基于时空交互网络的人体行为检测方法研究  

HUMAN BEHAVIOR DETECTION METHOD BASED ON SPATIO-TEMPORAL INTERACTIVE NETWORK

作　　者：田青[1] 张浩然 楚柏青[2] 张正[1] 豆飞[2,3] Tian Qing;Zhang Haoran;Chu Baiqing;Zhang Zheng;Dou Fei(School of Information,North China University of Technology,Beijing 100144,China;Beijing Mass Transit Railway Operation Co.,Ltd.,Beijing 100144,China;Beijing Key Laboratory of Subway Operation Safety Technology,Beijing 100144,China)

机构地区：[1]北方工业大学信息学院,北京100144 [2]北京市地铁运营有限公司,北京100144 [3]地铁运营安全保障技术北京市重点实验室,北京100144

出　　处：《计算机应用与软件》2025年第4期156-165,共10页Computer Applications and Software

基　　金：国家重点研发计划项目(2020YFB1600702);国家自然科学基金项目(61806008)。

摘　　要：针对现有的人体行为检测方法中,存在特征融合能力较差、时序信息相关性不强和行为边界不明确等问题,提出一种基于时空交互网络的人体行为检测方法。重新设计了双流特征提取模块,在空间流和时空流两个网络之间添加连接层;分别在空间流和时间流网络中引入改进的空间变换网络和视觉注意力模型;设计基于像素筛选器的特征融合模块,用于重点区域时序信息相关性的计算和两类不同维度特征的聚合;对网络的损失函数进行了优化。在AVA数据集上的实验结果表明该方法在检测精度、速度以及泛化能力上具有优越性。Aimed at the problems of poor feature fusion ability,weak correlation of time-series information and unclear behavior boundary in the existing human behavior detection methods,a human behavior detection method based on spatio-temporal interactive network is proposed.The dual flow feature extraction module was redesigned,and a connection layer was added between the two networks of spatial flow and spatio-temporal flow.The improved spatial transformation network and visual attention model were introduced into spatial flow and temporal flow networks respectively.A feature fusion module based on pixel filter was designed to calculate the correlation of time series information in key areas and aggregate two kinds of features with different dimensions.The loss function of the network was optimized.Experimental results on AVA dataset show that this method has advantages on detection accuracy,speed and generalization ability.

关 键 词：时空交互网络 人体行为检测 视觉注意力 特征融合 损失函数 

分 类 号：TP3901[自动化与计算机技术—计算机应用技术]