华中科技大学学报：自然科学版2012，Vol.40Issue(3)：9-12,4.
基于NSCT与形状特征的遥感影像道路提取
Road extraction from remote sensing images based on NSCT and shape features
摘要
Abstract
An algorithm for road extraction from remote sensing images based on the NSCT（nonsubsampled Contourlet transform） and shape features was proposed.Firstly,the coefficients in different scales and different directions were obtained by NSCT,which were enhanced and used to construct the enhanced image by the inverse transformation.Then the enhanced image was segmented,and the roads were extracted by using several object shape features.Finally,the extracted roads were judged by spectral feature and regulated by mathematical morphology.The experiments show the proposed method has a better effect on the high-resolution remote sensing images.关键词
图像增强/图像分割/遥感影像/非抽样Contourlet变换/形状特征/道路提取Key words
image enhancement/image segmentation/remote sensing images/NSCT(nonsubsampled Contourlet transform)/shape features/road extraction分类
电子信息工程引用本文复制引用
梁栋,刘书丽,颜普,鲍文霞..基于NSCT与形状特征的遥感影像道路提取[J].华中科技大学学报：自然科学版,2012,40(3):9-12,4.基金项目
国家自然科学基金资助项目（61172127 （）
11071002） （）
安徽大学博士科研启动经费资助项目 （）
安徽大学青年骨干教师培养经费资助项目 （）
