首页|Fusion of Convolutional Self-Attention and Cross-Dimensional Feature Transformation for Human Posture Estimation

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

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
Human posture estimation is a prominent research topic in the fields of human-com-puter interaction,motion recognition,and other intelligent applications.However,achieving high accuracy in key point localization,which is crucial for intelligent applications,contradicts the low detection 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 significant feature 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,where the 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.The results show that AT-HRNet outperforms HRNet by improving 3.2%in mAP,4.0%in AP75,and 3.9%in APM.This suggests that AT-HRNet can offer more beneficial solutions for human posture estimation.

human posture estimationadaptive fusion methodcross-dimensional interactionattention modulehigh-resolution network

Anzhan Liu、Yilu Ding、Xiangyang Lu

展开 >

School of Computer College,Zhongyuan University of Technology,Zhengzhou 451191,China

School of Electronic and Informa-tion College,Zhongyuan University of Technology,Zhengzhou 451191,China

National Natural Science Foundation of ChinaResearch and Innovation Project for Graduate Students at Zhongyuan University of Technology

61975015YKY2024ZK14

2024

10.15918/j.jbit1004-0579.2024.018

北京理工大学学报(英文版)
北京理工大学

北京理工大学学报(英文版)

影响因子：0.168
ISSN：1004-0579
年,卷(期)：2024.33(4)
  • 2