场景关系图学习的群组行为识别  

Scene relation graph network for group activity recognition

作　　者：焦畅 吴克伟[1] 于磊[1] 谢昭[1] 李文中 Jiao Chang;Wu Kewei;Yu Lei;Xie Zhao;Li Wenzhong(School of Computer Science&Information Engineering,Hefei University of Technology,Hefei 230601,China)

机构地区：[1]合肥工业大学计算机与信息学院,合肥230601

出　　处：《计算机应用研究》2023年第10期3173-3179,共7页Application Research of Computers

基　　金：安徽省重点研究与开发计划资助项目(202004d07020004);安徽省自然科学基金资助项目(2108085MF203);中央高校基本科研业务费专项资金资助项目(PA2021GDSK0072,JZ2021HGQA0219)。

摘　　要：为解决群组行为识别中复杂个体关系描述不准确,造成的个体关系推理不可靠的问题,关注于面向个体、群体、场景三个方面来构建场景关系图,提出场景关系图网络用于实现群组行为识别。该网络包括特征提取模块、场景关系图推理模块以及分类模块。特征提取模块通过卷积神经网络提取个体特征、群组特征、和场景特征。为了充分描述场景对于个体和群组描述的影响,场景关系图推理模块通过使用两分支网络分别建立个体—场景关系图以及群组—场景关系图帮助学习个体特征和群组特征。场景关系图推理同时考虑了个体特征对群组特征的影响,并引入了跨分支关系。分类模块用于将个体特征和群体特征进行分类预测。实验结果显示该方法在volleyball和collective activity数据集上的群组识别准确率分别提升了1.1%和0.5%,证实了提出的场景关系图在描述个体特征和群组特征上的有效性。To solve the problem of inaccurate description and unreliable relation inference in group activity recognition,this paper focused on constructing a scene relationship graph for three aspects:individual,group,and scene,and proposed a scene relationship graph network(SRGN)for group activity recognition.This method included a feature extraction module,a scene relation graph inference module,and a classification module.The feature extraction module extracted individual features,group features,and scene features by convolutional neural network.To fully explore the impact of scene on individual and group descriptions,the scene relation graph inference module learnt individual features and group features by building individual-scene and group-scene relationship graphs in a two-branch framework.Scene graph inference took into account the influence of individual on group and introduced a cross-branch module.It used the classification module to classify individual features and group features for prediction.The experimental results show that the group recognition accuracy of the proposed method on volleyball and collective activity data sets is improved by 1.1%and 0.5%,respectively.It verifies the validity of the scene graph in describing individual feature and group feature.

关 键 词：群组行为识别 场景关系图 关系建模 行为识别 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]