信息与控制2023，Vol.52Issue(6)：758-772,15.DOI:10.13976/j.cnki.xk.2023.2374
基于时序拓扑非共享图卷积和多尺度时间卷积的骨架行为识别
Temporal Topology Unshared Graph Convolution and Multiscale Temporal Convolution for Skeleton-based Action Recognition
费树岷 1赵宏涛 2杨艺 2李春锋3
作者信息
- 1. 河南理工大学电气工程与自动化学院,河南焦作 454003||东南大学自动化学院,江苏南京 210096
- 2. 河南理工大学电气工程与自动化学院,河南焦作 454003
- 3. 河南天通电力有限公司,河南平顶山 467099
- 折叠
摘要
Abstract
In skeleton action recognition based on graph convolution,the different skeleton frames share the same spatial topology,and the temporal feature model employs single-scale temporal convolution.We address these issues and propose an action recognition methodology based on temporal topology unshared graph convolution and multiscale temporal convolution.First,in spatial modeling,we cal-culate the joint relationship of each frame according to the input samples to establish the independent spatial topology for each skeleton frame.Second,we use the multiscale temporal convolution module with five branches in the temporal modeling to extract action features on different time scales.Final-ly,we propose a spatiotemporal graph convolutional network for the skeleton action recognition by combining the temporal topology unshared graph convolution and multiscale temporal convolution modules.We carry out comparative experiments on NTU RGB+D,NTU RGB+D 120,and North-western-UCLA datasets.The results show that the proposed method has better recognition accuracy with lower model complexity than the current main action recognition methods.关键词
图卷积网络/人体骨架/行为识别/非共享拓扑/多尺度时间卷积Key words
graph convolutional network/human skeleton/action recognition/unshared topology/multi-scale temporal convolution分类
计算机与自动化引用本文复制引用
费树岷,赵宏涛,杨艺,李春锋..基于时序拓扑非共享图卷积和多尺度时间卷积的骨架行为识别[J].信息与控制,2023,52(6):758-772,15.
