Trackers gives you clean, modular re-implementations of leading multi-object tracking algorithms released under the permissive Apache 2.0 license. You combine them with any detection model you already use.
- Updated
Oct 22, 2026 - Python
Trackers gives you clean, modular re-implementations of leading multi-object tracking algorithms released under the permissive Apache 2.0 license. You combine them with any detection model you already use.
Track video objects with YOLOv8 and StrongSORT, using appearance embeddings and MOT metrics for reliable multi-object tracking
Core implementation of ClarityTrack for online multi-object tracking via confidence-aware data association.
Advanced multi-object tracking pipeline — YOLOv8m + StrongSORT with OSNet appearance embeddings on MOT17. HOTA 41.6 | MOTA 38.1 | IDF1 50.8. Benchmarked against ByteTrack baseline with TrackEval.
Object detection + multi-object tracking on CPU-only edge-class compute: C++ ONNX Runtime, Docker, reproducible benchmarks
End-to-end multi-object tracking and trajectory analytics using YOLO11 and ByteTrack, with experiment comparisons, MOT17 evaluation, visualizations, and automated tests.