Towards-Realtime-MOT/README.md

31 lines
1.8 KiB
Markdown
Raw Normal View History

2019-09-28 07:29:26 +00:00
# Towards-Realtime-MOT
2019-10-01 01:32:20 +00:00
Still in progress, will update constantly, thank you for your attention!
2019-09-28 07:52:12 +00:00
2019-09-28 07:29:26 +00:00
## Introduction
2019-09-29 09:15:19 +00:00
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](https://arxiv.org). By using this repo, you can simply achieve **MOTA 64%+** on the "private" protocol of [MOT-16 challenge](https://motchallenge.net/tracker/JDE), and with a near real-time speed at **18~24 FPS** (Note this speed is for the entire system, including the detection step! ) .
2019-09-29 09:08:32 +00:00
2019-10-01 01:32:20 +00:00
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 raw videos as input without any bells and whistles.
2019-09-28 07:29:26 +00:00
2019-10-01 13:46:21 +00:00
## Requirements
* Python 3.6
* [Pytorch](https://pytorch.org) >= 1.0.1
* [syncbn](https://github.com/ytoon/Synchronized-BatchNorm-PyTorch) (Optional, compile and place it under utils/syncbn, or simply replace with nn.BatchNorm [here](https://github.com/Zhongdao/Towards-Realtime-MOT/blob/master/models.py#L12))
* [maskrcnn-benchmark](https://github.com/facebookresearch/maskrcnn-benchmark) (Their GPU NMS is used in this project)
* python-opencv
* ffmpeg (Optional, used in the video demo)
2019-09-28 07:52:12 +00:00
2019-09-28 07:29:26 +00:00
## Video Demo
## Dataset zoo
## Pretrained Models
## Test on MOT-16 Challenge
## Training
## Train with custom datasets
2019-10-01 13:46:21 +00:00
## Acknowledgement
A large portion of code is borrowed from [ultralytics/yolov3](https://github.com/ultralytics/yolov3) and [longcw/MOTDT](https://github.com/longcw/MOTDT), many thanks to their wonderful work!