Track Objects (Hybrid SORT)

How it fits

Typical backends

Caveats

• I/O contractOutput is track-centric. Each frame emits the set of active CONFIRMED tracks, so the count is the number of live tracks, not the number of input detections.
• I/O contractThe [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.
• I/O contractThe [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.
• AccuracyHybrid-SORT adds weak cues - a confidence-state score and a velocity-direction term - on top of observation-centric SORT, so tracks whose boxes overlap heavily are separated by how their scores and motion headings evolve rather than by geometry alone.
• State lifetimeA new track is tentative until matched on min_hits consecutive frames, then confirmed and emitted. A confirmed track unmatched for up to track_buffer frames coasts on its motion prediction; after that it is dropped and its id is never reused.
• AccuracyAssociation is geometry, motion, confidence and velocity direction only, with no appearance model. Add reidentify_objects_torchreid downstream when ids must survive long occlusions or identical-looking objects crossing.
• Parameter interactionmatch_thresh is the IoU-distance gate; track_thresh is the high-confidence gate that drives the first association pass and is the only score allowed to start a new track. Raise track_thresh to suppress spurious tracks from weak detections.