practical implications. An installer commissioning cameras at a retail location could type or speak a set of instructions: “Alert the manager if more than five people are waiting at checkout for longer than two minutes.” A facilities director could ask the system to “Track vehicles that enter the east parking lot after 9 p.m. and flag any that remain for more than 30 minutes.” A school security coordinator might specify: “Notify campus police if anyone approaches the perimeter fence between midnight and 5 a.m.” Appropriate perception capabilities None of these instructions require the operator to select a specific analytic from a catalogue, configure a detection model, or define pixel-level zones in a complex VMS interface. The system interprets the intent, selects the appropriate perception capabilities, configures thresholds and context, and validates behaviour over time. When the operator’s needs change, a new instruction replaces the old one. The camera hardware stays the same. The AI adapts. This is the core of the shift: minimal user input, maximum flexibility, and a security system that personalises itself without requiring the operator to navigate the traditional customise-certify-deploy cycle. Vision language models make it practical A conventional neural network trained for people counting can count people The enabling technology is the vision language model, or VLM. A VLM combines visual encoders with language reasoning, allowing it to interpret images or video in the context of natural language prompts. This is a qualitative leap beyond traditional convolutional neural networks, which classify or detect predefined objects and have no mechanism for open-ended interpretation. A conventional neural network trained for people counting can count people. It cannot distinguish between a crowd of commuters exiting a train station and a crowd assembling in protest. A VLM, by integrating contextual reasoning with visual analysis, can draw inferences that a task-specific model cannot. It can assess behavioural patterns, interpret spatial relationships, and respond to queries about scenes it has never been explicitly trained to analyse. Where a neural network might register two people carrying objects, a VLM could infer whether the scene suggests travellers with luggage or workers transporting equipment, provided the visual context supports that inference. Supporting multimodal input This matters in physical security because operational questions are rarely phrased as taxonomy labels. Operators want to express outcomes. They want to say “show me anything unusual near the loading bay after hours,” and the system should be able to reason about what “unusual” means given the site context. VLMs also support multimodal input. Audio cues such as a raised voice, a scream, an alarm, or breaking glass can contribute to scene interpretation when paired with video. In security applications, where events routinely unfold across both visual and auditory channels, this capability adds a meaningful layer of situational awareness. The edge constraint that forces discipline Large language models in the cloud use hundreds of billions of parameters and consume hundreds of watts None of this works if the architecture assumes data centre conditions. Most surveillance cameras operate under strict power and thermal limits. Power over Ethernet (PoE), the standard delivery mechanism, typically provides between 15 and 30 watts depending on the PoE class, and only a fraction of that budget is available for AI processing after the sensor, ISP, video encoder, and network stack have taken their share. In many installations, the AI workload must fit within a few watts. Large language models in the cloud use hundreds of billions of parameters and consume hundreds of watts. That scale does not translate to a camera mounted on a pole or embedded in a ceiling tile. For agentic AI to work at the edge of a physical security network, the models must be compact, efficient, and designed for the purpose. Neural network acceleration This is where smaller, domain-specific VLMs become essential. Models trained on industry-relevant image and text datasets, combined with techniques such as pruning, quantisation, and parameter-efficient fine-tuning, can deliver meaningful visual reasoning within the compute and memory constraints of an edge processor. The result is a VLM that fits inside a camera’s power budget and still responds to natural language instructions with useful accuracy. Ambarella’s CVflow AI architecture, now in its third generation, was designed for this class of workload. The architecture integrates advanced neural network acceleration with high-resolution image signal processing and video encoding on a single system-on-chip, allowing cameras to run complex AI inference alongside their core imaging functions without exceeding the thermal and power boundaries that define edge deployments. The company's latest addition to its portfolio, the 4-nanometer CV7, runs CNNs and vision language models concurrently across multiple video streams while consuming 20 percent less power than its predecessor. For infrastructure and robotic applications requiring heavier models, the 5-nanometer N1 family supports multimodal LLMs in multi-camera configurations. Distributing intelligence across far edge, near edge, and cloud This tier must respond in milliseconds and operate within a fixed power envelope A workable agentic architecture for physical security distributes intelligence across three tiers, each matched to the processing demands and latency requirements of its role. At the far edge, inside the camera itself, the processor handles real-time perception: object detection, tracking, zone logic, and initial event classification. This tier must respond in milliseconds and operate within a fixed power envelope. At the near edge, on a local gateway or network video recorder, a more capable processor orchestrates across multiple cameras, maintains state, correlates events, retrieves site-specific policies and procedures, and classifies incidents requiring more context than any single camera provides. At the cloud/server tier, available when connectivity permits, the system accesses heavier models for forensic analysis, fleet-wide analytics, model updates, and long-horizon reporting. Periodic cloud access This tiered approach keeps the most time-sensitive decisions local, where latency is lowest and data privacy is strongest. It also means agentic capabilities can scale incrementally. A small installation might run entirely at the far edge with periodic cloud access. A large campus might employ all three tiers, with near-edge orchestration coordinating PTZ patrol patterns across dozens of cameras while the cloud generates shift summaries and updates models based on fleet-wide telemetry. In practice, a security workflow built on this pattern often combines real-time detection at the far edge, behaviour-tree orchestration at the near edge for multi-camera coordination, local retrieval over site playbooks, and conservative safe-mode escalation when system confidence is low. The discipline of deterministic guardrails and structured verification loops is essential in security operations, where unpredictable system behaviour is not acceptable. A hybrid future, with VLMs orchestrating specialist models The transition to agentic AI does not eliminate specialised neural networks The transition to agentic AI does not eliminate specialised neural networks. Purpose-trained models will continue to deliver superior accuracy for well-defined, high-frequency tasks such as license plate recognition, face matching, and fire and smoke detection. In a mature agentic system, the VLM acts as an orchestrator. It handles open-ended perception and natural language interaction while routing to specialised models when a task demands their precision. A PTZ camera at a transportation hub might receive the instruction “monitor the west concourse for unattended items.” The VLM interprets the request, manages the interface, and reasons over broader scene context. Real-time video processing When it identifies a candidate object, it routes to a dedicated abandoned-item classifier optimised for that specific validation step. The VLM orchestrates. The specialist model validates. The operator receives a refined, actionable alert. That hybrid pattern places specific demands on the silicon. The processor must support both traditional CNN inference and generative AI workloads simultaneously while maintaining real-time video processing within the same power envelope. The value of a tightly integrated SoC, one that combines an advanced ISP, a deep learning accelerator, and a video encoder on a single die, is that it eliminates the multi-chip complexity and power overhead that would otherwise make this approach impractical at the edge. Making agentic AI deployable for the ecosystem Ambarella’s Developer Zone, launched at CES 2026, provides a centralised portal of tools Physical security is built on a broad ecosystem of camera OEMs, VMS providers, independent software vendors, module builders, and system integrators. For agentic AI to reach the market at scale, these participants need model-ready tooling, reference workflows, and a practical path from prototype to production. This is where developer ecosystems become part of the story. Ambarella’s Developer Zone, launched at CES 2026, provides a centralised portal of tools, optimised AI models, agentic blueprints, low-code templates, and documentation aimed at accelerating edge AI application development on Ambarella’s SoCs. Common software stack ISVs and integrators can evaluate models, prototype applications, and deploy using a common software stack that spans the company’s CV7 and N1 SoC families through the Cooper development platform. That consistency across the product range reduces per-project engineering cost and accelerates time-to-market for partners building perception and analytics solutions. The point is broader than any single portal: agentic systems require components that have already been tested and optimised for edge deployment, so that integrators can focus on solving their customers' problems rather than rebuilding the AI pipeline from scratch. The ecosystem participants who lead the transition to agentic AI in physical security will be the ones with access to tooling that fits into their existing development and deployment processes. What comes next Physical security has searched for years for a scalable answer to personalisation Physical security has searched for years for a scalable answer to personalisation. The app store model did not provide it. Manual configuration, while functional on a per-site basis, scales poorly across large portfolios of cameras and changing operational requirements. Agentic AI offers a credible path forward because it aligns with how operators actually think. They express outcomes, not model specifications. They want systems that adapt to new requirements without repeated engineering cycles. Traditional neural networks With VLMs as the interface layer, smaller domain-specific models at the far edge, orchestration at the near edge, and disciplined verification loops throughout, personalisation can become a standard part of deployment rather than a custom project. The building blocks are now in place. Power-efficient edge AI processors can run VLMs and traditional neural networks simultaneously. Developer ecosystems are maturing to support rapid prototyping and deployment. Reference architectures for distributing intelligence across far-edge, near-edge, and cloud tiers are solidifying. For an industry that already installs vast numbers of AI-capable cameras each year, the opportunity is to make the intelligence already embedded in those endpoints genuinely usable for the people who rely on them every day.

Combining VIVOTEK’s branded video security business with March Networks paves the way for the combined brands to meet customers’ increasing appetite for integrated solutions rather than individual components. The merger brings VIVOTEK's branded video security business together under one operating structure with March Networks’ enterprise-grade video surveillance, AI analytics, and cloud-managed security solutions. Customers now have access to a broader, more integrated portfolio spanning enterprise video management, advanced cameras, edge artificial intelligence (AI), cloud services, recording platforms, and business intelligence, says Net Payne, Chief Sales & Marketing Officer at March Networks and VIVOTEK. Distinct product strategies Given the combined companies, product development, sales, marketing, and customer support can move in step rather than in parallel. March Networks and VIVOTEK were already both part of the Delta Electronics family, but they previously operated as separate businesses with distinct product strategies, teams, and routes to market. March Networks and VIVOTEK announced the merger of their branded video security businesses last spring following Delta Electronics' acquisition of remaining VIVOTEK shares. “Aligning our complementary capabilities lets us innovate faster, simplify engagement, and respond more quickly to a market moving toward AI, cloud and intelligent video,” says Payne. This merger reflects a broader shift across the physical security industry, adds Payne. “Customers no longer see video purely as a tool for reviewing incidents after the fact,” he says. “They expect it to help identify risks earlier, simplify investigations, improve operations, and support better decisions across the organisation.” Cloud video management Meeting customer expectations requires more than bolting AI features onto existing systems Meeting customer expectations requires more than bolting AI features onto existing systems. Rather, it requires cameras, edge intelligence, recording, software, cloud services, and business data working together as one coordinated platform. “By bringing March Networks and VIVOTEK together, we combine deep expertise across the full video technology stack while preserving the relationships, sector knowledge and customer focus both companies have built over many years,” says Payne. “Our goal is to make intelligent video more integrated, scalable, and practical for customers and partners worldwide.” Both entities bring strengths to the combined companies. March Networks brings experience in enterprise software, cloud video management and large-scale deployments; while VIVOTEK brings strength in imaging, camera technology and edge intelligence. Together they seek to ensure more choice when designing systems, a clearer path for future expansion, and technologies that work together more effectively without compromising the reliability, cybersecurity, and support customers expect from both companies. Advantages for channel partners Channel partners gain a broader portfolio to address a wider range of customer requirements, combining components as each deployment demands. Channel partners also benefit from expanded geographic reach, deeper technical expertise, and greater investment in training and enablement. “Importantly, this is designed to be a seamless transition,” says Payne. “Partners keep working with the teams and relationships they already know, while gaining access to new capabilities and certification opportunities. Over time, that alignment should make it easier to design, deploy and support complete solutions.” Because they are established and respected brands, March Networks and VIVOTEK branding will continue to be used. Rebranding is not a goal, and neither identity is being replaced by the other. Coordinated decision-making “The immediate priority is organisational alignment by making it easier for customers and partners to benefit from the combined portfolio,” says Payne. Product branding will continue to reflect the relevant portfolio and market context. As product roadmaps become more closely coordinated, customers can expect greater interoperability and a more cohesive experience, says Payne. Any future branding changes will be managed carefully and communicated clearly. Combining the businesses reduces duplication and enables coordinated decision-making across product strategy, engineering, sales, marketing, operations, and customer support. “Instead of developing capabilities independently, teams can share their expertise, align roadmaps, and direct investment to where it has the greatest customer impact,” says Payne. Combining specialised knowledge globally The combined organisation operates across six continents and more than 75 countries The combined organisation includes more than 300 research and development (R&D) engineers across four Centres of Excellence in Canada, Taiwan, Italy and Poland, thus bringing together a substantial base of specialist knowledge. The unified network also sharpens the ability to prioritise global opportunities, respond to regional needs and bring innovations to market faster. The combined organisation operates across six continents and more than 75 countries, supported by more than 1,100 certified channel partners. That footprint provides greater capacity to support multinational customers while staying responsive to local market needs. Looking ahead, future growth will increasingly come from helping customers turn video into useful, actionable intelligence. “The market is moving beyond conventional surveillance toward solutions combining AI, cloud services, edge processing, video management and operational data — and our new structure brings these together as one connected solution rather than several isolated technologies,” says Payne. Broader technical expertise There will also be closer collaboration among specialists in imaging, hardware, software, analytics, and cloud, which is important given how much customer infrastructure, regulatory, and deployment requirements vary. The companies can support cloud, hybrid, and on-premise environments, giving organisations a practical path toward more intelligent video. More choice comes from bringing together complementary technologies across product groups. Greater scale is achieved through a larger engineering organisation, broader technical expertise and more capacity to invest in innovation. Challenges for the industry at large Looking to the future for the industry at large, the greatest challenge will be managing the rapid growth of AI Looking to the future for the industry at large, the greatest challenge will be managing the rapid growth of AI responsibly, securely and at scale, says Payne. Video systems will generate more data and automate more decisions, but organisations must be able to trust how that intelligence is created, protected, and applied, he adds. “Cybersecurity, privacy, data sovereignty, system interoperability and AI accuracy are more important than ever,” says Payne. Addressing these elements requires expertise across the entire technology stack: from camera and edge processing to recording, cloud infrastructure, video management and analytics. “Together, March Networks and VIVOTEK can coordinate development across all these layers, giving customers flexible architectures that balance innovation with security, transparency and operational control,” says Payne.

The security landscape is undergoing a profound transformation, as evidenced by the innovations showcased at the ISC West Expo 2026. From dismantling of silos between physical and digital security to the ongoing transition to cloud and hybrid platforms, much of the discussion on the show floor was familiar, if somehow more urgent than ever. Clearly the industry is moving toward unified, cloud-native, and highly automated ecosystems. In a series of deep-dive meetings and demonstrations at the recent show, I got a first-hand glimpse of the future of the physical security marketplace. Spoiler alert: The future is now! HID Global: Tearing down the silos HID Global is addressing the long-requested convergence of physical and digital security. Recognising that the industry has historically operated in silos, HID is now leading with a combined implementation team to leverage the power of both sides. HID is supporting the transition by combining its logical and physical security teams to help end users design secure, end-to-end journeys for their employees. By leveraging its massive existing footprint in physical access, HID is uniquely positioned to help organisations upgrade their cybersecurity posture without a total "rip and replace" of their hardware. HID is seeing a surge in demand for converged credentials that unite building access with digital identity. On the digital front, HID has implemented FIDO (Fast Identity Online) and passkeys to replace traditional passwords with more secure, biometric-backed authentication methods. Acre Security: Bridging the gap to the cloud Acre Security previewed a cloud-native video solution, reinforcing its cloud-first security strategyAcre Security is currently consolidating brands, bringing established names like Feenics and AccessIt under a single corporate umbrella. A primary theme for the company at ISC West is the migration of legacy systems to modern infrastructure. To facilitate the transition, they are launching "The Bridge," a technology designed to help on-premise customers transition to the cloud at a pace that suits their operational needs. The company is also expanding its portfolio into video. Attendees at the show received a preview of a new cloud-native video solution slated for release later this year, signaling Acre’s commitment to a holistic, cloud-first security suite. Acoem: Real-time acoustic threat detection With a 35-year foundation in vibration and acoustics—including military sniper detection—Acoem is providing gunshot detection through edge processing. Unlike systems that rely on the cloud and may suffer from latency, Acoem’s technology processes data at the sensor level for instant alerts. Their sensors are engineered for massive outdoor spaces, covering a 500-foot radius (roughly 11 football fields) and can detect high-powered rifle shots from up to half a mile away. The system provides critical intelligence by distinguishing between muzzle blasts and "mach noise" from bullet travel, delivering an audio file to the end-user that maps the location and direction of the threat. They use AI to filter out environmental false positives, such as skateboards hitting metal rails. Alarm.com: The all-in-one dealer ecosystem Beyond hardware, Alarm.com is leveraging AI to streamline the sales process Alarm.com is doubling down on "giving tools to dealers to help them be successful," with a focus on unified commercial solutions. A highlight at ISC West is their new fire communicator, which integrates fire monitoring into their single app, completing what they call the "fourth leg of the stool." The product allows fire systems to benefit from the same real-time customer engagement and push notifications that have long been available for intrusion and video. The key products, such as commercial-grade hardware, are now available for immediate purchase. Beyond hardware, Alarm.com is leveraging AI to streamline the sales process. Their new AI Proposal Builder uses customer meeting notes to automatically generate customised, value-driven sales proposals for dealers. Allegion: A global shift in credentialing Following the acquisition of ELATEC, Allegion is adopting a more global market approach and expanding its OEM business. The company is involved in the development of Aliro, the newly unveiled mobile credentialing standard. Allegion’s strategy is built on versatility: While Aliro serves the burgeoning mobile market, they also offer PKOC for plastic cards, allowing them to provide solutions regardless of the user's preferred credential type. The ELATEC acquisition has effectively filled previous gaps in their use-case portfolio, positioning them as a comprehensive provider for both physical and digital access needs. AtlasIED: Engineering for life safety Transitioning from audio to a fully automated threat detection company, AtlasIED showcased its new IPX line at ISC West. This modular platform uses a single PoE++ port to power various "plug-and-play" modules, allowing for easy system upgrades. Their gun detection technology achieves a 99% confidence rating by "stacking" AI models; it cross-references audio data with infrared signatures to detect muzzle flashes and air quality sensors for particulates. With systems already running in 80% of U.S. international airports, the company maintains 24/7 domestic engineering support to manage these "life-safety adjacent" environments. Axis Communications: Unifying connectivity Axis Communications is advancing network video with 4G/5G surveillance, reducing cabling needs Axis Communications continues to lead in network video, with a new focus on offering surveillance through 4G and 5G networks to eliminate the need for extensive cabling in long-range applications. Axis also introduced several specialised hardware pieces, including the P1486-LE global shutter camera for high-speed traffic monitoring and the Q2802-TE, which integrates thermal and visual monitoring into a single unit.  To assist technicians, they launched a new installer app that uses Bluetooth for easier camera pairing and management directly from a mobile device. Axon: De-escalation through enterprise wearables Focusing on frontline safety, Axon is expanding from law enforcement into the enterprise sector with its retail and healthcare-focused body camera. Weighing only 0.25 lb, these cameras are designed to be less intimidating, using colorful designs and acting as a primary de-escalator for aggressive behavior. A clear front display signals when recording is active, striking a balance between safety and a non-intimidating appearance. These devices feature live-streaming and panic alarms that connect workers to a Global Security Operations Center (GSOC). To ensure the footage is legally viable, Axon maintains a rigorous audit trail that authenticates every action recorded. Genetec: The value of the unified platform Genetec is advocating for unified platforms that reduce the time between incident detection and resolution. They argue that AI is becoming a commodity and that the true value lies in unified platforms that reduce the time from incident to resolution. Their approach emphasises the "outcomes" customers need, such as allowing security teams to coalesce around an investigation quickly. Genetec remains a strong supporter of open systems for enterprise customers, ensuring they have the choice to integrate diverse technologies rather than being locked into a manufacturer’s “walled garden.” This flexibility is critical for high-end security environments that require tailored, responsive systems. Johnson Controls: Large-scale enterprise solutions Johnson Controls has made a significant push into the enterprise video market with C-Cure IQ, a standalone VMS designed for major hubs like airports and large campuses. Through a partnership with Scylla, they have integrated 11 advanced analytics—including facial recognition and weapons detection—directly into their cameras. They also showcased new multi-sensor panoramic cameras capable of "stitching" multiple images into a single 360-degree view. While innovating in video, Johnson Controls also confirmed modern upgrades to their intrusion line, including their legacy DSC Neo line. The new DSC PowerSeries Neo 5, a high-end residential and commercial platform, features an all-new user interface and built-in PowerG+. They have also begun shipping the IQ5 family lineup, which is powered by a Qualcomm DragonWing processor.  ONVIF: Standardising the future of AI and cloud ONVIF continues to lead the charge in establishing common languages for the security industry. A major focus is their new "Cloud Profile," which enables cameras to connect directly to the cloud through a standardised protocol. They are also expanding into audio standards to ensure IP-based speakers can seamlessly connect to Video Management Systems (VMS). To combat the rise of sophisticated digital manipulation, ONVIF is developing "video signing" standards. ONVIF is actively seeking more diverse enterprise participation to help shape these emerging AI standardsThis feature protects the integrity of video for evidentiary purposes by embedding a digital signature and timestamp directly into the footage at the camera level. Additionally, the organisation has formed an AI Working Group to develop common communication methods for "AI agents" within physical security systems. ONVIF is actively seeking more diverse enterprise participation to help shape these emerging AI standards. Roberto Licari is the new ONVIF Ambassador, seeking to attract new companies (even outside the security sector) to ONVIF as they look to expand their offerings. SwiftConnect: Bridging digital and physical identity SwiftConnect is redefining access control by shifting the focus from physical cards to digital identity. As a cloud-based "connected access network," the platform bridges the gap between IT identity providers (like Okta or Azure AD) and legacy physical access control systems. At the show's Security Experience Center demonstrations, SwiftConnect showcased its ability to integrate mobile credentials within Apple and Google Wallets across multiple technology platforms. By aligning physical security with Zero Trust principles, they ensure that access is governed by the same rigorous standards as digital networks. Their software-centric approach allows for a more seamless employee experience while simplifying the management of complex, multi-site building security. This emphasises a future where the mobile device becomes the primary tool for navigating the physical workspace. Wasabi Technologies: Redefining cloud storage economics With cloud technology becoming a baseline requirement at every booth, Wasabi Technologies highlighted its "hot cloud storage" as a cost-effective alternative to major hyperscalers. Their model claims to be 80% less expensive than competitors, notably removing hidden fees. Wasabi is increasingly bundled at the "back end" of security solutions through partnerships with integrators and end users. A key feature for law enforcement and high-security sectors is their "Object Lock" capability, which ensures that video evidence remains untampered with and immutable during defined retention periods. By providing high-performance storage without the unpredictable costs typically associated with the cloud, Wasabi is positioning itself as the foundational layer for data-heavy video surveillance applications that require long-term, secure retention. Wasabi is positioning itself as the foundational layer for data-heavy video surveillance applications ZKTeco USA: Versatile and integrated access ZKTeco USA showcased a range of integrated solutions, including turnstiles, visitor management, and access control. Their Atlas access control series offers versatility, supporting everything from traditional readers and keypads to QR codes and fingerprint scanning, with the flexibility to operate on-premise or in the cloud. For tight environments, they introduced the Mars 100 turnstile, which features a compact 2x3-foot footprint. They also highlighted the Omni series, an all-in-one standalone reader-controller that manages access, intercom, and visitor functions in a single device. Innovation in portability was evident in their new walk-through metal detectors, which consist of two poles with an 8-hour battery life—ideal for schools and temporary events. While they offer their own Armatura readers, ZKTeco emphasised that their solutions can integrate with other industry leaders to fit diverse customer needs.

Artificial Intelligence (AI) had a major presence at the ISC West 2026 show in Las Vegas. Almost every booth offered some variation on AI and how intelligence is transforming the physical security industry. Several industry leaders led the way, showcasing how they are tackling complex security challenges with smarter, more efficient solutions. Obviously, the security industry will never be the same. Milestone Systems: Responsible AI and open platforms Milestone has declared 2026 the "year of delivery” on previously announced developments and enhancements. A standout feature is their new natural language AI search, which is being integrated across XProtect, Arcules, and Briefcam platforms to simplify how users interact with vast amounts of video data. A core pillar of their strategy is responsible AI development, which prioritises using licensed data over "scraped" data. They have introduced new anonymisation tools that protect privacy by replacing faces with AI-generated characteristics like hair color while keeping the person unrecognisable. Furthermore, Milestone is moving workloads to Linux to reduce costs, transitioning toward an app marketplace, and has partnered with NVIDIA for the "Hafnia" project to ensure high-quality data to train AI models. Ambarella: Powering the edge with AI chips With their presence at ISC West in a meeting room near the trade show floor, Ambarella is the "engine" behind many high-performance intelligent video products, specialising in low-power AI chips like the N1 and CV7 families. Their technology is moving beyond cameras, where they provide systems-on-chips [SOCs] to many manufacturers. They have expanded into "AI boxes" that can process 64+ video channels simultaneously. A standout feature is the Natural Language technology, which allows users to search for specific objects or abstract scenes using simple prompts. To address modern security concerns, Ambarella has implemented "agentic" programming for a no-code development of automated workflows and media signing to combat AI-generated deepfakes by verifying video integrity through metadata. Motorola Solutions: Simplifying intelligence Motorola Solutions shows physical security evolving into a real-time enterprise intelligence layer Motorola Solutions is prioritising user accessibility by integrating natural language processing into its system configuration. Motorola's portfolio demonstrates how physical security technology is evolving into a real-time operational intelligence layer across the enterprise. Instead of requiring custom coding, operators can now use simple commands—like asking the system to "show me when someone fell down"—to set up advanced analytics and search parameters. The company is also deploying AI agents designed to aggregate data and automatically flag safety or compliance risks, such as perimeter breaches or blocked fire exits.  To ensure maximum utility of the hardware, Motorola Solutions’ system can ingest massive, complex physical manuals and automatically generate monitoring rules based on those standard operating procedures. Furthermore, Motorola is focusing on interoperability, using industry-standard interfaces to ingest data from various hardware brands and networks. This approach aims to provide operators with clear, recommended next steps during critical events, streamlining the decision-making process in high-pressure environments. i-PRO: Putting generative AI at the edge i-PRO is bringing generative AI directly to the edge with a new fisheye camera i-PRO is bringing generative AI directly to the edge with a new fisheye camera, which processes complex analytics locally rather than relying solely on the cloud. These cameras, on display at ISC West, have moved beyond simple attribute-based tracking to identify complex behaviors like aggression, fighting, and slip-and-fall incidents.  By running on the latest Ambarella chips, i-PRO cameras can use generative AI to improve image quality and analyse scenes in real-time without external processing. This focus on edge-based intelligence ensures high-performance analytics are available even in environments where constant cloud connectivity might be a challenge. Brivo: The rise of agentic AI Brivo and Eagle Eye Networks have officially unified under the Brivo name, focusing on streamlining the experience for large integrators. They are pioneers in agentic AI, introducing features that allow users to talk to their mobile apps to initiate lockdowns or add users. Their Eagle Eye Video Assistant (EEVA) acts as a natural language AI agent that can monitor for specific threats, such as a brandished weapon or a specific vehicle, and automatically trigger access control responses. By treating access and video as a unified system, Brivo enables users to connect specific video skills—like detecting a red car or a brandished weapon—to automated access control actions. They are also using AI to achieve "zero-cost integration," linking disparate cloud systems using AI-generated instructions. Everon: Emphasis on video monitoring Everon is making a massive investment in active video monitoring, using AI-driven systems to deter crime even before it happens. “The market is ripe for it, and customers are demanding it,” says David Charney, Everon’s Sr. Vice President, Video Command Center. Employing virtual guards who can use voice commands, lights, and horns to "shoo away" unauthorised individuals. The company has implemented senior-level leadership that has facilitated more than 5,000 video-based apprehensions. Everon, specialising in integrated systems for multi-site businesses, uses a rigorous selection process to choose AI providers that can accurately filter alerts for specific applications, such as identifying when a fire door is blocked. As a "trusted advisor" to their 300,000 customers, the company focuses on delivering professional-level results that move beyond basic recording to proactive threat mitigation. Hanwha: New hybrid VMS combines cloud and on-prem Hanwha Vision highlighted the official public launch of Blaze, a hybrid video management system (VMS). The platform uses a hybrid architecture to manage on-premise and cloud-connected devices across multiple sites without complex port forwarding. Blaze features native AI capabilities, including semantic search that allows operators to find specific incidents using natural language queries, such as "person with a safety jacket." The AI security platform lets teams search surveillance footage the way they search Google. AI similarity detection allows operators to quickly trace a person’s movement and investigate incidents faster (useful in active shooter behavior, medical emergencies, or crowd panic scenarios, and more). The system also provides a "histogram" view of traffic patterns to help security professionals quickly identify anomalies in historical footage. OpenEye: Operational intelligence and shift to OpEx OpenEye unveiled AI-powered features such as visual chat and scene analysis OpenEye is redefining video surveillance by moving intelligence from the camera level to the cloud, significantly reducing the need for on-site server management. At ISC West, OpenEye introduced new AI-driven tools like visual chat and scene analysis. Beyond security, these tools provide valuable operational alerts, such as identifying overflowing dumpsters, dirty tables in restaurants, or vehicles blocking dock doors.  The system also utilises natural language for search, allowing users to find specific attributes like "people wearing backpacks" within designated timeframes. OpenEye also highlighted an industry-wide shift toward operational expenditures (OpEx) billing models, as users increasingly prefer predictable monthly or yearly payments over large upfront capital expenditures (CapEx). This model aligns with their channel-based operations, meeting customers where they currently operate without the burden of high fees. IQSIGHT: New name, same mission for Bosch video Formerly Bosch Video, the newly named IQSIGHT seeks to maintain the “Bosch pedigree” under the new name. It’s the same engineering, manufacturing, etc. IQSIGHT also pledges to be "easier to do business with" by improving user interfaces and end-to-end user experiences. Despite the transition, the company has increased their pace of innovation and reinforced the open systems philosophy with enhanced integrations with Milestone, Genetec, and others. The major product release at the show is IVA Pro Context, which uses generative AI to provide human-level scene understanding. Through a partnership with Laelaps AI, a robotics startup, IQSIGHT is exploring autonomous dispatch and response. When a camera identifies a scene, it triggers a robot to provide a tailored response. Commercialisation is expected in 12 to 18 months. Verkada: How their system can solve a crime But how does AI operate in the real world? Verkada had a “themed” exhibit demonstrating how their system could solve a hypothetical theft at the Louvre museum in Paris. The exhibit took attendees through and showed how Verkada technologies (e.g., license plate recognition and search capabilities) could provide fast results to solve the crime. AI-powered tools, like their newest unified timeline, demonstrate value in the real world of investigations.

As Missouri’s largest and busiest aviation facility, St. Louis Lambert International Airport (STL) welcomed more than 15 million passengers in 2025. To implement a digital 360-degree surveillance system and secure over 70 million square feet of airport infrastructure, STL required a solution capable of covering vast spatial areas while significantly reducing infrastructure costs and complexity. At the same time, the airport aims to implement AI-applications to optimise its operations. With Dallmeier’s Panomera® multifocal sensor technology, STL achieved comprehensive high-resolution coverage with approximately 90 % fewer cameras and 75 % less infrastructure compared to the original surveillance design. Video security system Due to the continuous growth in passenger numbers, the STL Operations and Security Teams decided to modernise the existing video security system in June of 2018 in two areas: Firstly, in surface parking areas to increase customer safety and eliminate criminal activity such as vandalism and theft. The second solution targeted the airport’s four runways, the taxiways, and all terminal buildings to monitor the activities of aircraft, ground vehicles, and airport personnel. STL Airport Operations Team contacted their security integrator, Tech Electronics, to design and deploy an updated camera solution. The initial design used a combination of PTZ and single sensor IP cameras and would have required more than 130 cameras in total. From an infrastructure perspective, this would have required the installation of more than 42 new camera poles and the corresponding infrastructure (cable, network, power, etc.). The airside solution required significantly more technology to achieve the desired surveillance coverage. So, STL and Tech Electronics decided to look for another, more economical solution. Desired surveillance coverage During their technology search, STL discovered the Dallmeier Panomera® multifocal sensor technology, which was developed specifically for surveillance of large spatial areas using the fewest number of cameras to achieve the required surveillance coverage.  David Kulinsky, Deputy Director of Operations & Maintenance at STL, recalls: “When we discovered Panomera® and saw that one Panomera® camera can capture large areas at high resolution and replace several single-sensor cameras, including the costly infrastructure, it became clear that Panomera® provided STL a more economical solution with higher quality images at a lower overall cost.” Intuitive user experience The test installation at the airport proved the image quality of the Panomera®. Kevin Hubble, Services Manager for STL with Tech Electronics, comments: “I was surprised at how few Panomera® cameras were needed to replace several PTZs and single sensor cameras and display the images in a much more user-friendly format. The SeMSy® Compact VMS software enables the user to view a single high-resolution image of the entire scene with simple digital PTZ controls to ‘zoom’ into any part of the image in greater detail. The result is an intuitive user experience resulting in greater operational efficiency – not to mention the superior high resolution video coverage.” To date, STL has installed more than 27 Panomera® cameras. Multiple IPS 10000 recording appliances and 5 user workstations with the SeMSy® Compact VMS client software complete the video system. Compared to the original planning, this resulted in approximately 90 % reduction in the number of cameras and approximately 75 % reduction in infrastructure required for the installation. Comprehensive situational awareness A particular highlight of the deployment is STL’s digital 360-degree surveillance concept. Using only ten Panomera® cameras, the airport achieves comprehensive situational awareness across large airside areas including runways, taxiways and apron operations.  Unlike conventional camera concepts that require numerous PTZ and single-sensor cameras, Panomera® delivers a complete high-resolution overview in a single seamless image. This enables operators to monitor critical airport activities more efficiently across large spatial areas, while significantly reducing infrastructure complexity, maintenance effort and overall operating costs. AI-based video analysis Beyond security applications, STL is also evaluating Panomera® technology for operational process optimisation inside the terminals. As part of a planned deployment in the ticketing area, a Panomera® V8 system will support AI-based video analysis functions such as passenger flow and waiting time analysis. The objective is to improve operational efficiency, optimise check-in processes and enhance the passenger experience — while leveraging the same high-resolution surveillance infrastructure already deployed throughout the airport. Video information technology David Kulinsky with STL summarises: “Any technology project at an airport must deliver a solution that is operationally efficient, resilient, and built for long-term performance. Our decision to deploy Panomera® cameras significantly enhanced overall surveillance coverage across the airport while reducing the technology and infrastructure footprint required to support it.” “The system also provides the ability to zoom into specific areas without sacrificing full-scene situational awareness or recording capabilities—an operational advantage over traditional PTZ cameras, which only record the field of view being actively monitored and can limit broader operational visibility.”  In 1984, Dieter Dallmeier founded what is now Dallmeier electronic – not in the proverbial garage, but in a garden shed in Regensburg, Germany. Today, the company, which can justifiably call itself a hidden champion for video information technology "Made in Germany", has several hundred employees worldwide, more than 250 of them at the company headquarters in the center of Regensburg alone. Digital image storage system Dallmeier's camera, recording, software, and analysis solutions optimise security and processes for B2B end customers in a wide range of industries in over 60 countries. The focus is on users from the casino, smart city, airports, logistics, stadiums, and industrial sectors. But also, banks, critical infrastructure facilities as well as medium-sized companies from all sectors. With pioneering innovations, Dallmeier has succeeded time and again in placing itself at the forefront of technology: From the world's first digital image storage system with motion analysis in 1992, the patented "multifocal sensor technology" Panomera® with its "Mountera®" mounting system, to the latest Domera® camera family, which allows up to 300 camera variants with only 18 components. Complete manufacturing process These and many other innovations provide real, tangible customer benefits. And with a low Total Cost of Ownership (TCO) and a high Return on Investment (ROI) they can easily compete with systems produced and supplied from low-wage countries. With "Made in Germany", we also guarantee our customers the highest standards in data protection, cybersecurity, and ethical responsibility. With high quality and short supply chains, we also ensure – almost incidentally – sustainability and environmental protection. From our prestigious headquarters in the center of Regensburg, Dallmeier not only carries out its own research and development but also the complete manufacturing process – from component to product to solution.

Gozoki, a French family-owned company and pioneer in the freshly prepared meals market (Maison Briau, Maison Tino and other brands), has taken the step of investing to secure its industrial sites. At its facilities in Agen, the company now benefits from a state-of-the-art video surveillance system deployed by specialist integrator SDP, using Hanwha Vision hardware and software solutions. Production sites in the food manufacturing sector face stringent requirements for security, access control and traceability. Protecting staff, preventing intrusions, monitoring logistics flows and securing sensitive areas all present significant challenges. Present significant challenges As part of its ongoing commitment to improving its infrastructure, Gozoki began modernising its surveillance system in 2025 to enhance reliability, accuracy and responsiveness. “We needed a system capable of operating 24/7 in a demanding environment while delivering outstanding image quality. The Hanwha Vision solution meets these requirements perfectly,” says Nicolas Jeannesson, buildings and energy manager at Gozoki. To deliver the project, Gozoki selected SDP, a company renowned for its expertise in integrating electronic security solutions. SDP carried out the site survey, designed the network architecture, installed the equipment and completed its advanced configuration. The objective was to deliver a robust, scalable solution perfectly suited to the demands of a challenging industrial environment. “Our role is to provide a turnkey solution that is reliable and built to last. Hanwha Vision cameras enable us to deliver high levels of performance while simplifying maintenance,” says Pierre Albanese, managing director of SDP. Video analytics capabilities The cameras SDP and Gozoki chose to install were Hanwha Vision’s, and were selected for their exceptional image quality, even in challenging conditions, thanks to high-resolution sensors and WDR technologies. Advanced video analytics capabilities that enable intrusion detection, intelligent management of sensitive areas, and behavioural analysis, were also key features that Gozoki required. The reliability and durability of Hanwha Vision’s cameras are essential in industrial environments that are subject to fluctuations in temperature, humidity or lighting, such as Gozoki’s sites. Enhanced cybersecurity - a critical factor in preventing the risk of cyber attacks on connected systems - was also a vital element of the project’s requirements. The installed cameras cover all strategic areas, including vehicle entrances, loading bays, storage areas, internal traffic routes and external perimeters. “The integrated video analytics allow us to go far beyond simple monitoring. We now have a decision-support tool capable of anticipating risk situations,” adds Nicolas Jeannesson of Gozoki. Future regulatory requirements With the planned deployment of nearly 200 cameras across multiple sites around Agen, Gozoki now benefits from a modern video surveillance system that supports the company’s growth while meeting current and future regulatory requirements. “This project perfectly illustrates our commitment to supporting our customers over the long term with reliable, scalable technologies,” concludes Pierre Albanese. Together, SDP and Hanwha Vision delivered Gozoki a cohesive, high-performance and scalable solution, providing a clear, centralised view of security across its facilities.

Stadiums and arenas are no longer places that come to life only on an event day. Increasingly, they are becoming year-round hubs for concerts, conferences, hospitality, retail, and community activity. The Tottenham Hotspur Stadium is one such example of a venue generating additional revenue and audiences beyond football matches, with its 2025 commercial income rising from £255.2 million to £277.1 million, due to hosting four National Football League (NFL) franchises, high-profile boxing events, and a Beyoncé summer concert series. Positive visitor experience Yet, as these venues grow more complex and multifaceted, so does the challenge of keeping visitors and staff safe throughout the year. Security is no longer simply about responding to incidents.; Instead, it has become a strategic function that enables stadium leadership to tailor security to different event types and risk levels, keep on top of health and safety and maintenance, and add value to marketing, sales, operations, and more. More pointedly, venue operators will soon have to comply with the Terrorism (Protection of Premises) Act 2025, better known as Martyn's Law, which received Royal Assent in April 2025 and is expected to come into force in spring 2027. With less than a year before implementation is anticipated, organisations responsible for large publicly accessible venues are increasingly assessing how they can strengthen preparedness while maintaining a positive visitor experience. Wider readiness strategy Named in memory of Martyn Hett, a victim of the Manchester Arena attack in 2017, the legislation introduces new responsibilities for venue operators to consider the risk of terrorism and put appropriate measures in place to help prevent, respond to, and reduce the impact of a terrorist attack if it occurs. Notably, for venues with attendees of over 800 people, physical protection such as video surveillance, vehicle access control, ground security, and more, must be considered and evaluated on a regular basis. AI-powered video solutions can help organisations meet their obligation under Martyn’s Law as part of a wider readiness strategy. Video surveillance systems Traditional video surveillance systems have always played a critical role in venue security, but their effectiveness has often relied on human operators monitoring dozens, or even hundreds, of video feeds simultaneously. In busy environments, critical details can be missed, particularly when security teams are managing large crowds, multiple entry points, and fast-moving situations. With AI-powered cameras and video management systems (VMS), operators no longer need to continuously monitor multiple video, chat, and sensor data streams. Instead, AI does the monitoring, flagging any suspicious activity, unauthorised objects (people and vehicles), crowd congestion, and so on, for operators to respond to if needed. Operators are freed up to focus on other activities, while the system will quickly alert them to events that require intervention, helping them respond to events rapidly and prevent situations from escalating. Ground teams also benefit from contextual, AI-powered insights that can help them track and locate a person or vehicle of interest, such as clothing colour, direction of travel, and if they are potentially carrying a weapon. Multi-directional models By enabling security teams to assess and respond to situations before they develop into something more serious, venues are better prepared for some of the objectives underpinning Martyn's Law. The legislation places particular emphasis on preparedness, requiring organisations to consider how they would respond to incidents through measures such as evacuation, lockdown procedures, and effective communication. Situational awareness is fundamental to all four. Modern-day cameras equip operators with high-definition footage of an event or object of interest. Most cameras available on the market start at 1080p definition, with 4MP, 6MP, 8MP or 4K resolution options. Camera form factors have also improved, with dome, flat eye, bullet, fish eye, pan-tilt-zoom (PTZ), thermal, and multi-directional models providing venues with a range of options to fit any sized area and surveillance need. Monitoring crowd movements Real-time intelligence from video surveillance provides operators with a clearer understanding of what is happening across a venue and its surrounding environment. Vitally, AI-powered video analytics and AI object detection help operators to avoid missing events that need their attention and action. During an emergency, security teams can monitor crowd movements, identify potential bottlenecks, move towards the last known location of a potential attacker, and direct the public away from dangerous areas. Information on an attacker’s location, physical appearance, and direction of travel, plus the location of any casualties or people hiding within the venue, can be shared with on-site personnel and emergency services, helping to coordinate a faster and more efficient response. Multiple analytics triggers To further refine operator response times and efficiency, alerts can be set based on multiple analytics triggers, for example, if a person is detected crossing a line and then remains in a pre-defined area for a set number of seconds. For post-event investigations, operators can search footage quickly using the metadata stored within video. For example, they can pull up all footage of all people wearing a grey top, or, to filter this further, a child wearing a grey top. This improves the efficiency and speed of carrying out investigations. Generative AI tool Moreover, if a video analytics tool supports it, operators can use an AI-powered search feature that enables them to input a phrase or sentence of what they are looking for, with the system showing them all relevant results. This feature, known as semantic search, is a more natural way of searching akin to prompting a generative AI tool to come to a result. Operators can also select a specific area of interest to view all footage related to that area, allowing them to quickly find motion within that area. They can see all motion within that section on all captured video footage, to see, for example, who left a suspicious package in a room. Some video analytics systems can also pull footage of similar objects across multiple cameras, which can help track the direction of a vehicle or person of interest as they move across a busy and large event space. Wider entertainment districts Modern venue security increasingly extends beyond the perimeter fence or turnstile. Many new stadium developments are embedded within wider entertainment districts, retail destinations, and mixed-use communities. As a result, operators are responsible for understanding activity not only inside a venue but also across surrounding public spaces where large crowds gather before and after events. AI-enabled video helps operators to monitor large areas efficiently, maintaining situational awareness across multiple locations and mixed-use premises (the arena, retail, transport links, storage and backroom areas, and so forth). Operators gain a comprehensive understanding of potential risks and a stronger ability to respond before issues escalate. AI-powered video analytics There are also value-added benefits to other departments, such as marketing, sales, maintenance, staffing, and cleaning. Understanding and predicting busy periods and crowd flow patterns, alerting to long queue lengths, identifying congestion points, and monitoring vehicle movements and parking spaces all help to improve the visitor experience and streamline event operations. This is particularly useful for multi-use venues where one day a football match may be hosted, the next day a corporate event, and the following day a concert, with different stadium areas being used each time. Operators need visibility of how people move through their spaces and where resources are best deployed. AI-powered video analytics can provide that intelligence in real time. Venue leaders have a short window of opportunity to strengthen their security strategies ahead of Martyn’s Law coming into force. Investing in AI-powered video security shifts security into a proactive, value-generating function that meets the needs of today’s multi-use event spaces and helps to deliver the visitor experience that attendees have become accustomed to.

Viação Santa Brígida partnered with Dahua Technology to improve the safety and efficiency of its bus fleet in São Paulo, Brazil. The integrated solution enables real-time monitoring, reduces blind spots, supports passenger counting and fare-evasion control, and helps operators respond to incidents more effectively. Overview - Viação Santa Brígida is a major operator serving São Paulo with a fleet of more than 650 buses. To improve fleet supervision, passenger and driver safety, and operational visibility, the client partnered with Dahua Technology to deploy an intelligent mobile video surveillance and fleet management solution featuring onboard cameras, passenger counting, vehicle tracking, and centralised real-time monitoring. Potential safety risks Challenges - Managing hundreds of buses operating across a densely populated metropolitan area requires continuous coordination and reliable access to operational information. Viação Santa Brígida needed a more effective way to monitor its vehicles in real time and respond rapidly to incidents. Limited visibility inside and around buses made it difficult for the company to verify events, identify potential safety risks, and support drivers during daily operations. Blind spots around large vehicles also presented a concern, particularly during passenger boarding, manoeuvring, and interactions with pedestrians and other road users. Assessing vehicle occupancy The company additionally needed better tools to address fare evasion and monitor passenger movement. Without centralised and accurate data, assessing vehicle occupancy, reviewing suspicious activity, and identifying possible revenue losses could be time-consuming. Another priority was improving the efficiency of fleet management. Information from individual vehicles had to be consolidated and made readily accessible to the operations team, enabling managers to make faster, better-informed decisions. Centralised management software Solutions - Working with Dahua Technology, Viação Santa Brígida deployed an integrated mobile video surveillance solution combining strategically positioned onboard cameras, intelligent analytics, vehicle information, and centralised management software. Cameras installed inside the buses provide continuous recording and real-time monitoring of passenger areas. This allows the operations team to review incidents, observe passenger movement, and obtain reliable video evidence when necessary. The system also helps identify cases of fare evasion, supporting the protection of company revenue and improving operational control. Passenger-counting capabilities External cameras give drivers a more complete view of the areas surrounding each vehicle. By reducing blind spots, the solution helps drivers see pedestrians, passengers, and other nearby road users more clearly throughout the journey. This is particularly valuable during boarding and disembarking, when people may be positioned close to the vehicle or outside the driver’s direct field of vision. The deployment also incorporates intelligent passenger-counting capabilities. By automatically analysing boarding activity, the system provides more accurate information about passenger volumes, vehicle occupancy, and potential discrepancies associated with revenue collection. Comprehensive view of fleet activity All information is brought together at Viação Santa Brígida’s Integrated Control Center, where operators can monitor the fleet through a video wall and Dahua’s mobile management software. The platform consolidates live and recorded video with vehicle location and operational information, giving the control team a clearer and more comprehensive view of fleet activity. The centralised system also supports the identification and investigation of unusual events. When an incident occurs, operators can access the relevant vehicle information and video footage, helping the company evaluate the situation and take appropriate action more efficiently. Continuous video monitoring Results - Dahua’s integrated mobile video surveillance solution has significantly improved Viação Santa Brígida’s fleet visibility by enabling continuous video monitoring, more accurate passenger counting, stronger fare-evasion control, and faster incident verification. External cameras also reduce blind spots, helping drivers operate more safely during daily journeys and passenger boarding. By centralising video, location, and operational data in the Integrated Control Center, the company can analyse events more quickly and make better-informed decisions. Overall, the collaboration between Viação Santa Brígida and Dahua Technology has delivered a safer, more transparent, and more efficient approach to public transportation management, benefiting the company, its employees, and the thousands of passengers who rely on its services each day. “Today, we can continuously monitor the cameras installed across our buses and provide our managers with more accurate operational information. Dahua’s technology helps us control fare evasion, improve safety for drivers and passengers, and manage our fleet with much greater efficiency and confidence,” says a representative from Viação Santa Brígida.

Genetec Inc., the global pioneer in enterprise physical security software, announces that SoFi Stadium and Hollywood Park have unified their physical security operations using Genetec™ Security Center. Home to the Los Angeles Rams and Los Angeles Chargers, SoFi Stadium is the premier sports and entertainment destination located at Hollywood Park. The stadium has established itself as a world-class venue, hosting record-breaking concerts and global sporting events while consistently ranking among the top venues in the world. Global sporting events To support events of this scale, the organisation standardised on Security Center to unify video surveillance, access control, automatic license plate recognition (ALPR), and other physical security systems in the 3.1 million-square-foot venue and across the 300-acre Hollywood Park development. Operators manage more than 3,000 cameras, 700 readers, and numerous other systems and sensors from three security control rooms, helping teams maintain situational awareness while streamlining day-to-day operations. "Genetec Security Center has improved our response time efficiency by giving us all the information we need in one platform. We’re able to understand what's happening and make decisions quickly," said Nick Bermensolo, Vice President of Security and Safety at SoFi Stadium and Hollywood Park. Physical security systems Since deploying Security Center, the SoFi Stadium IT team has a reliable, scalable, and cybersecure platform that runs on an isolated network and connects back to centralised servers. During big events, they support security operations by monitoring system performance from the Network Operations Center, ensuring everything is working as it should. The security team can easily handle daily tasks, while IT keeps systems running smoothly on the backend. "The Genetec team doesn’t just understand physical security systems, but IT systems too. With their help, we’ve been able to deploy a reliable and high-performing security platform at scale," said Paul Maldonado, Vice President of IT Infrastructure and Operations at SoFi Stadium and Hollywood Park. AI-based tools Looking ahead, both teams are focused on getting more value out of Security Center, exploring AI-based tools and more automation. They know they have a flexible, scalable platform that can support evolving cybersecurity and network requirements. "Genetec has really helped us establish a technology standard. Security Center is reliable and cybersecure, integrates well with our network, and reduces overhead for both IT and security. That’s the type of technology we want to continue implementing across our business," said Maldonado.

Carrefour Brazil is one of the largest retail groups in Brazil and Latin America, operating more than 1,000 stores and serving a high volume of customers every day. Its Pamplona store in São Paulo, for example, located in one of the city’s busiest areas, greatly reflects the operational complexity faced by modern retailers: maintaining safety, reducing losses, improving efficiency, and delivering a better shopping experience at scale. Limited real-time visibility Challenges - Carrefour needed to address several key pain points. Manual processes and disconnected systems created risks of inaccurate alarms and inconsistent service. High customer traffic increased exposure to theft, fraud, and checkout losses, while traditional investigation methods made incident tracing slow and inefficient. At the same time, limited real-time visibility into customer flow, queues, inventory, and in-store behaviour made it difficult to optimize staffing, replenishment, store layout, and checkout efficiency. Unified retail ecosystem Solutions - To meet these needs, Dahua provided an integrated smart retail solution combining video surveillance, AI analytics, alarm linkage, customer flow analysis, and digital in-store technologies. The solution was built around Dahua’s DSS PRO platform, Retail Loss Prevention IVD/IVSS, Retail NVR, AcuPick intelligent search, people-counting cameras, Electronic Article Surveillance (EAS) integration, alarm host, access control, electronic shelf labels, and digital signage. These systems work together to connect security, operations, and customer engagement within a unified retail ecosystem. Integration of video surveillance For loss prevention, Dahua’s video analytics can detect suspicious behaviors such as item concealment and issue real-time alerts to security staff. Integration with EAS and intrusion alarms provides immediate contextual information for each alarm, helping teams respond faster and more accurately. High-value merchandise is further protected with anti-theft tags, while restricted storage areas are secured through access control. In the event of an incident, AcuPick and intelligent video analysis can be used to track the movement paths of customers or employees, significantly reducing investigation time. The solution is also projected to checkout and self-checkout security. Cart analysis can help to identify unscanned items, while intelligent barriers at self-checkout stations prevent customers from exiting before completing payment. Looking ahead, the integration of video surveillance with transaction data can further support automated sales auditing, discrepancy detection, and faster resolution of operational variances. Data-driven store operations Beyond security, Dahua’s smart retail technologies support data-driven store operations. People-counting cameras, customer flow analysis, queue monitoring, and heatmap analysis provide Carrefour with insights into occupancy, peak hours, movement patterns, high-traffic areas, and dwell time. This can help to optimize staff scheduling, product placement, promotional planning, and checkout lane management. Shelf replenishment monitoring enable detection of low stock or abnormal product removal and triggers real-time alerts, helping prevent lost sales and improving product availability. Dahua also enhanced the in-store customer experience through electronic shelf labels and digital signage. Electronic shelf labels enable automatic price updates, reduce manual errors, and support promotional communication. Digital signage and point-of-sale displays provide product information, strengthen brand presence, and create a more interactive shopping environment. Interactive shopping environment Results - As a result, Carrefour Brazil now operates in a safer, more efficient, and more connected retail environment. The project improves operational visibility, strengthens loss prevention, accelerates incident analysis, supports better staffing and merchandising decisions, and enhances the customer journey from entrance to checkout. Through this collaboration, Dahua helped Carrefour transform traditional store management into an intelligent retail model powered by integrated security, analytics, and digital engagement.

Adequate video surveillance coverage depends entirely on a facility's layout, square footage, and security goals. Historically, better coverage required more cameras, but technology innovations are changing those expectations and undermining previously held rules of thumb. We asked our Expert Panel Roundtable: Do today's video systems generally require more cameras or fewer cameras, and why?

Access control, video surveillance, and intrusion detection systems evolved largely independently in the physical security industry. Integrating those systems to the benefit of an enterprise's overall security has traditionally fallen on security integrators working in cooperation with manufacturers. However, today's market has also evolved to include companies that provide "unified platforms,” bringing together various disparate security systems and functions under a single, centralised management interface. We asked our Expert Panel Roundtable: What are the advantages of installing physical security systems as a unified platform?

The role of audio in physical security is multifaceted and increasingly vital, offering a layer of intelligence and interaction that access control and/or video surveillance alone cannot provide. Sounds provide crucial context to visual events. For instance, someone running might appear suspicious on video, but audio could reveal they are shouting for help, changing the interpretation entirely. Even so, historically speaking, audio has been an underused component in physical security. How is the situation changing? We asked our Expert Panel Roundtable: Is audio an underused component in today’s physical security systems? What obstacles are keeping audio from expanding?