计算机工程与应用 ›› 2022, Vol. 58 ›› Issue (13): 227-234.DOI: 10.3778/j.issn.1002-8331.2012-0217

• 图形图像处理 • 上一篇    下一篇

基于非局部高分辨率网络的人体姿态估计方法

孙琪翔,张睿哲,何宁,张聪聪   

  1. 1.北京联合大学 北京市信息服务工程重点实验室,北京 100101
    2.北京联合大学 智慧城市学院,北京 100101
  • 出版日期:2022-07-01 发布日期:2022-07-01

Human Pose Estimation Method Based on Non-Local High-Resolution Networks

SUN Qixiang, ZHANG Ruizhe, HE Ning, ZHANG Congcong   

  1. 1.Beijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing 100101, China
    2.Smart City College, Beijing Union University, Beijing 100101, China
  • Online:2022-07-01 Published:2022-07-01

摘要: 人体姿态估计是计算机视觉中的基础任务,其可应用于动作识别、游戏、动画制作等。受非局部均值方法的启发,设计了非局部高分辨率网络(non-local high-resolution,NLHR),在原始图像1/32分辨率的网络阶段融合非局部网络模块的,使网络有了获取全局特征的能力,从而提高人体姿态估计的准确率。NLHR网络在MPII数据集上训练,在MPII验证集上测试,PCKh@0.5评价标准下的平均准确率为90.5%,超过HRNet基线0.2个百分点;在COCO人体关键点检测数据集上训练,在COCO验证集上测试,平均准确率为76.7%,超过HRNet基线2.3个百分点。通过3组消融实验,验证NLHR网络针对人体姿态估计在精度上能够超过现有的人体姿态估计网络。

关键词: 人体姿态估计, 非局部均值, 非局部网络模块, HRNet基线

Abstract: Human pose estimation is the basic task in computer vision. It can be used in action recognition, games, animation production and so on. Inspired by the nonlocal mean method, a non-local high-resolution(NLHR) network is designed. Fusion of non-local network modules in the network phase of the original image 1/32 resolution, so that the network has the ability to obtain global features, in order to improve the accuracy of human posture estimation. The NLHR network is trained on MPII datasets and tested on the MPII validation set, the average accuracy under PCKh@0.5 evaluation criteria is 90.5%, 0.2 percentage points higher than the HRNet baseline. Training on the COCO human key point detection dataset, test result on the COCO validation set AP is 76.7%, 2.3 percentage points higher than HRNet baseline. Three ablation experiments verify that the NLHR network for human pose estimation can exceed the existing human pose estimation network in accuracy.

Key words: human pose estimation, non-local means, non-local network module, HRNet(high-resolution network) baseline