Awesome
Sparse Graph Tracker (SGT)
Official code for Sparse Graph Tracker (SGT) based on the Detectron2 framework. Please feel free to leave an ISSUE or send me an email (jhyunaa@ust.hk).
News
- (2022.10.11) Our paper is accepted WACV 2023! (arxiv paper will be updated soon)
- (2022.10.06) Code and pretrained weights are released!
Installation
- Please refer INSTALL.md for the details
Dataset Setup
- Please refer DATASET.md for the details
Model Zoo
- Please modify the path of checkpoints in the config file based on your checkpoint directory
MOT17
| Name | Dataset | HOTA | MOTA | IDF1 | Download |
|---|---|---|---|---|---|
| SGT | MOT17 | 58.2 | 73.2 | 70.2 | model |
| SGT | MOT17 + CrowdHuman | 60.8 | 76.4 | 72.8 | model |
MOT20
| Name | Dataset | HOTA | MOTA | IDF1 | Download |
|---|---|---|---|---|---|
| SGT | MOT20 | 51.6 | 64.5 | 62.7 | model |
| SGT | MOT20 + CrowdHuman | 57.0 | 72.8 | 70.6 | model |
HiEve
| Name | Dataset | MOTA | IDF1 | Download |
|---|---|---|---|---|
| SGT | HiEve | 47.2 | 53.7 | model |
How to run?
Train
python projects/SGT/train_net.py --config-file projects/SGT/configs/MOT17/sgt_dla34.yaml --data-dir /root/datasets --num-gpus 2 OUTPUT_DIR /root/sgt_output/mot17_val/dla34_mot17-CH
Inference
python projects/SGT/train_net.py --config-file projects/SGT/configs/MOT17/sgt_dla34.yaml --data-dir /root/datasets --num-gpus 1 --eval-only OUTPUT_DIR /root/sgt_output/mot17_test/dla34_mot17-CH
Visualization
## GT
python projects/Datasets/MOT/vis/vis_gt.py --data-root <$DATA_ROOT> --register-data-name <e.g., mot17_train>
python projects/Datasets/MOT/vis/vis_gt.py --data-root <$DATA_ROOT> --register-data-name <e.g., mix_crowdhuman_train> --no-video-flag
## model output
python projects/Datasets/MOT/vis/vis_seq_from_txt_result.py --data-root <$DATA_ROOT> --result-dir <$OUTPUT_DIR> --data-name {mot17, mot20, hieve, mot17_sub, mot20_sub} --tgt-split {val,test}
Motivation
Pipeline
MOT Benchmark Results
Ablation Experiment Results
Visualization
License
Code of SGT is licensed under the CC-BY-NC 4.0 license and free for research and academic purpose. SGT is based on the framework Detectron2 which is released under the Apache 2.0 license and the detector CenterNet which is released under the MIT license. This codebase also provides Detectron2 version of FairMOT which is released under the MIT license.
Citation
@inproceedings{hyun2023detection,
title={Detection recovery in online multi-object tracking with sparse graph tracker},
author={Hyun, Jeongseok and Kang, Myunggu and Wee, Dongyoon and Yeung, Dit-Yan},
booktitle={Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
pages={4850--4859},
year={2023}
}