基于超图卷积和多角度拓扑细化的骨骼行为识别方法  

Hypergraph Convolutional Network with Multi-perspective Topology Refinement for Skeleton-based Action Recognition

作　　者：黄倩[1] 苏新凯 李畅 巫义锐 HUANG Qian;SU Xinkai;LI Chang;WU Yirui(College of Computer Science and Software Engineering,Hohai University,Nanjing 211106,China)

机构地区：[1]河海大学计算机与软件学院,南京211106

出　　处：《计算机科学》2025年第5期220-226,共7页Computer Science

摘　　要：由于人体骨架是一个天然存在的拓扑结构,因此图卷积网络(GCNs)被广泛地应用于基于骨骼的人体行为识别。然而,目前的基于GCN的方法只关注关节点对之间的低阶关系,而忽略了潜在的关节点在关节点群中的高阶关系。同时,现有的方法忽略了空间拓扑随时间的动态变化。这些不足影响了模型的表现。为此,利用K-NN计算出相关性高的关节点构成超边,提出了超图构建方法和超边图卷积来动态地学习关节点间的高阶关系。此外,设计了一个从时间和通道角度细化的拓扑图来学习帧级的和通道级的关节点对之间的相关性。最后,开发了一个多角度拓扑细化的超图卷积网络(HyperMTR-GCN)用于骨骼行为识别,其在NTU RGB+D和NTU RGB+D 120数据集上具有显著优势。具体地,所提方法在NTU RGB+D的X-sub基准上比2s-AGCN提高了3.7%,在NTU RGB+D 120的X-sub基准上比2s-AGCN提高了5.7%。Since the human skeleton is a natural topological structure,graph convolutional networks(GCNs)are widely used for skeleton-based human action recognition.In recent research,skeleton sequences are represented as spatio-temporal graphs and topology graphs are used to model the correlation between human joints.However,current GCN-based methods only focus on pairwise joint relationships and ignore potential high-order relationships beyond pairwise relationships,leading to underutilization of the graph structure of skeleton data.To solve this problem,this paper proposes the concept of hypergraph to represent potential high-order relationships of joints.Since the high-order relationships of joints within each frame in the skeleton sequence may vary,the model dynamically learns the high-order correlations within each frame with the K-NN method and initialize the hypergraph structure using the high-level representation of joints.This hypergraph structure can better learn the high-order relationships between joints as the hyperedges dynamically adjust with the evolution of joint features.In current hypergraph neural networks,hypergraph convolution transforms the hypergraph into a simple graph using the Laplace’s transformation and then performs graph convolution.This method does not fully utilize the characteristics of the hypergraph.The proposed hypergraph convolution method better utilizes the relationship between hyperedges and hypernodes in the hypergraph,performing hyperedge graph convolution on each hyperedge to learn the high-order relationships between joints.The second problem with current GCN-based human action recognition methods is that the topology built by GCNs to represent pairwise joint relationships is not dynamic enough,such as using the same topology for all frames in a sample.To fully explore the dynamic correlation between pairwise joints,the frame-wise topology modeling method is proposed to capture correlation between pairwise joints under different frames and channel-le vel topology modeling meth

关 键 词：行为识别 图卷积网络 超图神经网络 骨架建模 拓扑细化 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]