摘要
针对智能视频监控系统中阴影常由于其自身的属性而被错误地检测成前景目标的问题,提出了一种YUV颜色空间和图切割算法相结合检测阴影的新方法.首先,在获取的前景运动区域中综合考虑YUV颜色空间的亮度和色度信息来检测阴影区域并融合形态学滤波等操作得到确定的阴影和目标种子点,然后进一步通过图切割算法获得阴影与目标的优化分割,以提高阴影区域的检测精度.实验证明,该方法能有效地检测并去除视频监控场景中运动物体所携带的阴影.
In intelligent video surveillance systems,the moving cast shadows are often mistaken as the object due to its own properties.Consequently,a YUV color space-based theory and a graph-theory-based shadow detection method were proposed to improve the quality of detection.First,the precise seeds of the foreground and shadow were obtained by the YUV color space based on the comprehensive consideration of luminance and chrominance information and morphological filtering.Then the maximum flow minimum cut graph theory algorithm was employed to obtain the optimized segmentation of the shadow and target.Experimental results show that the proposed method can detect and eliminate the cast shadow effectively.
出处
《智能系统学报》
2010年第6期556-560,共5页
CAAI Transactions on Intelligent Systems
基金
湖北省自然科学基金资助项目(2009CDB403)
关键词
前景分割
阴影去除
YUV颜色空间
图切割
foreground segmentation
shadow elimination
YUV color space
graph-theory
