基于多谱注意力高分辨率网络的人体姿态估计  

Human Pose Estimation Based on Multi-Spectral Attention and High Resolution Network

作　　者：马皖宜 张德平[1] Ma Wanyi;Zhang Deping(School of Computer Science and Technology,Nanjing University of Aeronautics and Astronautics,Nanjing 211000)

机构地区：[1]南京航空航天大学计算机科学与技术学院,南京211000

出　　处：《计算机辅助设计与图形学学报》2022年第8期1283-1292,共10页Journal of Computer-Aided Design & Computer Graphics

基　　金：国防基础科研重点项目(JCKY2020605C003)。

摘　　要：针对人体姿态估计中多分辨率特征融合时出现的特征信息丢失的问题,基于Lite-HRNet引入多谱注意力机制,设计了一个轻量级的结合多谱注意力机制的高分辨率人体姿态估计网络LiteMSA-HRNet.将多谱注意力机制融入Lite-HRNet,利用多个频率分量,提取更丰富的特征信息,获得更优的多分辨率特征重复融合的效果;在主体网络后利用一个反卷积模块,将其生成的更高分辨率特征和主体网络生成的高分辨率特征进行融合;引入通道置换、逐点分组卷积和深度可分离卷积,轻量化反卷积模块中的残差块,提升网络定位关键点的速度.在COCO2017数据集上的实验结果表明,与其他网络相比,Lite MSA-HRNet在人体姿态估计精度和复杂度之间取得了较好的平衡结果.In view of the problem of feature information loss during multi-resolution feature fusion in human pose estimation,a lightweight high resolution human pose estimation network named Lite MSA-HRNet is designed based on Lite-HRNet and multi-spectral attention mechanism,which integrates multi-spectral attention mechanism into Lite-HRNet.Multiple frequency components are used to extract richer feature information,contributing to the repeated fusion of different resolution feature.A deconvolution module is used behind the main network to fuse the higher resolution features generated by itself with the high resolution features generated by the main network.Channel shuffle,pointwise group convolutions and depthwise separable convolution are introduced to lighten the residual block in the deconvolution module and improve the speed of network positioning key points.The experimental results on the COCO2017 data set show that Lite MSA-HRNet achieves a better balance between the accuracy and complexity of human posture estimation compared with other networks.

关 键 词：人体姿态估计 多谱注意力 高分辨率网络 轻量化网络 多分辨率特征融合 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]