- 基于FairMOT训练人脸跟踪模型，速度和性能都非常好.
- repo里的模型精度不是最好的，如有需要重新训练.
- 1.修改./src/lib/opts.py 118行--input-video 为自己的视频路径.
- 2.run demo.py 即可演示跟踪demo.
- 详见本人博客 https://blog.csdn.net/zengwubbb/article/details/108693096.
A simple baseline for one-shot multi-object tracking:
FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking,
Yifu Zhang, Chunyu Wang, Xinggang Wang, Wenjun Zeng, Wenyu Liu,
arXiv technical report (arXiv 2004.01888)
There has been remarkable progress on object detection and re-identification in recent years which are the core components for multi-object tracking. However, little attention has been focused on accomplishing the two tasks in a single network to improve the inference speed. The initial attempts along this path ended up with degraded results mainly because the re-identification branch is not appropriately learned. In this work, we study the essential reasons behind the failure, and accordingly present a simple baseline to addresses the problems. It remarkably outperforms the state-of-the-arts on the MOT challenge datasets at 30 FPS. We hope this baseline could inspire and help evaluate new ideas in this field.
- (2020.09.10) A new version of FairMOT is released! (73.7 MOTA on MOT17)
- We pretrain FairMOT on the CrowdHuman dataset using a self-supervised learning approach.
- To detect bounding boxes outside the image, we use left, top, right and bottom (4 channel) to replace the WH head (2 channel).
| Dataset | MOTA | IDF1 | IDS | MT | ML | FPS |
|---|---|---|---|---|---|---|
| 2DMOT15 | 60.6 | 64.7 | 591 | 47.6% | 11.0% | 30.5 |
| MOT16 | 74.9 | 72.8 | 1074 | 44.7% | 15.9% | 25.9 |
| MOT17 | 73.7 | 72.3 | 3303 | 43.2% | 17.3% | 25.9 |
| MOT20 | 61.8 | 67.3 | 5243 | 68.8% | 7.6% | 13.2 |
All of the results are obtained on the MOT challenge evaluation server under the “private detector” protocol. We rank first among all the trackers on 2DMOT15, MOT16, MOT17 and MOT20. The tracking speed of the entire system can reach up to 30 FPS.
- Clone this repo, and we'll call the directory that you cloned as ${FAIRMOT_ROOT}
- Install dependencies. We use python 3.7 and pytorch >= 1.2.0
conda create -n FairMOT
conda activate FairMOT
conda install pytorch==1.2.0 torchvision==0.4.0 cudatoolkit=10.0 -c pytorch
cd ${FAIRMOT_ROOT}
pip install -r requirements.txt
- We use DCNv2 in our backbone network and more details can be found in their repo.
git clone https://github.com/CharlesShang/DCNv2
cd DCNv2
./make.sh
- In order to run the code for demos, you also need to install ffmpeg.
- CrowdHuman The CrowdHuman dataset can be downloaded from their official webpage. After downloading, you should prepare the data in the following structure:
crowdhuman
|——————images
| └——————train
| └——————val
└——————labels_with_ids
| └——————train(empty)
| └——————val(empty)
└------annotation_train.odgt
└------annotation_val.odgt
Then, you can change the paths in src/gen_labels_crowd.py and run:
cd src
python gen_labels_crowd.py
- MIX We use the same training data as JDE in this part and we call it "MIX". Please refer to their DATA ZOO to download and prepare all the training data including Caltech Pedestrian, CityPersons, CUHK-SYSU, PRW, ETHZ, MOT17 and MOT16.
- 2DMOT15 and MOT20 2DMOT15 and MOT20 can be downloaded from the official webpage of MOT challenge. After downloading, you should prepare the data in the following structure:
MOT15
|——————images
| └——————train
| └——————test
└——————labels_with_ids
└——————train(empty)
MOT20
|——————images
| └——————train
| └——————test
└——————labels_with_ids
└——————train(empty)
Then, you can change the seq_root and label_root in src/gen_labels_15.py and src/gen_labels_20.py and run:
cd src
python gen_labels_15.py
python gen_labels_20.py
to generate the labels of 2DMOT15 and MOT20. The seqinfo.ini files of 2DMOT15 can be downloaded here [Google], [Baidu],code:8o0w.
- Pretrained models
DLA-34 COCO pretrained model: DLA-34 official. HRNetV2 ImageNet pretrained model: HRNetV2-W18 official, HRNetV2-W32 official. After downloading, you should put the pretrained models in the following structure:
${FAIRMOT_ROOT}
└——————models
└——————ctdet_coco_dla_2x.pth
└——————hrnetv2_w32_imagenet_pretrained.pth
└——————hrnetv2_w18_imagenet_pretrained.pth
- Baseline model
Our baseline FairMOT model (DLA-34 backbone) is pretrained on the CrowdHuman for 60 epochs with the self-supervised learning approach and then trained on the MIX dataset for 30 epochs. The models can be downloaded here: crowdhuman_dla34.pth [Google] [Baidu, code:ggzx ] [Onedrive]. fairmot_dla34.pth [Google] [Baidu, code:uouv] [Onedrive]. (This is the model we get 73.7 MOTA on the MOT17 test set. ) After downloading, you should put the baseline model in the following structure:
${FAIRMOT_ROOT}
└——————models
└——————fairmot_dla34.pth
└——————...
- Download the training data
- Change the dataset root directory 'root' in src/lib/cfg/data.json and 'data_dir' in src/lib/opts.py
- Pretrain on CrowdHuman and train on MIX:
sh experiments/crowdhuman_dla34.sh
sh experiments/mix_ft_ch_dla34.sh
- Only train on MIX:
sh experiments/mix_dla34.sh
- Only train on MOT17:
sh experiments/mot17_dla34.sh
- Finetune on 2DMOT15 using the baseline model:
sh experiments/mot15_ft_mix_dla34.sh
- Finetune on MOT20 using the baseline model:
sh experiments/mot20_ft_mix_dla34.sh
- For ablation study, we use MIX and half of MOT17 as training data, you can use different backbones such as ResNet, ResNet-FPN, HRNet and DLA:
sh experiments/mix_mot17_half_dla34.sh
sh experiments/mix_mot17_half_hrnet18.sh
sh experiments/mix_mot17_half_res34.sh
sh experiments/mix_mot17_half_res34fpn.sh
sh experiments/mix_mot17_half_res50.sh
- Performance on the test set of MOT17 when using different training data:
| Training Data | MOTA | IDF1 | IDS |
|---|---|---|---|
| MOT17 | 69.8 | 69.9 | 3996 |
| MIX | 72.9 | 73.2 | 3345 |
| CrowdHuman + MIX | 73.7 | 72.3 | 3303 |
- The default settings run tracking on the validation dataset from 2DMOT15. Using the baseline model, you can run:
cd src
python track.py mot --load_model ../models/fairmot_dla34.pth --conf_thres 0.6
to see the tracking results (76.5 MOTA and 79.3 IDF1 using the baseline model). You can also set save_images=True in src/track.py to save the visualization results of each frame.
- For ablation study, we evaluate on the other half of the training set of MOT17, you can run:
cd src
python track.py mot --load_model ../exp/mot/mix_mot17_half_dla34.pth --conf_thres 0.4
- To get the txt results of the test set of MOT16 or MOT17, you can run:
cd src
python track.py mot --test_mot17 True --load_model ../models/fairmot_dla34.pth --conf_thres 0.4
python track.py mot --test_mot16 True --load_model ../models/fairmot_dla34.pth --conf_thres 0.4
and send the txt files to the MOT challenge evaluation server to get the results. (You can get the SOTA results 73+ MOTA on MOT17 test set using the baseline model 'fairmot_dla34.pth'.)
- To get the SOTA results of 2DMOT15 and MOT20, run the tracking code:
cd src
python track.py mot --test_mot15 True --load_model your_mot15_model.pth --conf_thres 0.3
python track.py mot --test_mot20 True --load_model your_mot20_model.pth --conf_thres 0.3
Results of the test set all need to be evaluated on the MOT challenge server. You can see the tracking results on the training set by setting --val_motxx True and run the tracking code. We set 'conf_thres' 0.4 for MOT16 and MOT17. We set 'conf_thres' 0.3 for 2DMOT15 and MOT20.
You can input a raw video and get the demo video by running src/demo.py and get the mp4 format of the demo video:
cd src
python demo.py mot --load_model ../models/fairmot_dla34.pth --conf_thres 0.4
You can change --input-video and --output-root to get the demos of your own videos. --conf_thres can be set from 0.3 to 0.7 depending on your own videos.
A large part of the code is borrowed from Zhongdao/Towards-Realtime-MOT and xingyizhou/CenterNet. Thanks for their wonderful works.
@article{zhang2020fair,
title={FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking},
author={Zhang, Yifu and Wang, Chunyu and Wang, Xinggang and Zeng, Wenjun and Liu, Wenyu},
journal={arXiv preprint arXiv:2004.01888},
year={2020}
}