基于亚像素定位的人体姿态热图后处理
Postprocessing of human pose heatmap based on sub-pixel location
王宇 1赵凯2
作者信息
- 1. 长春理工大学 电子信息工程学院,长春 130022
- 2. 长春理工大学 电子信息工程学院,长春 130022;黑龙江科技大学 电子与信息工程学院,哈尔滨 150022
- 折叠
摘要
为提高热图预测关节点的精度,提出了一种基于亚像素定位的人体姿态热图后处理方法,该方法包括2个策略:第一个策略是翻转图像热图的亚像素偏移处理,可以消除与原始图像热图的未对齐偏差;第二个策略是局部区域曲面拟合的热图解码,实现关节点的亚像素定位.本文热图后处理方法独立于网络模型,不需要对模型进行任何修改即可应用于当前基于热图的人体姿态估计模型.在COCO2017 和MPII数据集上对本文方法进行了实验.以HRNet-W32-256×192模型和Simple Baseline-W32-256×192模型为例,COCO2017数据集上平均精度分别提高了0.9和1.1,验证了方法的有效性.
Abstract
To improve the prediction accuracy of joint points of the heatmap,this paper proposes a postprocessing method of human pose heatmap based on sub-pixel localization.The method includes two strategies:the first is the sub-pixel shift processing of the flipped image heatmap,which can eliminate the unaligned deviation from the original image heatmap;the second is the heatmap decoding for local region surface fitting to achieve sub-pixel localization of the joint points.The heatmap postprocessing method in this paper is independent of the network model and can be applied to the current heatmap-based human pose estimation models without any modification.To verify the effectiveness of the proposed method,experiments have been carried out by using two publicly available datasets named COCO2017 and MPII.The average precision can be improved by 0.9 and 1.1 on COCO2017,respectively,by adopting two deep learning models,i.e.,HRNet-W32-256×192 model and Simple Baseline-W32-256×192 model.
关键词
计算机视觉/人体姿态估计/热图后处理/高斯拟合/热图解码Key words
computer vision/human pose estimation/heatmap postprocessing/gaussian fitting/heatmap decoding引用本文复制引用
基金项目
吉林省自然科学基金(20210101180JC)
出版年
2024
NETL
NSTL
万方数据