A new clustering algorithm applicable to multispectral and polarimetric SAR images

The authors applied 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, a 12-dimensional feature vector for each pixel was extracted from the...

Full description

Saved in:
Bibliographic Details
Published inIEEE transactions on geoscience and remote sensing Vol. 31; no. 3; pp. 634 - 644
Main Authors Wong, Y., Posner, E.C.
Format Journal Article
LanguageEnglish
Published Legacy CDMS IEEE 01.05.1993
Institute of Electrical and Electronics Engineers
Subjects
540210 - Environment, Terrestrial- Basic Studies- (1990-)
990200 - Mathematics & Computers
ALGORITHMS
Calibration
CLASSIFICATION
Classification algorithms
Clustering algorithms
CROPS
Earth Resources And Remote Sensing
Earth sciences
Earth, ocean, space
ENVIRONMENTAL SCIENCES
Exact sciences and technology
GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE
IMAGE PROCESSING
MATHEMATICAL LOGIC
MEASURING INSTRUMENTS
Multidimensional systems
MULTISPECTRAL SCANNERS
Noise cancellation
Partitioning algorithms
PROCESSING
Radiometry
REMOTE SENSING
Scattering
Shape
Soils
Surficial geology
algorithms
multispectral analysis
classification
image analysis
backscattering
agriculture
synthetic aperture radar
land use
algorithm performance
imagery
radiometry
Polarimetry
cluster analysis
Online AccessGet full text

Cover

More Information
Summary:The authors applied 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, a 12-dimensional feature vector for each pixel was extracted from the scattering matrix. The clustering algorithm partitioned 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 its 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.< >
Bibliography:CDMS
Legacy CDMS
ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0196-2892
1558-0644
DOI:10.1109/36.225530