基于二维Rosin阈值方法的道路裂纹边缘检测  

Edge Detection Based on 2D Rosin Threshold Method in Road Crack Images

作　　者：刘悦 李一兵[1] 谢红[1] 

机构地区：[1]哈尔滨工程大学信息与通信工程学院,黑龙江哈尔滨150001

出　　处：《中国公路学报》2013年第3期70-76,共7页China Journal of Highway and Transport

基　　金：国家重点基础研究发展计划("九七三"计划)项目(61393010101-1)

摘　　要：为了在道路裂纹图像边缘检测时选择准确的区分噪声与边缘阈值,针对一维Rosin算法不能充分利用图像局部结构信息的缺陷,将传统Rosin方法推广至二维,联合Canny边缘检测算法和Rosin算法,利用像素点本身及其邻域的局部结构信息建立图像二维直方图;利用直方图的最高点和最低点构造全角旋转阈值选取平面,以搜索直方图与各阈值平面的空间距离最大值确定阈值点,获得一种自适应的Canny算法中的阈值选取方法。研究结果表明:该算法可对道路裂纹边缘进行有效检测,并扩展Canny算法的应用范围。In order to make an accurate threshold selection to distinguish noise and edge in the road crack images, the traditional Rosin method was extended to 2D by combination of the Canny edge detection algorithm and Rosin algorithm since the traditional one-dimensional Rosin algorithm cannot make full use of local structure information. The pixel itself and its neighboring local structure information were used to establish the 2D histogram of image. Using the peak and the bottom point of histogram to construct the whole angle rotation threshold selection plane and searching the maximum value of space distance between histogram and every threshold plane to determine threshold, this paper developed an adaptive threshold selection method. The results show that this algorithm for the road crack edge detection is effective and the application scope of the Canny algorithm is expanded.

关 键 词：道路工程 路面裂纹 Rosin阈值方法 边缘检测 

分 类 号：U418.6[交通运输工程—道路与铁道工程]