结合亮度比值梯度与颜色特征的阴影去除算法

Shadow Removal Algorithm by Combining Gradient of the Brightness Ratio and Color Features

在视频监控场景下的目标检测中,运动的阴影会对所检测目标的准确性造成不利影响.为了去除运动阴影的干扰,本文提出了一种结合亮度比值的四方向梯度与颜色特征的阴影去除算法.该算法首先在RGB颜色空间使用混合高斯模型提取前景和背景;其次在rgI颜色空间计算前景与其对应背景亮度分量的比值;由于阴影区域的相邻像素亮度比值变化较小,通过计算亮度比值的四方向梯度均值来判断阴影区域并加以去除;最后为了避免运动目标被误去除,考虑到运动目标与背景的颜色差异远远大于阴影与背景之间颜色的差异,结合颜色特征来保留目标,确保检测目标的完整性.实验结果表明,本文提出的算法在阴影去除率和保持目标完整性方面优于其他阴影去除算法.

M oving shadow s have adverse effects on the accuracy of the detected target,while detecting moving target in video surveillance scene. In order to eliminate the interference of the moving shadow s,a shadow removal algorithm is proposed by combining the four-direction gradient of the brightness ratio and color features in this paper. First,the Gaussian M ixture M odel is employed to extract foreground and background in RGB color space. Secondly,the ratio of brightness of the foreground pixel to its corresponding background pixel is calculated in rgI color space. Because the ratio of the brightness among a pixel’s neighborhood in shadow region changes small,the calculated four-direction gradient mean can be applied to detect and remove shadow. Finally,in order to avoid that the moving targets are removed as shadow s and ensure the integrity of the detected targets,color features are employed to keep the integrity of moving targets because difference of color features between the moving targets and its corresponding background is much larger than that between shadowand its corresponding background. The experimental results show that the algorithm presented in this paper is superior to other similar shadow removal algorithms in shadow removal ratio and keeping the integrity of the detected targets.