摘要
阴影检测是运动车辆目标识别与追踪中非常重要的环节。结合基于颜色和模型的两种检测方法,提出一种基于移动区域的快速粗模型阴影检测方法。该方法首先通过改进的背景差分方法快速获取图像中的移动区域,然后在此基础上根据基于模型的方法建立阴影的粗模型,即快速确定阴影区域的粗略区域。阴影检测时只对该区域内的图像采用基于HSV颜色空间的方法进行分析处理。实验结果表明该方法可以有效地提高阴影检测的效率。
Shadow detection is a very important part in the recognition and tracking of the moving vehicles. Based on the color-based and model-based shadow detection methods, a fast coarse model shadow detection method is presented according to the moving region. Firstly, the moving region of the image is quickly detected using the improved background subtraction method. Then a coarse model of the shadow detection is established by the model-based method. Only the coarse region is applied to the shadow detection method based on the HSV color space. Experimental results show that this method can improve the efficiency of the shadow detection greatly.
出处
《计算机工程与设计》
CSCD
北大核心
2007年第16期4001-4003,共3页
Computer Engineering and Design
关键词
背景差分
阴影检测
HSV颜色空间
粗模型
标签法去噪
background subtraction
shadow detection
HSV color space
coarse model
label-based de-noising method