一种高分辨率影像道路中心线提取算法  

A road centerline extraction algorithm from high resolution satellite imagery

作　　者：苗则朗[1] 史文中[2] 张华[1] 

机构地区：[1]中国矿业大学环境与测绘学院,江苏徐州221116 [2]武汉大学-香港理工大学空间信息联合实验室,香港九龙999077

出　　处：《中国矿业大学学报》2013年第5期887-892,898,共7页Journal of China University of Mining & Technology

基　　金：国家高技术研究发展计划(863)项目(2012AA12A305);国家"十二五"科技支撑计划项目(2012BAJ15B04);国家自然科学基金项目(41201451);江苏高校优势学科建设工程项目(SZBF2011-6-B35)

摘　　要：针对传统道路提取算法欠缺几何特征的考虑以及中心线提取不光滑的问题,提出一种基于形状特征和多元自适应样条回归(MARS)的遥感影像道路中心线提取算法.算法首先改进了传统的长宽比指数,然后利用该指数对遥感影像分割结果进行滤波,提取线性特征;在此基础上,结合光谱特征从线性特征中提取纯净道路段,最后利用多元自适应样条回归算法提取道路中心线.采用Matlab语言编程实现道路提取算法,并采用3幅高分辨率遥感影像对算法进行了验证.试验结果表明:改进后的长宽比指数可以有效地提取线性特征;同时,相比于传统的道路中心线提取算法,利用多元自适应样条回归算法提取的中心线更加光滑.Traditional road extraction methods rarely consider the shape features and thus the extracted centerline is not smooth. To overcome the aforementioned limitations, a new road centerline extraction algorithm from high resolution satellite imagery using shape features and multivariate adaptive regression splines （MARS） is proposed in this paper. The method has three main steps. Firstly, an improved shape feature is developed to filter the segmentation re- sult to extract linear features. The spectral information is then used to extract pure road seg- ments from the linear features. Finally, road centerline is extracted using MARS. The pro- posed method is programmed by Matlab and tested on three high resolution imageries. The ex- perimental results indicate that the improved shape feature can effectively extract linear fea- tures and the smoothness of road centerlines extracted by MARS is higher than that of tradi- tional methods.

关 键 词：形状特征 多元自适应样条 高分辨率影像 道路中心线提取 

分 类 号：TP75[自动化与计算机技术—检测技术与自动化装置]