Multiple Saliency Features Based Automatic Road Extraction from High-Resolution Multispectral Satellite Images

被引:17
作者
Zhang Jing [1 ,4 ]
Chen Lu [1 ]
Zhuo Li [1 ,3 ]
Geng Wenhao [2 ]
Wang Chao [2 ]
机构
[1] Beijing Univ Technol, Signal & Informat Proc Lab, Beijing 100124, Peoples R China
[2] Beijing Univ Technol, Coll Elect Informat & Control Engn, Signal & Informat Proc Lab, Beijing 100124, Peoples R China
[3] Collaborat Innovat Ctr Elect Vehicles Beijing, Beijing 100124, Peoples R China
[4] Univ Texas San Antonio, Dept Comp Sci, San Antonio, TX USA
基金
中国国家自然科学基金;
关键词
High-resolution multispectral satellite images; Road extraction; Multiple saliency features; Road network;
D O I
10.1049/cje.2017.11.008
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Roads as important artificial objects are the main body of modern traffic system, which provide many conveniences for human civilization. With the development of remote sensing and hyperspectral imaging technology, how to automatically and accurately extract road network from high-resolution multispectral satellite images has become a hot and challenging research topic of geographic information technology. In this paper, an automatic road extraction method from high-resolution multispectral satellite images is proposed by using multiple saliency features. Firstly, road edge is extracted by detecting local linear edge with Singular value decomposition (SVD). Secondly, road regions are constructed by K-means clustering after extracting the feature of background difference. Then road network is achieved by integrating multiple saliency features with Total variation (TV) based image fusion algorithm. Finally, the non-road parts and noises are removed from road network by optimizing multiple salient features with post-processing and morphological operations. The experimental results show that the proposed method can achieve a superior performance in completeness and correctness.
引用
收藏
页码:133 / 139
页数:7
相关论文
共 20 条
[1]   Automatic Road Extraction From Remote Sensing Images Based on a Normalized Second Derivative Map [J].
Bae, Yoonsung ;
Lee, Won-Hee ;
Choi, Yunjun ;
Jeon, Young Woo ;
Ra, Jong Beom .
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2015, 12 (09) :1858-1862
[2]   Use of Salient Features for the Design of a Multistage Framework to Extract Roads From High-Resolution Multispectral Satellite Images [J].
Das, Sukhendu ;
Mirnalinee, T. T. ;
Varghese, Koshy .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2011, 49 (10) :3906-3931
[3]  
Heipke C., 1997, International Archives of Photogrammetry and Remote Sensing, V32, P151
[4]   A model of saliency-based visual attention for rapid scene analysis [J].
Itti, L ;
Koch, C ;
Niebur, E .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1998, 20 (11) :1254-1259
[5]  
Kumar Mrityunjay, 2010, Proceedings of the 2010 IEEE Workshop on Signal Processing Systems (SiPS 2010), P25, DOI 10.1109/SIPS.2010.5624819
[6]  
Li R. S., 2014, COMPUT SYST APPL, V23, P114
[7]  
Luc C., 2011, INT WORKSH PATT REC, P3906
[8]  
Maurya R., 2011, P INT C IM INF PROC, P1, DOI [10.1109/ICIIP.2011.6108839, DOI 10.1109/ICIIP.2011.6108839]
[9]   Integration of Region and Edge-based information for efficient Road Extraction from High Resolution Satellite Imagery [J].
Mirnalinee, T. T. ;
Das, Sukhendu ;
Varghese, Koshy .
ICAPR 2009: SEVENTH INTERNATIONAL CONFERENCE ON ADVANCES IN PATTERN RECOGNITION, PROCEEDINGS, 2009, :373-376
[10]  
Paralic M, 2012, 2012 35TH INTERNATIONAL CONFERENCE ON TELECOMMUNICATIONS AND SIGNAL PROCESSING (TSP), P706, DOI 10.1109/TSP.2012.6256388