基于非抽样Contourlet变换的遥感影像道路提取  

Road extraction from remote sensing images based on nonsubsampled contourlet transform

作　　者：刘书丽[1] 梁栋[1] 颜普[1] 鲍文霞[1] 程志友[1] 

机构地区：[1]安徽大学电子信息工程学院,安徽合肥230039

出　　处：《安徽大学学报（自然科学版）》2012年第3期54-59,共6页Journal of Anhui University(Natural Science Edition)

基　　金：国家自然科学基金资助项目(61172127;11071002)

摘　　要：提出一种基于非抽样Contourlet变换的遥感影像道路提取算法.该算法首先对图像进行非抽样Contourlet变换得到不同尺度不同方向上的变换系数,再通过给定窗口大小分别计算各个尺度各个方向上的变换系数模在窗口内的局部最大值,然后比较各尺度在同一方向和同一窗口位置上系数模的最大值,取值最大的点作为特征点;同时利用自适应阈值对各个尺度各个方向上的系数模值进行二值化,消除小于一定面积的区域,筛选出特征点位于提取区域内的点;最后以筛选出的特征点为种子点,对道路进行Snake跟踪.实验结果表明:该文算法在道路提取的精确度、完整性方面比小波变换好.A new algorithm for road extraction from remote sensing images was proposed based on nonsubsampled contourlet transform （NSCT）. Firstly, the coefficients in different scales and different directions were obtained by decomposition using the nonsubsampled contourlet transform. Then, the maximum module within certain limit area of different scales and different directions was calculated, the adaptive threshold to make the coefficients module binaryzation was used and the small areas, were deleted Further, the points of the maximum module were extracted if they were located in the extraction areas. Finally, the result could be achieved by Snake tracing. Experimental results demonstrated that our algorithm outperformed other algorithms such as Gabor wavelet in accuracy and completeness.

关 键 词：非抽样CONTOURLET变换 特征点选取 区域选取 道路提取 Snake跟踪 

分 类 号：TP79[自动化与计算机技术—检测技术与自动化装置]