On the Construction of a Color Model for Real-time Visual Moving Objects Segmentation

Chin-Hwa Kuo; Ping-Huang Wu; Tay-Shen Wang

doi:10.6180/jase.2005.8.2.01

On the Construction of a Color Model for Real-time Visual Moving Objects Segmentation

Computer Science and Information Engineering

Chin-Hwa Kuo This email address is being protected from spambots. You need JavaScript enabled to view it.¹, Ping-Huang Wu¹ and Tay-Shen Wang¹

¹Department of Computer Science and Information Engineering, Tamkang University, Tamsui, Taiwan 251, R.O.C.

Received: March 2, 2005
Accepted: May 9, 2005
Publication Date: June 1, 2005

Download Citation: ||https://doi.org/10.6180/jase.2005.8.2.01

ABSTRACT

A color model, called RGB-Ellipse, is developed in this paper. The proposed color model takes advantages of CIE-L*a*b*94 and CMC(l:c) in determining color differences. Furthermore, the transformation between RGB and RGB-Ellipse is linear. As a result, we are able to manipulate the noise tolerance processing as well as the computation efficiency in dealing with color differences. By using the above features, we develop a real-time moving objects segmentation scheme. The developed segmentation scheme consists of two main steps: (1) region seed determination and region growing and (2) region-based change detection and background update. The results from a visual surveillance system are given to highlight the value of the proposed color model and moving objects segmentation scheme.

Keywords: Image Segmentation, Color Model, Surveillance System

REFERENCES

[1] Canny, J., “A Computational Approach to Edge Detection,” IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. PAMI-8, No. 6, pp. 679698 (1986).
[2] Ma, W. Y. and Manjunath, B. S., “Edge Flow: A Framework of Boundary Detection and Image Segmentation,” Proc. of IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 744 749 (1997).
[3] Sarkar, S. and Boyer, K. L., “Optimal, Efficient, Recursive Edge Detection Filters,” Proc. of 10th Int’l Conf. on Pattern Recognition, Vol. 1, pp. 931936 (1990).
[4] Christopoulos, C. A., Philips, W., Skodras, A. N. and Cornelis, J., “Segmented Image Coding: Techniques and Experimental Results,” Signal Processing: Image Communication, Vol. 11, pp. 6380 (1997).
[5] Elgammal, A., Duraiswami, R., Harwood, D. and Davis, L. S., “Background and Foreground Modeling Using Nonparametric Kernel Density Estimation for Visual Surveillance,” Proc. of IEEE, Vol. 90, pp. 1151 1163 (2002).
[6] Dufaux, F. and Moscheni, F., “Segmentation Based Motion Estimation for Second Generation Video Coding Techniques,” L. Torres and M. Kunt, editors, Video Coding: The Second Generation Approach, Chapter 6, Kluwer Academic Publishers, Boston, MA, U.S.A. pp. 219263 (1996).
[7] Dufaux, F., Moscheni, F. and Lippman, A., “SpatioTemporal Segmentation Based on Motion and Static Segmentation,” Proc. of ICIP’95, IEEE, Vol. 1, pp. 306309 (1995).
[8] Fan, J., Yau, K. Y., Elmagarmid, A. K. and Aref, W. G., “Automatic Image Segmentation by Integrating Color-Edge Extraction and Seeded Region Growing,” IEEE Trans. on Image Processing, Vol. 10, pp. 1454 1466 (2001).
[9] Deklerck, R., Corneils, J. and Bister, M., “Segmentation of Medical Images,” Image and Vision Computing, Vol. 11, pp. 486503 (1993).
[10] Kim, C. and Hwang, J. N., “Fast and Automatic Video Object Segmentation and Tracking for Content-Based Applications,” IEEE Trans. on Circuit and System for Video Tech., Vol. 12, pp. 122129 (2002).
[11] Deng, Y. and Manjunath, B. S., “Unsupervised Segmentation of Color-Texture Regions in Images and Video,” IEEE Trans. on Pattern Analysis and Machine Learning, Vol. 23, pp. 800810 (2001).
[12] Etoh, M., “Promotion of Block Matching: Parametric Representation for Motion Estimation,” Proc. 4th ICPR, Vol. 1, pp. 282285 (1998).
[13] Gao, H., Siu, W. C. and Hou, C. H., “Improved Techniques for Automatic Image Segmentation,” IEEE Trans. on Circuit and System for Video Tech., Vol. 11, pp. 12731280 (2001).
[14] Harville, M., Gordon, G. and Woodfill, J., “Foreground Segmentation Using Adaptive Mixture Models in Color and Depth,” Proc. of the IEEE Workshop on Detection and Recognition of Events in Video, pp. 311 (2001).
[15] Rosin, P. L., “Thresholding for Change Detection,” Proc. of 6th Int’l Conf. on Computer Vision, IEEE, pp. 274279 (1998).
[16] Chien, S. Y., Ma, S. Y. and Chen, L. G., “Efficient Moving Object Segmentation Algorithm using Background Registration Technique,” IEEE Trans. on Circuit and System for Video Tech., Vol. 12, pp. 577586 (2002).
[17] Foresti, G. L. and Regazzoni, C. S., “A Change-Detection Method for Multiple Object Localization in Real Scenes,” Proc. of Int’l Conf. on Industrial Electronic, Control and Instrumentation, pp. 984987 (1994).
[18] Gibbins, D., Newsam, G. N. and Brooks, M. J., “Detecting Suspicious Background Changes in Video Surveillance of Busy Scenes,” Proc. of 3rd IEEE Workshop on Application of Computer Vision, pp. 2226 (1996).
[19] “http://www.komoto.com.tw/html/idx-info.html” (2005).
[20] Kuo, C. H., Wang, T. S. and Wu, P. H., “Design of Networked Visual Monitoring Systems,” The Tamkang Journal of Science and Engineering, Vol. 2, pp. 149 161 (1999).