Moving Cast Shadow Detection Based on Region Color and Texture
CAO Jian1, CHEN Hongqian1, ZHANG Kai2, NIU Changfeng2
1. School of Computer Science and Information Engineering, Beijing Technology and Business University, Beijing, 100048, China; 2. School of Computer Science and Technology, Beijing Institute of Technology, Beijing 100081, China
Abstract：In video tracing,due to the fact that moving shadows have some similar physical characteristics to moving objects,it is difficult for known object extracting methods to distinguish moving shadows from moving objects.To address this problem,an algorithm for detecting moving shadows based on the relationship between region color and the illumination information of the pixels is proposed.Therefore,the noise effect on the detecting structure when using one pixel as the smallest detecting unit can be efficiently reduced by the proposed algorithm.Meanwhile,the illumination invariance of local binary pattern(LBP) texture is used to detect shadow,after proven by the analysis on the physical model of moving shadows.According to the actual characteristics of video image,a method based on region color and texture is presented to detect moving shadows.Experiment results show that the proposed method is robust and efficient in shadow detection under different scenes.
[1] Cucchiara R,Grana C,Piccardi M,et al.Improving shadow suppression in moving objoct detection with HSV color information[C]//Proceedings of the Intelligent Transportation Systems.Piscataway,NJ,USA:IEEE,2001:334-339.
[2] Salvador E,Cavallaro A,Ebrahimi T.Cast shadow segmentation using invariant color features[J].Computer Vision and Image Understanding,2004,95(2):238-259.
[3] Leone A,Distante C,Buccolieri F.Shadow detection for movIng objects based on texture analysis[J].Pattern Recognition,2007,40(4):1222-1233.
[4] Zhang W,Fang Z X,Yang X K,et al.Moving cast shadows detection using ratio edge[J].IEEE Transactions on Multimedia,2007,9(6):1202-1214.
[5] Wang Y,Loc K F,We J K.A dynamic conditional random field model for foreground and shadow segmentstion[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2006,28(2):279-289.
[6] Tatsuya T,Atsushi S,Daisalu A,et al.Non-parametric background and shadow modeling for object detection[M]//Lecture Notes in Computer Science:vol.4843.Berlin,Germany:Springer-Verlag,2007:159-168.
[7] Joshi A J,Papanikolopoulos N P.Learning to detect moving shadows in dynamic environments[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(11):2055-2063.
[8] Mikic I,Cosman P C,Kogut G T,et al.Moving shadow and object detection in traffic scenes[C]//Proceedings of the International Conference on Pattern Recognition.Piscataway,NJ,USA:IEEE,2000:321-324.
[9] Choi J M,Yoo Y J,Choi J Y.Adaptive shadow estimator for removing shadow of moving object[J].Computer Vision and Image Understanding,2010,114(9):1017-1029.
[10] Prati A,Mikic I,Trivedi M M,et al.Detecting moving shadows:Algorithms and evaluation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(7):918-923.
[11] Ojala T,Pietikainen M,Maenpaa T.Multiresolution gray-scale and rotation invariant texture classification with local binary paterns[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2002,24(7):971-987.
[12] Stander J,Moch R,Ostennann J.Detection of moving cast shadows for object segmentation[J].IEEE Transactions on Multimedia,1999,1(1):65-76.
