A texture-based method for modeling the background and detecting moving objects

被引:848
作者
Heikkilä, M [1 ]
Pietikäinen, M [1 ]
机构
[1] Univ Oulu, Machine Vis Grp, Dept Elect & Informat Engn, Oulu 90014, Finland
基金
芬兰科学院;
关键词
motion; texture; background subtraction; local binary pattern;
D O I
10.1109/TPAMI.2006.68
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 presents a novel and efficient texture-based method for modeling the background and detecting moving objects from a video sequence. Each pixel is modeled as a group of adaptive local binary pattern histograms that are calculated over a circular region around the pixel. The approach provides us with many advantages compared to the state-of-the-art. Experimental results clearly justify our model.
引用
收藏
页码:657 / 662
页数:6
相关论文
共 19 条
[1]  
[Anonymous], P IEEE INT C COMP VI
[2]   Background and foreground modeling using nonparametric kernel density estimation for visual surveillance [J].
Elgammal, A ;
Duraiswami, R ;
Harwood, D ;
Davis, LS .
PROCEEDINGS OF THE IEEE, 2002, 90 (07) :1151-1163
[3]  
Friedman N., 1997, PROC UNCERTAINTY ART, P175, DOI DOI 10.1016/J.CVIU.2007.08.003
[4]  
Heikkila M., 2004, British Machine Vision Conference, P187, DOI DOI 10.5244/C.18.21
[5]  
Jabri S, 2000, INT C PATT RECOG, P627, DOI 10.1109/ICPR.2000.902997
[6]  
KaewTraKulPong P., 2001, P EUR WORKSH ADV VID
[7]   An HMM-based segmentation method for traffic monitoring movies [J].
Kato, J ;
Watanabe, T ;
Joga, S ;
Rittscher, J ;
Blake, A .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2002, 24 (09) :1291-1296
[8]  
Kim K, 2004, IEEE IMAGE PROC, P3061
[9]   Using histograms to detect and track objects in color video [J].
Mason, M ;
Duric, Z .
30TH APPLIED IMAGERY PATTERN RECOGNITION WORKSHOP, PROCEEDINGS: ANALYSIS AND UNDERSTANDING OF TIME VARYING IMAGERY, 2001, :154-159
[10]  
Matsuyama T., 2000, P AS C COMP VIS, P622