BoxMOT: pluggable SOTA tracking modules for segmentation, object detection and pose estimation models

Introduction

This repository addresses the fragmented nature of the multi-object tracking (MOT) field by providing a standardized collection of pluggable, state-of-the-art trackers. Designed to seamlessly integrate with segmentation, object detection, and pose estimation models, the repository streamlines the adoption and comparison of MOT methods. For trackers employing appearance-based techniques, we offer a range of automatically downloadable state-of-the-art re-identification (ReID) models, from heavyweight (CLIPReID) to lightweight options (LightMBN, OSNet). Additionally, clear and practical examples demonstrate how to effectively integrate these trackers with various popular models, enabling versatility across diverse vision tasks.

Tracker	Status	HOTA↑	MOTA↑	IDF1↑	FPS
boosttrack	✅	69.253	75.914	83.206	25
botsort	✅	68.885	78.222	81.344	46
strongsort	✅	68.05	76.185	80.763	17
deepocsort	✅	67.796	75.868	80.514	12
bytetrack	✅	67.68	78.039	79.157	1265
ocsort	✅	66.441	74.548	77.899	1483

_{NOTES: Evaluation was conducted on the second half of the MOT17 training set, as the validation set is not publicly available and the ablation detector was trained on the first half. We employed pre-generated detections and embeddings. Each tracker was configured using the default parameters from their official repositories.}

Why BOXMOT?

Multi-object tracking solutions today depend heavily on the computational capabilities of the underlying hardware. BoxMOT addresses this by offering a wide array of tracking methods tailored to accommodate diverse hardware constraints, ranging from CPU-only setups to high-end GPUs. Furthermore, we provide scripts designed for rapid experimentation, enabling users to save detections and embeddings once and subsequently reuse them with any tracking algorithm. This approach eliminates redundant computations, significantly speeding up the evaluation and comparison of multiple trackers.

Installation

Install the boxmot package, including all requirements, in a Python>=3.9 environment:

pip install boxmot

BoxMOT provides a unified CLI boxmot with the following subcommands:

Usage: boxmot COMMAND [ARGS]...

Commands:
  track                  Run tracking only
  generate-dets-embs     Generate detections and embeddings
  generate-mot-results   Generate MOT evaluation results based on pregenerated detecions and embeddings
  eval                   Evaluate tracking performance using the official trackeval repository
  tune                   Tune tracker hyperparameters based on selected detections and embeddings

YOLOv12 | YOLOv11 | YOLOv10 | YOLOv9 | YOLOv8 | RFDETR | YOLOX examples

Tracking

$ boxmot track --yolo-model rf-detr-base.pt     # bboxes only
  boxmot track --yolo-model yolox_s.pt          # bboxes only
  boxmot track --yolo-model yolo12n.pt         # bboxes only
  boxmot track --yolo-model yolo11n.pt         # bboxes only
  boxmot track --yolo-model yolov10n.pt         # bboxes only
  boxmot track --yolo-model yolov9c.pt          # bboxes only
  boxmot track --yolo-model yolov8n.pt          # bboxes only
                            yolov8n-seg.pt      # bboxes + segmentation masks
                            yolov8n-pose.pt     # bboxes + pose estimation

Tracking methods

$ boxmot track --tracking-method deepocsort
                                 strongsort
                                 ocsort
                                 bytetrack
                                 botsort
                                 boosttrack

Tracking sources

Tracking can be run on most video formats

$ boxmot track --source 0                               # webcam
                        img.jpg                         # image
                        vid.mp4                         # video
                        path/                           # directory
                        path/*.jpg                      # glob
                        'https://youtu.be/Zgi9g1ksQHc'  # YouTube
                        'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP stream

Select ReID model

Some tracking methods combine appearance description and motion in the process of tracking. For those which use appearance, you can choose a ReID model based on your needs from this ReID model zoo. These model can be further optimized for you needs by the reid_export.py script

$ boxmot track --source 0 --reid-model lmbn_n_cuhk03_d.pt               # lightweight
                                       osnet_x0_25_market1501.pt
                                       mobilenetv2_x1_4_msmt17.engine
                                       resnet50_msmt17.onnx
                                       osnet_x1_0_msmt17.pt
                                       clip_market1501.pt               # heavy
                                       clip_vehicleid.pt
                                      ...

Filter tracked classes

By default the tracker tracks all MS COCO classes.

If you want to track a subset of the classes that you model predicts, add their corresponding index after the classes flag,

boxmot track --source 0 --yolo-model yolov8s.pt --classes 16 17  # COCO yolov8 model. Track cats and dogs, only

Here is a list of all the possible objects that a Yolov8 model trained on MS COCO can detect. Notice that the indexing for the classes in this repo starts at zero

Evaluation

Evaluate a combination of detector, tracking method and ReID model on standard MOT dataset or you custom one by

$ boxmot eval --yolo-model yolov8n.pt --reid-model osnet_x0_25_msmt17.pt --tracking-method deepocsort --verbose --source ./assets/MOT17-mini/train
$ boxmot eval --yolo-model yolov8n.pt --reid-model osnet_x0_25_msmt17.pt --tracking-method ocsort     --verbose --source ./tracking/val_utils/MOT17/train

add --gsi to your command for postprocessing the MOT results by gaussian smoothed interpolation. Detections and embeddings are stored for the selected YOLO and ReID model respectively. They can then be loaded into any tracking algorithm. Avoiding the overhead of repeatedly generating this data.

Evolution

We use a fast and elitist multiobjective genetic algorithm for tracker hyperparameter tuning. By default the objectives are: HOTA, MOTA, IDF1. Run it by

# saves dets and embs under ./runs/dets_n_embs separately for each selected yolo and reid model
$ boxmot generate-dets-embs --source ./assets/MOT17-mini/train --yolo-model yolov8n.pt yolov8s.pt --reid-model weights/osnet_x0_25_msmt17.pt
# evolve parameters for specified tracking method using the selected detections and embeddings generated in the previous step
$ boxmot tune --dets yolov8n --embs osnet_x0_25_msmt17 --n-trials 9 --tracking-method botsort --source ./assets/MOT17-mini/train

The set of hyperparameters leading to the best HOTA result are written to the tracker's config file.

Export

We support ReID model export to ONNX, OpenVINO, TorchScript and TensorRT

# export to ONNX
$ python3 boxmot/appearance/reid_export.py --include onnx --device cpu
# export to OpenVINO
$ python3 boxmot/appearance/reid_export.py --include openvino --device cpu
# export to TensorRT with dynamic input
$ python3 boxmot/appearance/reid_export.py --include engine --device 0 --dynamic

Custom tracking examples

Example Description	Notebook
Torchvision bounding box tracking with BoxMOT
Torchvision pose tracking with BoxMOT
Torchvision segmentation tracking with BoxMOT

Contributors

Contact

For BoxMOT bugs and feature requests please visit GitHub Issues. For business inquiries or professional support requests please send an email to: box-mot@outlook.com