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。
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...
出处
《光电子．激光》
EI
CAS
CSCD
北大核心
2009年第10期1348-1352,共5页
Journal of Optoelectronics·Laser
基金
国家自然科学基金资助项目(60743007
60872050)
关键词
模式识别
运动阴影检测
智能交通系统
pattern recognition
moving shadow detection
intelligent transportation system
