Share Email Print
cover

Proceedings Paper

Classification of high spatial resolution remote sensing image using SVM and local spatial statistics Getis-Ord Gi
Author(s): Xinming Wang; Xin Chen; Maolin Li
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

In this paper, the support vector machine (SVM) algorithm was utilized to tackle the classification of high resolution images from airborne digital sensor systems. Firstly, the original image was classified using SVM of four common types of kernel functions, namely linear, polynomial, RBF and sigmoid function, and the SVM with RBF kernel function can achieve the most satisfactory result. On the other hand, Getis-Ord Gi, one type of local spatial statistics, had been calculated with varying lags from 1 to 10. When classifying Gi image with lag of 3 using SVM of the RBF kernel function, an overall accuracy of 95.66% was achieved, which is more satisfactory than the result from the original image. The result shows that Gi images with lags less than the variogram range can be used instead of the original multi-spectral image to improve classification accuracy between features with similar spectral characteristics like trees and lawns, as a result, to increase the overall classification accuracy.

Paper Details

Date Published: 23 November 2011
PDF: 6 pages
Proc. SPIE 8006, MIPPR 2011: Remote Sensing Image Processing, Geographic Information Systems, and Other Applications, 80060N (23 November 2011); doi: 10.1117/12.901810
Show Author Affiliations
Xinming Wang, Science and Technology on Information Systems Engineering Lab. (China)
Xin Chen, Nanjing Univ. of Science and Technology (China)
Maolin Li, Science and Technology on Information Systems Engineering Lab. (China)


Published in SPIE Proceedings Vol. 8006:
MIPPR 2011: Remote Sensing Image Processing, Geographic Information Systems, and Other Applications
Faxiong Zhang; Faxiong Zhang, Editor(s)

© SPIE. Terms of Use
Back to Top