一种基于纹理的车辆阴影消除新算法

基于对智能交通系统(ITS,Intelligent Transport Systems)中视频检测的研究和分析,特别针对其中关键步骤之一的阴影消除展开深入探讨,分析了阴影产生的原理和特点,阐述了现有的阴影去除算法,在现有算法的基础上提出了一种基于区域聚类的阴影消除算法。实践证明,该方法能够较好的去除运动车辆的阴影,保留较完整的车辆目标信息,为准确提取车辆目标奠定了基础。

based on the research and analysis of video sequence of the Intelligent Transport Systems,this paper especially had a in-depth discussion about the critical step of video detection--shadow removing, analyzing the causes and characteristics of the shadow, describing the current shadow removal algorithms,and proposed a new method of image texture-based vehicle cast shadow elimination approach based on the existing algorithms.Experimental results have proved that this method can remove the vehicle shadow well and still hold very complete target vehicle information and laid the foundation for extracting vehicle target.