Moving object detection with background subtraction and shadow removal

This paper presents a moving object detection method with background subtraction and shadow removal in the RGB color space. For background subtraction, the metrically trimmed mean is employed as a robust estimate of the background model and the mean absolute deviation (MAD) is adopted as a scale estimate. A cascading chromaticity difference estimator, brightness difference estimator, and spatial analysis are explored to discriminate the shadow and the moving object. Our experimental results validate the good performance of the proposed method.

[1]  Marko Heikkilä,et al.  A texture-based method for modeling the background and detecting moving objects , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Mohan M. Trivedi,et al.  Detecting Moving Shadows: Algorithms and Evaluation , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Touradj Ebrahimi,et al.  Cast shadow segmentation using invariant color features , 2004, Comput. Vis. Image Underst..

[4]  Jin Young Choi,et al.  Adaptive shadow estimator for removing shadow of moving object , 2010, Comput. Vis. Image Underst..

[5]  Kai-Tai Song,et al.  Image-Based Traffic Monitoring With Shadow Suppression , 2007, Proceedings of the IEEE.

[6]  Rita Cucchiara,et al.  Detecting Moving Objects, Ghosts, and Shadows in Video Streams , 2003, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  Cláudio Rosito Jung,et al.  Efficient Background Subtraction and Shadow Removal for Monochromatic Video Sequences , 2009, IEEE Transactions on Multimedia.

[8]  Wei Zhang,et al.  Moving Cast Shadows Detection Using Ratio Edge , 2007, IEEE Transactions on Multimedia.

[9]  W. Eric L. Grimson,et al.  Adaptive background mixture models for real-time tracking , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).