Wavelet transform based land cover classification of hyperspectral images

Author

Kavitha, K. ; Nivedha, P. ; Arivazhagan, S. ; Palniladevi, P.

Author_Institution

Dept. of ECE, Mepco Schlenk Eng. Coll., Sivakasi, India

fYear

2014

Firstpage

109

Lastpage

112

Abstract

This paper aims at the wavelet transform based algorithm for landcover classification of Hyperspectral remote sensing images using Support Vector Machines (SVM). In this paper Feature Extraction and Hyperspectral pixel classification are done based on Discrete Wavelet Transform (DWT) features which includes the Statistical Features and the Gray Level Co-occurrence Features. The experiment is performed on a hyperspectral dataset acquired from ROSIS sensor and the experimental results indicate that it provides an Overall accuracy of about 98.28%. When compared to the other methods, the wavelet transform based method increases the overall classification accuracy.

Keywords

feature extraction; geophysical image processing; hyperspectral imaging; land cover; remote sensing; vegetation; wavelet transforms; DWT features; ROSIS sensor-acquired hyperspectral dataset; SVM-based land cover classification; discrete wavelet transform; feature extraction; gray level co-occurrence features; hyperspectral images; hyperspectral pixel classification; hyperspectral remote sensing images; land cover classification accuracy; statistical features; support vector machines; wavelet transform based algorithm; wavelet transform based land cover classification; wavelet transform based method; Accuracy; Hyperspectral imaging; Support vector machines; Wavelet transforms; Feature Extraction; Hyperspectral Image; Support Vector Machines; Wavelet Decomposition;

fLanguage

English

Publisher

ieee

Conference_Titel

Communication and Network Technologies (ICCNT), 2014 International Conference on

Print_ISBN

978-1-4799-6265-5

Type

conf

DOI

10.1109/CNT.2014.7062735

Filename

7062735