Fork from https://github.com/Zhongdao/Towards-Realtime-MOT for surfacing suspicion (PhD. research project)

Go to file

lynn 7e741b2985 cl		2019-10-01 21:45:46 +08:00
cfg	test	2019-09-29 13:13:23 +08:00
tracker	can save video output now	2019-09-27 16:58:09 +08:00
utils	Merge branch 'master' of https://github.com/Zhongdao/Towards-Realtime-MOT	2019-09-29 13:14:05 +08:00
.gitignore	add video demo	2019-09-28 11:40:41 +08:00
LICENSE	Initial commit	2019-09-27 13:09:34 +08:00
README.md	Update README.md	2019-09-29 17:15:19 +08:00
demo.py	hh	2019-09-28 12:07:58 +08:00
extract_ped_per_frame.py	setup	2019-09-27 13:37:47 +08:00
models.py	cl	2019-10-01 21:45:46 +08:00
test.py	cl	2019-10-01 21:45:46 +08:00
track.py	fix a bug in track.py	2019-09-29 13:18:38 +08:00
train.py	setup	2019-09-27 13:37:47 +08:00

README.md

Towards-Realtime-MOT

Introduction

This repo is the a 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. Techical details are described in our arXiv preprint paper. By using this repo, you can simply achieve MOTA 64%+ on the "private" protocol of MOT-16 challenge, and with a near real-time speed at 18~24 FPS (Note this speed is for the entire system, including the detection step! ) .

We hope this repo will help researches/engineers to develop more practical MOT systems. For algorithm development, we provide training data, baseline models and evaluation methods to make a level playground. For application usage, we also provide a small video demo that takes a raw video as input without any bells and whistles.

README.md

Towards-Realtime-MOT

Introduction

Installation

Video Demo

Dataset zoo

Pretrained Models

Test on MOT-16 Challenge

Training

Train with custom datasets