Earthquake-induced damage classification from postearthquake satellite image using spectral and spatial features with support vector selection and adaptation

Gulsen Taskin; Okan K. Ersoy; Mustafa E. Kamasak

doi:10.1117/1.JRS.9.096017

20 August 2015 Earthquake-induced damage classification from postearthquake satellite image using spectral and spatial features with support vector selection and adaptation

Gulsen Taskin, Okan K. Ersoy, Mustafa E. Kamasak

Author Affiliations +

Journal of Applied Remote Sensing, Vol. 9, Issue 1, 096017 (August 2015). https://doi.org/10.1117/1.JRS.9.096017

Abstract

For more accurate classification of earthquake-induced damaged regions, a high-resolution satellite image is required to extract textural and spatial features of the damage. In addition to using textural features, spectral features may improve the identification of the damaged regions. Earthquake-induced damage that occurred in the city of Bam in Iran was identified by a nonparametric and nonlinear classifier called support vector selection and adaptation (SVSA) using both the textural and the spectral features. SVSA can achieve the performance of nonlinear support vector machines (NSVM) without the need for a kernel function. Our aim is to show the effectiveness of the SVSA algorithm compared with the linear support vector machines, NSVM, and K-nearest neighbor (KNN) methods in terms of classification accuracy when using the textural features. A nonparametric weighted feature extraction was also implemented before the classification in order to increase the classification accuracy further by assigning a different weight to the textural feature. The results indicate that SVSA is significantly better than the linear SVM (LSVM) and KNN classifiers, and it is quite competitive with NSVM in terms of damage detection accuracy.

Citation Download Citation

Gulsen Taskin, Okan K. Ersoy, and Mustafa E. Kamasak "Earthquake-induced damage classification from postearthquake satellite image using spectral and spatial features with support vector selection and adaptation," Journal of Applied Remote Sensing 9(1), 096017 (20 August 2015). https://doi.org/10.1117/1.JRS.9.096017

Published: 20 August 2015

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