Spectral-Spatial Classification and Shape Features for Urban Road Centerline Extraction

被引：69

作者：

Shi, Wenzhong ^{[1
]}

Miao, Zelang ^{[2
,3
]}

Wang, Qunming ^{[1
]}

Zhang, Hua ^{[3
]}

机构：

[1] Wuhan Univ, Hong Kong Polytech Univ, Joint Res Lab Spatial Informat, Wuhan 430079, Hubei, Peoples R China

[2] Hong Kong Polytech Univ, Dept Land Surveying & Geoinformat, Kowloon, Hong Kong, Peoples R China

[3] China Univ Min & Technol, Sch Environm Sci & Spatial Informat, Xuzhou 221116, Peoples R China

来源：

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS | 2014年 / 11卷 / 04期

基金：

中国国家自然科学基金;

关键词：

High-resolution remotely sensed imagery; local Geary's C; main road extraction; path openings and closings; shape features; spectral-spatial classification; NETWORK; OPENINGS;

D O I：

10.1109/LGRS.2013.2279034

中图分类号：

P3 [地球物理学]; P59 [地球化学];

学科分类号：

0708 ; 070902 ;

摘要：

This letter presents a two-step method for urban main road extraction from high-resolution remotely sensed imagery by integrating spectral-spatial classification and shape features. In the first step, spectral-spatial classification segments the imagery into two classes, i.e., the road class and the nonroad class, using path openings and closings. The local homogeneity of the gray values obtained by local Geary's C is then fused with the road class. In the second step, the road class is refined by using shape features. The experimental results indicated that the proposed method was able to achieve a comparatively good performance in urban main road extraction.

引用

页码：788 / 792

页数：5

共 25 条

[11] Path openings and closings [J].