基于判别稀疏编码视频表示的人体动作识别  

Human Action Recognition Based on Discriminative Sparse Coding Video Representation

作　　者：王斌[1] 王媛媛 肖文华[1] 王炜[1] 张茂军[1] 

机构地区：[1]国防科学技术大学信息系统与管理学院,湖南长沙410073 [2]陆军军官学院基础部,安徽合肥230031

出　　处：《机器人》2012年第6期745-750,757,共7页Robot

基　　金：国家自然科学基金资助项目(61275016;61271438;61175006;61175015;60872150;60803101)

摘　　要：为解决视频动作识别中"词袋"模型视频表示误差大、判别性弱,而影响人体动作识别精度的问题,本文提出判别稀疏编码视频表示算法:在稀疏编码框架下,引入Fisher判别分析,对视频局部时空特征编码,增强视频稀疏表示判别性.并提出在线判别字典学习算法,从海量视频数据中训练判别字典.实验表明,与现有算法相比,本文算法有效提高了人体动作识别精度.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.

关 键 词：动作识别 词袋 稀疏编码 FISHER判别准则 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]