Fusion of Convolutional Self-Attention and Cross-Dimensional Feature Transformationfor Human Posture Estimation  

作　　者：Anzhan Liu Yilu Ding Xiangyang Lu 

机构地区：[1]School of ComputerCollege,Zhongyuan University of Technology,Zhengzhou 451191,China [2]School of Electronic and Information College,Zhongyuan University of Technology,Zhengzhou 451191,China

出　　处：《Journal of Beijing Institute of Technology》2024年第4期346-360,共15页北京理工大学学报（英文版）

基　　金：the National Natural Science Foundation of China(No.61975015);the Research and Innovation Project for Graduate Students at Zhongyuan University of Technology(No.YKY2024ZK14).

摘　　要：Human posture estimation is a prominent research topic in the fields of human-com-puter interaction,motion recognition,and other intelligent applications.However,achieving highaccuracy in key point localization,which is crucial for intelligent applications,contradicts the lowdetection accuracy of human posture detection models in practical scenarios.To address this issue,a human pose estimation network called AT-HRNet has been proposed,which combines convolu-tional self-attention and cross-dimensional feature transformation.AT-HRNet captures significantfeature information from various regions in an adaptive manner,aggregating them through convolu-tional operations within the local receptive domain.The residual structures TripNeck and Trip-Block of the high-resolution network are designed to further refine the key point locations,wherethe attention weight is adjusted by a cross-dimensional interaction to obtain more features.To vali-date the effectiveness of this network,AT-HRNet was evaluated using the COCO2017 dataset.Theresults show that AT-HRNet outperforms HRNet by improving 3.2%in mAP,4.0%in AP75,and3.9%in AP^(M).This suggests that AT-HRNet can offer more beneficial solutions for human posture estimation.

关 键 词：human posture estimation adaptive fusion method cross-dimensional interaction attention module high-resolution network 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]