How Video Analytics and AI Assist in Taking Decisions
Right Results for the Right People at the Right Time
At Intersec in Dubai Avigilon showcased its latest video, artificial intelligence, video analytics and access control solutions at the combined Motorola Solutions stand. GIT SECURITY talked to Paul Such, Vice President for EMEA Sales at Avigilon about advances in their video management system, the use of AI and their latest product developments.
GIT SECURITY: The Motorola stand here at Intersec shows the whole portfolio of Motorola Solutions’ security solutions and it looks like there were some nice additions to the video surveillance offering.
Paul Such: Yes, one of the things that Motorola has brought to the table since we last met were the acquisitions of Watchguard, Vigilant Solutions and Edesix. These acquisitions have added body-worn cameras and onboard police vehicle cameras with ANPR to our portfolio. The acquisitions expand our mission-critical ecosystem, adding to the video security solutions platform of fixed cameras and advanced analytics from Avigilon the license plate recognition cameras and software from Vigilant Solutions and Watchguard’s body-worn cameras. They are a great fit to our Avigilon products, which allow us to strengthen our video analytics and AI capabilities.
Artificial intelligence is on most people’s agenda. Can you outline what you have to offer here?
Paul Such: I think we are at the forefront of using AI for security needs. AI has become an integral part of the newest version of our video management software, Avigilon Control Center (ACC) 7.4 that incorporates artificial intelligence-powered facial recognition technology. Talking about AI, I need to mention the latest updates of our Avigilon Appearance Search technology, the sophisticated deep learning AI search engine that can help you to sort through hours of footage with ease. We have launched ‘Focus of Attention’ a cutting-edge user interface for live video monitoring. Rather than watching static video feeds, Focus of Attention uses AI-powered Avigilon self-learning video analytics and Unusual Motion Detection technologies to determine what information is important and should be presented to security operators.
By providing actionable information immediately to users, the system is designed to help ensure that critical events do not go unnoticed. This new level of proactive response is set to help change the future of video security operations
Can you explain the function of what you call ‘Unusual Motion Detection’?
Paul Such: Unusual Motion Detection is AI technology that brings a new level of automation to security. Without any predefined rules or setup, the technology is capable to continuously learn what typical activity in a scene looks like, and then detect and flag unusual motion. This allows operators to filter through large amounts of recorded video faster when using Avigilon Control Center (ACC) video management software, as it flags atypical events that may need further investigation, helping to reduce hours of work to minutes. Unusual Motion Detection is the perfect example for Avigilon’s strength to deliver the end-user the information they need via an intuitive user interface.
AI only works with sophisticated hardware. Are you working on advances in your camera portfolio, too?
Paul Such: We are continuously working on developing our products and solutions. The latest updates to our Access Control Manager with enhanced video security unification are remarkable. It is introducing a new concept for managing access control offering a streamlined ordering and licensing delivery system. The H5A camera line on the camera side is built with the next generation of advanced video analytics with the ability to detect more objects with even greater accuracy. Our new high-resolution H4 Thermal camera combines patented Avigilon technology with heat-sensing capabilities to improve perimeter security in areas with poor visibility, difficult lighting conditions and absolute darkness. Another highlight is our most advanced multi-sensor camera, the H4 Multisensor, which features up to 32 MP total resolution, self-learning video analytics, H.265 compression and content-adaptive infrared technologies.