Components

OMNI seamlessly captures video streams from cameras and video files using RTCP protocols. The received frames are processed in parallel within face and body frame processing modules.

OMNI Agent modules detect faces and bodies in the frames, identify facial attributes, build face biometric templates, and search for face matches wth the database.

Simultaneously, the modules perform face/body tracking: from frame to frame, the displacement vector of the face/body area is calculated, confirming or refuting the prediction of the next face/body coordinate with false-positive filtering.

The formed body tracks are used as input for detecting people in the region of interest (ROI), crossing of lines marked in the video stream, recognition of actions including fights, falls, sitting and lying, as well as tracking people on a room map (Map tracking).

The collected data for each detected person, formatted as processes and events, is transmitted to OMNI Platform or external service (via webhook/MQTT) for further processing.