移动车辆上全方向摄像机的3D环境识别  

3D Environment Recognition Using Omni-directional Camera from Moving Vehicle

作　　者：孙龙[1] 胡茂林[2] 张长耀[1] 

机构地区：[1]中国电子科技集团公司第38研究所雷达成像中心,安徽合肥230031 [2]安徽大学数学与计算科学学院

出　　处：《计算机应用研究》2006年第10期163-165,共3页Application Research of Computers

基　　金：国家科技部重大基础研究资助项目(2001CCC02100)

摘　　要：提出一个能够从移动的车辆来识别城市区域环境的感应器系统。城市区域环境是相当复杂的户外人造环境,它要求与户内或者高速公路环境的不同识别方法。为了达到识别3D环境的目的,利用三个固定的扭曲参数为0的全方向摄像机组和对极几何的知识来标定摄像机内参矩阵K,进而由自标定的方法进行几何重构。This research aims at developing a sensor system which will be able to recognize city area environments from a moving vehicle, A city area which is a rather cluttered outdoor man-made environment requires different recognition methods from indoor or highway environments. Toward this goal, an omni-directional camera and epipolar geometry are employed. At the end of the paper, the result of the experiments are gaved and the theory is verified.

关 键 词：全方向摄像机 对极几何 自标定 欧氏重构 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]