Comparison of Target Detection Performance for Radiance and Reflectance Domain in VNIR Hyperspectral Images

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 p...

Full description

Saved in:
Bibliographic Details
Main Authors: Ozdil, Omer, Gunes, Ahmet, Esin, Yunus Emre, Demirel, Berkan, Ozturk, Safak
Format: Conference Proceeding
Language:English
Subjects:
Atmospheric measurements
Atmospheric modeling
Atmospheric waves
Hyperspectral image processing
Hyperspectral imaging
Libraries
Object detection
pure pixel
radiance domain
reflectance domain
target detection
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2153-7003
DOI:10.1109/IGARSS.2019.8899139