cuijianzhu/OpenGait

A flexible and extensible framework for gait recognition. You can focus on designing your own models and comparing with state-of-the-arts easily with the help of OpenGait.

---

📣📣📣 SUSTech1K relseased, pls checking the tutorial. 📣📣📣

🎉🎉🎉 OpenGait has been accpected by CVPR2023 as a highlight paper！ 🎉🎉🎉

OpenGait is a flexible and extensible gait recognition project provided by the Shiqi Yu Group and supported in part by WATRIX.AI.

What's New

• [Oct 2023] Several representative pose-based methods are supported in opengait/modeling/models. This feature is mainly inherited from FastPoseGait. Many thanks to the contributors😊.
• [July 2023] CCPG is supported in datasets/CCPG.
• [July 2023] SUSTech1K is released and supported in datasets/SUSTech1K.
• [May 2023] A real gait recognition system All-in-One-Gait provided by Dongyang Jin is available.
• [Apr 2023] CASIA-E is supported by OpenGait.
• [Feb 2023] HID 2023 competition is open, welcome to participate. Additionally, the tutorial for the competition has been updated in datasets/HID/.
• [Dec 2022] Dataset Gait3D is supported in datasets/Gait3D.
• [Mar 2022] Dataset GREW is supported in datasets/GREW.

Our Publications

• [TPAMI 2023] Learning Gait Representation from Massive Unlabelled Walking Videos: A Benchmark, Paper, Dataset and Code(Coming soon).
• [CVPR 2023] LidarGait: Benchmarking 3D Gait Recognition with Point Clouds, Paper, Dataset and Code.
• [CVPR 2023 Highlight] OpenGait: Revisiting Gait Recognition Toward Better Practicality, Paper, Code.
• [ECCV 2022] GaitEdge: Beyond Plain End-to-end Gait Recognition for Better Practicality, Paper, Code.

A Real Gait Recognition System: All-in-One-Gait

The workflow of All-in-One-Gait involves the processes of pedestrian tracking, segmentation and recognition. See here for details.

Highlighted features

• Mutiple Dataset supported: CASIA-B, OUMVLP, SUSTech1K, HID, GREW, Gait3D, CCPG, and CASIA-E.
• Multiple Models Support: We reproduced several SOTA methods and reached the same or even better performance.
• DDP Support: The officially recommended Distributed Data Parallel (DDP) mode is used during both the training and testing phases.
• AMP Support: The Auto Mixed Precision (AMP) option is available.
• Nice log: We use tensorboard and logging to log everything, which looks pretty.

Getting Started

Please see 0.get_started.md. We also provide the following tutorials for your reference:

• Prepare dataset
• Detailed configuration
• Customize model
• Advanced usages

Model Zoo

Results of appearance-based gait recognition are available here.

Results of pose-based gait recognition are available here.

Authors:

Open Gait Team (OGT)

• Chao Fan (樊超), 12131100@mail.sustech.edu.cn
• Chuanfu Shen (沈川福), 11950016@mail.sustech.edu.cn
• Junhao Liang (梁峻豪), 12132342@mail.sustech.edu.cn

Acknowledgement

• GLN: Saihui Hou (侯赛辉)

• GaitGL: Beibei Lin (林贝贝)

• GREW: GREW TEAM

• FastPoseGait Team: FastPoseGait Team

Citation

@InProceedings{Fan_2023_CVPR,
    author    = {Fan, Chao and Liang, Junhao and Shen, Chuanfu and Hou, Saihui and Huang, Yongzhen and Yu, Shiqi},
    title     = {OpenGait: Revisiting Gait Recognition Towards Better Practicality},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2023},
    pages     = {9707-9716}
}

Note: This code is only used for academic purposes, people cannot use this code for anything that might be considered commercial use.