Recognition of Group Activities Using Complex Wavelet Domain Based Cayley-Klein Metric Learning

作     者：Gensheng Hu Min Li Dong Liang Mingzhu Wan Wenxia Bao 

作者机构：Key Laboratory of Intelligent Computing and Signal ProcessingMinistry of EducationAnhui University Hefei 230039China School of Electronics and Information EngineeringAnhui UniversityHefei 230601 China School of Information Science and TechnologyFudan UniversityShanghai 200433China Anhui Key Laboratory of Polarization Imaging Detection TechnologyHefei 230031China 

出 版 物：《Journal of Beijing Institute of Technology》 (北京理工大学学报（英文版）)

年 卷 期：2018年第27卷第4期

页      面：592-603页

核心收录：

学科分类：0810[工学-信息与通信工程] 08[工学] 081002[工学-信号与信息处理] 

基　　金：Supported by the National Natural Science Foundation of China(61672032,61401001) the Natural Science Foundation of Anhui Province(1408085MF121) the Opening Foundation of Anhui Key Laboratory of Polarization Imaging Detection Technology(2016-KFKT-003) 

主　　题：video surveillance group activity recognition non-sampled dual-tree complex wavelet packet transform(NS-DTCWPT) Cayley-Klein metric learning 

摘      要：A group activity recognition algorithm is proposed to improve the recognition accuracy in video surveillance by using complex wavelet domain based Cayley-Klein metric ***-sampled dual-tree complex wavelet packet transform(NS-DTCWPT)is used to decompose the human images in videos into multi-scale and *** improved local binary pattern(ILBP)and an inner-distance shape context(IDSC)combined with bag-of-words model is adopted to extract the decomposed high and low frequency coefficient *** extracted coefficient features of the training samples are used to optimize Cayley-Klein metric matrix by solving a nonlinear optimization *** group activities in videos are recognized by using the method of feature extraction and Cayley-Klein metric *** results on behave video set,group activity video set,and self-built video set show that the proposed algorithm has higher recognition accuracy than the existing algorithms.