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

Title: A new clustering algorithm applicable to multispectral and polarimetric SAR images

Abstract

The authors describe an application of a scale-space clustering algorithm to the classification of a multispectral and polarimetric SAR image of an agricultural site. After the initial polarimetric and radiometric calibration and noise cancellation, the authors extracted a 12-dimensional feature vector for each pixel from the scattering matrix. The clustering algorithm was able to partition a set of unlabeled feature vectors from 13 selected sites, each site corresponding to a distinct crop, into 13 clusters without any supervision. The cluster parameters were then used to classify the whole image. The classification map is much less noisy and more accurate than those obtained by hierarchical rules. Starting with every point as a cluster, the algorithm works by melting the system to produce a tree of clusters in the scale space. It can cluster data in any multidimensional space and is insensitive to variability in cluster densities, sizes and ellipsoidal shapes. This algorithm, more powerful than existing ones, may be useful for remote sensing for land use.

Authors:
 [1];  [2]
  1. Lawrence Livermore National Lab., CA (United States). Inst. for Scientific Computing Research
  2. California Inst. of Tech., Pasadena, CA (United States). Dept. of Electrical Engineering
Publication Date:
OSTI Identifier:
7067893
Resource Type:
Journal Article
Journal Name:
IEEE Transactions on Geoscience and Remote Sensing (Institute of Electrical and Electronics Engineers); (United States)
Additional Journal Information:
Journal Volume: 31:3; Journal ID: ISSN 0196-2892
Country of Publication:
United States
Language:
English
Subject:
99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE; 54 ENVIRONMENTAL SCIENCES; CROPS; REMOTE SENSING; IMAGE PROCESSING; ALGORITHMS; CLASSIFICATION; MULTISPECTRAL SCANNERS; MATHEMATICAL LOGIC; MEASURING INSTRUMENTS; PROCESSING; 990200* - Mathematics & Computers; 540210 - Environment, Terrestrial- Basic Studies- (1990-)

Citation Formats

Wong, Y F, and Posner, E C. A new clustering algorithm applicable to multispectral and polarimetric SAR images. United States: N. p., 1993. Web. doi:10.1109/36.225530.
Wong, Y F, & Posner, E C. A new clustering algorithm applicable to multispectral and polarimetric SAR images. United States. doi:10.1109/36.225530.
Wong, Y F, and Posner, E C. Sat . "A new clustering algorithm applicable to multispectral and polarimetric SAR images". United States. doi:10.1109/36.225530.
@article{osti_7067893,
title = {A new clustering algorithm applicable to multispectral and polarimetric SAR images},
author = {Wong, Y F and Posner, E C},
abstractNote = {The authors describe an application of a scale-space clustering algorithm to the classification of a multispectral and polarimetric SAR image of an agricultural site. After the initial polarimetric and radiometric calibration and noise cancellation, the authors extracted a 12-dimensional feature vector for each pixel from the scattering matrix. The clustering algorithm was able to partition a set of unlabeled feature vectors from 13 selected sites, each site corresponding to a distinct crop, into 13 clusters without any supervision. The cluster parameters were then used to classify the whole image. The classification map is much less noisy and more accurate than those obtained by hierarchical rules. Starting with every point as a cluster, the algorithm works by melting the system to produce a tree of clusters in the scale space. It can cluster data in any multidimensional space and is insensitive to variability in cluster densities, sizes and ellipsoidal shapes. This algorithm, more powerful than existing ones, may be useful for remote sensing for land use.},
doi = {10.1109/36.225530},
journal = {IEEE Transactions on Geoscience and Remote Sensing (Institute of Electrical and Electronics Engineers); (United States)},
issn = {0196-2892},
number = ,
volume = 31:3,
place = {United States},
year = {1993},
month = {5}
}