“Face recognition is becoming a must-have security feature for smart homes and buildings, smart retail, transportation, access control and the gaming industry,” said Krishna Khadloya, IntelliVision VP of Engineering and Products. “Our face recognition now gives system integrators the flexibility to implement facial detection and recognition in the cloud, on servers, or at the edge, providing real-time results, and reducing bandwidth usage.”
The latest version of IntelliVision’s facial recognition technology is highly optimized for in-camera processing and is capable of detecting at least ten faces in less than one second with only 25% CPU usage on an Ambarella S5L-based camera. As many as twenty faces can be recognized in a single frame. In the cloud-based Face Recognition as a Service (FRaaS), recognition time is sub-second and allows for additional analytics in the overall workflow where camera processing capacity is limited.
Facial recognition is part of the IntelliVision family of video analytics solutions that also includes object classification (humans, vehicles, pets, airplanes), intelligent motion detection, intrusion/perimeter watch, object left/removed, license plate recognition (ALPR/ANPR) and audio/sound recognition.