Artificial intelligence (AI)

In the third quarter of 2018, Dahua Technology, a solution provider in the global video surveillance industry, held a variety of successful roadshows in multiple countries and regions, impressing distributors, installers, integrators as well as specialists in the field of security. The roadshows aimed to introduce Dahua Technology’s cutting-edge technologies and new product advantages to local markets, driving business momentum and increasing the willingness of customers to cooperate with the company. Elaborately designed event Dahua Technology Singapore held a grand security gathering themed ‘Dahua Beyond CCTV’ at the Mount Faber Peak with prestigious clients from various Singapore government departments. Dahua Technology Turkey held ‘Dahua Technology Day’, which was focused on transportation, energy and safe city solutions Combing the eye-catching UAV X820 and face-recognition AI cameras, Dahua Technology’s face recognition technology successfully became the highlight of the elaborately designed event. Dahua Technology Turkey, on the other hand, held ‘Dahua Technology Day’, which was focused on transportation, energy and safe city solutions, to display some of the most advanced products and technologies in these vertical markets, demonstrating the strength and sincerity ofthe company to customers and the security industry in Turkey. The drone and solutions on display were so attractive that a well-known Turkish newspaper made detailed report to them. Showing the professionalism There were many more worth-mentioning roadshows held in other parts of the world, like in Spain, Armenia, Poland, Latvia, Romania, Republic of Montenegro, Czech Republic and Croatia. They all introduced different products and solutions such as HDCVI, Imou, VTO, AI series products according to different market demands. All Dahua Technology employees were fully prepared and worked smoothly with each other, showing the professionalism and enthusiasm of Dahua team to a great extent. The series of Dahua roadshows, by enhancing the brand image of Dahua Technology, laid a solid foundation for Dahua Technology’s future cooperation with its customers. With a mission of ‘Enabling a Safer Society and Smarter living’, Dahua Technology will continue to focus on ‘innovation, quality and service’ to serve partners and customers across the globe.

Hikvision, the global supplier of innovative video surveillance products and solutions, exhibited the latest AI products and technologies at 2018 Security China. More than 1,000 organisations participated in the exhibition which attracted a diverse audience of global distributors, integrators, IT professionals, technology enthusiasts and consumers to join the conversations about solutions around AI, intelligent security, cloud and other mega trends. At the show, Hikvision announced the release to the Chinese market of its AI Cloud framework including platforms for AI Applications, Resource Management, Operations and Maintenance Services. Hikvision is working closely with eco-system partners on AI Cloud network infrastructure, platform services and application interfaces. A 3D camera with the capability of 3D face modelling, which can prevent spoofing attack of photos, video and masksExhibiting various cameras In the product area of the exhibition, Hikvision showed its latest, core technological breakthroughs and products including: A 3D camera with the capability of 3D face modelling, which can prevent spoofing attack of photos, video and masks, and improve the comparison of facial features and side face; A demo model of 64MP PanoVu camera that adopts integrated design, panoramic images by an eight-sensors patchwork to support 360 ° panoramic monitoring, as well as simultaneous panoramic and close-up pictures; A deep learning-based thermal imaging camera for effective fire detection and with algorithms for behaviour analysis and accurate face temperature measurement. Intelligent solutions for public security In addition, Hikvision showcased its intelligent solutions for public security and commercial applications, like safe cities, intelligent transport systems (ITS) and smart retail with more than 20 scenario-specific intelligent solutions on display. One example was the ITS solution, which has the capability to analyse video feeds, learn traffic behaviour and support management of traffic flow, congestion and incidents. Visitors could also see a wide range of innovations and products for new Hikvision enterprises, such as smart home products (EZVIZ), industrial automation (Hik Robotics), automotive electronics and intelligent storage.

Dahua Technology, a solution provider in the global video surveillance industry, has launched three new AI XVR products—the DH-XVR8208A-4K-I, DH-XVR8216A-4KL-I, and XVR8816S-4KL-I. Offering incomparable perimeter protection, face recognition and metadata search technology, they are applicable to numerous industries ranging from retail to banking and real estate. Being cost-effective and user-friendly, Dahua AI XVRs aim to create more value to users. With 8/16ch perimeter protection, the XVR intelligently avoids false alarms to less important objects such as falling leaves and rain, and send alarms only when identifying human or vehicle, therefore hostile intrusion can be contained, potential losses can be reduced, and manpower can be saved. Target object modelling The AI-powered face recognition technology behind these XVR products enjoys a high reputation in the industry, winning several first prizes in international competitions. Being acknowledged on performance for both efficiency and accuracy, Dahua Face Recognition could alarm for suspects on blacklist, allow passing for authorised people on whitelist, also alert for approaching of strangers. The new products offer enhanced process efficiency as well as reduced time and labour cost with the integration of a powerful, multicore CPU Utilising 4ch Metadata Search functions, the new XVR products are smart search enabled, capable of automatically extracting face feature attributes, including gender, age, glasses, masks, beard, facial expressions, and target object modelling. Furthermore, the new products offer enhanced process efficiency as well as reduced time and labour cost with the integration of a powerful, multicore CPU. Providing human-related metadata to platforms, Dahua Technology’s AI XVRs allow potential business applications realised by third-party software and algorithms. Intelligent perimeter protection Holding Dahua Technology’s patented HDCVI technology, these new AI XVR products are featured with long distance transmission, seamless upgrading, and IoT into analogue monitoring—all while maintaining perfect 4K resolution over coax. Dahua has already launched several series of cameras, recorders, and network video servers. With its extensive portfolio of front-end and back-end products with HDCVI technology, Dahua solutions can be easily integrated into self-contained systems to satisfy the needs of both system integrators and users. Integrating intelligent perimeter protection, advanced face recognition, powerful metadata search and HDCVI technology, Dahua Technology’s AI XVRs are designed to bolster video security to offer a safe, efficient, and intelligent environment. With a mission of ‘Enabling a Safer Society and Smarter Living’, Dahua will continue to focus on serving partners and customers around the world by ‘Innovation, Quality, and Service.’

Sensory, a provider of speech and vision technologies that enhance the user experience and security of consumer electronics, announces the release of its fourth generation of TrulySecure FIDO Certified multimodal biometric authentication technology. Now smarter, faster and more secure than ever before, the TrulySecure 4.0 SDK boasts a variety of new AI features that cater to today’s smartphones, mobile apps, and IoT devices, including support for 3D cameras, GPU utilisation for authentication processing, new liveness challenges and options for integrating components of TrulySecure into cloud-based authentication systems. With each subsequent revision, Sensory continues to significantly enhance the performance, security and features offered by TrulySecure. Version 4.0 continues the trend by expanding on Sensory’s market-proven face authentication AI performance and accuracy. Facial recognition solutions A common problem with traditional 2D facial recognition solutions is the inability to authenticate users in challenging lighting or no-light scenarios With version 4.0, TrulySecure’s deep learning AI has been trained on a data set that is an order of magnitude larger than the previous generation, which has improved 2D facial recognition accuracy more than 50-percent. A common problem with traditional 2D facial recognition solutions is the inability to authenticate users in challenging lighting or no-light scenarios. The use of an IR illuminator completely eliminates this problem, essentially allowing TrulySecure to see clearly and authenticate users in all lighting conditions, including complete darkness. 3D camera support also increases the robustness of TrulySecure to varying pose angles, making the system more accurate during casual use across a broader range of conditions, and more resistant to spoof attacks. Biometric authentication data processing TrulySecure's support of 3D camera data has been developed in collaboration with pmd Technologies from Germany, the worldwide 3D Time-of-Flight CMOS-based digital imaging technology supplier. 3D cameras from pmd are already integrated into smartphones, robots, cars and AR headsets. Another major update in TrulySecure is the ability to split the biometric authentication data processing load between a device’s GPU and applications processor. To accomplish this, key processor-heavy components of the core TrulySecure algorithm were isolated, streamlined and specially ported to run on a GPU. In testing, it was found that those isolated components of TrulySecure run as fast or even faster on the GPU than on the AP. Moving heavy processing components of TrulySecure from the AP to the GPU allows the applications processor to either prioritise other tasks, or work in parallel with the GPU to cut the amount of processing time required for the TrulySecure algorithm in half. Liveness detection capabilities The first major leap forward from the previous version of TrulySecure is the use of 3D image data for authentication As an added bonus, isolating and streamlining processor-heavy components of the TrulySecure algorithm has opened up a whole new realm of possibilities for porting to other embedded environments in the future. An area of concern for all authentication modalities is spoofing. While previous generations of TrulySecure face and voice recognition featured anti-spoofing and liveness detection capabilities, TrulySecure 4.0 makes spoofing a concern of the past. The first major leap forward from the previous version of TrulySecure is the use of 3D image data for authentication. This allows TrulySecure to not only recognise the user’s face, but the shape and contour of it too – and immediately reject 2D images and videos of the user’s face. Requiring 3D facial imagery serves as an excellent anti-spoofing measure, but not all devices have 3D cameras. For traditional 2D RGB camera applications, Sensory’s TrulySecure now features a face liveness challenge that makes it virtually impossible for anybody but the enrolled user to get in. Cloud-based authentication TrulySecure’s face liveness challenge requires the enrolled user to follow prompts telling them what kind of movement to make in order to be authenticated. Additionally, TrulySecure now features an ‘eyes open’ challenge, that requires the user’s eyes to be open during authentication. Sensory’s technologies have long been the go-to for those looking to integrate powerful AI at the edge, but now TrulySecure can make cloud-based authentication technologies faster, more convenient and more secure. One way that TrulySecure can do this is via its incredibly quick on-device enrollment component for federated authentication. With federated authentication, once a user completes the TrulySecure enrollment process on their device, TrulySecure creates a user enrollment template that can be handed off to the authentication server. Once the template is received by the server, it can be sent to other devices as needed, allowing the enrolled user to authenticate by face on any permitted device or app. Authentication images This mitigates security risks associated with sending photos of a user’s face used for authentication over the internet TrulySecure can also be used to reduce authentication data loads sent to cloud-based authentication systems by moving pre-authentication steps like liveness detection and feature extraction to the edge. TrulySecure’s on-device liveness detection can be used to immediately verify user authentication samples for liveness before sending captured authentication images to the server for processing. Taking it another step further, by enabling TrulySecure’s on-device feature extraction, once the AI detects liveness, it can then immediately convert the user’s facial features into templates (irreversible mathematical data) that can be sent to the authentication server instead of sending multiple images. This mitigates security risks associated with sending photos of a user’s face used for authentication over the internet, and significantly reduces the amount of data sent to the cloud for authentication. Ideal for a wide range of applications, including smartphones, tablets, PCs, personal assistant technologies and robots, Sensory’s SDK for TrulySecure 4.0 face authentication is now available and currently supports ToF 3D cameras from pmd Technologies.

According to Save The Rhino statistics, over 1000 rhinos are killed annually in South Africa. These harrowing poaching statistics display a gloomy future for survival of this beautiful species. While many attempts have been undertaken over the past ten years to combat the devastating results of poaching, the country has not yet seen a steady decline in numbers year-on-year. It is with this knowledge that AxxonSoft’s Global Marketing Director, Colleen Glaeser, who is based in South Africa, decided to create a strategical and proactive anti-poaching approach, utilising the tools at her disposal, assisting a country in dire need of assistance. While Deep Learning, using Artificial Intelligence and neural network analytics in its algorithm, is not new to the security and surveillance industry, Colleen and the team at AxxonSoft global took the technology a step further, developing and implementing the software to help differentiate between humans and animals. Identifying actual poaching threats AxxonSoft’s surveillance software, which leverages Artificial Intelligence and Deep Learning technology now alerts the operators in the control room to an immediate poaching threat The implementation of this technology in game reserves and parks across South Africa has certainly been a game-changer regarding the war against poaching. For two reasons namely; this neural network solution can identify actual poaching threats (distinguishing poachers from their prey) while providing a proactive surveillance solution as opposed to a reactive one. Predominately utilised for face and license plate recognition, Deep Learning technology has never been adapted to tell the difference between humans and animals. Prior to the incorporation of Deep Learning in anti-poaching surveillance, software often failed control rooms and response units in that false alarms were on many occasions, set off by animals, insects and weather. Control rooms were not able to tell the difference between an actual threat and a false alarm, which often resulted in exhausting resources as teams were dispatched for animals who had touched the fence while grazing in their natural habitat. AxxonSoft’s leading surveillance software, which leverages Artificial Intelligence and Deep Learning technology now alerts the operators in the control room to an immediate poaching threat as poachers try and breach the fence perimeter to enter the reserve or park. Proactive surveillance solution AxxonSoft’s Deep Learning technology provides a proactive solution to surveillance whereas previous systems were somewhat archaic and reactive in their response to real threats Global Marketing Director for AxxonSoft, Colleen Glaeser says, “Our Deep Learning technology has been extremely successful thus far in telling the difference between animals and humans as the neural network algorithm can identify, through certain indicators, whether a human or animal has set off the alarm. If the software detects a human, the operations team is immediately notified and a dispatch team is sent to the scene in question.” Furthermore, AxxonSoft’s Deep Learning technology provides a proactive solution to surveillance whereas previous systems were somewhat archaic and reactive in their response to real threats. Due to expansive terrain and limited resources, rangers and antipoaching units often get to the scene of the crime too late. With the AxxonSoft technology, as soon as the breach occurs, cameras will identify if the breach has been caused by an animal or human, and the control room is immediately notified as to where the occurrence has taken place in the reserve or park. The dispatch team is given the necessary information and they head to the site where the occurrence has taken place. Real-time identification of threats By utilising this technology, we have been able to take a proactive approach, identifying the threat in a real time situation" The beauty about Deep Learning and Neural Network analysis is in its ability to learn and understand the conditions which lead up to an event, and that ultimately allows us to prepare for threats or potential breaches when the known conditions are met. “AxxonSoft’s technology has proved very successful in preventing killings as the team is able to get to the scene of the crime quickly. “By utilising this technology, we have been able to take a proactive approach, identifying the threat in a real time situation. The AxxonSoft team and I really believe this anti-poaching solution can aid in the war against poaching and drastically bring down the upsetting statistics. I can attest to the fact that we have seen great success in curbing poaching,” concludes Glaeser.

As an innovator in airport security, Oakland International Airport (OAK) announced that it has installed the Evolv Edge, a physical threat detection and prevention system powered by artificial intelligence, to streamline its employee screening program. This installation enhances OAK’s security posture by protecting against metallic and non-metallic threats while simultaneously improving operational efficiency. Physical threat detection system OAK is committed to applying advanced, innovative solutions to complex security operations OAK is committed to applying advanced, innovative solutions to complex security operations. The TSA acknowledged this commitment by selecting OAK as a TSA Innovation Site, a prestigious distinction that promotes improved efficiency and allows the airport to try technologies to benefit its growing passenger and employee base. As the second busiest airport in northern California, passenger travel at OAK is on pace to surpass the 13.2 million travelers that passed through the airport last year. To accommodate this growth, more and more employees are being hired to work at OAK. Therefore, OAK began researching innovative solutions related to employee inspection methods and equipment. Evolv Edge provides OAK with the ability to screen employees for metallic and non-metallic threats with a fast, non-invasive process. Designed with built-in wheels for portability, OAK can easily move the system throughout the airport allowing maximum efficiency for its employee inspection program. Non-invasive employee screening With Edge, organisations, such as OAK, can adapt a risk-based security approach while balancing security with positive experience With this installation, OAK continues to be at the forefront of security through its use of modern technologies to combat today’s evolving threat landscape. By replacing traditional physical screenings with Evolv Edge’s precision, mobility and multi-threat detection capabilities, OAK can control access and respond to different threat scenarios quickly and efficiently. With Edge, organisations, such as OAK, can adapt a risk-based security approach while balancing security with positive experience. “With today’s threat landscape, the security perimeter has expanded beyond traditional checkpoints,” said Mike Ellenbogen, CEO of Evolv Technology and a 20-year veteran in aviation security. “Evolv Edge’s flexibility and portability provides Oakland International Airport with an added layer of security when it comes to employee screening. Oakland International Airport is always at the forefront of innovation, and we will continue working closely with their team to ensure success and safety.”

It was over a century ago that Charlotte Hungerford Hospital (CHH) was founded, as a gift by industrialist Uri T. Hungerford. The vision was to create a community hospital that would serve as a beacon of hope and a place of comfort for the ill and injured. 100 years later, that same community spirit has helped CHH evolve into a vibrant, independent, affordable healthcare network that delivers a comprehensive range of healthcare programs and services for over 100,000 lives in Northwestern Connecticut. A challenging safety diagnosis Avigilon has made us more efficient as we don’t have to spend much time sifting through large amounts of video” Charlotte Hungerford Hospital prides itself on supporting patient and staff safety in all hospital areas and locations. Several years ago, they found themselves with an outdated security system that lacked quality video coverage and recording capabilities. CHH struggled with reliable video playback and faced frequent system crashes. As a result, the hospital’s security operators were often unable to provide accurate evidence during forensic investigations and many liability claims and hospital incidents went unresolved. CHH needed a cost-effective, comprehensive security solution that could protect patients and staff across multiple locations while still being flexible enough to scale with the hospital’s growing needs.  Avigilon AI & analytics technology With a desire to improve its legacy surveillance system, CHH looked to Avigilon’s advanced artificial intelligence (AI) technology and video analytics to meet their security needs. CHH began a multi-phase upgrade that included installing over 100 Avigilon cameras with self-learning video analytics, deploying AI-based Avigilon Appearance Search technology and using impulse radar technology with the Avigilon Presence Detector (APD) Sensor. Avigilon Appearance Search technology – a sophisticated deep learning AI search engine – helps CHH quickly locate a specific person or vehicle of interest across all cameras both inside the hospital and care centres as well as outside parking lots. This technology provides CHH’s operators with enhanced situational awareness, enabling fast event response and helping to save time and effort during critical investigations. To protect areas of the hospital where cameras cannot be installed, CHH installed the Avigilon Presence Detector (APD), a discreet impulse radar device with self-learning radar analytics that scans, learns, and continuously adapts to its environment. Avigilon presence detector sensors Our Security Department’s mission at Charlotte Hungerford Hospital is the safety of our patients, visitors, and employees” Capable of detecting persons who aren’t moving or are hidden, the APD sensors help improve situational awareness for CHH staff, and are used in areas where cameras are not permitted, such as restrooms or change rooms. When integrated with Avigilon Control Centre (ACC) video management software, APD sensors alert CHH operators of human presence while still maintaining privacy. Avigilon H4 cameras were used throughout the hospital to provide exceptional image quality and built-in self-learning video analytics, which provides accurate detection and notification of movement of people and vehicles. CHH also deployed HD Multi-sensor cameras which provide up to four camera views per camera installation, using only one camera license and network drop. This allows CHH’s staff to efficiently cover all angles in order to detect, verify, and act on potential security events across the hospital’s premises. Avigilon H4 and HD multi-sensor cameras At the core of CHH is a desire to help the community and still serve as the beacon of compassion it was founded to be 100 years ago. With these values in mind, the hospital’s mission when it comes to security is the safety of patients, visitors, and employees. Avigilon’s AI solutions have helped achieve this by moving the CHH system from legacy to advanced and providing effective monitoring around the clock while also helping to create operational efficiencies. Since deploying ACC software, CHH’s operators spend significantly less time reviewing recorded video, allowing them to focus on proactive event response. Working with Avigilon, Charlotte Hungerford Hospital has a roadmap for continued growth and exceptional patient safety.

Founded in 1871, Fulton County School System is the fourth largest school district in Georgia, United States. It consists of 101 schools and administrative support buildings, including 67 elementary schools, 19 middle schools, 17 high schools and eight charter organisations. Fulton’s mission is to provide a safe and secure environment for its more than 96,000 students and more than 12,000 full-time employees. To help enhance safety Search Technology at more than 100 schools, Fulton has installed a full Avigilon surveillance solution that includes Avigilon cameras with self-learning video analytics, Avigilon network video recorders, and Avigilon Control Center (ACC) video management software with Avigilon Appearance Search technology. Fulton is also deploying Avigilon Access Control Manager to secure physical access points, providing an integrated security solution for the district. Fulton sought to replace analogue cameras with an end-to-end high definition surveillance system camera system in order to maximise protection Simplifying recording and capturing of footage Fulton sought to replace analogue cameras with an end-to-end high definition surveillance system camera system in order to maximise protection, enable proactive event response, and facilitate the recording, capturing and sharing of clear footage with its school board, police and the concerned public. Securing more than 100 buildings is no easy feat, but it’s of utmost importance to the Department of Safety and Security at Fulton, which also includes the School Police and Student Health Services and Emergency. Upgrading video surveillance system With recent data showing above average student incident rates and student disciplinary concerns at some schools, upgrades to the surveillance system were needed to allow better local and remote monitoring in important areas. “One of the biggest security challenges we face is our ability to reliably monitor important areas throughout our schools, especially during an emergency. With Avigilon, we not only benefit from exceptional image quality, but their advanced video analytics, like Avigilon Appearance Search technology, save us valuable time and effort, ultimately making our schools a safer place.” - Paul Hildreth, Emergency Operations, Safety and Security, Fulton County School System. Avigilon high-definition cameras with self-learning video analytics and access control solutions have been installed in 101 schools Appearance Search Technology Avigilon high-definition cameras with self-learning video analytics and access control solutions have been installed in 101 schools. ACC 6 video management software with Avigilon Appearance Search technology is a particularly exciting new development for the district. “We chose Avigilon because of the capabilities it offers in its advanced video analytics search technologies, including Avigilon Appearance Search,” said Paul Hildreth, Emergency Operations, Safety and Security for Fulton. “Their analytics are easy to set up and use, and can save us valuable time and effort, ultimately making our schools a safer place for generations to come.” Video data analysis Avigilon Appearance Search video analytics technology uses a sophisticated deep learning artificial intelligence search engine to sort through hours of footage with ease. This technology allows Fulton’s operators to click on a button and search for all instances of a person or vehicle across all cameras on a site, quickly and efficiently. This can save Fulton time and effort during critical investigations as Avigilon Appearance Search technology intelligently analyses video data, helping to track a person’s or vehicle’s route and identify previous and last-known locations. Avigilon self-learning video analytics enable proactive, real-time event response. Built from the ground up to manage high-definition video, Avigilon offers self-learning analytics on camera resolutions of up to 5K (16 MP). Avigilon Multisensor cameras were also set up to capture challenging angles and provide total coverage within a 180 to 360-degree area Avigilon H4 Platform Avigilon H4 bullet and dome cameras from the new H4 platform were installed, offering self-learning video analytics, greater resolution performance and Wide Dynamic Range support. Avigilon H4 cameras are available in 1 to 5 MP and 4K Ultra HD (8 MP) resolutions. Avigilon Multisensor cameras were also set up to capture challenging angles and provide total coverage within a 180 to 360-degree area. Upgrading the district’s surveillance solutions began three years ago with a single high school as a pilot program. The success of this replacement led the district to integrate ACC in other school projects and, in 2014, Fulton opened new administrative centres with both Avigilon access control and video surveillance solutions. At the start of 2017, Fulton began implementing a three-year approach to completing the upgrade. Image quality and resolution Before switching to the Avigilon solution, the district was challenged with low system reliability, which resulted in not having video evidence when needed. Furthermore, in situations where there was recorded footage, it was not of high enough quality to provide value. With the installation of Avigilon video surveillance, Fulton has benefited from exceptional image quality and resolution across wide areas in all lighting conditions. The ongoing Avigilon implementation will provide the district with crucial and powerful insights that can help save time and effort during critical investigations. With the help of Avigilon trusted security solutions, the future looks bright for Fulton County Schools.

There is no expectation of privacy in a public space. That’s the premise on which most video surveillance applications are justified. But new concerns about privacy, specifically the General Data Protection Regulation (GDPR) in Europe, are changing expectations. And what if a camera must be positioned where a private area happens to be within its range? Fortunately, there are technology approaches to solving these dilemmas, as our Expert Panellists explain. We asked: What new technologies are helping video systems overcome concerns about privacy?

Artificial intelligence (AI) is a current buzzword in the physical security market – and the subject of considerable hype. However, AI sometimes get negative press, too, including dire warnings of its potential and eventual impact from some of our most prominent technology thinkers. We decided to take the issue to our Expert Panel Roundtable with this week’s question: What are the negative impacts and/or new challenges of AI for physical security?

We are living in the age of Big Data, and businesses are inundated with large volumes of data every day. Success depends on capturing, analysing and ultimately transforming that data into information and intelligence that can be used to improve the business. So, it is with today's physical access control and video systems, too, which also generate unprecedented levels of data. But how can we make the data useful to end users and how can they realise its full value? We asked this week's Expert Panel Roundtable: Relating to physical security systems, what is the value of data and how can that value be measured?