Surveillance AI for Object detection and Face Recognition
A study published in Security Oz magazine 2002 states that, after 12 minutes of continuous CCTV video monitoring an operator will often miss up to 45% of screen activity, after 22 min of viewing, up to 95% is overlooked.
After 20-40 minutes of active monitoring, CCTV operators will suffer from “video-blindness” and cannot recognise people and objects in the video anymore. Using Machine learning and Deep learning for biometric security solutions is an emerging AI trend for ensuring compliance and safety of an office or commercial space. ZASTI built a deep neural network-based AI model for Face Recognition, Object Detection, and event recognition, thereby providing proactive and real-time security.