getinglxf / mtmct

Design and Implementation of a Multi-Target Multi-Camera Tracking Solution

Home Page:https://wiser.cas.mcmaster.ca/?docs=interactive-perception-on-edge-devices#6-toc-title

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

English | 简体中文

MTMCT

This project demonstrates the design and implementation of a Multi-Target Multi-Camera Tracking (MTMCT) solution.

Pipeline of our solution:

Tracking performance

Results and comparisons with FairMOT and wda_tracker trained and tested on a 6x2-minute MTA dataset

Method Single-Camera Multi-Camera
MOTA IDF1 IDs MT ML MOTA IDF1 IDs MT ML
WDA 58.2 37.3 534.2 16.8% 17.2 46.6 19.8 563.8 6.5% 7.0%
FairMOT 64.1 48.0 588.2 34.7% 7.8% N/A N/A N/A N/A N/A
Ours 70.8 47.8 470.2 40.5% 5.6% 65.6 31.5 494.5 31.2% 1.1%

Demo GIFs can be seen here

Full-length demo videos can be found at: https://youtu.be/lS9YvbrhOdo

Installation

conda create -n mtmct python=3.7.7 -y
conda activate mtmct
pip install -r requirements.txt

Install dependencies for FairMOT:

cd trackers/fair
conda install pytorch==1.7.0 torchvision==0.8.0 cudatoolkit=10.2 -c pytorch
pip install cython
pip install -r requirements.txt
cd DCNv2
./make.sh
conda install -c conda-forge ffmpeg

Download data

Go to https://github.com/schuar-iosb/mta-dataset to download the MTA data. Or use other datasets that match the same format.

Configurations

Modify config files under tracker_configs and clustering_configs for customization. Create a work_dirs and see more instructions at FairMOT and wda_tracker.

E.g. in configs/tracker_configs/fair_high_30e set the data -> source -> base_folder to your dataset location.

Tracking

Run single and the multi-camera tracking with one script:

sh start.sh fair_high_30e

Modify config files under tracker_configs and clustering_configs for customization. More instructions can be found at FairMOT and wda_tracker.

Acknowledgement

A large part of the code is borrowed from FairMOT and wda_tracker. The dataset used is MTA

Copyright

Ruizhe Zhang is the author of this repository and the corresponding report, the copyright belongs to Wireless System Research Group (WiSeR), McMaster University.

About

Design and Implementation of a Multi-Target Multi-Camera Tracking Solution

https://wiser.cas.mcmaster.ca/?docs=interactive-perception-on-edge-devices#6-toc-title

License:MIT License


Languages

Language:Python 71.2%Language:Jupyter Notebook 21.8%Language:Cuda 3.5%Language:C++ 2.5%Language:Shell 0.5%Language:C 0.2%Language:Cython 0.2%Language:Dockerfile 0.1%Language:MATLAB 0.0%Language:Batchfile 0.0%Language:Makefile 0.0%