摘要
针对人体姿态估计中直接回归坐标方法缺乏鲁棒性,精度较差等问题,总结了历年以来基于坐标回归的表征方法,提出了密集回归人体关节点的新型表征方法,增加关节点融合模块,同时兼顾速度与精度。在数据集COCO test-dev2017上获得了71.5%的得分,比HRNet基准模型提高了1%。
In human pose estimation,the direct regression of coordinates method lacks robustness and accuracy.The coordinate regression-based representation methods were summarized over the years and a novel representation method was proposed for densely regressing human keypoints,incorporating a joint fusion module while balancing speed and accuracy.On the COCO test-dev2017 dataset,a score of 71.5%was achieved,and improved by 1%over the HRNet benchmark model.
作者
吴晓亮
李霆
WU Xiaoliang;LI Ting(School of Advanced Manufacturing,Fuzhou University,Quanzhou Fujian 362000,CHN;Fujian College,University of Chinese Academy of Sciences,Quanzhou Fujian 362000,CHN;Quanzhou Institute of Equipment Manufacturing Haixi Institutes,Chinese Academy of Sciences,Quanzhou Fujian 362000,CHN)
出处
《光电子技术》
CAS
2024年第3期218-223,共6页
Optoelectronic Technology
基金
福建省科技计划引导性项目(2022H0042)。
关键词
坐标回归
密集回归
融合模块
表征方法
coordinate regression
dense regression
fusion module
representation method
