一种基于2D时空信息提取的行为识别算法  

A behavioral recognition algorithm based on 2D spatiotemporal information extraction

作　　者：刘董经典 孟雪纯 张紫欣 杨旭[1] 牛强[1] LIU Dongjingdian;MENG Xuechun;ZHANG Zixin;YANG Xu;NIU Qiang(College of Computer Science&Technology,China University of Mining and Technology,Xuzhou 221008,China)

机构地区：[1]中国矿业大学计算机科学与技术学院,江苏徐州221008

出　　处：《智能系统学报》2020年第5期900-909,共10页CAAI Transactions on Intelligent Systems

基　　金：国家自然科学基金项目(51674255).

摘　　要：基于计算机视觉的人体行为识别技术是当前的研究热点,其在行为检测、视频监控等领域都有着广泛的应用价值。传统的行为识别方法,计算比较繁琐,时效性不高。深度学习的发展极大提高了行为识别算法准确性,但是此类方法和图像处理领域相比,效果上存在一定的差距。设计了一种基于DenseNet的新颖的行为识别算法,该算法以DenseNet做为网络的架构,通过2D卷积操作进行时空信息的学习,在视频中选取用于表征行为的帧,并将这些帧按时空次序组织到RGB空间上,传入网络中进行训练。在UCF101数据集上进行了大量实验,实验准确率可以达到94.46%。Human behavior recognition technology based on computer vision is a research hotspot currently.It is widely applied in various fields of social life,such as behavioral detection,video surveillance,etc.Traditional behavior recognition methods are computationally cumbersome and time-sensitive.Therefore,the development of deep learning has greatly improved the accuracy of behavior recognition algorithms.However,compared with the field of image processing,there is a certain gap in the effect of such methods.We introduce a novel behavior recognition algorithm based on DenseNet,which uses DenseNet as the network architecture,learns spatio-temporal information through 2D convolution,selects frames for characterizing behavior in video,organizes these frames into RGB space in time-space order and inputs them into our network to train the network.We have carried out a large number experiments on the UCF101 dataset,and our method can reach an accuracy rate of 94.46%.

关 键 词：行为识别 视频分析 神经网络 深度学习 卷积神经网络 分类 时空特征提取 密集连接卷积网络 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]