RGB和HSI颜色空间的一种改进的阴影消除算法  

An improved shadow removal algorithm based on RGB and HSI color spaces

作　　者：韩延彬[1,2] 郭晓鹏[1] 魏延文[1,2] 李恒建[1,2] 

机构地区：[1]济南大学信息科学与工程学院,山东济南250022 [2]山东省网络环境智能计算技术重点实验室,山东济南250022

出　　处：《智能系统学报》2015年第5期769-774,共6页CAAI Transactions on Intelligent Systems

基　　金：国家自然科学基金资助项目(61103117;61303199);山东省科技发展计划(2013YD01043);山东省高校科研计划项目(J12LN19;J14LN15)

摘　　要：在智能视频监控中,运动目标的准确提取至关重要。现有的运动目标检测算法虽然很多,但是阴影去除效果都不甚理想,因此提出了一种基于RGB和HSI颜色空间的阴影消除改进算法。该算法在分析视频中像素点被阴影覆盖和未被阴影覆盖时色调的近似一致性和亮度值成线性关系的基础上,利用2个颜色空间中组成颜色的各分量值在该颜色中所占的比例和亮度的相对变化率,实现运动目标的阴影消除。实验表明,该算法去除阴影的效果优于采用(r,g,I)颜色空间阴影去除算法,且能有效弥补运动目标孔洞的现象,是对运动目标检测算法的补充。It is critical to exactly extract moving targets in intelligent video surveillance. There are many moving tar- get detection algorithms, but for all the effects of shadow elimination are not ideal. In order to remove the shadow, an improved shadow removal algorithm based on RGB and HSI color spaces is presented. The analysis of the pixels in videoes shows that the hue is approximately consistent before and after the pixels are shaded, and there exists a linear relation between this approximate consistency and the value of luminance. On this basis, by utilizing the pro- portion of each color component in the color spaces and the relative change rates of brightness, the shadow of a moving object can be removed. The experimental results show that the shadow removal effect of this algorithm is bet- ter than that of the algorithm with （ r, g, I） color space. In addition, it can also cope with holes in moving targets and is a supplement to the moving object detection algorithm.

关 键 词：目标检测 阴影消除 颜色空间 孔洞现象 视频分析 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]