BoT-SORT: Unofficial C++ Implementation

BoT-SORT: Robust Associations Multi-Pedestrian Tracking

Nir Aharon, Roy Orfaig, Ben-Zion Bobrovsky

Description

This repository contains an unofficial C++ implementation of BoT-SORT multi-pedestrian tracking algorithm.

This implementation has been tested on NVIDIA Jetson NX and it achieves real-time performance on 1080p videos.

YOLOv8-tracking, Official BoT-SORT and Official ByteTrack GitHub repositories were used as references.

TODO

• Implement BoT-SORT tracker
• Load parameters from config file
• Implement Re-ID model for BoT-SORT tracker using TensorRT
• Dockerize the project
• Re-ID performance analysis
• Re-ID model quantization

Preview of Results

These results demonstrate the BoT-SORT tracker, implemented in this repository, utilizing MOT provided detections.

More Result Videos

Installation Guide

1. Install Docker and NVIDIA Container Toolkit

2. Clone the repository

   git clone git@github.com:viplix3/BoTSORT-cpp.git
   cd BoTSORT-cpp
   

3. Build Docker image

   ./docker_build.sh
   

4. Run Docker container

   ./docker_run.sh
   

5. Build BoT-SORT tracker

   cd /home/user/work/
   mkdir build && cd build
   cmake .. -DCMAKE_BUILD_TYPE=Release
   make -j$(nproc)
   

Usage

Example code for using the BoT-SORT tracker is provided in botsort_tracking_example.cpp The project by default builds the example code.

To test the example code, run the following command:

cd <project-root-dir>/build
./bin/botsort_tracking_example ../config/tracker.ini ../config/gmc.ini ../config/reid.ini ../assets/osnet_x0_25_market1501.onnx ../examples/data/MOT20-01.mp4 ../examples/data/det/det.txt ../output/

Performance Analysis

The performance of the BoT-SORT tracker, implemented in this repository, was evaluated on the MOT20 dataset. Details are provided in this document.

Execution time of different modules (Host Machine, Release Build, Best of 3)

Execution time of different modules (Jetson-NX, Release Build, Best of 3)

Accuracy Analysis

The accuracy of the BoT-SORT tracker, implemented in this repository, was evaluated on the MOT20 train set. Details are provided in this document.