Share Email Print
cover

Proceedings Paper

Vector tunnel algorithm for hyperspectral target detection
Author(s): S. Demirci; I. Erer; O. Ersoy
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

In this study, targets and nontargets in a hyperspectral image are characterized in terms of their spectral features. Target detection problem is considered as a two-class classification problem. For this purpose, a vector tunnel algorithm (VTA) is proposed. The vector tunnel is characterized only by the target class information. Then, this method is compared with Euclidean Distance (ED), Spectral Angle Map (SAM) and Support Vector Machine (SVM) algorithms. To obtain the training data belonging to target class, the training regions are selected randomly. After determination of the parameters of the algorithms with the training set, detection procedures are accomplished at each pixel as target or background. Consequently, detection results are displayed as thematic maps. The algorithms are trained with the same training sets, and their comparative performances are tested under various cases. During these studies, various levels of thresholds are evaluated based on the efficiency of the algorithms by means of Receiver Operating Characteristic Curves (ROC) as well as visually.

Paper Details

Date Published: 13 June 2014
PDF: 10 pages
Proc. SPIE 9088, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XX, 90880D (13 June 2014); doi: 10.1117/12.2053540
Show Author Affiliations
S. Demirci, Turkish Air Force Academy (Turkey)
I. Erer, Istanbul Technical Univ. (Turkey)
O. Ersoy, Purdue Univ. (United States)


Published in SPIE Proceedings Vol. 9088:
Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XX
Miguel Velez-Reyes; Fred A. Kruse, Editor(s)

© SPIE. Terms of Use
Back to Top