mikel-brostrom/boxmot
BoxMOT: Pluggable SOTA multi-object tracking modules with support for axis-aligned and oriented bounding boxes
Combines pluggable tracker implementations (BoTSORT, ByteTrack, DeepOCSORT, etc.) with unified CLI and Python APIs for detection-agnostic multi-object tracking. Supports caching detections and embeddings across experiments to accelerate benchmarking, and natively handles both axis-aligned and oriented bounding box formats. Includes local evaluation workflows for MOT17, MOT20, and DanceTrack datasets with hyperparameter tuning and model export capabilities.
8,053 stars. Actively maintained with 10 commits in the last 30 days.
Stars
8,053
Forks
1,891
Language
Python
License
AGPL-3.0
Category
Last pushed
Mar 13, 2026
Commits (30d)
10
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/mikel-brostrom/boxmot"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related tools
roboflow/rf-detr
[ICLR 2026] RF-DETR is a real-time object detection and segmentation model architecture...
RizwanMunawar/yolov7-object-tracking
YOLOv7 Object Tracking Using PyTorch, OpenCV and Sort Tracking
stereolabs/zed-sdk
⚡️The spatial perception framework for rapidly building smart robots and spaces
google-deepmind/tapnet
Tracking Any Point (TAP)
NVIDIA-ISAAC-ROS/isaac_ros_object_detection
NVIDIA-accelerated, deep learned model support for image space object detection