
ByteTrack multi-object tracker over per-frame [BoundingBox] or [Segmentation]. Its two-stage association keeps low-confidence detections instead of discarding them, recovering objects through occlusion. A Kalman motion model plus class-aware gating give stable ids. Emits one active-track list per frame, not per box.
Tracked detections with trajectories into zone-transition logic.
Counted, tracked detections summarised over HTTP.
Instance-mask tracking - segmentations in, mask-bearing tracks out.
Re-id chain into a tracked-object summariser.
[TrackedSegmentation] output arm is only selectable when the input is [Segmentation]; the carried mask comes from the input. With [BoundingBox] input it cannot be resolved and the worker errors at startup.[Track] arm is the only one that fills each track's ``trajectory``; it holds the track's own past centre points, oldest first, capped at 64 samples.track_low_thresh and track_thresh to existing tracks, so a well-tracked object surviving on a weak detection is recovered rather than losing its id. Detections below track_low_thresh are dropped.min_hits consecutive frames, then confirmed and emitted. A confirmed track unmatched for up to track_buffer frames coasts on its Kalman prediction; after that it is dropped and its id is never reused.match_thresh is the IoU-distance gate; track_thresh splits high/low detections and, with spawn_thresh, controls how readily new tracks spawn. Raise spawn_thresh to suppress spurious tracks from weak detections.Rebuild against the current pipeml