Change detection based on color edges

This paper discusses a novel approach for change detection robust to illumination variations. The proposed technique makes use of a color edge detection scheme applied to the difference between a current and a reference image. Simulation results and comparisons to techniques in literature are reported and show that the proposed scheme offers a good detection performance, while providing robustness to illumination variations.

[1]  A. Koschan.  A Comparative Study On Color Edge Detection , 1995 .

[2]  Paul L. Rosin.  Thresholding for change detection , 1998, Sixth International Conference on Computer Vision (IEEE Cat. No.98CH36271).

[3]  Didier Aubert.  Passengers queue length measurement , 1999, Proceedings 10th International Conference on Image Analysis and Processing.

[4]  Touradj Ebrahimi,et al.  Robust and illumination invariant change detection based on linear dependence for surveillance application , 2000, 2000 10th European Signal Processing Conference.

[5]  Ramesh C. Jain,et al.  Illumination independent change detection for real world image sequences , 1989, Comput. Vis. Graph. Image Process..

[6]  Jean-Marc Vesin,et al.  Intrusion detection robust to slow and abrupt lighting changes , 1996, Electronic Imaging.

[7]  Til Aach,et al.  Statistical model-based change detection in moving video , 1993, Signal Process..

[8]  Shyang Chang,et al.  Statistical change detection with moments under time-varying illumination , 1998, IEEE Trans. Image Process..

[9]  K. Plataniotis,et al.  Color Image Processing and Applications , 2000 .