期刊名称：International Journal of Computer and Information Technology
印刷版ISSN：2279-0764
出版年度：2013
卷号：2
期号：1
页码：1
出版社：International Journal of Computer and Information Technology
摘要：This paper proposes a statistical color model of background extraction based on Hue-Saturation-Value (HSV) color space instead of RGB which shows better use of the color information. HSV color space corresponds closely to the human perception of color and it has revealed more accuracy to distinguish shadows. The key feature of this segmentation method is processing hue component of HSV on image. The components of HSV are efficiently analyzed and treated separately so that the proposed algorithm can adapt to different environmental illumination conditions and shadows. Polar and linear statistical operations have been applied to extract the background from the video frames. Morphological operations are used to reduce the noise of foreground of the input frame. Label matrix has been determined for finding the object region in the foreground image. The proposed system considered age (duration of object existence) of the objects, misses, potential detections and potential for meeting stationary objects criterions. Finally, detected objects have been indicated with yellow boundary and frame number. The experimental results show that the proposed foreground segmentation method can automatically segment video objects robustly and accurately in various illuminating and shadow environments.
