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

Title: Polarimetric SAR Image Terrain Classification

Abstract

In practical applications of automated terrain classification from high-resolution polarimetric synthetic aperture radar (PolSAR) imagery, different terrain types may inherently contain a high level of internal variability, as when a broadly defined class (e.g., “trees”) contains elements arising from multiple subclasses (pine, oak, and willow). In addition, real-world factors such as the time of year of a collection, the moisture content of the scene, the imaging geometry, and the radar system parameters can all increase the variability observed within each class. Such variability challenges the ability of classifiers to maintain a high level of sensitivity in recognizing diverse elements that are within-class, without sacrificing their selectivity in rejecting out-of-class elements. In an effort to gauge the degree to which classifiers respond robustly in the presence of intraclass variability and generalize to untrained scenes and conditions, here we compare the performance of a suite of classifiers across six broad terrain categories from a large set of polarimetric synthetic aperture radar (PolSAR) image sets. The main contributions of this article are as follows: 1) an analysis of the robustness of a variety of current state-of-the art classification algorithms to intraclass variability found in PolSAR image sets, and 2) the associated PolSAR imagemore » and feature data that Sandia is releasing to the research community with this publication. The analysis of the classification algorithms we provide will serve as a benchmark of performance for the future PolSAR terrain classification algorithm research and development enabled by the image sets and data provided. By sharing our analysis and high-resolution fully polarimetric Sandia data with the research community, we enable others to develop and assess a new generation of robust terrain classification algorithms for PolSAR.« less

Authors:
ORCiD logo [1];  [2]; ORCiD logo [1]; ORCiD logo [1];  [3];  [1]
  1. Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
  2. Sandia National Lab. (SNL-CA), Livermore, CA (United States)
  3. Amazon.com Inc., Seattle, WA (United States)
Publication Date:
Research Org.:
Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Sandia National Lab. (SNL-CA), Livermore, CA (United States)
Sponsoring Org.:
USDOE National Nuclear Security Administration (NNSA)
OSTI Identifier:
1697988
Report Number(s):
SAND-2019-12177J
Journal ID: ISSN 1939-1404; 680205
Grant/Contract Number:  
AC04-94AL85000; NA0003525
Resource Type:
Accepted Manuscript
Journal Name:
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Additional Journal Information:
Journal Volume: 12; Journal Issue: 11; Journal ID: ISSN 1939-1404
Publisher:
IEEE
Country of Publication:
United States
Language:
English
Subject:
42 ENGINEERING; polarimetric SAR (PolSAR); machine learning; wishart; terrain classification

Citation Formats

West, R. Derek, LaBruyere III, Thomas E., Skryzalin, Jacek, Simonson, Katherine M., Hansen, Ross L., and Van Benthem, Mark H.. Polarimetric SAR Image Terrain Classification. United States: N. p., 2019. Web. https://doi.org/10.1109/jstars.2019.2946768.
West, R. Derek, LaBruyere III, Thomas E., Skryzalin, Jacek, Simonson, Katherine M., Hansen, Ross L., & Van Benthem, Mark H.. Polarimetric SAR Image Terrain Classification. United States. https://doi.org/10.1109/jstars.2019.2946768
West, R. Derek, LaBruyere III, Thomas E., Skryzalin, Jacek, Simonson, Katherine M., Hansen, Ross L., and Van Benthem, Mark H.. Wed . "Polarimetric SAR Image Terrain Classification". United States. https://doi.org/10.1109/jstars.2019.2946768. https://www.osti.gov/servlets/purl/1697988.
@article{osti_1697988,
title = {Polarimetric SAR Image Terrain Classification},
author = {West, R. Derek and LaBruyere III, Thomas E. and Skryzalin, Jacek and Simonson, Katherine M. and Hansen, Ross L. and Van Benthem, Mark H.},
abstractNote = {In practical applications of automated terrain classification from high-resolution polarimetric synthetic aperture radar (PolSAR) imagery, different terrain types may inherently contain a high level of internal variability, as when a broadly defined class (e.g., “trees”) contains elements arising from multiple subclasses (pine, oak, and willow). In addition, real-world factors such as the time of year of a collection, the moisture content of the scene, the imaging geometry, and the radar system parameters can all increase the variability observed within each class. Such variability challenges the ability of classifiers to maintain a high level of sensitivity in recognizing diverse elements that are within-class, without sacrificing their selectivity in rejecting out-of-class elements. In an effort to gauge the degree to which classifiers respond robustly in the presence of intraclass variability and generalize to untrained scenes and conditions, here we compare the performance of a suite of classifiers across six broad terrain categories from a large set of polarimetric synthetic aperture radar (PolSAR) image sets. The main contributions of this article are as follows: 1) an analysis of the robustness of a variety of current state-of-the art classification algorithms to intraclass variability found in PolSAR image sets, and 2) the associated PolSAR image and feature data that Sandia is releasing to the research community with this publication. The analysis of the classification algorithms we provide will serve as a benchmark of performance for the future PolSAR terrain classification algorithm research and development enabled by the image sets and data provided. By sharing our analysis and high-resolution fully polarimetric Sandia data with the research community, we enable others to develop and assess a new generation of robust terrain classification algorithms for PolSAR.},
doi = {10.1109/jstars.2019.2946768},
journal = {IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing},
number = 11,
volume = 12,
place = {United States},
year = {2019},
month = {11}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Save / Share: