Tracking Algorithm Python Packages

norfair

Lightweight Python library for adding real-time multi-object tracking to any detector.

btrack

Bayesian multi-object tracking

xtrack

Python package for tracking simulations in particle accelerators on CPU and GPU.

pyfortracc

pyFortraCC is a Python library for tracking and forecasting clusters.

viame

Video and Image Analytics for Multiple Environments

skellytracker

A pose estimation and object detection/tracking backend for freemocap.

multisensor-lmb-filters-rs

50-1000x Faster multi-sensor labelled Bernoulli filters in Rust and Python via Py03 - A (mostly automated) port of https://github.com/scjrobertson/multisensor-lmb-filters

yupi

Python package designed for collecting and processing trajectory data.

norfair-rs

Drop-in Rust/Python replacement for norfair — Add real-time multi-object tracking to any detector — A (mostly automated) rust port of norfair https://github.com/tryolabs/norfair

deeplabcut-live

SDK for running DeepLabCut on a live video stream

trajectory-forecast

Forecast where tracked objects will move next. A lightweight extension to Ultralytics YOLO that adds Kalman-filtered trajectory prediction; stable, low-jitter, and efficient for real-time systems.

deep-sort-reid

An adaption of the prominent 'Deep Sort' Algorithm, with re-identification features.

tintx

Object based tracking for model, radar and any other kind of data

nanotrack

NanoTrack is a lightweight object detection and tracking package designed for use with YOLO. It provides efficient tracking algorithms with minimal resource requirements.

simple-filters

A collection of simple NumPy-based filters and trackers optimized for real-time performance.

norfairwhl

Lightweight Python library for adding real-time multi-object tracking to any detector.