首页 | 本学科首页   官方微博 | 高级检索  
     

智能交通系统中的椭球法运动阴影检测
引用本文:高俊祥.智能交通系统中的椭球法运动阴影检测[J].光电子.激光,2009(10):1348-1352.
作者姓名:高俊祥
作者单位:北京邮电大学信息与通信工程学院;
基金项目:国家自然科学基金资助项目(60743007,60872050)
摘    要:基于背景像素被阴影覆盖后RGB值的变化,提出了一种智能交通系统(ITS)中运动阴影的检测算法。首先定义了归一化亮度比例坐标系并将阴影检测视为该坐标系中的分类问题,然后采用阴影像素在该坐标系中的分布信息构建一椭球,并根据像素的坐标值是否处在椭球内部以及RGB3种颜色归一化亮度比例的相对大小确定阴影像素。对比实验表明,该方法能够有效地检测运动阴影,性能优于SNP算法和DNM算法。

关 键 词:模式识别  运动阴影检测  智能交通系统  

Moving shadow detection by ellipsoidal method in intelligent transportation system
GAO Jun-xiang.Moving shadow detection by ellipsoidal method in intelligent transportation system[J].Journal of Optoelectronics·laser,2009(10):1348-1352.
Authors:GAO Jun-xiang
Affiliation:GAO Jun-xiang,TIAN Yan,LIU Yong (School of Information and Communication Engineering,Beijing University of Posts and Telecommunications,Beijing 100876,China)
Abstract:A moving shadow detection approach was proposed based on the change of RGB values of shaded pixels.The coordinate systems were defined based on normalized ratio of luminance,and shadow segmentation was treated as a clustering problem in the coordinate systems.Consequently,an ellipsoid was constructed according to scattering feature of shaded pixels.Possible shaded pixels were extracted by the computation whether they lie in above ellipsoid.Meanwhile,the relative values among the normalized luminance ratio o...
Keywords:pattern recognition  moving shadow detection  intelligent transportation system  
本文献已被 CNKI 等数据库收录!
点击此处可从《光电子.激光》浏览原始摘要信息
点击此处可从《光电子.激光》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号