skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Application of neural networks for sea ice classification in polarimetric SAR images

Abstract

Classification of sea ice types using polarimetric radar is an area of considerable current interest and research. Several automatic methods have been developed to classify sea ice types from fully polarimetric synthetic aperture radar (SAR) images, and these techniques are generally grouped into supervised and unsupervised approaches. In previous work, supervised methods have been shown to yield higher accuracy than unsupervised techniques, but suffer from the need for human interaction to determine classes and training regions. In contrast, unsupervised methods determine classes automatically, but generally show limited ability to accurately divide terrain into natural classes. In this paper, a new classification technique is applied to determine sea ice types in polarimetric and multifrequency SAR images, utilizing an unsupervised neural network to provide automatic classification, and employing an iterative algorithm to improve the performance.

Authors:
; ; ;  [1]; ;  [2]
  1. Massachusetts Inst. of Tech., Cambridge, MA (United States)
  2. California Inst. of Tech., Pasadena, CA (United States). Jet Propulsion Lab.
Publication Date:
OSTI Identifier:
137129
Resource Type:
Journal Article
Journal Name:
IEEE Transactions on Geoscience and Remote Sensing
Additional Journal Information:
Journal Volume: 33; Journal Issue: 3; Other Information: PBD: May 1995
Country of Publication:
United States
Language:
English
Subject:
44 INSTRUMENTATION, INCLUDING NUCLEAR AND PARTICLE DETECTORS; 54 ENVIRONMENTAL SCIENCES; 58 GEOSCIENCES; ICE; CLASSIFICATION; REMOTE SENSING; POLAR REGIONS; SYNTHETIC-APERTURE RADAR; IMAGE PROCESSING; NEURAL NETWORKS

Citation Formats

Hara, Yoshihisa, Atkins, R G, Shin, R T, Kong, J A, Yueh, S H, and Kwok, R. Application of neural networks for sea ice classification in polarimetric SAR images. United States: N. p., 1995. Web. doi:10.1109/36.387589.
Hara, Yoshihisa, Atkins, R G, Shin, R T, Kong, J A, Yueh, S H, & Kwok, R. Application of neural networks for sea ice classification in polarimetric SAR images. United States. doi:10.1109/36.387589.
Hara, Yoshihisa, Atkins, R G, Shin, R T, Kong, J A, Yueh, S H, and Kwok, R. Mon . "Application of neural networks for sea ice classification in polarimetric SAR images". United States. doi:10.1109/36.387589.
@article{osti_137129,
title = {Application of neural networks for sea ice classification in polarimetric SAR images},
author = {Hara, Yoshihisa and Atkins, R G and Shin, R T and Kong, J A and Yueh, S H and Kwok, R},
abstractNote = {Classification of sea ice types using polarimetric radar is an area of considerable current interest and research. Several automatic methods have been developed to classify sea ice types from fully polarimetric synthetic aperture radar (SAR) images, and these techniques are generally grouped into supervised and unsupervised approaches. In previous work, supervised methods have been shown to yield higher accuracy than unsupervised techniques, but suffer from the need for human interaction to determine classes and training regions. In contrast, unsupervised methods determine classes automatically, but generally show limited ability to accurately divide terrain into natural classes. In this paper, a new classification technique is applied to determine sea ice types in polarimetric and multifrequency SAR images, utilizing an unsupervised neural network to provide automatic classification, and employing an iterative algorithm to improve the performance.},
doi = {10.1109/36.387589},
journal = {IEEE Transactions on Geoscience and Remote Sensing},
number = 3,
volume = 33,
place = {United States},
year = {1995},
month = {5}
}