Model

ByteTrack

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

shipped Multi-Object Tracking TrackingMOT

Overview

ByteTrack associates both high- and low-confidence boxes to keep tracks alive through partial occlusion. Overseer layers a short coasting window on top: a last-known box is held briefly through a momentary detection drop so tracklets do not flicker. Track ids key everything downstream, Re-ID, speed, intent, ghosts and the tactical radar.

RoleMulti-Object Tracking
Expected latency< 2 ms / frame
Hardware requirementsCPU-bound; no GPU required
Memory requirementsNegligible

Inputs & Outputs

Inputs
  • Per-frame detections
  • Previous track state
Outputs
  • Stable track id per object
  • Track age / velocity state

Advantages & Limitations

Advantages

  • Robust through occlusion
  • Cheap (association only)
  • Foundation for all identity features

Limitations

  • Identity switches possible in dense crowds
  • Long full occlusions break continuity
  • 2D only, no depth-aware association yet

Example outputs

Configuration

Keys in config/default.yaml that govern this model.

KeyDefault
detectors.yolo.trackerbytetrack
tracking.coast_frames3

Benchmarks

Placeholder

Benchmark figures below are illustrative and awaiting a standardised harness. Treat them as placeholders.

BenchmarkDatasetMetricValueHardware
MOTAMOT17 (ref)MOTA~80reference
Overheadlivems/frame< 2CPU