Parametric model for video content analysis

被引：14

作者：

Chen, Wei ^{[1
]}

Zhang, Yu-jin ^{[1
]}

机构：

[1] Tsinghua Univ, Image Engn Lab, Dept Elect Engn, Beijing 100084, Peoples R China

来源：

PATTERN RECOGNITION LETTERS | 2008年 / 29卷 / 03期

关键词：

parametric model; shot boundary; key frame; spatial-temporal feature;

D O I：

10.1016/j.patrec.2007.09.020

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper, we propose a parametric model for the video content analysis. We use the autoregressive (AR) modeling to model the frame feature sequence over time and make the future analysis in the AR parametric space. Based on our parametric framework, applications of detecting shot boundaries in video sequences, extracting key frames and combined spatial-temporal features for shot classification are proposed. Experiments show that our new parametric framework can present the video content better than the traditional color histogram. (c) 2007 Elsevier B.V. All rights reserved.

引用

页码：181 / 191

页数：11

共 38 条

[21] An effective post-refinement method for shot boundary detection
Lu, H
Tan, YP
[J]. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2005, 15 (11) : 1407 - 1421
[22] Lu H. B., 1999, Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348), P304, DOI 10.1109/ICIP.1999.817122
[23] A metric for ARMA processes
Martin, RJ
[J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2000, 48 (04) : 1164 - 1170
[24] Motion-based video representation for scene change detection
Ngo, CW
Pong, TC
Zhang, HJ
[J]. INTERNATIONAL JOURNAL OF COMPUTER VISION, 2002, 50 (02) : 127 - 142
[25] NGO CW, 1999, P C COMP VIS PATT RE, V1, P23
[26] NGO CW, 2000, THESIS HONG KONG U S
[27] NICOLAS H, 2004, ICIP, V1, P637
[28] RAINER WL, 2001, P SOC PHOTO-OPT INS, V4315, P219
[29] RAJESH R, 2002, IEEE T IMAGE PROCESS, V11, P26
[30] RAJESH R, 1997, IEEE T IMAGE PROCESS, V6, P1503

← 1 2 3 4 →