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

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.