Joint Detection and Embedding for fast multi-object tracking

Multiple Object Tracker, Based on Hungarian algorithm + Kalman filter.

[CVPR'23] Universal Instance Perception as Object Discovery and Retrieval

[ECCV'22 Oral] Towards Grand Unification of Object Tracking

C++ implementation to Detect, track and classify multiple objects using LIDAR scans or point cloud

[CVPR 2025] Multiple Object Tracking as ID Prediction

Library for tracking-by-detection multi object tracking implemented in python

[AAAI 2024] UCMCTrack: Multi-Object Tracking with Uniform Camera Motion Compensation. UCMCTrack achieves SOTA on MOT17 using estimated camera parameters.

The official code for our ECCV22 oral paper: tracking objects as pixel-wise distributions.

Cascade-RCNN+DeepSort MOTDT Trackor++

This is the official implementation of TransCenter (TPAMI). The code and pretrained models are now available here: https://gitlab.inria.fr/yixu/TransCenter_official.

Анализ трафика на круговом движении с использованием компьютерного зрения

Multiple Object Tracking System in Keras + (Detection Network - YOLO)

Deep Motion Modeling Network

A multi object tracking Library Based on tensorrt

Python package to label and track unique geospatial features from gridded datasets

Contains implementation of multi-threaded object detection followed by tracking

[ECCV 2026] History-Aware Transformation of ReID Features for Multiple Object Tracking

Official code of CAMO-MOT

combine state of art deep neural network based detectors with most efficient trackers to solve motion based multiple objects tracking problems