A method of building information extraction based on mathematical morphology and multiscale

Jing-wen Li; Ke Wang; Zi-ping Zhang; Long-li Xue; Shou-qiang Yin; Song Zhou

doi:10.1117/12.2207657

9 December 2015 A method of building information extraction based on mathematical morphology and multiscale

Jing-wen Li, Ke Wang, Zi-ping Zhang, Long-li Xue, Shou-qiang Yin, Song Zhou

Proceedings Volume 9808, International Conference on Intelligent Earth Observing and Applications 2015; 98082S (2015) https://doi.org/10.1117/12.2207657
Event: International Conference on Intelligent Earth Observing and Applications, 2015, Guilin, China

Abstract

In view of monitoring the changes of buildings on Earth's surface ,by analyzing the distribution characteristics of building in remote sensing image, combined with multi-scale in image segmentation and the advantages of mathematical morphology, this paper proposes a multi-scale combined with mathematical morphology of high resolution remote sensing image segmentation method, and uses the multiple fuzzy classification method and the shadow of auxiliary method to extract information building, With the comparison of k-means classification, and the traditional maximum likelihood classification method, the results of experiment object based on multi-scale combined with mathematical morphology of image segmentation and extraction method, can accurately extract the structure of the information is more clear classification data, provide the basis for the intelligent monitoring of earth data and theoretical support.

Citation Download Citation

Jing-wen Li, Ke Wang, Zi-ping Zhang, Long-li Xue, Shou-qiang Yin, and Song Zhou "A method of building information extraction based on mathematical morphology and multiscale", Proc. SPIE 9808, International Conference on Intelligent Earth Observing and Applications 2015, 98082S (9 December 2015); https://doi.org/10.1117/12.2207657

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

Includes PDF, HTML & Video, when available