Facial recognition systems

In order to improve security standards, in the last few months and since the beginning of the 2018/2019 season the Panomera camera system has been installed and tested in the Generali Arena in Prague, home ground of AC Sparta Praha. This technology is also used by many football clubs in the German Bundesliga and the English Premier League. After successful completion of the test phase, the club then switched the system into operational mode. AC Sparta Praha has launched a modernisation project for its security system with the objective of providing fans greater comfort and a feeling of increased security in their home arena, and to help prevent the occurrence of unwelcome incidents. Substantial financial investment If the rules are violated while a match is being played, this technology makes it possible to bring charges against individual offenders The system is also used for incident analysis, to deliver better video material so that the involvement of specific individuals can be proven accurately when offences occur. If the rules are violated while a match is being played, this technology makes it possible to bring charges against individual offenders or a larger group of fans. The system records continuously and stores what is happening at all locations on the tribunes. This in turn enables the direct display and investigation of incidents and their causes, which is made simpler by the simultaneous, time-synchronised playback of multiple video streams. The installation of this new camera system is not a reaction to what took place during the Europa League qualifying round match against Subotica, but a strategic measure for which the ACS club management decided earlier despite the substantial financial investment. Evidentiary procedure By the time of the game against the Serbian team Subotica, which was played on 2 August 2018, the CCTV system was already in the final stage of testing, which meant that the material recorded could be used for the investigation and evidentiary procedure. The club is prosecuting fans who engaged in unacceptable behaviour during the match extremely vigorously, and long stadium bans and fines have already been imposed. The club cooperated successfully with three companies to achieve the implementation of this CCTV solution: with Dallmeier – manufacturer of the Panomera technology, with T-Mobile – data infrastructure provider – and with Made in PUBLICITY, which was responsible for integrating the system and installation. Unambiguous facial identification The video material recorded with Panomera far surpasses the standard 1080-HD format, while capturing up to 30 images per second in real time The Panomera camera system has already been installed successfully in most stadiums in the Bundesliga (e.g., Allianz Arena - Bayern Munich, Signal Iduna Park - Borussia Dortmund, Commerzbank Arena - Eintracht Frankfurt) and in the English Premier League (e.g., Old Trafford - Manchester United, Emirates Stadium - Arsenal London) as well as in modern stadiums in Russia, host nation to the 2018 World Cup competition. The video material recorded with Panomera far surpasses the standard 1080-HD format, while capturing up to 30 images per second in real time. Recording is performed in a resolution of up to 320 pixels per metre, enabling unambiguous facial identification. For comparison: typically only half of this resolution, 125 pixels per metre is needed for normal facial recognition.

BriefCam, the provider of Video Synopsis and Deep Learning solutions, announces v5.3 of its innovative and extensible video content analytics platform. BriefCam v5.3 introduces new breakthrough capabilities across all three of the platform’s seamlessly integrated solutions, delivering a powerful and innovative approach to making video content searchable, actionable and quantifiable. BriefCam’s v5.3 highly accurate face recognition extends its real-time alerting, search and quantitative analytics capabilities. Leveraging state-of-the-art Deep Neural Networks trained in diverse data sets for accuracy in face matching, BriefCam v5.3’s face recognition capabilities help streamline post-event investigations, supports rapid response to situational changes, and derive richer operational intelligence for data-driven decision making. Accelerate investigations Robust multi-camera search capabilities identify men, women, children and vehicles with speed and precision, using 25 classes and attributes Robust multi-camera search capabilities identify men, women, children and vehicles with speed and precision, using 25 classes and attributes, face recognition, appearance similarity, color, size, speed, path, direction, and dwell time Precise face recognition rapidly pinpoints people of interest in real-time using digital images extracted from video, external image sources and pre-defined watchlists Dynamic case collaboration improves investigation productivity and time to target Derive operational intelligence Seamlessly correlated video content with 3rd party data sources such as Point of Sale, Time Management, and Access Control provides unique insights into operations Highly customisable dashboards aggregate and trend identities, object interactions, demographics, hotspots, and vehicle movement patterns over time Integrated face recognition enables unique insights into employee productivity and customer satisfaction Attain situational awareness Real-time alerts based on face recognition, vehicles and people in areas of interest, provide immediate notification of situational changes Real-time alerts based on face recognition, vehicles and people in areas of interest, provide immediate notification of situational changes Scalable watchlist management enable rapid and powerful rule configuration Effective balancing of sensitivity, accuracy, and efficiency minimising alert fatigue Real-time actionable intelligence “BriefCam v5.3 further enables organisations to derive exponential value from their existing video surveillance system investments,” said Trevor Matz, BriefCam president and CEO. “With the addition of highly accurate, real-time face recognition capabilities to our extensible video content analytics platform, organisations can further benefit from real-time actionable intelligence for their situational awareness and operational agility initiatives.” BriefCam will demonstrate the advanced capabilities of its v5.3 platform at ISC East 2018 in booth #458. BriefCam has also been named a finalist for the Astor’s Awards in the category for Best Video Analytics Solution. Winners will be announced on November 14th, 2018.

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.

Dahua Technology has been exhibiting its full line of machine vision products at Vision Stuttgart, a trade fair for machine vision, during November 6th to 8th at booth 1C22, Messe Stuttgart. With the -vision ‘Turning Vision into Productivity’, Dahua Technology highlights the company’s deep expertise and its roadmap for the future. Nowadays, manufacturing is evolving towards automation, but the key for productivity improvement lies in vision technologies like image capture, analysis and pattern recognition. Underscoring the vision of ‘Turning Vision into Productivity’, Dahua Technology showcased a portfolio of varied industrial cameras, including large area scan cameras, area scan cameras, line scan cameras, smart cameras, code reading cameras, 3D measurement cameras, industrial lenses and train OCR solution. Precisely reading codes Combining intelligent cameras and code readers, the system is capable of precisely reading codes at a high speed High-accuracy 3D camera: Equipped with laser, the camera can measure features with an accuracy of 20μm, and can widely be used in demanding data collection applications such as extremely small parts or PCR. High-speed code reading system: Combining intelligent cameras and code readers, the system is capable of precisely reading codes at a high speed. The system can be widely applied in logistics, storage and tracing parcels on vehicles. MZR camera: Featuring an A75000PG polarised chip, the camera is capable of detecting uneven surfaces, and is very useful in applications like examining the evenness of acrylic surface. 12MP XGS camera: This camera is a visual detection device that replaces human in measuring. Greatly enhancing automation and productivity, the camera has proven application in production, assembling and packaging, etc. Large image detection 3D measurement camera: Equipped with laser, the camera is capable of large volume measuring at an accuracy of 5mm, and is widely applied in volume measurement of logistics parcels. 16K/4K resolution line scan camera: Offering a line sweep rate of up to 140K to ensure accurate large image detection even at a high speed, it can be widely used in Train OCR, printing quality control and other areas. Dahua Technology’s self-developed deep-learning algorithms enhance its performance in high accuracy detection of GEVI, UIC, container number and carriage number. 50MP CXP large area scan camera: Offering ultra-high resolution at 30 frames per second, the camera is suitable for applications such as LCD screen detection, PCB inspection, and railway inspection. Wide dynamic range 25MP large area scan camera: Equipped with Gpixel GMAX0505 CMOS sensor to minimise power consumption and increase pixel sensitivity, the camera outputs images at 1:1 ratio, while maintaining a wide dynamic range at a very low noise level, and is suitable for high accuracy detection of wafer, solar panels, etc. High DOF code reading system: A smart camera with high DOF design for enhanced precision and accuracy. 0 815fps camera: The high-speed camera is capable of capturing water drops and high-speed moving objects respectively. Multi-functional integrated solution Dahua Technology also presents its multi-functional integrated solution over manufacturing Besides these products, Dahua Technology also presents its multi-functional integrated solution over manufacturing, which includes the small area cameras with visual controller for pattern matching, X86 smart camera SI5500MG000 for OCR character recognition, Movidius smart camera S5051MG00 for liquid level detection, and the 1.3 mega pixels code reader R5131MG000 for code reading. Through exhibiting cutting-edge products and technologies, Dahua Technology emphasises the vision of ‘Turning Vision into Productivity’. Tapping into trends such as digitalisation and automation, the company is committed to its vision by delivering widely applicable solutions featuring high performance and high intelligence.

Season-ticket holders at Belgian football club RWD Molenbeek will soon find it easier to enter the stands at their stadium, thanks to facial recognition technology that is set to be introduced at the turnstiles. Although the project is still in the test phase, fans ordering their season tickets on-line can already upload an ID photo. This photo will be compared in real time with images taken by two cameras installed in the season-ticket holders’ queue at the stadium entrance, allowing supporters to enter much faster. An automatic gate will be installed in early 2019. Data processing facility Spectators who have forgotten their paper ticket can still enter the stadium with no problem. Those who haven't uploaded a photo, or who have borrowed an entry ticket, will still have to pass through the conventional gates and show their ticket at the turnstiles. The system was installed by Zetes using Panasonic facial recognition technology. The detection system, with its fast and reliable data processing facility, means we can install a system to speed up entry checks to the stadium" The facial recognition software applies only to the access checks, as a further benefit for season-ticket holders. Thierry Dailly, chairman of RWDM, explains: “The detection system, with its fast and reliable data processing facility, means we can install a system to speed up entry checks to the stadium.” Alain Wirtz, CEO of Zetes, adds: “This project is a perfect example of how we can benefit from the innovative capabilities provided by the Panasonic group, owner of Zetes. Zetes specialises in this identification technology, which has many different applications. We hope this project can act as a shop window for our products.” The pilot project will run for about a year. Guaranteeing confidentiality Supporters’ photos are scanned and stored on an RWDM server, which is not connected to the Internet or to any other system. Only RWDM-authorised personnel have access to the data. Data collected by the entrance gate cameras is not recorded, guaranteeing confidentiality for the supporters. At this stage, the system is still in the test phase, and the facial recognition facility is not yet fully operational. The installation of the automatic gate at the beginning of 2019 will complete the planned programme. 2017 April, Panasonic acquired a majority shareholding in Zetes and 2017 July completed the acquisition of 100% shares of Zetes. Zetes was founded in 1984, and employs 1100 employees in 21 countries in EMEA in 2016. Its headquarters is in Brussels.

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.’

When a child goes missing in a large, crowded mall, we have a panicking mom asking for help from the staff, at least a dozen cameras in the area, and assuming the child has gone missing for only 15 minutes, about 3 hours’ worth of video to look through to find the child. Typical security staff response would be to monitor the video wall while reviewing the footage and making a verbal announcement throughout the mall so the staff can keep an eye out for her. There is no telling how long it will take, while every second feels like hours under pressure. As more time passes, the possible areas where the child can be will widen, it becomes more time-consuming to search manually, and the likelihood of finding the child decreases. What if we can avoid all of that and directly search for that particular girl in less than 1 second? Artificial neural networks are improving every day and now enable us to search for a person across all selected camera streamsWith Artificial Intelligence, we can. Artificial neural networks are improving every day and now enable us to search for a person across all selected camera streams in a fraction of a second, using only one photo of that person. The photo does not even have to be a full frontal, passport-type mugshot; it can be a selfie image of the person at a party, as long as the face is there, the AI can find her and match her face with the hundreds or thousands of faces in the locations of interest. The search result is obtained in nearly real time as she passes by a certain camera. Distinguishing humans from animals and statues The AI system continuously analyses video streams from the surveillance cameras in its network, distinguishes human faces from non-human objects such as statues and animals, and much like a human brain, stores information about those faces in its memory, a mental image of the facial features so to speak. When we, the system user, upload an image of the person of interest to the AI system, the AI detects the face(s) in that image along with their particular features, search its memory for similar faces, and shows us where and when the person has appeared. We are in control of selecting the time period (up to days) and place (cameras) to search, and we can adjust the similarity level, i.e., how much a face matches the uploaded photo, to expand or fine-tune the search result according to our need. Furthermore, because the camera names and time stamps are available, the system can be linked with maps to track and predict the path of the person of interest. AI Face Search is not Face Recognition for two reasons: it protects people’s privacy, and it is lightweight Protecting people’s privacy with AI Face Search  All features of face recognition can be enabled by the system user, such as to notify staff members when a person of interest is approaching the store AI Face Search is not Face Recognition for two reasons: it protects people’s privacy, and it is lightweight. First, with AI Face Search, no names, ID, personal information, or lists of any type are required to be saved in the system. The uploaded image can be erased from the system after use, there is no face database, and all faces in the camera live view can be blurred out post-processing to guarantee GDPR compliance. Second, the lack of a required face database, a live view with frames drawn around the detected faces and constant face matching in the background also significantly reduces the amount of computing resource to process the video stream, hence the lightweight. Face Search versus Face Recognition AI Face Search Face Recognition Quick search for a particular person in video footage Identify everyone in video footage Match detected face(s) in video stream to target face(s) in an uploaded image Match detected face(s) in video stream to a database Do not store faces and names in a database Must have a database with ID info Automatically protect privacy for GDPR compliance in public places May require additional paperwork to comply with privacy regulations Lightweight solution Complex solution for large-scale deployment Main use: locate persons of interest in a large area Main use: identify a person who passes through a checkpoint Of course, all features of face recognition can be enabled by the system user if necessary, such as to notify staff members when a person of interest is approaching the store, but the flexibility to not have such features and to use the search tool as a simple Google-like device particularly for people and images is the advantage of AI Face Search.Because Face Search is not based on face recognition, no faces and name identifications are stored Advantages of AI Face Search Artificial Intelligence has advanced so far in the past few years that its facial understanding capability is equivalent to that of a human. The AI will recognise the person of interest whether he has glasses, wears a hat, is drinking water, or is at an angle away from the camera. In summary, the advantages of Face Search: High efficiency: a target person can be located within a few seconds, which enables fast response time. High performance: high accuracy in a large database and stable performance, much like Google search for text-based queries. Easy setup and usage: AI appliance with the built-in face search engine can be customised to integrate to any existing NVR/VMS/camera system or as a standalone unit depending on the customer’s needs. The simple-to-use interface requires minimal training and no special programming skills. High-cost saving: the time saving and ease of use translate to orders of magnitude less manual effort than traditionally required, which means money saving. Scalability: AI can scale much faster and at a wider scope than human effort. AI performance simply relies on computing resource, and each Face Search appliance typically comes with the optimal hardware for any system size depending on the customer need, which can go up to thousands of cameras. Privacy: AI Face Search is not face recognition. For face recognition, there are privacy laws that limits the usage. Because Face Search is not based on face recognition, no faces and name identifications are stored, so Face Search can be used in many public environments to identify faces against past and real-time video recordings. AI Face Search match detected face(s) in video stream to target face(s) in an uploaded image Common use cases of AI Face Search In addition to the scenario of missing child in a shopping mall, other common use cases for the AI Face Search technology include: Retail management: Search, detect and locate VIP guests in hotels, shopping centres, resorts, etc. to promptly attend to their needs, track their behaviour pattern, and predict locations that they tend to visit. Crime suspect: Quickly search for and prove/disprove the presence of suspects (thief, robber, terrorist, etc.) in an incident at certain locations and time. School campus protection: With the recent increase in number of mass shootings in school campuses, there is a need to identify, locate and stop a weapon carrier on campus as soon as possible before he can start shooting. Face Search will enable the authorities to locate the suspect and trace his movements within seconds using multiple camera feeds from different areas on campus. Only one clear image of the suspect’s face is sufficient. In the race of technology development in response to business needs and security concerns, AI Face Search is a simple, lightweight solution for airports, shopping centres, schools, resorts, etc. to increase our efficiency, minimise manual effort in searching for people when incidents occur on site, and actively prevent potential incidents from occurring. By Paul Sun, CEO of IronYun, and Mai Truong, Marketing Manager of IronYun

In today’s market, efficient use of bandwidth and storage is an essential part of maintaining an effective video surveillance system. A video management system’s ability to provide analysis, real time event notifications and crucial image detail is only as a good as the speed and bandwidth of a surveillance network. In the physical security industry, H.264 is the video compression format used by most companies. Some companies also employ H.264 enhancements to compress areas of an image that are irrelevant to the user at a higher ratio within a video stream in order to preserve image quality for more important details like faces, license plates or buildings. The H.265, H.264’s successor, will be increasingly used for compression in the future. Some companies are already using H.265 in their cameras and video management systems, while a host of other manufacturers are certainly preparing for its broader adoption in the years to come. Video compression technologies Reduced bandwidth and storage requirements are the primary benefits of video compression technologies Reduced bandwidth and storage requirements are the primary benefits of video compression technologies. In some cases, H.265 can double the data compression ratio of H.264, while retaining the same quality. Increased compression rate translates into decreased storage requirements on hard drives, less bandwidth usage and fewer switches – all of which reduce overall costs of system ownership. H.265 compression delivers a lower bitrate than H.264, which is relevant to end users and integrators because the lower bitrate reduces strain on hardware and can reduce playback issues. It’s very important that the compression format that is used is supported in all of the different components of a system: cameras, desktop computers on which the VMS is running and the VMS itself. It is also good for end users and integrators to understand the basics of video compression. Having a basic understanding of compression allows users to tweak settings to reduce bandwidth usage even more. Many cameras come with default settings that can be changed to ultimately reduce costs. ONVIF physical security In the physical security industry, ONVIF is working to incorporate into its specifications the use of new formats such as H.265 but is not directly involved in developing the compression standards themselves. With Profile T, the new ONVIF video profile released will employ a new media service that is compression agnostic. This means that it can support new video compression formats, including H.265, as well as new audio compression formats, with the ability to include new video and audio codecs as needed in the future without having to redesign its media service. In the physical security industry, ONVIF is working to incorporate into its specifications the use of new formats such as H.265 Standardisation organisations that are directly addressing new compression standards include the International Telecommunication Union (ITU), the Moving Picture Experts Group (MPEG) and a joint commission of the International Organization for Standardization (ISO)/International Electrotechnical Commission (IEC), which is addressing the coding of audio, picture, multimedia and hypermedia information. Other compression formats on par with H.264 and H.265 are being developed by companies such as Google. H.265 compression formats Using products that employ H.265 compression will reduce costs through bandwidth reduction, as will changing default settings on cameras, which are often conservative. Having a basic understanding of compression formats and how to tweak camera factory default settings also gives integrators the ability to further reduce bandwidth for added costs savings and increased system performance. These enhancements will analyse which parts of an image are most important and adjust local levels of compressions accordingly It is also worth noting that H.265 enhancements will likely be developed by camera manufacturers to further reduce bandwidth, as was the case with H.264. These enhancements will analyze which parts of an image are most important and adjust local levels of compressions accordingly. While H.265 itself is ready for prime time, its value as a tool for IP-based surveillance systems is dependent on support for the codec in all parts of the system – the VMS, server hardware, graphics cards and camera. Though widespread H.265 adoption is predicted, providers of these components are jumping on the H.265 bandwagon at different rates of speed. ONVIF is including support for H.265 in its new video profile, Profile T, because it believes it will become the most widely used compression format and ONVIF recognises the need to anticipate that migration as a future need of the industry. The new media service, which will be implemented with Profile T, will be future-proof in that when new compression formats are released in the future, ONVIF can adopt them very quickly. That flexibility will definitely help integrators.

Facial recognition has a long history dating back to the 1800s. To track down criminals, such as infamous bandits Jesse Woodson James and Billy the Kid, law enforcement would place “Wanted Alive or Dead” posters advertising bounties and soliciting public cooperation to help locate and even apprehend the alleged criminals. In addition to the bounty, these posters would include a photo and brief description of the crime, which would then be circulated to law enforcement agencies around the country and displayed in every US Post Office to speed up apprehension. Facial recognition Advancements in artificial intelligence and biometric technology have led to the widespread use of computerised facial recognition Today, technology such as social media, television and other more specialised communication networks play a more influential role in the recognition process. Advancements in artificial intelligence and biometric technology, including the development of Machine Learning capabilities, have led to increased accuracy, accessibility and the widespread use of computerised facial recognition. The significance of this means that facial recognition can occur on an even larger scale and in more challenging environments. This article will explore key milestones and technological advances that have resulted in the modern incarnation of facial recognition, before discussing the capabilities of cutting-edge “one-to-many” technology which is increasingly being used by counter-terror defence, police and security forces around the world. Technology inception and developments The technology was able to match 40 faces an hour, which was considered very impressive at the time The 1960s marked the start of computerised facial recognition, when Woodrow Wilson (Woody) Bledsoe developed a way to classify faces using gridlines. Bledsoe’s facial recognition still required a large amount of human involvement because a person had to extract the co-ordinates of the face’s features from a photograph and enter this information into a computer. The technology was able to match 40 faces an hour (each face took approximately 90 seconds to be matched) which was considered very impressive at the time. By the end of the 1960s, facial recognition had seen further development at the Stanford Research Institute where the technology proved to outperform humans in terms of accuracy of recognition (humans are notoriously bad at recognising people they don’t know). By the end of the century, the leading player in the field was a solution that came out of the University of Bochum in Germany – and the accuracy of this technology was such that it was even sold on to bank and airport customers. From this stage on, the facial recognition market began to blossom, with error rates of automatic facial recognition systems decreasing by a factor of 272 from 1993 to 2010 according to US Government-sponsored evaluations. The aim for facial technology is to achieve successful and accurate recognition on commonly available hardware like live CCTV feeds and standard computing hardware Modern usage of facial recognition Fast-forward to the modern day and facial recognition has become a familiar technology when using applications such as the iPhone X’s Face ID capability or MasterCard Identity Check, passport e-gates at airports and other security and access control points. These solutions implement a consensual form of identity verification, as the user has a vested interest in being identified. This is a “one-to-one” facial recognition event, one person in front of the camera being compared to one identity either on a passport or the app. In these scenarios, the hardware is specifically developed for the application at hand, therefore technically much easier to accomplish. Facial recognition can now be used in a variety of governmental and commercial environments The safety and security world brings a much more complex problem to solve – how to pick out a face in a moving and changing environment and compare it to several faces of interest. “One-to-many” facial recognition is a much harder problem to solve. It’s even more challenging when the aim is to achieve successful and accurate recognition on commonly available hardware like live CCTV feeds and standard computing hardware. And unlike in the 1960’s where identifying a face every 90 seconds was acceptable; the safety and security market requires near instant feedback on who a person matched against a watchlist is. Security and safety applications The idea behind all facial recognition technologies is broadly the same: you start with an image of a person’s face (ideally a high quality one, although machine learning means that to a point we can now even use video without reducing accuracy). A fully front facing image is best, think a passport photo, but machine learning and new software has made this more flexible. An algorithm converts this image into a numeric template, which cannot be converted back to an image and so represents a secure one way system. Every numeric template is different, even if it started out as an image of the same person, although templates from the same person are more similar than templates from different people. The accuracy of facial recognition continues to increase alongside deployments in more challenging and complex environments What happens next sounds simple although the technology is extremely complex: templates of people’s faces are taken in real time and compared to those in the database. The technology identifies individuals by matching the numeric template of their face with all the templates saved in a database in a matter of seconds or milliseconds. To put this into perspective, imagine you are at the turnstiles of a busy train station looking for a person on the run. Today’s facial recognition technology would be able to identify that person should they pass in view of a CCTV camera, as well as notify the police of any additional persons of interest, whether they are a known terrorist or missing vulnerable person on an entirely separate watch list. Because of technical progression, facial recognition can now be used in a variety of governmental and commercial environments, from identifying barred hooligans attempting entry at a football stadium or helping self-excluded gamblers at casino to overcome addiction. Real-time assessments The latest evolution of facial recognition pits the technology against an even more challenging application – directly matching individuals from body worn cameras for real time recognition for police officers on the beat. This capability equips first responders with the ability to detect a person from a photo and verify their identity with assurance. The broader implication for this means that every interaction, such as stop and search or arrest, can be supported by real-time facial recognition which will see cases of mistaken identity driven down on the streets. First responders can now for the first time be deployed and furnished with the ability to identify wider groups of people of interest with a degree of accuracy that previously relied only on the fallible human memory. As the accuracy of the technology continues to increase alongside deployments in more challenging and complex environments, its ability to support government initiatives and law enforcement means the debate about the lawful and appropriate use of facial recognition must be addressed. Facial recognition should not be everywhere looking for everyone, but when used properly it has the potential to improve public safety and we should make the most of its potential.

Security Essen 2018, held in Messe Essen, Germany, promised attendees a newly modernised trade show with a simplified layout and more interactive experience. Compared to previous years, halls were reorganised by technology area, with aisles laid out to make more direct pathways for attendees. The fair welcomed 950 exhibitors and more than 36,000 trade visitors from the global security market. Several manufacturers mentioned that footfall had been lighter than expected, but that the show had delivered on its promise to welcome more international visitors, in particular from the Middle East region. Exhibitors also grumbled about higher costs for booth space. Key security industry exhibitors Exhibitors expressed concern that the absence of key players reduced overall foot traffic Exhibitors praised the bigger aisles, which made it easier for visitors to navigate the show. However, some were unsure whether this was due to a better layout or simply because the show was missing key exhibitors. Notably absent were access control provider Dormakaba, security solutions company Honeywell, and surveillance providers Geutebruck and Dallmeier. Exhibitors expressed concern that the absence of key players reduced overall foot traffic. Security Essen hosted a particularly strong access control presence. Halls 2 and 3 were home to companies from across the access control and mechatronics spectrum. Sponsorship by EVVA covered the west entrance. The locking systems manufacturer, which celebrates its 100th anniversary next year, boasted significant floorspace. Exhibitors were pleased with the large access and locking presence, commenting that London-based IFSEC International tends to be dominated by video surveillance providers. EVVA, which celebrates its 100th anniversary next year, boasted significant floorspace Deep learning and artificial intelligence The push toward artificial intelligence (AI) in physical security continues, although the tone at Security Essen seemed to be shifting beyond hype and more toward how the technology can actually add value. For example, Hikvision’s cameras boasted more intelligence and processing power, and the company emphasised faster-paced product cycles. Customers ultimately do not buy AI – they buy benefits and solutions VIVOTEK embraced artificial intelligence as the biggest trend in the industry. The company demonstrated its latest deep learning technology for crowd detection applications. For Dahua, artificial intelligence allows users to easily search metadata in a video, including age and behaviour. Dahua demonstrated its solution for the transportation market, which is able to learn if a bus or train driver is falling asleep at the controls. However, some manufacturers chose not to focus on artificial intelligence. Representatives from Brivo and Eagle Eye Networks highlighted that customers ultimately do not buy AI – they buy benefits and solutions. Historically, video analytics were oversold and underdelivered, and the same could happen to AI if the term is overused in marketing security solutions. VIVOTEK embraced artificial intelligence as the biggest trend in the industry The German market & GDPR While the fair welcomed an increase in international visitors, many stands offered a distinctly German flavour. Exhibitors catered to German customers’ preference for data protection and high levels of privacy. Visitors were welcomed to the show by banners from Genetec, emblazoned with the slogan “Privacy matters… So, remember to forget me.” The video security provider’s stand demonstrated this concept more tangibly, via its Privacy Protector Module.  The surveillance software, which is certified with the European Privacy Seal (EuroPriSe), monitors events while automatically pixelating people and vehicles in real time. If an incident occurs, an authorised operator can securely access the unaltered video. Visitors were welcomed to the show by banners from Genetec Other companies also acknowledged issues of privacy and cybersecurity. Hikvision noted that Europe is more regulated, which limits the implementation of the company’s products compared to those used in China. Dahua emphasised that its data for the German market is stored in Frankfurt to meet demands for data protection. IDIS made a point of saying there are no backdoors to their products. The deep learning products are easy to use and 96% accurate, says the company. FLIR has developed a cybersecurity hardening document, and strives to be transparent about cyber issues, including a web landing page where customers can raise any concerns. Vanderbilt is also pushing the cloud as a way forward with its ACT365 cloud-based access and video solution. Users are not intimidated by the cloud anymore since we all use it in our personal lives, says the company. Also on the access control side, EVVA were clear on the security of their AirKey mobile access system, which uses technology based on internet banking, double encryption and high-quality hardware. As well as demonstrating its SAROS thermal camera, FLIR strived for cybersecurity concerns to be addressed by customers Taking a broader view Nedap views security as being about allowing people to focus on their daily lives and work, safe in the knowledge that security is being taken care of. At the show, Nedap launched its new slogan ‘Security for Life’, stating that “true security is when you don’t have to think about it”. Nedap’s global client program represents a long-term commitment to projects. They are having more discussions with clients about risk management through standardisation and centralised policy.Solutions – as opposed to products – were also a focus at Security Essen, as at IFSEC before it Clients remain with Nedap because they keep investing in the platform, constantly updating the code and simplifying it to improve scalability for organisations, says the company. Nedap had one of the few double-decker booths at Security Essen. Solutions – as opposed to products – were also a focus at Security Essen, as at IFSEC before it. HID Global touted their extensive use of partnerships to provide solutions. SeeTec highlighted their move away from products to a more solution-based approach. FLIR, perhaps best known as a thermal camera company, were pushing their solutions approach to markets including intelligent traffic, smart city, video management and PSIMs.  Nedap had one of the few double-decker booths at Security Essen Vertical markets in focus As vertical markets go, retail was big, and several players were offering some type of retail solution. Retail – along with banking, finance and transportation – was among Hikvision’s vertical markets of choice. Dahua's new panoramic cameras stitch together the image inside the camera instead of on the server SeeTec’s retail solution combines EAS with business intelligence and heat mapping. Dahua’s retail offerings include people counting and emotion detection, which can correlate with weather data, for example. Genetec also showcased a range of retail solutions. Technology improvements announced at Security Essen include FLIR's more robust FB6 series thermal line, Promise Technology's SMARTBOOST technology improved playback performance, and Videotec's cameras with better night performance. The extended 50m range of Optex's intrusion detection laser sensor reduces the need for cameras. Dahua's new panoramic cameras stitch together the image inside the camera instead of on the server. The Hanwha Techwin booth featured Korean flags and a “Korean at heart” motto to set the company apart Signs of the U.S. congressional ban There were signs at Security Essen of an impact of the recent U.S. ban on use of Hikvision and Dahua equipment in government installations, although both big Chinese manufacturers maintained a high profile at the German show. For example, the Hanwha Techwin booth featured Korean flags and a “Korean at heart” motto to set the company apart. Chinese camera manufacturer Uniview were keen to stress that they are not owned by Chinese government (neither is Dahua). Uniview’s all-IP camera line offers high resolution, low-light, multisensor and fisheye options, and AI software provides facial recognition, object detection, and fire and smoke detection at the edge. The company aims to increase its global presence with more international branch offerings and international factories.

More good news for exhibitors on the second day of the Global Security Exchange (GSX) in Las Vegas. Brisk attendance continued early in the day, and then slowed somewhat in the afternoon, but most comments from exhibitors were positive. Exhibitors such as Lenel were “thrilled” with the show, and noticed the steady, good traffic and lots of sales leads. Lenel’s position at the front of the hall probably helped. New developments in mobile credentialing are a big trend at GSX, and Lenel’s BlueDiamond mobile credentials are traveling on a new path, so to speak. The access control company is introducing the idea of “Pathways” as a way of automatically signaling intent to a Bluetooth-enabled smart phone to open a door. A recognisable “pathway” is programmed into the phone, based on signals from nearby readers and locks and also geolocation signals. The system recognises when a user travels along the pathway and automatically signals the correct door(s) to be opened along the way without the user having to touch his smart phone.A recognisable “pathway” is programmed into the phone, based on signals from nearby readers, locks and also geolocation signals Providing a lightweight alternative “When you trigger a pathway, it’s signalling intent to open the door,” says Greg Berry, Vice President Mobile Credentialing, Global Security Products, for United Technologies, parent company of Lenel. “Pathways are customised to a user’s needs and are the common places you are going all the time.” A user who walks the same path daily to the door of an office will find that door opens automatically. Previously using mobile credentials has been “slightly more work than using a badge,” says David Weinbach, Manager of Identity and Product Innovation for Lenel. “Now with Pathways, it’s less work than using a badge.” Specifically, a user no longer has to take out his phone and push a button to signal intent. “Rather than trying to emulate the badge, you create an experience that is better than the badge,” adds Berry. “We want to change the paradigm and turn the market on its ear.”New browser-based clients are being released with each new version of OnGuard software Other news from Lenel includes the release of more mobile and browser-based clients for OnGuard to be used for greater convenience alongside the Window-based clients. Providing a “lightweight” alternative enables some of the functionality of the Windows client in a format that is easy to access on the go. New browser-based clients are being released with each new version of OnGuard software. Cloud-hosted systems using Microsoft Azure are also among the plans for OnGuard, which ultimately will offer on-premises and cloud options. There’s not much comment from the Lenel folks about their parent company United Technologies’ plan to acquire S2 Security, which was announced days before the show. They would only say that the acquisition is waiting for regulatory approval, and that the expectation is that the two companies’ products will be complementary, given S2’s focus on the SMB (small and medium-sized business) market and Lenel’s strength at the enterprise level. The acquisition strategy is to grow both businesses. More details to come about the new combined company. Modern network infrastructure NVT Phybridge, a PoE connections company located near the back of the hall, also reported steady booth traffic on Day 2. “There are lots of customers and partners here,” said Steven Fair, Executive Vice President. “We are pleased with the quality of people, but not overwhelmed with the quantity.” FacePRO AI facial recognition is used for real-time searches of terror suspects or criminals throughout a location NVT Phybridge, which provides IP networking products for the telephony industry as well as security, is focused on networking concepts at GSX, in particular the changing requirements for network infrastructure in the age of IoT. We are pleased with the quality of people, but not overwhelmed with the quantity.” Fair uses the term “Modern LAN” to describe the new, changing requirements and in consideration of the specific networking needs of each edge device, whether cameras, sensors, or door access control devices. “Start with the edge device — what does it need from the network? What are its needs and have there been any innovations to enable you to connect to the network more economically?” asks Fair. There is also a green aspect to designing network infrastructure. Can existing equipment, such as coaxial or single twisted-pair cabling, be used, and thus save on disposal costs of the used cabling as well as lowering installation costs? Among NVT Phybridge’s offerings that can serve the changing networking needs in the IoT era is Smart Path PoE, which offers smart power, smart network access and secure connections. The CLEER family of products provides ethernet over existing coaxial cabling to enable easy transition from analogue to IP cameras. The PoLRE products supply ethernet and power to travel over a single unshielded twisted pair cable with reach over 400 metres. The products have been used recently to transition a series of cruise ships from analogue to IP video without having to replace cabling and spending only two days in dry dock for the installs. A new focus away from AI Panasonic is looking to apply AI-based capabilities to vehicle recognition in the near future, with the ability to identify vehicle characteristics Deep learning and artificial intelligence (AI) seem to be taking a lower profile at this show, perhaps signaling the end of the hype. Companies that mention AI point to specific products that use the technology and are currently available. For example, Panasonic is featuring its FacePRO AI-based facial recognition system. The system uses face images captured from video — grabbing up to 30 to 35 faces a second as video is recorded. The system saves the best of those face images, eliminating extensive duplication, as thumbnails, which are linked to the video footage where the faces appear. To find video in which a face appears, the operator merely drags-and-drops the thumbnail image and commands the system to “go fetch” video that contains that face. The system then produces a timeline showing where the face appears in the feed from each video camera on the premises, so an operator can track the movements of a suspect throughout a facility. The tool helps to simplify and shorten the workflow of locating a suspect in real-time and is affordable for a wider range of uses beyond the traditional airports or high-end applications.  The FacePRO software is offered on any Panasonic camera, and works with a separate FacePRO server that is integrated with the video recorder. The system can be added easily to existing systems and is useful for such applications as real-time searches for terror suspects or other criminals throughout a location. Panasonic is also looking to apply AI-based capabilities to vehicle recognition, too, in the near future, with the ability to identify vehicle characteristics such as color, type of vehicle and direction of travel. On the VMS side, Panasonic is transitioning its Video Insight software to a modular approach, tailoring solutions for a growing range of vertical markets, such as transportation and retail, all using “plug-ins” that enhance operation of Video Insight software. No additional license fees are involved That’s just a sampling of what I saw on Day 2 of the show. I have more to share in a final show report, including what I see tomorrow on the final (shortened) day.

Data was always bound to be a hot topic at this year's IFSEC International event. Artificial Intelligence (AI) has been a buzzword since last year's show. This year, manufacturers are ready to demonstrate solutions capable of processing and analysing large volumes of information to bolster security and provide business intelligence. Organisers deliberately positioned IFSEC as a converged security event, highlighting the inherent link between the security of physical assets and the security of data. In the wake of the recent passing of the European General Data Protection Regulation (GDPR), visitors to the London-based show sought reassurance that physical security systems could help them comply to stricter rules regarding the collection and protection of personal information. Analysing Big Data Seagate Technology, known for providing the surveillance industry with hard disk drives and storage solutions, showcased its Skyhawk AI hard disk drive, its first drive created specifically to enable artificial intelligence (AI) applications for video surveillance. Seagate's drive is designed for data-intensive workloads associated with recording large volumes of footage The drive is designed for data-intensive workloads associated with recording and analysing large volumes of video surveillance footage. According to Seagate's Sales Manager Andy Palmer, AI-enabled analytics at the edge can avoid the latency associated with cloud-based systems. This makes the solution suitable for smart city applications requiring 24/7 intelligence from multiple cameras.  The company also highlighted its strategic partnership with video surveillance provider Dahua Technology, with the latter seeking to leverage Seagate's technology to boost its own AI solutions. The Digital Barriers solution allows organisations to optimise how video data is transmitted depending on their particular needs Video transmission and privacy One manufacturer addressing the challenges of data transmission was Digital Barriers. The company demonstrated the integration of its EdgeVis Live platform with Milestone's XProtect video management system (VMS). The platform is designed for safe city applications, in which law enforcement and security professionals may need to stream incidents and events in real time over a limited bandwidth. The Digital Barriers solution allows organisations to optimise how video data is transmitted depending on their particular needs. For example, while some applications may favour a high clarity of video, others necessitate low data usage or a quick turnover of frames. The full, high quality video can then be downloaded later, meaning no intelligence is lost.While some applications may favour a high clarity of video, others necessitate low data usage or a quick turnover of frames The company also demonstrated its deep-learning facial recognition software, which can be used to identify suspects or vulnerable persons. To maximise accuracy, the deep learning system is trained on a wide range of images with varying angles and lighting. The solution is designed around data protection and privacy, explained Product Manager Fernande van Schelle, as all information is encrypted, and the system only identifies faces of known individuals on a pre-defined watch-list. Daniel Chau, Overseas Marketing Director at Dahua; Adam Brown, security Solutions Manager at Synopsys; Udo Scalla, Global Head Centre of Excellence - IOT Privacy, TÜV Rheinland Group GDPR for physical security professionals Dahua Technology addressed data protection concerns with an expert panel dedicated to the cybersecurity questions posed by the new European General Data Protection Regulation (GDPR). Speakers included Daniel Chau, Overseas Marketing Director at Dahua; and Adam Brown, security Solutions Manager at Synopsys. Chau explained that Dahua encourages customers to address cybersecurity by undertaking independent audits and penetration tests. Brown elaborated that for any organisation, cybersecurity must be a boardroom issue. Stakeholders must avoid a 'tick box' methodology for assessing cybersecurity, and instead integrate the concept into the company's overall strategy so that best practices can cascade through the organisation.Stakeholders must avoid a 'tick box' methodology for assessing cybersecurity  The panel also included insights from Udo Scalla, who specialises in data protection for IoT and smart home devices at TÜV Rhineland Group. Scalla proposed that manufacturers must avoid focusing on how best to capture data, and instead ask why the data is being collected, and whether it should even be collected in the first place. Integrators must ask why the customer intends to install the system, and what they want to do with the data – only then can they begin to assess the GDPR requirements. While the possibilities for collecting data are now endless, explained Scalla, not everything that is technologically possible ought to be made into a business reality. MOBOTIX highlighted its Cactus Concept cybersecurity campaign with a large blue cactus Protecting video surveillance systems Video surveillance manufacturer VIVOTEK also tackled cybersecurity, with a presentation on 'Security within Security.' The company showcased its partnership with cybersecurity software provider Trend Micro, which enables VIVOTEK to provide cybersecurity-enhanced cameras. The cameras include embedded anti-intrusion software to prevent and mitigate cyber-attacks by detecting hacking attempts and blocking the source IP address. Should a camera be compromised, explained Shengfu Cheng, VIVOTEK's Director of Marketing and Product Planning, it can be quarantined to stop the spread of the attack, thus controlling the damage and reducing the cost of the infection. The Cactus Concept campaign aims to educate partners and customers on how to build a cyber-secure video surveillance system Cybersecurity was also a key theme at the MOBOTIX stand. The stand played host to a large blue cactus, a very literal representation of the German manufacturer's Cactus Concept. The campaign, launched earlier this year, aims to educate partners and customers on how to build a cyber-secure video surveillance system. According to the concept, every element of the system, from image capture through to video management, must be encrypted. These are the digital "thorns" which prevent the entire system –the cactus – being compromised. Exhibitors at IFSEC 2018 made a conscious effort to address customers' challenges around the collection, transmission and protection of security system data. As solutions become more powerful, with increasing numbers of connected sensors, this is a theme which is unlikely to go away anytime soon.

In order to improve security standards, in the last few months and since the beginning of the 2018/2019 season the Panomera camera system has been installed and tested in the Generali Arena in Prague, home ground of AC Sparta Praha. This technology is also used by many football clubs in the German Bundesliga and the English Premier League. After successful completion of the test phase, the club then switched the system into operational mode. AC Sparta Praha has launched a modernisation project for its security system with the objective of providing fans greater comfort and a feeling of increased security in their home arena, and to help prevent the occurrence of unwelcome incidents. Substantial financial investment If the rules are violated while a match is being played, this technology makes it possible to bring charges against individual offenders The system is also used for incident analysis, to deliver better video material so that the involvement of specific individuals can be proven accurately when offences occur. If the rules are violated while a match is being played, this technology makes it possible to bring charges against individual offenders or a larger group of fans. The system records continuously and stores what is happening at all locations on the tribunes. This in turn enables the direct display and investigation of incidents and their causes, which is made simpler by the simultaneous, time-synchronised playback of multiple video streams. The installation of this new camera system is not a reaction to what took place during the Europa League qualifying round match against Subotica, but a strategic measure for which the ACS club management decided earlier despite the substantial financial investment. Evidentiary procedure By the time of the game against the Serbian team Subotica, which was played on 2 August 2018, the CCTV system was already in the final stage of testing, which meant that the material recorded could be used for the investigation and evidentiary procedure. The club is prosecuting fans who engaged in unacceptable behaviour during the match extremely vigorously, and long stadium bans and fines have already been imposed. The club cooperated successfully with three companies to achieve the implementation of this CCTV solution: with Dallmeier – manufacturer of the Panomera technology, with T-Mobile – data infrastructure provider – and with Made in PUBLICITY, which was responsible for integrating the system and installation. Unambiguous facial identification The video material recorded with Panomera far surpasses the standard 1080-HD format, while capturing up to 30 images per second in real time The Panomera camera system has already been installed successfully in most stadiums in the Bundesliga (e.g., Allianz Arena - Bayern Munich, Signal Iduna Park - Borussia Dortmund, Commerzbank Arena - Eintracht Frankfurt) and in the English Premier League (e.g., Old Trafford - Manchester United, Emirates Stadium - Arsenal London) as well as in modern stadiums in Russia, host nation to the 2018 World Cup competition. The video material recorded with Panomera far surpasses the standard 1080-HD format, while capturing up to 30 images per second in real time. Recording is performed in a resolution of up to 320 pixels per metre, enabling unambiguous facial identification. For comparison: typically only half of this resolution, 125 pixels per metre is needed for normal facial recognition.

Season-ticket holders at Belgian football club RWD Molenbeek will soon find it easier to enter the stands at their stadium, thanks to facial recognition technology that is set to be introduced at the turnstiles. Although the project is still in the test phase, fans ordering their season tickets on-line can already upload an ID photo. This photo will be compared in real time with images taken by two cameras installed in the season-ticket holders’ queue at the stadium entrance, allowing supporters to enter much faster. An automatic gate will be installed in early 2019. Data processing facility Spectators who have forgotten their paper ticket can still enter the stadium with no problem. Those who haven't uploaded a photo, or who have borrowed an entry ticket, will still have to pass through the conventional gates and show their ticket at the turnstiles. The system was installed by Zetes using Panasonic facial recognition technology. The detection system, with its fast and reliable data processing facility, means we can install a system to speed up entry checks to the stadium" The facial recognition software applies only to the access checks, as a further benefit for season-ticket holders. Thierry Dailly, chairman of RWDM, explains: “The detection system, with its fast and reliable data processing facility, means we can install a system to speed up entry checks to the stadium.” Alain Wirtz, CEO of Zetes, adds: “This project is a perfect example of how we can benefit from the innovative capabilities provided by the Panasonic group, owner of Zetes. Zetes specialises in this identification technology, which has many different applications. We hope this project can act as a shop window for our products.” The pilot project will run for about a year. Guaranteeing confidentiality Supporters’ photos are scanned and stored on an RWDM server, which is not connected to the Internet or to any other system. Only RWDM-authorised personnel have access to the data. Data collected by the entrance gate cameras is not recorded, guaranteeing confidentiality for the supporters. At this stage, the system is still in the test phase, and the facial recognition facility is not yet fully operational. The installation of the automatic gate at the beginning of 2019 will complete the planned programme. 2017 April, Panasonic acquired a majority shareholding in Zetes and 2017 July completed the acquisition of 100% shares of Zetes. Zetes was founded in 1984, and employs 1100 employees in 21 countries in EMEA in 2016. Its headquarters is in Brussels.

Cosmo Music was established in Richmond Hill, Ontario, Canada in 1968. Its current 56,000 sq ft store opened in 2008, making it the largest music instrument store in North America. It is also home to the Cosmopolitan Music Hall venue. Needing to replace a 20-year-old analogue video system, Cosmo Music Vice President and COO Rudi Brouwers, started researching modern video management software (VMS). Initially he intended to purchase IP cameras and a basic VMS with the ability to record and playback. But Brouwers soon learned of the vast capabilities of modern systems. He turned his focus to finding one that went beyond basic video management to offer business intelligence. Identify suspicious customers Brouwers ultimately decided on Axis cameras and Senstar’s Symphony VMS with its Face Recognition analytic In particular, he was interested in face recognition, which would enable Cosmo Music to identify suspicious customers to prevent shoplifting. Working with integrator Northern Alarm Protection Ltd. (NAP), Brouwers looked at a number of different systems, and ultimately decided on Axis cameras and Senstar’s Symphony VMS with its Face Recognition analytic. “I was sold on Symphony when I got to actually use it,” said Brouwers. “It floored me how easy it is to work, how straightforward it is. It is so user friendly it is unbelievable.” Brouwers likes several of Symphony’s core features, including: the ability to save video for up to six months (he had been hoping for 90 days) customisation options (for example, recording only when motion is detected) ability to bookmark video the mobile app, which lets users connect to Symphony via a smartphone or tablet to view and playback video, control pan-tilt-zoom (PTZ) cameras, manage I/O devices, receive alarm notifications, and more. Face recognition analytic Before implementing Senstar’s Face Recognition video analytic, when a suspicious customer was identified through video surveillance, Brouwers would screen capture an image, email it to staff, and ask them to keep an eye out for that person. With Senstar’s Face Recognition video analytic, Brouwers can flag suspicious customers in Symphony. When that person enters the store again, Brouwers is automatically notified. One of our staff had a full beard one day and it was shaved off the next day and the system still picked him up" Brouwers tested the analytic thoroughly and was amazed by its capabilities. “One of our staff had a full beard one day and it was shaved off the next day and the system still picked him up,” said Mr. Brouwers. “That’s what sold me on it.” Symphony and the Face Recognition analytic, deployed on Senstar’s R-Series network video recorder (NVR) hardware, have been running at Cosmo Music since April 2018 and Brouwers couldn’t be happier. Business intelligence applications “It’s everything I dreamed of and more,” he said. From an integrator perspective, NAP, who had significant VMS experience but never used Symphony, thinks the product is a great option for business intelligence applications. “Symphony is the right fit for any application that requires enhanced security such as analytics. It’s superior to many other systems out there,” said NAP President and CEO Dave Koziel. “From a deliver what is promised standpoint, it’s 12 out of 10 on the scale.” Senstar’s Face Recognition analytic adds an additional layer of security to any video surveillance deployment Identify known and unknown individuals Create allow and deny lists, and be alerted when someone on that list is identified Save time and resources with a robust search functionality that lets users look for registered and unknown people in video Search across multiple cameras, and filter search results by match score or date and time Two-factor authentication processes for access control applications

Senstar, a global provider of video management and perimeter intrusion detection solutions, announces that its Symphony video management software and Face Recognition video analytic are helping to protect Cosmo Music. Working with integrator Northern Alarm Protection (NAP) Ltd., Richmond Hill, Ontario, Canada-based Cosmo Music selected Senstar after comprehensive research and testing to replace its 20-year-old analog video system. “Senstar Symphony delivers an all-in-one solution for video management, video analytics, perimeter intrusion detection system integration, and alarm management for deployments of all sizes,” said Justin Shorn, Senstar’s Vice-President of Product Management. “We are glad that Symphony’s core features and ease-of-use, along with our Face Recognition analytic, were able to meet Cosmo Music’s needs.” Flag suspicious customers Senstar’s Face Recognition analytic adds an additional layer of security to any video surveillance deployment and is a powerful tool for retail loss prevention. At Cosmo Music, the analytic is used to identify and flag suspicious customers and provide real-time alerts if a flagged individual enters the store, with the goal to prevent theft. “(During testing) one of our staff had a full beard one day and it was shaved off the next day and the system still picked him up,” said Rudi Brouwers, Vice-President and COO of Cosmo Music. “That’s what sold me on it.”

Princeton Identity Inc., a provider of secure biometric security systems, has announced the deployment of its Biometric Conex, designed to assist customers with quick and accurate personnel authentication for campuses and facilities. The Conex is a 20-foot long standard shipping container outfitted with on-the-move facial, iris and fingerprint biometric capture technology, which can be operational in less than 24 hours. Biometric Conex Princeton Identity is showcasing the Biometric Conex at the 2018 AUSA Annual Meeting & Exposition this week in Washington, DC The first two containers will be shipped in October to government facilities. Princeton Identity is showcasing the Biometric Conex at the 2018 AUSA Annual Meeting & Exposition in Washington, DC. The Conex’s combination of patented authentication technology and portable configuration give organisations the flexibility to deploy these high throughput, accurate authentication units anytime, anywhere. Biometric high-throughput system The multi-modal, biometric high-throughput system offers more secure rapid personnel authentication and the following features: Face, dual iris, and 8 fingerprint rapid enrollment of personnel and on-the move multi-modal personnel identification Throughputs of over 15 people per minute Self-contained or networked configurations Allow list and watch list capable Can support large personnel database configurations Climate controlled, air conditioned and weatherproof Can be powered by a generator and comes with UPS backup Facility entry control The Biometric Conex eliminates these issues and provides a more accurate, seamless entry process Current facility entry control procedures generally rely on credentials or limited biometric information to allow entry. In many cases, these procedures can cause excessive queuing, require extensive manpower, and are limited in their identification accuracy. The Biometric Conex eliminates these issues and provides a more accurate, seamless entry process. It contains a rapid enrollment station to simultaneously register subjects’ biometric signatures – fingerprints, face and irises – which takes less than a minute to process. The fusing of these three separate biometric modalities ensures the highest level of identification accuracy and eliminates potential spoofing attacks. When subjects enter the Conex, they walk through at a normal pace without stopping or touching any sensors, gain clearance, and are granted access to the facility. Contactless iris authentication “The government engaged with Princeton Identity to provide these units because we are the only identification firm with patented walkthrough, contactless iris authentication capabilities to support large groups of people,” said Mark Clifton, CEO of Princeton Identity. “Our software and physical hardware provide versatile identity authentication solutions designed to verify and manage individuals’ identities for a wide range of physical security and access applications, and we are already exploring other commercial uses for the Biometric Conex.”

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.