电子学报2024，Vol.52Issue(3)：991-1001,11.DOI:10.12263/DZXB.20221106
基于多维动态拓扑学习图卷积的骨架动作识别
Multi-Dimensional Dynamic Topology Learning Graph Convolution for Skeleton-Based Action Recognition
摘要
Abstract
Graph convolution is widely used in skeleton-based action recognition because of its effectiveness of pro-cessing graph data.However,the existing graph convolution methods use the shared graph topology for feature aggregation on all frames or channels,which greatly limits the representation ability of graph convolution network.In order to solve these problems,a multi-dimensional dynamic topology learning graph convolution is proposed in this paper to dynamically model the topology with temporal and channel specificity.The multi-dimensional dynamic topology learning graph convolu-tion mainly includes three parts:pure joint topology learning graph convolution(J-GC),dynamic temporal-wise topology learning graph convolution(DTW-GC)and channel-wise topology learning graph convolution(CW-GC).In particular,in DTW-GC,a dynamic skeleton topology modeling method(DSTL)is designed to efficiently model the dynamic skeleton to-pology with rich global spatio-temporal topological features.Finally,by combining multi-dimensional dynamic topology learning graph convolution with multi-scale temporal convolution(Muti-Scale TCN),a graph convolution network with powerful modeling capability is constructed in this paper.In addition,in order to supplement the spatial information of skel-eton data,the relative joint data and relative bone data are introduced for multi-stream network fusion.Our method achieves 92.64%and 89.29%accuracy on NTU-RGB+D and NTU-RGB+D 120 datasets,respectively,which is superior to the cur-rent state-of-the-art methods.关键词
动作识别/深度学习/图卷积/动态骨架拓扑/数据融合Key words
action recognition/deep learning/graph convolution/dynamic skeleton topology/data fusion分类
信息技术与安全科学引用本文复制引用
罗会兰,曹立京..基于多维动态拓扑学习图卷积的骨架动作识别[J].电子学报,2024,52(3):991-1001,11.基金项目
国家自然科学基金(No.61862031) （No.61862031）
江西省主要学科技术带头人领军人才计划资助项目(No.20213BCJ22004) （No.20213BCJ22004）
江西省学位与研究生教育教学改革研究重点项目(No.JXYJG-2020-120) National Natural Science Foundation of China(No.61862031) （No.JXYJG-2020-120）
The Project Supported by the Leading Talents Plan for the Technical Leaders of Major Disciplines in Jiangxi Province(No.20213BCJ22004) （No.20213BCJ22004）
Jiangxi Province Degree and Postgraduate Education and Teaching Reform Research Key Project(No.JXYJG-2020-120) （No.JXYJG-2020-120）
