基于逆透视变换的智能车辆定位技术  

Technology of Intelligent Vehicle Location Based on Inverse Projective Transformation

作　　者：高德芝[1] 郑榜贵[1] 段建民[1] 

机构地区：[1]北京工业大学电子信息与控制工程学院,北京100124

出　　处：《计算机测量与控制》2009年第9期1810-1812,共3页Computer Measurement &Control

基　　金：北京市教委科技创新平台项目(JJ002790200802)

摘　　要：为了根据车道线参数准确地确定本车在车道中的位置和方向信息,提出了一种基于逆投影变换的本车定位算法。算法利用逆透视变换对投影图中的车道线进行三维逆透视重建,得到实际路面的车道线,并经过坐标变换求出本车在车道中的当前位置参数、方向参数及车道宽度等信息。试验表明,该算法对光照条件、道路结构等变化具有较好的适应能力和抗干扰能力,在一定程度上满足多种横向主动安全系统的要求。In order to realize the host vehicle＇ s parameters of position and direction accurately according to lane line parameters, a kind of practical localization algorithm of the host vehicle based on inverse projective transformation has been proposed. The real lane line is ob rained through inverse projective reconstruction. The parameters such as the host vehicle＇s Iocation parameter, the direction variable and the lane width are obtained using the coordinate transformation. The experiments results indicated that this algorithm has the good adaptive ability and anti--jamming ability when roadway structure and illumination condition changes. It can satisfy many kinds of initiative safety system＇ s requests in a certain extent.

关 键 词：智能车辆 逆透视变换 车辆定位 车道线识别 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]