graviti logo产品公开数据集关于我们
登录
860
0
65
CrowdPose
创建来自Hello Dataset / Robert
概要
活动

Overview

Multi-person pose estimation is fundamental to many computer vision tasks and has made significant progress in recent years. However, few previous methods explored the problem of pose estimation in crowded scenes while it remains challenging and inevitable in many scenarios. Moreover, current benchmarks cannot provide an appropriate evaluation for such cases. In this paper, we propose a novel and efficient method to tackle the problem of pose estimation in the crowd and a new dataset to better evaluate algorithms. Our model consists of two key components: joint-candidate single person pose estimation (SPPE) and global maximum joints association. With multi-peak prediction for each joint and global association using graph model, our method is robust to inevitable interference in crowded scenes and very efficient in inference. The proposed method surpasses the state-of-the-art methods on CrowdPose dataset by 5.2 mAP and results on MSCOCO dataset demonstrate the generalization ability of our method. Source code and dataset will be made publicly available.

Instruction

We provide evaluation tools for CrowdPose dataset. Our evaluation tools is developed based on @cocodataset/cocoapi. The source code of our model has been integrated into AlphaPose.

CrowdPose API (based on COCO API)

To install:

  • For Python, run "sh install.sh" under coco/PythonAPI

Citation

If you find our works useful in your reasearch, please consider citing:

@article{li2018crowdpose,
  title={CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmark},
  author={Li, Jiefeng and Wang, Can and Zhu, Hao and Mao, Yihuan and Fang, Hao-Shu and Lu, Cewu},
  journal={arXiv preprint arXiv:1812.00324},
  year={2018}
}
数据集信息
应用场景Pose Estimation
标注类型Box2DKeypoints2D
LicenseUnknown
更新时间2021-03-24 22:56:02
数据概要
数据格式Image
数据数量20k
文件大小2MB
标注数量0
版权归属方
Shanghai Jiao Tong University
标注方
未知
了解更多和支持
相关数据集
立即开始构建AI
免费开始联系我们