Out-of-the-box code and models for CMU's object detection and tracking system for multi-camera surveillance videos. Speed optimized Faster-RCNN model. Tensorflow based. Also supports EfficientDet. WACVW'20

Real-time multi-object tracker using YOLOv7 and StrongSORT with OSNet

State-of-the-art model for person re-identification in Multi-camera Multi-Target Tracking. Benchmarked on Market-1501 and DukeMTMTC-reID datasets.

A multi-camera vehicle detection, tracking and re-identification system

[ICCV 2023] ReST: A Reconfigurable Spatial-Temporal Graph Model for Multi-Camera Multi-Object Tracking

This repo contains links to multi-person re-identification and tracking dataset in top view multi-camera environment.

A Low-cost Open-source High-speed Multi-camera Motion Capture System.

The main abnormal behaviors that this project can detect are: Violence, covering camera, Choking, lying down, Running, Motion in restricted areas. It provides much flexibility by allowing users to choose the abnormal behaviors they want to be detected and keeps track of every abnormal event to be reviewed. We used three methods to detect abnormal behaviors: Motion influence map, Pattern recognition models, State event model. For multi-camera tracking, we combined a single camera tracking algorithm with a spatial based algorithm.

Official Implementation of "Tracking Grow-Finish Pigs Across Large Pens Using Multiple Cameras"

Multi-camera Network research resources

live, low-latency markerless multi-camera 3D animal tracking system

[CVPRW 2023] "Leveraging Future Trajectory Prediction for Multi-Camera People Tracking"

Official Repo For "RockTrack"

Vehicle MTMC Tracking

JARVIS Markerless 3D Motion Capture Pytorch Library

This is the official Python and C++ implementation repository for a paper entitled "Track Initialization and Re-Identification for 3D Multi-View Multi-Object Tracking", Information Fusion (http://arxiv.org/abs/2405.18606).

TrackNet: A Triplet metric-based method for Multi-Target Multi-Camera Vehicle Tracking

Real-time multi-camera face tracking system with PyQt5 interface and alert notifications (including Telegram notifications). Supports webcams, RTSP streams, and provides face recognition with InsightFace models.

Markerless Motion Capture Software is required to build the low-cost, modular and multi-camera ML-MoCap system.

Tracking staff activities with multiple camera support by using yolo for the head, and using dlib for face recognition.

Evaluation Toolkit for Track-based Multi-camera Tracking on DukeMTMC tracking challenge

Multi-sensor GLMB for nuScences dataset

Multi-Tracking Multi-Camera Person Re-Identification

Code for "Space-Time Guided Association Learning For Unsupervised Person Re-Identification"

MP-MCWT paper evaluation and MC-MOT Annotation Tool

Multi-target Multi-camera Person Tracking (M.S. Project at UCSB)

⚽️A deep learning-based system designed for re-identifying football players across video frames and camera angles using person re-identification techniques. This project combines computer vision, feature extraction, and player tracking to help automate sports analytics and player recognition.