基于多流空间注意力图卷积SRU网络的骨架动作识别  

Skeleton Action Recognition Based on Multi-Stream Spatial Attention Graph Convolutional SRU Network

作　　者：赵俊男 佘青山[1] 孟明[1] 陈云[1] ZHAO Jun-nan;SHE Qing-shan;MENG Ming;CHEN Yun(College of Automation,Hangzhou Dianzi University,Hangzhou,Zhejiang 310018,China)

机构地区：[1]杭州电子科技大学自动化学院,浙江杭州310018

出　　处：《电子学报》2022年第7期1579-1585,共7页Acta Electronica Sinica

基　　金：国家自然科学基金(No.61871427);浙江省自然科学基金重点项目(No.LZ22F010003)。

摘　　要：基于骨架的动作识别越来越受到重视.针对现有算法推理速度慢、数据模式单一等问题,本文提出了一种轻量且高效的方法.该网络在简单循环单元(Simple Recurrent Unit,SRU)中嵌入图卷积算子构建图卷积SRU(GCSRU)模型,来捕获数据的时空域信息.同时,为了加强节点间的区分,采用空间注意力网络和多流数据融合方式,将GC-SRU拓展成多流空间注意力图卷积SRU(MSAGC-SRU).最后,在公开数据集上进行实验分析.结果表明,本文方法在Northwestern-UCLA上的分类准确率达到了93.1%,模型FLOPs为4.4 G;NTU RGB+D上的分类准确率在CV、CS评估协议下分别达到92.7%和87.3%,模型FLOPs为21.3 G,达到了计算效率和分类精度的良好平衡.Action recognition with skeleton data has attracted more attention.In order to solve the problems of low reasoning speed and single data mode of most algorithms,a lightweight and efficient method is proposed.The network embeds the graph convolution operator in the simple recurrent unit(SRU)to construct the graph convolutional SRU(GC-SRU),which can capture the spatial-temporal information of data.Meanwhile,to enhance the distinction between nodes,spatial attention network and multi-stream data fusion are used to expand GC-SRU into multi-stream spatial attention graph convolutional SRU(MSAGC-SRU).Finally,the proposed method is evaluated on two public datasets.Experimental results show that the classification accuracy of our method on Northwestern-UCLA reaches 93.1%and the FLOPs of the model is 4.4G.The accuracy on NTU RGB+D reaches 92.7%and 87.3%under the CV and CS evaluation protocols,respectively,and the FLOPs of the model is 21.3G.The proposed model has achieved good trade-off between computational efficiency and classification accuracy.

关 键 词：动作识别 图卷积 注意力机制 数据融合 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]