An annotation and instance segmentation-based multiple animal tracking and behavior analysis package.

Lightweight Go library for adding real-time multi-object tracking to any detector — A golang port of norfair https://github.com/tryolabs/norfair

A common data structure and basic tools for multi-object tracking.

A unified library for object tracking featuring clean room re-implementations of leading multi-object tracking algorithms

Official implementation of 🐫 CAMELTrack: Context-Aware Multi-cue ExpLoitation for Online Multi-Object Tracking 🐫

A modular, high-throughput Computer Vision pipeline that utilizes YOLOv8 and advanced transformation techniques (View Transformer, camera compensation) to extract real-world tactical metrics (speeds, distances) from broadcast video.

BoxMOT: Pluggable SOTA multi-object tracking modules modules for segmentation, object detection and pose estimation models

Ultralytics Assistant repo

[CVPR 2023 Best Paper Award] Planning-oriented Autonomous Driving

Survey: A collection of AWESOME papers and resources on the latest research in Object Tracking.

This project demonstrates a comprehensive Computer Vision Perception System that combines multiple state-of-the-art techniques for autonomous vehicle perception. The system integrates lane detection, object detection, and multi-object tracking to create a robust perception pipeline suitable for autonomous driving applications.

Source code for paper "Adaptive Confidence Threshold for ByteTrack in Multi-Object Tracking"

[ICCV 2023] MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking

🔥🔥 CVPR 2025 (Nashville TN) - The 4th Anti-UAV Workshop & Challenge 🥉

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

Gather research papers, corresponding codes (if having), reading notes and any other related materials about Hot🔥🔥🔥 fields in Computer Vision based on Deep Learning.

Bayesian multi-object tracking

Focusing on Tracks for Online Multi-Object Tracking

This project provides the first publicly available long-distance abnormal parking dataset. It contains 1,000 video sequences, including 200 abnormal videos and 800 normal videos.

EBEVTrack: Estimated Bird's-Eye View for Multi-Object Tracking