Supervised machine learning of fused RADAR and optical data for land cover classification

Guido Cervone; Barry N. Haack

doi:10.1117/1.JRS.6.063597

30 October 2012 Supervised machine learning of fused RADAR and optical data for land cover classification

Guido Cervone, Barry N. Haack

Author Affiliations +

Journal of Applied Remote Sensing, Vol. 6, Issue 1, 063597 (October 2012). https://doi.org/10.1117/1.JRS.6.063597

Abstract

Supervised machine learning algorithms are used to classify pixels of a multi-sensor remote sensing dataset comprising RADAR and optical measurements for central Sudan. A total of 19 layers were used, 16 RADAR bands from RADARSAT DN, and texture bands acquired on 13 December 2008 (dry season) and on 2 June 2009 (wet season), and three optical bands acquired by Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) on 25 February 2009. Three different machine learning supervised classification algorithms were used to test the advantage of combining RADAR and optical data: a decision rule, a decision tree, and a naive Bayesian. In all the experiments performed, a combination of RADAR and optical bands leads to higher predictive accuracy and better land cover classification than either sensor used independently. The decision rule classifier performed best among the three methods used.

Citation Download Citation

Guido Cervone and Barry N. Haack "Supervised machine learning of fused RADAR and optical data for land cover classification," Journal of Applied Remote Sensing 6(1), 063597 (30 October 2012). https://doi.org/10.1117/1.JRS.6.063597

Published: 30 October 2012

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available