一种基于几何约束的轨道提取方法研究  

Geometry Constraints-based Method for Visual Rail Track Extraction

作　　者：王忠立[1] 蔡伯根[1] 

机构地区：[1]北京交通大学电子信息工程学院,北京100044

出　　处：《交通运输系统工程与信息》2017年第6期56-62,84,共8页Journal of Transportation Systems Engineering and Information Technology

基　　金：国家自然科学基金;国家科技支撑计划项目;中央高校基本科研业务费专项资金~~

摘　　要：针对基于Hough变换或螺旋曲线模型的视觉轨道检测方法存在的不足,本文提出了一种基于几何约束的轨道提取方法.该方法利用摄像机和轨道平面之间的成像关系近似满足单因矩阵的特点,利用逆透视映射(IPM)将输入图像转换为Bird-view图像,并采用一种改进的边缘检测方法进行边缘检测.然后将二值化的边缘图像在垂直方向上分割为多个区段,在每个区段上,利用先验知识生成的系列模板图像,对分段IPM图像进行去噪处理和Chamfer距离变换后进行距离匹配检测,将轨道检测转换为一个二维匹配搜索过程.在分段检测结果的基础上,进一步利用曲线拟合得到边缘图像中完整的轨道曲线方程.该曲线方程通过已知的单因矩阵转换为原始图像中的曲线描述,实现在原始图像中的检测和定位.实验验证了所提方法的可行性和可靠性.This paper introduces an approach that extracts rail track by matching the edge features of the real image to the candidate rail patterns which is parameterically modeled, and the geometric constraints of the rail pattern are taken into consideration during the pattern generation. To address the challenge posed by the open environment, we assume the top surfaces of the pair rails are located in a virtual plane, and a homography matrix can be used to describe the geometry relationship between the virtual plane and the camera image plane. Then based on inverse projective mapping（IPM）, the whole image is divided into several sections along the vertical direction. In each section, the rail pair can be approximated by two parallel line segmentations. Based on the prior geometric constraints, candidate rail patterns are generated and the rail track recognition is modeled as a 2D searching process. Some prior knowledge is used for robust detection.The rail track extraction in the whole IPM image is obtained by integrating the results of each section.During this integration stage, a curve fitting is applied and statistics of some parameters, such as the direction and position of the line segments can be adopted to remove the noise results from each section. The fitting curve is converted back to the original grey image. Experiments with on-site image show the performance of the proposed approach.

关 键 词：铁路运输 视觉检测 逆透视映射 轨道提取 单应矩阵 Chamfer距离变换 

分 类 号：U268.6[机械工程—车辆工程]