TRASSIR Neuro Left Object Detector


TRASSIR Neuro Left Object Detector

The module is designed to detect orphan and forgotten objects left in the field of view of the camera. The detector is used in areas where security is especially important, for example, at airports, train stations, in the "Safe City" on street cameras, etc.

Neuro Left Object Detector works on the basis of a detector of objects and people - unlike the classical one, it does not depend on the background and works better in difficult conditions. The detector is based on two grids and tracking. The first network detects people and several classes of objects: suitcase, backpack, box, bag, duffle and bag. The second uses frames of objects recognized by the first network to create their unique features. Tracking is the main part of the object detector. Works on the basis of the unique features of objects. Having carried out basic heuristics over the tracks, he determines the owner of the object (by the nature of movement and proximity to the object), whether he left the frame or moved away a certain distance.

  • The quality of the network, which affects the accuracy and speed of work. The higher the quality, the better the detector works on complex scenes, but at the same time the higher the load on the server.
  • The number of frames per second collected for the detector to operate. The more frames, the lower the number of false positives, but the higher the load on the video card.
  • The minimum and maximum size of the object to be detected.

Other Products

TRASSIR Pose Detector

TRASSIR Direction Detector

TRASSIR Neuro Detector

TRASSIR Crowd Detector


TRASSIR Neuro Left Object Detector

TRASSIR Face Recognition