结合区域颜色和纹理的运动阴影检测方法

Moving Cast Shadow Detection Based on Region Color and Texture

  • 摘要: 在视频跟踪中,由于运动阴影和运动对象具有相似的物理特性,现有方法很难区分运动对象和运动阴影.为解决这一问题,本文利用区域间的颜色和像素亮度的关系进行运动阴影的检测,有效克服了以像素为最小检测单位时检测结构容易受到噪声影响的不足;在通过分析运动阴影的物理模型证明局部二值模式(LBP)纹理的光照不变性之后,利用局部二值模式光照不变性检测阴影;根据视频图像的实际特点,还提出了结合区域颜色和纹理进行运动阴影检测的方法.试验结果表明,该方法能够在不同场景下稳定有效地检测出运动阴影.

     

    Abstract: In video tracing,due to the fact that moving shadows have some similar physical characteristics to moving objects,it is difficult for known object extracting methods to distinguish moving shadows from moving objects.To address this problem,an algorithm for detecting moving shadows based on the relationship between region color and the illumination information of the pixels is proposed.Therefore,the noise effect on the detecting structure when using one pixel as the smallest detecting unit can be efficiently reduced by the proposed algorithm.Meanwhile,the illumination invariance of local binary pattern(LBP) texture is used to detect shadow,after proven by the analysis on the physical model of moving shadows.According to the actual characteristics of video image,a method based on region color and texture is presented to detect moving shadows.Experiment results show that the proposed method is robust and efficient in shadow detection under different scenes.

     

/

返回文章
返回