作　　者： ; ;

机构地区： 华南理工大学

出　　处： 《微计算机信息》 2006年第03S期232-234,共3页

摘　　要： 介绍了一种基于车辆模板和车辆与阴影的边缘信息的阴影消除方法。该方法先利用了背景和车辆之间灰度差距比较明显,找出大概的车辆模板。通过应用光源投射时候形成的阴影方位的先验知识以及车辆和阴影之间的边缘信息,在模板内部消除阴影,可以达到很高的准确性。在进行分割过程的时候,采用了动态的阈值选取方法,可以在不同情况下实现很好的鲁棒性。 This paper introduces a new shadow eliminate method, which based on car modal and edge information. Since the difference between the color of the background and the color of the car is very obvious, find the car modal accord with these characters. According to direction of the shadow and the character of edge information which is cause by the difference of color between car and shadow. Eliminate the shadow in the car modal can increase the veracity .During the segmentation, dynamic valve is used which has been proved to be robust and highly adaptive in complex environment in actual application.

关 键 词： 背景重建 车辆模板 阴影消除 边缘信息

领　　域： [自动化与计算机技术] [自动化与计算机技术]