By Topic

Interactive Spectral Band Discovery for Exploratory Visual Analysis of Satellite Images

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Dragos Bratasanu ; Romanian Space Agency, Bucharest, Romania ; Ion Nedelcu ; Mihai Datcu

This paper advocates an automatic technique to discover the optimum combination of three spectral features of a multispectral satellite image that enhance visualization of learned targets/objects. The method is an application-free, single-click user effort, spectrally and spatially balanced, fast-response, low-cost, information-based feature selector that comes to optimize maybe the most important problem in the computer-assisted work of the human operator: visualization of target areas. The new tools developed to assist image experts in their work need to be tailored to the new products offered by the sub-meter spatial resolution multispectral imaging sensors. The spectral bands of the satellite image are ranked using measures of mutual information-the minimum-redundancy-maximum-relevance mRMR criterion- and the top three are automatically displayed on screen. The evaluation of results is performed in terms of both quality (expert-driven visual analysis) and quantity (color metrics) and shows that this approach can become a powerful tool in support of image analysis operations.

Published in:

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  (Volume:5 ,  Issue: 1 )