mikel-brostrom/boxmot
BoxMOT: Pluggable SOTA multi-object tracking modules with support for axis-aligned and oriented bounding boxes
This tool helps you reliably track multiple moving objects, like people, vehicles, or animals, across video footage. You provide video input or a live camera feed, and it outputs precise locations and unique IDs for each object, even if they temporarily disappear or cross paths. It's designed for professionals working with video analysis, surveillance, or automated systems that need to monitor activity.
8,053 stars. Actively maintained with 4 commits in the last 30 days.
Use this if you need to identify and follow individual objects in videos or real-time streams, ensuring each object retains its unique identifier over time.
Not ideal if you only need to detect objects at a single moment in time without needing to track their movement or identity across frames.
Stars
8,053
Forks
1,891
Language
Python
License
AGPL-3.0
Category
Last pushed
Mar 13, 2026
Commits (30d)
4
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.
Recent Releases
Related tools
roboflow/rf-detr
[ICLR 2026] RF-DETR is a real-time object detection and segmentation model architecture...
stereolabs/zed-sdk
⚡️The spatial perception framework for rapidly building smart robots and spaces
RizwanMunawar/yolov7-object-tracking
YOLOv7 Object Tracking Using PyTorch, OpenCV and Sort Tracking
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