Compressed domain action classification using HMM

被引：39

作者：

Babu, RV ^{[1
]}

Anantharaman, B ^{[1
]}

Ramakrishnan, KR ^{[1
]}

Srinivasan, SH ^{[1
]}

机构：

[1] Indian Inst Sci, Supercomp Educ & Res Ctr, Dept Elect Engn, Multimedia Syst Lab, Bangalore 560012, Karnataka, India

来源：

PATTERN RECOGNITION LETTERS | 2002年 / 23卷 / 10期

关键词：

action classification; compressed domain; content-based retrieval; feature extraction; indexing; MPEG-7;

D O I：

10.1016/S0167-8655(02)00067-3

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper proposes three techniques of feature extraction for person independent action classification in compressed MPEG video. The features used are extracted from motion vectors, obtained by partial decoding of the MPEG video. The feature vectors are fed to Hidden Markov Model (HMM) for classification of actions. Totally seven actions were trained with distinct HMM for classification. Recognition results of more than 90% have been achieved. This work is significant in the context of emerging MPEG-7 standard for video indexing and retrieval. (C) 2002 Elsevier Science B.V. All rights reserved.

引用

页码：1203 / 1213

页数：11

共 17 条

[1]

ALLMEN M, 1993, HUMAN ACTION RECOGNI

[2] Machine learning of event segmentation for news on demand [J].