基于判别稀疏编码视频表示的人体动作识别 - 机器人.pdfVIP

34 6 ROBOT Vol.34, No.6 2012 11 Nov., 2012 DOI 10.3724/SP.J.1218.2012.00745 1 2 1 1 1 1. 410073 2. 230031 Fisher Fisher TP391 A 1002-0446(2012)-06-0745-06 Human Action Recognition Based on Discriminative Sparse Coding Video Representation WANG Bin 1 WANG Yuanyuan 2 XIAO Wenhua 1 WANG Wei 1 ZHANG Maojun 1 (1. College of Information Systems and Management, National University of Defense Technology, Changsha 41007, China; 2. Department of Basic Courses, Army Officer Academy , Hefei 230031, China) Abstract: The bag-of-words (BoW) model usually causes large errors and weak discrimination in video representation in video action recognition, and affects the human action recognition accuracy. To solve this problem, a discriminative sparse coding (DSC) video representation algorithm is proposed. It’s a sparse coding framework involving a Fisher discriminative analysis to encode video local spatial-temporal features and increase the video sparse representation discrimination. And an online discriminative dictionary learning algorithm is also proposed to train a dictionary from massive video data. The experiments show that, comparing with the existing algorithms, the proposed algorithm effectively improves human action recognition accuracy. Keywords: action recognition; bag of words; sparse coding; Fisher discrimination criterion 1 Introduction 2-10