An automatic method of building extraction from high resolution satellite images

Xianwei Han; Yili Fu; Zhiqiang Qin; Kun Xing

doi:10.1117/12.832599

30 October 2009 An automatic method of building extraction from high resolution satellite images

Xianwei Han, Yili Fu, Zhiqiang Qin, Kun Xing

Author Affiliations +

Proceedings Volume 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis; 749540 (2009) https://doi.org/10.1117/12.832599
Event: Sixth International Symposium on Multispectral Image Processing and Pattern Recognition, 2009, Yichang, China

Abstract

In this paper, we propose a novel framework of building extraction from high resolution satellite remote sensing images. This approach combines regional information with edge features, which could avoid the limitations of traditional methods. Firstly, the irrelevant regions are filtered out from large images by extracting texture features, leaving buildings distributed in the remaining urban areas. Secondly, boundaries of objects are extracted and all the contours are tracked through the chain code method we developed. Finally, the short straight lines are linked to construct contours and extract rectangular building rooftops. Experiments show that this extraction strategy is robust and effective.

Citation Download Citation

Xianwei Han, Yili Fu, Zhiqiang Qin, and Kun Xing "An automatic method of building extraction from high resolution satellite images", Proc. SPIE 7495, MIPPR 2009: Automatic Target Recognition and Image Analysis, 749540 (30 October 2009); https://doi.org/10.1117/12.832599

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE