- We now upload the trained motion model.
- 2024-02-27: This work is accepted by CVPR-2024.
| Dataset | HOTA | IDF1 | Assa | MOTA | DetA | Weight | Results |
|---|---|---|---|---|---|---|---|
| DanceTrack | 62.3 | 63.0 | 47.2 | 92.8 | 82.5 | download | DanceTrack_Results |
| SportsMOT | 76.2 | 76.1 | 65.1 | 97.1 | 89.3 | download | SportsMOT_Results |
| MOT17 | 64.5 | 79.3 | 64.6 | 79.8 | 64.7 | download | MOT17_Results |
| MOT20 | 61.7 | 74.9 | 60.5 | 76.7 | 63.2 | download | MOT20_Results |
| Detector | HOTA | IDF1 | MOTA | FPS |
|---|---|---|---|---|
| YOLOX-S | 53.3 | 56.6 | 88.4 | 30.3 |
| YOLOX-M | 57.2 | 58.6 | 91.2 | 25.4 |
| YOLOX-L | 61.5 | 61.7 | 92.0 | 24.2 |
| YOLOX-X | 62.3 | 63.0 | 92.8 | 22.7 |
The tracking speed (including detection and tracking speed) is test on an RTX 3090 GPU. Smaller detectors can achieve higher FPS, which indicates that DiffMOT can flexibly choose different detectors for various real-world application scenarios. With YOLOX-S, the tracking speed of the entire system can reach up to 30.3 FPS.
- install torch
conda create -n diffmot python=3.9
conda activate diffmot
pip install torch==2.0.1 torchvision==0.15.2 torchaudio==2.0.2
- install other packages.
pip install -r requirement.txt
- install external dependencies.
cd external/YOLOX/
pip install -r requirements.txt && python setup.py develop
cd ../external/deep-person-reid/
pip install -r requirements.txt && python setup.py develop
cd ../external/fast_reid/
pip install -r docs/requirements.txt
The file structure should look like:
- DanceTrack
{DanceTrack ROOT}
|-- dancetrack
| |-- train
| | |-- dancetrack0001
| | | |-- img1
| | | | |-- 00000001.jpg
| | | | |-- ...
| | | |-- gt
| | | | |-- gt.txt
| | | |-- seqinfo.ini
| | |-- ...
| |-- val
| | |-- ...
| |-- test
| | |-- ...
- SportsMOT
{SportsMOT ROOT}
|-- sportsmot
| |-- splits_txt
| |-- scripts
| |-- dataset
| | |-- train
| | | |-- v_1LwtoLPw2TU_c006
| | | | |-- img1
| | | | | |-- 000001.jpg
| | | | | |-- ...
| | | | |-- gt
| | | | | |-- gt.txt
| | | | |-- seqinfo.ini
| | | |-- ...
| | |-- val
| | | |-- ...
| | |-- test
| | | |-- ...
- MOT17/20 We train the MOT17 and MOT20 together.
{MOT17/20 ROOT}
|-- mot
| |-- train
| | |-- MOT17-02
| | | |-- img1
| | | | |-- 000001.jpg
| | | | |-- ...
| | | |-- gt
| | | | |-- gt.txt
| | | |-- seqinfo.ini
| | |-- ...
| | |-- MOT20-01
| | | |-- img1
| | | | |-- 000001.jpg
| | | | |-- ...
| | | |-- gt
| | | | |-- gt.txt
| | | |-- seqinfo.ini
| | |-- ...
| |-- test
| | |-- ...
and run:
python dancetrack_data_process.py
python sports_data_process.py
python mot_data_process.py
We provide some trained YOLOX weights in download for DiffMOT. Some of them are inherited from ByteTrack, DanceTrack, and MixSort.
Ours ReID models for MOT17/MOT20 is the same as BoT-SORT , you can download from MOT17-SBS-S50, MOT20-SBS-S50. The ReID model for DanceTrack is the same as Deep-OC-SORT, you can download from Dance-SBS-S50. The ReID model for SportsMOT is trained by ourself, you can download from Sports-SBS-S50.
Notes:
- MOT20-SBS-S50 is trained by Deep-OC-SORT, because the weight from BOT-SORT is corrupted. Refer to Issue.
- ReID models for SportsMOT is trained by ourself.
Refer to models. We train on DanceTrack and MOT17/20 for 800 epochs, and train on SportsMOT for 1200 epochs.
- You can refer to the ByteTrack.
- You can refer to the BoT-SORT.
- Change the data_dir in config
- Train on DanceTrack, SportsMOT, and MOT17/20:
python main.py --config ./configs/dancetrack.yaml
python main.py --config ./configs/sportsmot.yaml
python main.py --config ./configs/mot.yaml
- You can obtain the detections by detection_model or use the detection_results we have provided.
- Change the det_dir in config.
- We have provided the ReID embeddings.
- Change the reid_dir in config.
- Change the info_dir, and save_dir in config.
- High_thres is set to 0.6, low_thres is set to 0.4, w_assoc_emb is set to 2.2, and aw_param is set to 1.7.
python main.py --config ./configs/dancetrack_test.yaml
- Change the info_dir, and save_dir in config.
- High_thres is set to 0.6, low_thres is set to 0.4, w_assoc_emb is set to 2.0, and aw_param is set to 1.2.
python main.py --config ./configs/sportsmot_test.yaml
- Change the info_dir, and save_dir in config.
- High_thres is set to 0.6, low_thres is set to 0.1, w_assoc_emb is set to 2.2, and aw_param is set to 1.7.
python main.py --config ./configs/mot17_test.yaml
- Change the info_dir, and save_dir in config.
- High_thres is set to 0.4, low_thres is set to 0.1, w_assoc_emb is set to 2.2, and aw_param is set to 1.7.
python main.py --config ./configs/mot20_test.yaml
If you have some questions, please concat with [email protected].
A large part of the code is borrowed from DDM-Public and Deep-OC-SORT. Thanks for their wonderful works.
@inproceedings{lv2024diffmot,
title={DiffMOT: A Real-time Diffusion-based Multiple Object Tracker with Non-linear Prediction},
author={Lv, Weiyi and Huang, Yuhang and Zhang, Ning and Lin, Ruei-Sung and Han, Mei and Zeng, Dan},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
pages={19321--19330},
year={2024}
}
