An HMM-based segmentation method for traffic monitoring movies

被引:61
作者
Kato, J [1 ]
Watanabe, T
Joga, S
Rittscher, J
Blake, A
机构
[1] Nagoya Univ, Dept Informat Engn, Chikusa Ku, Nagoya, Aichi 4648603, Japan
[2] France Telecome R&D, DMR RMO, F-92794 Issy Les Moulineaux 9, France
[3] GE Corp Res & Dev, Visualizat & Comp Vis Lab, Schenectady, NY 12301 USA
[4] Microsoft Res, Cambridge CB2 0FB, England
关键词
car tracking; hidden Markov model; image classification; image segmentation; wavelet coefficients;
D O I
10.1109/TPAMI.2002.1033221
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Shadows of moving objects often obstruct robust visual tracking. We propose an HMM-based segmentation method which classifies in real time each pixel or region into three categories: shadows, foreground, and background objects. In the case of traffic monitoring movies, the effectiveness of the proposed method has been proven through experimental results.
引用
收藏
页码:1291 / 1296
页数:6
相关论文
共 18 条
[1]   A MAXIMIZATION TECHNIQUE OCCURRING IN STATISTICAL ANALYSIS OF PROBABILISTIC FUNCTIONS OF MARKOV CHAINS [J].
BAUM, LE ;
PETRIE, T ;
SOULES, G ;
WEISS, N .
ANNALS OF MATHEMATICAL STATISTICS, 1970, 41 (01) :164-&
[2]  
BAUMBERG A, 1994, COMPUTER VISION ECCV, V1, P299
[3]  
Blake A., 1998, ACTIVE CONTOURS, P352
[4]  
Daubechies I., 1993, Ten Lectures of Wavelets, V28, P350
[5]   MAXIMUM LIKELIHOOD FROM INCOMPLETE DATA VIA EM ALGORITHM [J].
DEMPSTER, AP ;
LAIRD, NM ;
RUBIN, DB .
JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES B-METHODOLOGICAL, 1977, 39 (01) :1-38
[6]   VITERBI ALGORITHM [J].
FORNEY, GD .
PROCEEDINGS OF THE IEEE, 1973, 61 (03) :268-278
[7]   W4:: Who?: When?: Where?: What?: A real time system for detecting and tracking people [J].
Haritaoglu, I ;
Harwood, D ;
Davis, LS .
AUTOMATIC FACE AND GESTURE RECOGNITION - THIRD IEEE INTERNATIONAL CONFERENCE PROCEEDINGS, 1998, :222-227
[8]  
Isard M., 1998, Proc. 5th Europe Conference on Computer Vision, P893
[9]  
Kato J., 2001, Transactions of the Information Processing Society of Japan, V42, P1
[10]  
KOLLER D, 1994, COMPUTER VISION ECCV, V1, P189