Cities are becoming smarter. IoT is being implemented everywhere, improving the safety, security and convenience of city dwellers and workers, and the most important sensor in the Smart City is the video camera. But the days of beaming gigabytes of video into the cloud to be examined by human monitors is coming to an end.
AI-based video analytics are now being used to count cars and people, and to check for events such as crowd formation, illegal parking, and using LPR/ANPR to track vehicles either for parking convenience or for law enforcement.
The great thing about video analytics is that you don’t need special video cameras. They have to be digital, ip-enabled, and maybe have some IR lighting for night vision capabilities, but because the analytics are implemented either in on-premise servers, or over the cloud, analytics can be added to existing CCTV camera surveillance systems. Traditional motion detection uses PIR (Passive Infrared) detection, which detects ANY motion – cars, humans, small animals, even trees waving in the breeze, resulting in many false alarms. But AI-based video analytics are designed to detect only valid motion, such as humans or vehicles, cutting false alarms down to near zero.
License plate recognition (LPR or ANPR) is another AI-based video analytic technology that can improve the safety and convenience of city life. License plates are detected on moving vehicles and read using OCR technology. They can then be compared with known plates in a database either of wanted vehicles, or vehicles that are known such as owners of parking spots or gated communities.