In moving detection, moving objects are gained after current image minus background image. So background extraction is a very important step. We use Gaussian Background Modeling - a traditional method to detect moving objects. But because of illumination, the moving objects we get contain shadow regions which affect moving detection deeply. In this paper, a simple and effective method with RGB information is proposed to detect the real moving regions.%视频中运动物体的检测是用当前图像减去背景图像，背景提取是一个重要环节，本文利用传统的高斯背景建模的方法提取背景。由于光照等因素的影响，得到的前景图像会包含阴影区域，影响了运动物体检测。本文提出了一种简单有效的方法，即利用RGB颜色信息检测出前景区域中的阴影部分，从而检测到真正的运动物体区域。
展开▼
