OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

Boxmot

BoxMOT is a public AGPL-3.0 library that provides pluggable Python and C++ multi-object tracking modules for detections represented as axis-aligned or oriented bounding boxes.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Boxmot — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use BoxMOT when an existing or planned computer-vision pipeline needs a replaceable tracking layer for AABB or OBB detections, with Python integration or a documented native C++ path.

Who it is for

  • Computer-vision developers building video-analytics pipelines
  • Python developers embedding tracking components in applications
  • C++ developers needing a native tracker component
  • Researchers evaluating tracking and ReID workflows

Documented uses

  • Associate detections across video frames
  • Maintain object identities after another model produces bounding boxes
  • Track objects represented by rotated or oriented boxes
  • Compose detector, segmentor, appearance-encoder and tracker components
  • Evaluate, tune and research tracking workflows through the command-line interface
Before you choose

Requirements & limits

The repository is public and displays an AGPL-3.0 license. The documented package supports Python 3.10 through 3.13 and is available through PyPI.

  • Input representation: the library supports both axis-aligned and oriented bounding-box detections.
  • Integration language: Python APIs are available, with native C++ tracker implementations and CMake integration documented separately.
  • Component architecture: detectors, segmentors, appearance encoders and trackers are independently composable.
  • Workflow scope: the CLI includes tracking, materialization, evaluation, tuning, research, ReID and export-related workflows.
  • Licensing: incorporation requires consideration of the AGPL-3.0 license.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install BoxMOT for local development

Set up the BoxMOT package and inspect its command-line interface.

Before you start

  • Python 3.10 through 3.13
  • A Python environment with access to the PyPI package

Steps

  1. Install the package with the documented PyPI installation command.

  2. Run the documented help command to view the available interface.

  3. Consult the installation guide for CPU, CUDA 13.0 and mode-specific extras when those profiles or workflows are needed.

Expected outcome

BoxMOT is installed and its command-line options are available for selecting a documented workflow.

Guide limitations

  • This setup recipe does not document a completed tracking run or validate a particular hardware, model or input source.
  • Additional workflow extras and source-checkout profiles have separate installation guidance.
Documentation 1 ↗Documentation 2 ↗
Evidence and transparency

Sources & review

Official repository ↗Guide documentation ↗
Source record details
Source availability
Active
Sources checked
2 October 2026
Original website title
mikel-brostrom/boxmot · Official homepage title · retained in its source language
How we review sourcesSuggest a correction