Segmentation Approach Methods in Complex Environment


Article Preview

Segmentation is fundamental step in video surveillance system. It is hard to segmented interesting object in all environments due to the similarity features of objects and background. The segmentation results (foregrounds) are often broken. An approach composition of some methods including GMM, removing cast shadow, clustering and segmentation broken detection and recovery is proposed to improve the segmentation results. This method is suitable for the applications that the information of bounding boxes is required.



Advanced Materials Research (Volumes 121-122)

Edited by:

Donald C. Wunsch II, Honghua Tan, Dehuai Zeng, Qi Luo




H. I. Pai et al., "Segmentation Approach Methods in Complex Environment", Advanced Materials Research, Vols. 121-122, pp. 975-979, 2010

Online since:

June 2010




[1] Horprasert, T. and Harwood, D. and Davis, L. S, A statistical approach for real-time robust background subtraction and shadow detection, IEEE ICCV99 Frame-Rate Workshop, Corfu, Greece, Sep (1999).

[2] Carmona, E.J. and Mart´ınez-Cantos, J. and Mira, J, A new video segmentation method of moving objects based on blob-level knowledge, Pattern Recognition Letters. vol. 29, p.272285, (2008).


[3] Kim, K. and Chalidabhongse, T.H. and Harwood, D. and Davis, L, Real-time foregroundbackground segmentation using codebook model, Real-Time Imaging. vol. 11, pp.172-185, (2005).


[4] Y. Ren, C. S. Chua., and Y. K. Ho, Motion detection with nonstationary background, Machine Vision and Applications, vol. 13, no. 5, pp.332-343, (2003).


[5] H.I. Pai, K.M. Lan, Y.Y. Chen, J.H. Chuang, A fast method to remove case shadow, CVGIP 2009, (2009).

[6] Maheshwari, M. and Silakari, S. and Motwani, M, Image Clustering Using Color and Texture, Pro. of the 2009 First Inter. Conf. on Comp. Intel., Commu. Sys., pp.403-408, (2009).


Fetching data from Crossref.
This may take some time to load.