Multiple-Object Tracking with Transformer

TransTrack: Multiple-Object Tracking with Transformer

Introduction

TransTrack: Multiple-Object Tracking with Transformer

Models

Models are also available in Baidu Drive by code m4iv.

Notes

• Evaluating crowdhuman-training model and mot-training model use different command lines, see Steps.
• We observe about 1 MOTA noise.
• If the resulting MOTA of your self-trained model is not desired, playing around with the --track_thresh sometimes gives a better performance.
• The training time is on 8 NVIDIA V100 GPUs with batchsize 16.
• We use the models pre-trained on imagenet.

Demo

Installation

The codebases are built on top of Deformable DETR and CenterTrack.

Requirements

• Linux, CUDA>=9.2, GCC>=5.4
• Python>=3.7
• PyTorch ≥ 1.5 and torchvision that matches the PyTorch installation. You can install them together at pytorch.org to make sure of this
• OpenCV is optional and needed by demo and visualization

Steps

1. Install and build libs

git clone https://github.com/PeizeSun/TransTrack.git
cd TransTrack
cd models/ops
python setup.py build install
cd ../..
pip install -r requirements.txt

2. Prepare dataset

mkdir -p crowdhuman/annotations
cp -r /path_to_crowdhuman_dataset/annotations/CrowdHuman_val.json crowdhuman/annotations/CrowdHuman_val.json
cp -r /path_to_crowdhuman_dataset/annotations/CrowdHuman_train.json crowdhuman/annotations/CrowdHuman_train.json
cp -r /path_to_crowdhuman_dataset/CrowdHuman_train crowdhuman/CrowdHuman_train
cp -r /path_to_crowdhuman_dataset/CrowdHuman_val crowdhuman/CrowdHuman_val
mkdir mot
cp -r /path_to_mot_dataset/train mot/train
cp -r /path_to_mot_dataset/test mot/test
python track_tools/convert_mot_to_coco.py

CrowdHuman dataset is available in CrowdHuman. We provide annotations of json format.

MOT dataset is available in MOT.

3. Pre-train on crowdhuman

sh track_exps/crowdhuman_train.sh
python track_tools/crowdhuman_model_to_mot.py

The pre-trained model is available crowdhuman_final.pth.

4. Train TransTrack

sh track_exps/crowdhuman_mot_trainhalf.sh

5. Evaluate TransTrack

sh track_exps/mot_val.sh
sh track_exps/mot_eval.sh

6. Visualize TransTrack

python track_tools/txt2video.py

Notes

• Evaluate pre-trained CrowdHuman model on MOT

sh track_exps/det_val.sh
sh track_exps/mot_eval.sh

License

TransTrack is released under MIT License.

Citing

If you use TransTrack in your research or wish to refer to the baseline results published here, please use the following BibTeX entries:

@article{transtrack,
  title   =  {TransTrack: Multiple-Object Tracking with Transformer},
  author  =  {Peize Sun and Yi Jiang and Rufeng Zhang and Enze Xie and Jinkun Cao and Xinting Hu and Tao Kong and Zehuan Yuan and Changhu Wang and Ping Luo},
  journal =  {arXiv preprint arXiv: 2012.15460},
  year    =  {2020}
}