联合两种颜色空间的阴影检测算法  

Shadow Detection Algorithm Combined Two Color Space

作　　者：黄建强[1] 曹腾飞[1] 郭文静[1] 王瑞[1] 吴利[1] 

机构地区：[1]青海大学计算机技术与应用系,青海西宁810016

出　　处：《计算机技术与发展》2014年第7期95-98,共4页Computer Technology and Development

基　　金：青海省自然科学基金青年项目(2013-Z-930Q);青海大学中青年基金项目(2013-QGY-10)

摘　　要：在视频监控的运动检测中,由于光照、风吹等影响,运动阴影常常被误认为运动对象。为了有效解决动态背景下运动目标中存在的阴影问题,提出了一种归一化的RGB颜色空间和HSV颜色空间相结合的阴影消除方法。该方法首先在归一化RGB颜色空间下用背景减除法得到运动目标,然后在HSV空间下对阴影进行检测和消除,从而得到真实运动目标。实验结果证实:该方法在运动目标检测及跟踪方面取得了较好的效果,对动态背景的视频,能准确、实时地检测出阴影并进行消除。In video motion detection,the moving shadow is often mistaken as moving object due to the effects of light and wind. In order to effectively solve the problem of moving object detection in dynamic background,propose a novel method using the joint of normalized RGB color space and HSV color space. Firstly,this method gets the moving targets in normalized RGB color space with the subtraction method,then under the shadow of space in the HSV carry out detection and elimination,resulting in real moving targets. The experiment results demonstrate the method obtains good effect in the moving target detection and tracking,can detect and eliminate the shadow effec-tively in real-time for the dynamic background video.

关 键 词：归一化RGB颜色空间 HSV颜色空间 阴影消除 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]