mikel-brostrom /yolo_tracking
BoxMOT: Pluggable Python and C++ SOTA multi-object tracking modules with support for axis-aligned and oriented bounding boxes
★ 8,326⑂ 1,913👁 58⑃ 981● 1,280▤ 150
+0
日增长
+3
周增长
+12
月增长
8,326
stars
1,913
forks
58
watchers
981
prs
1,280
issues
150
releases
README
Pluggable Python and C++ multi-object tracking modules for axis-aligned and oriented bounding box detections from any model.
---
Docs • Installation • Modes • API Reference • Trackers • Datasets • Contributing
BoxMOT provides independent detector, segmentor, appearance-encoder, and tracker
components built around validated Torch structures. Pipelines compose those
components; the CLI owns sources, outputs, materialized datasets, evaluation,
tuning, research, and ReID workflows.
Why BoxMOT
- One interface for track, materialize, materialize --time-variant, eval,
tune, research, train-reid, eval-reid, compare-reid, export,
install, and native build workflows.
- Swappable components with explicit capabilities and requirements.
- Immutable, keyed Parquet builds with reusable detections, masks, and
embeddings.
- Support for both AABB and OBB tracking paths.
- Optional native C++ tracker implementations selected with --tracker-backend cpp, with shared detection/output contracts and documented backend differences. They are also embeddable in standalone C++ projects through CMake (see Native C++ Integration and platform dependency installation).
- A structured Python API for embedding components and pipelines in applications.
Installation
Requires Python 3.10–3.13.
Install from PyPI:
bash
pip install boxmot "ultralytics=8.4.58"
boxmot --help
Or, from a source checkout, run in the repository root:
bash
pip install "uv==0.12.4"
uv sync --extra cpu --extra yolo
uv run --no-sync python -m boxmot.engine.cli --help
Replace --extra cpu with --extra cu130 for CUDA 13.0.
See installation options,
source and CPU/CUDA setup, and
GPU batch sizing.
Benchmark Results
Tracker key
Status
MOT17 ablation
SportsMOT val
MMOT OBB test
OBB
HOTA
MOTA
IDF1
HOTA
MOTA
IDF1
HOTA
MOTA
IDF1
occluboost
✅
71.10(71.10)
78.50(78.50)
85.28(85.28)
83.17
97.48
89.36
49.84(49.84)
39.41(39.41)
58.60(58.60)
✅
botsort
✅
69.68(69.74)
78.23(78.27)
82.33(82.55)
76.93
98.11
78.30
52.31(52.40)
45.43(45.53)
61.42(61.42)
✅
boosttrack
✅
69.25(—)
75.91(—)
83.20(—)
76.32
97.08
77.82
48.39(—)
41.36(—)
56.36(—)
✅
strongsort
✅
68.05(—)
76.19(—)
80.76(—)
79.80
97.31
80.27
49.76(—)
43.70(—)
57.32(—)
✅
deepocsort
✅
67.95(—)
75.83(—)
80.54(—)
79.51
97.94
79.59
50.84(—)
44.21(—)
59.33(—)
✅
bytetrack
✅
67.68(67.68)
78.04(78.04)
79.16(79.16)
67.93
97.25
76.90
33.Discussions
#2239How can i use deep oc sort?1 comments · 2026-03-02#2089A question regarding a livestock multi-object tracking project in South Korea.0 comments · 2025-08-04#2067ID Not Writing To Label File4 comments · 2025-07-10#2035How do i store tracking state and them resume tracking from later0 comments · 2025-06-20#2010Strongsort not working1 comments · 2025-06-06#2006Saving Results1 comments · 2025-06-04#1833trackeval problem0 comments · 2025-03-01#1797Is there any example for others trackers?0 comments · 2025-01-22
Latest release
Release v26.0.0 v26.0.0 2026-10-27BoxMOT v26.0.0 BoxMOT v26.0.0 adds multimodal tracking, optional EdgeTAM mask guidance, typed tracker configuration, and joint motion-model selection. It also improves evaluation reproducibility, replay performance, and tuning diagnostics. Based on committed changes since v25.0.0, through 9da023fd. New features and improvements - EagerMOT sensor fusion: Track objects using calibrated 2D and 3D detections, with optional camera poses. New spatial structures represent 3D boxes, camera calibration, and multimodal outputs. Includes KITTI evaluation, class-specific tuning, and 3D Kalman