Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
Feng Ni 13c1fef14b | 2 years ago | |
---|---|---|
.. | ||
README.md | 2 years ago | |
README_cn.md | 2 years ago | |
fairmot_dla34_30e_1088x608_headtracking21.yml | 2 years ago |
English | 简体中文
现有行人跟踪器对高人群密度场景表现不佳,人头跟踪更适用于密集场景的跟踪。
HT-21是一个高人群密度拥挤场景的人头跟踪数据集,场景包括不同的光线和环境条件下的拥挤的室内和室外场景,所有序列的帧速率都是25fps。
骨干网络 | 输入尺寸 | MOTA | IDF1 | IDS | FP | FN | FPS | 下载链接 | 配置文件 |
---|---|---|---|---|---|---|---|---|---|
DLA-34 | 1088x608 | 64.7 | 69.0 | 8533 | 148817 | 234970 | - | 下载链接 | 配置文件 |
骨干网络 | 输入尺寸 | MOTA | IDF1 | IDS | FP | FN | FPS | 下载链接 | 配置文件 |
---|---|---|---|---|---|---|---|---|---|
DLA-34 | 1088x608 | 60.8 | 62.8 | 12781 | 118109 | 198896 | - | 下载链接 | 配置文件 |
注意:
FairMOT DLA-34使用2个GPU进行训练,每个GPU上batch size为6,训练30个epoch。目前MOTA精度位于MOT官网Head Tracking 21榜单榜首。
使用2个GPU通过如下命令一键式启动训练
python -m paddle.distributed.launch --log_dir=./fairmot_dla34_30e_1088x608_headtracking21/ --gpus 0,1 tools/train.py -c configs/mot/headtracking21/fairmot_dla34_30e_1088x608_headtracking21.yml
使用单张GPU通过如下命令一键式启动评估
# 使用PaddleDetection发布的权重
CUDA_VISIBLE_DEVICES=0 python tools/eval_mot.py -c configs/mot/headtracking21/fairmot_dla34_30e_1088x608_headtracking21.yml -o weights=https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608_headtracking21.pdparams
# 使用训练保存的checkpoint
CUDA_VISIBLE_DEVICES=0 python tools/eval_mot.py -c configs/mot/headtracking21/fairmot_dla34_30e_1088x608_headtracking21.yml -o weights=output/fairmot_dla34_30e_1088x608_headtracking21/model_final.pdparams
使用单个GPU通过如下命令预测一个视频,并保存为视频
# 预测一个视频
CUDA_VISIBLE_DEVICES=0 python tools/infer_mot.py -c configs/mot/headtracking21/fairmot_dla34_30e_1088x608_headtracking21.yml -o weights=https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608_headtracking21.pdparams --video_file={your video name}.mp4 --save_videos
注意:
请先确保已经安装了ffmpeg, Linux(Ubuntu)平台可以直接用以下命令安装:apt-get update && apt-get install -y ffmpeg
。
CUDA_VISIBLE_DEVICES=0 python tools/export_model.py -c configs/mot/headtracking21/fairmot_dla34_30e_1088x608_headtracking21.yml -o weights=https://paddledet.bj.bcebos.com/models/mot/fairmot_dla34_30e_1088x608_headtracking21.pdparams
python deploy/python/mot_jde_infer.py --model_dir=output_inference/fairmot_dla34_30e_1088x608_headtracking21 --video_file={your video name}.mp4 --device=GPU --save_mot_txts
注意:
跟踪模型是对视频进行预测,不支持单张图的预测,默认保存跟踪结果可视化后的视频,可添加--save_mot_txts
表示保存跟踪结果的txt文件,或--save_images
表示保存跟踪结果可视化图片。
@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}
}
@InProceedings{Sundararaman_2021_CVPR,
author = {Sundararaman, Ramana and De Almeida Braga, Cedric and Marchand, Eric and Pettre, Julien},
title = {Tracking Pedestrian Heads in Dense Crowd},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2021},
pages = {3865-3875}
}
PaddleDetection
Python Jupyter Notebook Markdown C++ Java other
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》