Academic Journals Database
Disseminating quality controlled scientific knowledge

IMPROVEMENT OF ANOMALY DETECTION ALGORITHMS IN HYPERSPECTRAL IMAGES USING DISCRETE WAVELET TRANSFORM

ADD TO MY LIST
 
Author(s): Mohsen Zare Baghbidi | Kamal Jamshidi | Ahmad Reza Naghsh Nilchi | Saeid Homayouni

Journal: Signal & Image Processing
ISSN 2229-3922

Volume: 2;
Issue: 4;
Start page: 13;
Date: 2012;
VIEW PDF   PDF DOWNLOAD PDF   Download PDF Original page

Keywords: Hyperspectral Remote Sensing | Anomaly Detection | Discrete Wavelet Transform | ROC Curve | RX.

ABSTRACT
Recently anomaly detection (AD) has become an important application for target detection in hyperspectralremotely sensed images. In many applications, in addition to high accuracy of detection we need a fast andreliable algorithm as well. This paper presents a novel method to improve the performance of current ADalgorithms. The proposed method first calculates Discrete Wavelet Transform (DWT) of every pixel vectorof image using Daubechies4 wavelet. Then, AD algorithm performs on four bands of “Wavelet transform”matrix which are the approximation of main image. In this research some benchmark AD algorithmsincluding Local RX, DWRX and DWEST have been implemented on Airborne Visible/Infrared ImagingSpectrometer (AVIRIS) hyperspectral datasets. Experimental results demonstrate significant improvementof runtime in proposed method. In addition, this method improves the accuracy of AD algorithms becauseof DWT’s power in extracting approximation coefficients of signal, which contain the main behaviour ofsignal, and abandon the redundant information in hyperspectral image data.
Why do you need a reservation system?      Affiliate Program