Towards-Realtime-MOT-Cpp

Towards-Realtime-MOT-Cpp

A C++ codebase implementation of Towards-Realtime-MOT.

Github

https://github.com/samylee/Towards-Realtime-MOT-Cpp

Introduction

This repo is the a c++ codebase of the Joint Detection and Embedding (JDE) model. JDE is a fast and high-performance multiple-object tracker that learns the object detection task and appearance embedding task simutaneously in a shared neural network. We hope this repo will help researches/engineers to develop more practical MOT systems.

Requirements

• Sys-Windows10 (Windows7 should also work)
• GPU-Nvidia (GTX-1080/RTX-2080/RTX-2080Ti)
• IDE-VS2017/VS2019
• cuda == 10.1, cudnn == 7.6
• LibTorch-1.4.0 [Baidu] (PWD: gr3t)
• OpenCV == 4.2.0
• eigen-3.3.9 [Baidu] (PWD: ziiw)

Quick Start

1. Download JDE weights from [Google] [Baidu].
2. Convert the pytorch model to a jit model based on Towards-Realtime-MOT, or download [jit_model] (PWD: tupu) directly.

python cvt2jit.py (based on pytorch-1.4.0)

1. Compile source code by VS2017/2019.
2. Run JDETracker.

Performance

Model	MOTA	IDF1	IDS	FP	FN	FPS @Hardware
JDE-576x320	63.7	63.3	1307	6657	32794	33.5 @i7-9700K, RTX-2080ti

Video Demo

 

Reference

• https://blog.youkuaiyun.com/samylee
• https://github.com/Zhongdao/Towards-Realtime-MOT

 

任何问题请加唯一QQ2258205918（名称samylee）！

或唯一VX：samylee_csdn