部位级遮挡感知的人体姿态估计

褚真; 米庆; 马伟; 徐士彪; 张晓鹏

doi:10.7544/issn1000-1239.20210723

部位级遮挡感知的人体姿态估计

¹(北京工业大学信息学部北京 100124)
²(北京邮电大学人工智能学院北京 100876)
³(模式识别国家重点实验室(中国科学院自动化研究所) 北京 100190) (zhen.chu@foxmail.com)

基金项目: 国家自然科学基金项目(61771026，62176010)；北京市教委重点项目(KZ201910005008)

详细信息

中图分类号: TP391.41
计量
- 文章访问数: 224
- HTML全文浏览量: 13
- PDF下载量: 123
出版历程
- 发布日期: 2022-11-30

Part-Level Occlusion-Aware Human Pose Estimation

¹(Faculty of Information Technology, Beijing University of Technology, Beijing 100124)
²(Artificial Intelligence School, Beijing University of Posts and Telecommunications, Beijing 100876)
³(National Laboratory of Pattern Recognition (Institute of Automation, Chinese Academy of Sciences), Beijing 100190)

Funds: This work was supported by the National Natural Science Foundation of China (61771026, 62176010) and the Key Project of Beijing Municipal Education Commission, China ( KZ201910005008).

摘要

摘要: 随着深度学习的快速发展，人体姿态估计技术近年来取得显著进步，但是现有方法仍难以较好地处理普遍存在的遮挡问题.针对此问题，提出一种部位级遮挡感知的人体姿态估计方法.首先，采用基准人体姿态估计网络从含遮挡噪声的图像中获得各人体部位的带噪声特征表达.然后，通过遮挡部位预测模块估计人体被遮挡部位，从而获得可见性向量.遮挡部位预测模块由遮挡部位分类网络和可见性编码器组成，前者预测关节点的遮挡状态，后者利用注意力机制将遮挡状态转换为一组权重.最后，通过通道重加权方式融合可见性向量和带噪声特征，获得部位级遮挡感知的人体部位相关特征，用于计算关节点热图.在MPII和LSP(leeds sports pose)数据集上的实验结果表明，相比基准姿态估计网络，该方法能够在较小的额外计算代价下更好地应对遮挡问题,并且取得了比目前先进方法更佳的结果.
- 人体姿态估计 /
- 人体关节点检测 /
- 遮挡推理 /
- 通道注意力机制 /
- 多任务学习
Abstract: With the rapid development of deep learning, human pose estimation technology has made remarkable progress in recent years, but the existing methods are still difficult to deal with the common occlusion problem. To address this problem, a human pose estimation method based on keypoint-level occlusion inference is proposed in this paper. Firstly, a baseline human pose estimation network is used to obtain the noisy representation of each keypoint of human body from images with occlusion noises. Then, the occluded keypoints are estimated through the occlusion part prediction module to obtain the visibility vector. The occlusion part prediction module is proposed in this study, which consists of two submodules: occlusion part classification network and visibility encoder. The occlusion part classification network predicts the occlusion state of each keypoint of the human body. Based on the channel attention mechanism, the visibility encoder converts the predicted occlusion state into a set of weight parameters. Finally, the visibility vector and noise features are fused by channel re-weighting method to obtain the keypoint-level occlusion aware features, which are used to calculate the heatmaps of the keypoints. Experimental results on MPII and LSP(leeds sports pose) datasets show that, compared with the baseline human pose estimation network, the proposed method can better deal with the occlusion problem at a small extra computational cost, and achieve better results than existing state-of-the-art methods.
- human pose estimation /
- human keypoint detection /
- occlusion inference /
- channel attention mechanism /
- multi-task learning

HTML全文

参考文献(0)

施引文献(13)

期刊类型引用(3)

1.	孙剑明，赵梦鑫. 边缘计算下差分隐私的应用研究综述. 计算机科学. 2024(S1): 896-904 . 百度学术
2.	张帅，陈建广，陈锐志，汪云甲，黄风华，李召洋. 基于MIMU与Wi-Fi的普适室内定位方法综述. 导航定位与授时. 2024(05): 1-16 . 百度学术
3.	张学军，席阿友，加小红，张斌，李梅，杜晓刚，黄海燕. 基于深度学习的指纹室内定位对抗样本攻击研究. 计算机工程. 2024(10): 228-239 . 百度学术