Models

Locate and classify people, vehicles, animals and hazards on every analysed frame.

Assign persistent identities to detections across frames, surviving brief occlusions.

Estimate a dense depth field from a single ordinary camera, with no stereo rig.

Reconstruct a sharper, super-resolved image of a face or licence plate from many sightings.

Produce per-pixel masks that separate standing objects from the background plate.

Extract body keypoints to support intent, posture cues and gait sampling.

Re-identify subjects across cameras and time to build long-term dossiers.

Estimate vehicle make and support plate / speed attributes for tracked vehicles.