Smart Tracking Advanced

AI Technology for Moving People Tracking

Smart Tracking Advanced is a state-of-the-art technology with intelligent people tracking and Video Content Analysis (VCA), designed to improve the performance of tracking objects via PTZ IP cameras.

Fine-tuned specifically to apply to a wide range of scenarios utilizing PTZ/speed dome surveillance, Smart Tracking Advanced enables users to closely inspect and follow suspicious persons in areas such as airports, critical infrastructure, city surveillance, shopping malls and parking lots.

Going even further, Smart Tracking Advanced covers four types of VCA detectors - intrusion detection, line crossing detection, loitering detection and face detection. Through user-defined rules, a person portraying hazardous behavior, such as intrusion into a prohibited area or crossing past a boundary line, would trigger preset alarms. Automatic tracking of the person of interest, optimizing the recording video quality, and notifying security personnel all activate simultaneously. With Smart Tracking Advanced, we are taking seamless security one step further.

Deep Learning Technology

The core of VIVOTEK’s Smart Tracking Advanced is a deep learning AI engine offering advanced accuracy in people detection compared with traditional rule-based designs, especially tailor-made for PTZ/speed dome cameras. VIVOTEK took advantage of its extensive experience in the surveillance field and resulting vast image databases to develop a neural-network powered detection engine for the human form. Based on a database of human silhouettes and rapid responses via a pre-trained deep learning model, the smart engine instantly recognizes the appearance of human forms in the surveillance area. As people are the objects of interest in the majority of video surveillance, the people-detection feature enables users to quickly configure their installation. With people-detection, only human activities will serve as event triggers, while swaying vegetation, vehicles passing by, or animal movements in the scene will be ignored. This both helps reduce false alarms, as well as minimize the time and effort needed for setting up camera configuration.

Intro Video

Example Application Scenarios

Suspicious person loitering in the parking lot