Comparison of Target Detection Performance for Radiance and Reflectance Domain in VNIR Hyperspectral Images
No Thumbnail Available
Date
2019
Authors
Güneş, Ahmet
Gunes,A.
Esin,Y.E.
Demirel,B.
Ozturk,S.
Journal Title
Journal ISSN
Volume Title
Publisher
Institute of Electrical and Electronics Engineers Inc.
Open Access Color
OpenAIRE Downloads
OpenAIRE Views
Abstract
In this paper, the hyperspectral detection of targets in visible-near infrared (VNIR) images is studied. The change of radiance domain signatures in images taken in different locations, time and altitudes are analyzed. A new radiance domain detection scheme for VNIR images under 1000 m altitude is proposed. The analysis shows that the radiance domain signatures of each target, that are collected from an image taken at 10 m altitude, can be effectively used for pure pixel target detection in other VNIR images taken at altitudes between 10 - 1000 m. The proposed approach is tested using several target types and on images taken at different altitudes and environmental conditions. Our results show that target detection in radiance domain provides a cheaper, easier and effective alternative to reflectance domain, in VNIR images. © 2019 IEEE.
Description
The Institute of Electrical and Electronics Engineers, Geoscience and Remote Sensing Society (GRSS)
Keywords
Hyperspectral image processing, pure pixel., radiance domain, reflectance domain, target detection
Turkish CoHE Thesis Center URL
Fields of Science
Citation
1
WoS Q
Scopus Q
Source
International Geoscience and Remote Sensing Symposium (IGARSS) -- 39th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2019 -- 28 July 2019 through 2 August 2019 -- Yokohama -- 154792
Volume
Issue
Start Page
2186
End Page
2189