Computer Science ›› 2014, Vol. 41 ›› Issue (3): 293-296.

Previous Articles     Next Articles

Robust Foreground Detection Using Local Intensity Ratio

XIANG Jin-hai,LIAO Hong-hong,FAN Heng,DAI Jiang-hua,SUN Wei-ping and YU Sheng-sheng   

  • Online:2018-11-14 Published:2018-11-14

Abstract: Real time segmentation of foreground objects in video sequences is a fundamental step for surveillance.This paper proposed a local intensity ratio(LIR) to remove shadow.The local intensity ratio has the illumination invariance feature which is based on the analysis of illumination change model.The distribution of the LIR was discussed.We used the local intensity ratio instead of pixel intensity for Gaussian Mixture Model(GMM),and then got the foreground without shadow.Based on experimental results,the LIR feature shows excellent performance under various illumination change conditions while operating in real-time.

Key words: Local intensity ratio(LIR),Shadow remove,Gaussian mixture model (GMM),Illumination change

[1] Piccardi M.Background subtraction techniques:a review [C]∥IEEE International Conference on Systems,Man and Cyberne-tics.2004:3099-3104
[2] Sanin A,Sanderson C,Lovell B.Shadow detection:A survey and comparative evaluation of recent methods[J].Pattern Recognition,2012,45:1684-1695
[3] Al-Najdawi N,Bez H E,Singhai J,et al.A survey of cast shadow detection algorithms[J].Pattern Recognition Letters,2012,3:752-764
[4] Joshi A,Papanikolopoulos N.Learning to detect moving sha-dows in dynamic environments[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2008,30(11):2055-2063
[5] Liu Z,Huang K,Tan T,et al.Cast shadow removal combining local and global features[C]∥IEEE Conference on Computer Vision and Pattern Recognition.2007:1-8
[6] Martel-Brisson N,Zaccarin A.Learning and removing cast sha-dows through a multi distribution approach[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(7):1133-1146
[7] Porikli F,Thornton J.Shadow flow:a recursive method to learn moving cast shadows[C]∥Tenth IEEE International Conference on Computer Vision.2005:891-898
[8] 查宇飞,楚瀛,王勋,等.一种基于Boosting判别模型的运动阴影检测方法[J].计算机学报,2007,0(8):1295-2113
[9] 韩忠民,刘志,张兆杨,等.视频分割中运动阴影消除的新方法[J].中国图象图形学报,2009,4(10):2110-2113
[10] Nadimi S,Bhanu B.Physical models for moving shadow and object detection in video[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,26(8):1079-1087
[11] Huang J-B,Chen C-S.Moving cast shadow detection using phy-sics-based features[C]∥IEEE Conference on Computer Vision and Pattern Recognition.2009:2310-2317
[12] Martel-Brisson N,Zaccarin A.Kernel-based learning of castshadows from a physical model of light sources and surfaces for low-level segmentation[C]∥IEEE Conference on Computer Vision and Pattern Recognition.2008:1-8
[13] Chen C-C,Aggarwal J.Human shadow removal with unknown light source[C]∥International Conference on Pattern Recognition.2010:2407-2410 (下转封三)(上接第296页)
[14] Hsieh J-W,Hu W-F,Chang C-J,et al.Shadow elimination foreffective moving object detection by Gaussian shadow modeling[J].Image and Vision Computing,2003,21(6):505-516
[15] Nicolas H,Joint J-M P.moving cast shadows segmentation and light source detection in video sequences[J].Signal Processing:Image Communication,2006,21(1):22-43
[16] Zhang W,Fang X Z,Yang X K,et al.Moving cast shadows detection using ratio edge[J].IEEE Trans.Multimedia,2007,9:1202-1213
[17] Stander J,Mech R,Ostermann J.Detection of moving cast sha-dows for object segmentation[J].IEEE Trans.Multimedia,1999,1:65-76
[18] Andersen M S,Jensen T,Madsen C B.Estimation of DynamicLight Changes in Outdoor Scenes Without the use of Calibration Objects[C]∥18th Int.Conf.Pattern Recognition.2006,4:91-94
[19] Stauffer C,Grimson W E L.Adaptive background mixture models for real-time tracking[C]∥IEEE Computer Society Conf.Computer Vision and Pattern Recognition.1999,2:637-663
[20] Prati A,Mikic I,Trivedi M M,et al.Detecting Moving Sha-dows:Algorithms and Evaluation[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2003,25(7):918-923

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!