基于单目视觉的前方车辆探测方法研究
首发时间:2004-03-18
摘要:本文系统地介绍了采用单目视觉技术获取前方车辆多元信息的方法,主要内容包括:利用单帧图像识别出的路径标线建立初始感兴趣区,并对目标进行初步探测;建立识别感兴趣区,应用对称性测度确认前方车辆的存在,并寻找出前方车辆的对称轴;在连续序列图像中,利用Kalman预估器进行目标跟踪;建立基于静态图像处理和摄像机内部参数标定的单目视觉测距方法并进行相关试验验证。
For information in English, please click here
Study on Method of Detecting Preceding Vehicle Based on Monocular Camera
Abstract:This paper describes systemically the method of detecting preceding vehicle based on monocular camera. The main contents are as following: First, a primary area of interesting is found by the lane borderlines that are identified in a camera image, and a likelihood target vehicle is searched by the gray difference between the target vehicle and background. Second, the identifying area of interesting is found again based on the area of likelihood target vehicle, a target vehicle is affirmed by a symmetry character of the vehicle outline and a position of the vehicle symmetrical axis is ascertained. Third, the object vehicle is tracked by Kalman estimator with the sequence images. Fourth, a method of detecting distance in a frame of image is introduced by the calibration of camera’s interior parameters. The correctness of these methods is supported by the results of some experiments that are given in this paper.
Keywords: Monocular camera;Area of interesting;Symmetry measurement;
论文图表:
引用
No.5072048107957245****
同行评议
共计0人参与
勘误表
基于单目视觉的前方车辆探测方法研究
评论
全部评论0/1000