A Learning-Based Resegmentation Method for Extraction of Buildings in Satellite Images

被引：16

作者：

Dikmen, Mehmet ^{[1
]}

Halici, Ugur ^{[2
]}

机构：

[1] Baskent Univ, Dept Comp Engn, TR-06810 Ankara, Turkey

[2] Middle E Tech Univ, Dept Elect & Elect Engn, TR-06800 Ankara, Turkey

来源：

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS | 2014年 / 11卷 / 12期

关键词：

Building extraction; feature extraction; image classification; image segmentation; remote sensing; satellite images;

D O I：

10.1109/LGRS.2014.2321658

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 introduces a new method for building extraction in satellite images. The algorithm first identifies the shadow segments on an oversegmented image, and then neighboring shadow segments, which are assumed to be cast by a single building, are merged. Next, candidate regions where buildings most likely occur are detected by using these shadow regions. Along with this information, closeness to shadows in illumination direction and spectral properties of segments are used to classify them as belonging to a "building" or not. Then, a resegmentation is performed by merging only the neighboring segments, which are classified as building. Finally, postprocessing is performed to eliminate some false building segments. The approach was tested on several Google Earth images, and the results are found to be promising.

引用

页码：2150 / 2153

页数：4

共 17 条

[11]

Liu ZJ, 2005, INT GEOSCI REMOTE SE, P2250

[12] Improved rooftop detection in aerial images with machine learning [J].

Maloof, MA ;

Langley, P ;

Binford, TO ;

Nevatia, R ;

Sage, S .

MACHINE LEARNING, 2003, 53 (1-2) :157-191

[13] SUPERVISED RE-SEGMENTATION FOR VERY HIGH-RESOLUTION SATELLITE IMAGES [J].

Michel, J. ;

Grizonnet, M. ;

Canevet, O. .

2012 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS), 2012, :68-71

[14] THRESHOLD SELECTION METHOD FROM GRAY-LEVEL HISTOGRAMS [J].

OTSU, N .

IEEE TRANSACTIONS ON SYSTEMS MAN AND CYBERNETICS, 1979, 9 (01) :62-66

[15] Assessment of different topographic corrections in Landsat-TM data for mapping vegetation types (2003) [J].

Riaño, D ;

Chuvieco, E ;

Salas, J ;

Aguado, I .

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2003, 41 (05) :1056-1061

[16]

Sirmacek B., 2008, P INT COMP INF SCI S

[17]

Wei YF, 2004, INT GEOSCI REMOTE SE, P2008

← 1 2 →