General object detection and tracking

Objects are located, labelled and followed from frame to frame, so each one keeps a consistent identifier for as long as it stays in view. That turns detections into trajectories, which is what counting, dwell and direction analysis need. Identifiers survive brief occlusions, so an object that passes behind something is not counted twice. Tracks are returned with their full path and duration.

Capacity can be permanent or temporary: a one-off archive can run on burst capacity and release it afterwards, while a continuous workload sits on a cluster reserved for you. Our AI advisors help pick the model and the hardware before anything is committed.