The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Neste artigo, um novo método é proposto para classificação supervisionada de tipos de cobertura do solo usando dados de radar polarimétrico de abertura sintética (SAR). O conceito de parâmetro de similaridade entre duas matrizes de espalhamento é introduzido para caracterizar o mecanismo de espalhamento alvo. Quatro parâmetros de similaridade de cada pixel na imagem são usados para classificação. São os parâmetros de similaridade entre um pixel e um plano, um diédrico, uma hélice e um fio. A potência total recebida de cada pixel também é usada, uma vez que o parâmetro de similaridade é independente dos vãos das matrizes de dispersão alvo. A classificação supervisionada é realizada com base na análise de componentes principais. Esta análise é aplicada a cada conjunto de dados na imagem no espaço de recursos para obter o vetor de transformação de recursos correspondente. O produto interno de dois vetores é usado como medida de distância na classificação. O resultado da classificação do novo esquema é mostrado e comparado com os resultados da análise de componentes principais com outros coeficientes de decomposição, para demonstrar a eficácia dos parâmetros de similaridade.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Junyi XU, Jian YANG, Yingning PENG, Chao WANG, Yuei-An LIOU, "Using Similarity Parameters for Supervised Polarimetric SAR Image Classification" in IEICE TRANSACTIONS on Communications,
vol. E85-B, no. 12, pp. 2934-2942, December 2002, doi: .
Abstract: In this paper, a new method is proposed for supervised classification of ground cover types by using polarimetric synthetic aperture radar (SAR) data. The concept of similarity parameter between two scattering matrices is introduced for characterizing target scattering mechanism. Four similarity parameters of each pixel in image are used for classification. They are the similarity parameters between a pixel and a plane, a dihedral, a helix and a wire. The total received power of each pixel is also used since the similarity parameter is independent of the spans of target scattering matrices. The supervised classification is carried out based on the principal component analysis. This analysis is applied to each data set in image in the feature space for getting the corresponding feature transform vector. The inner product of two vectors is used as a distance measure in classification. The classification result of the new scheme is shown and it is compared to the results of principal component analysis with other decomposition coefficients, to demonstrate the effectiveness of the similarity parameters.
URL: https://global.ieice.org/en_transactions/communications/10.1587/e85-b_12_2934/_p
Copiar
@ARTICLE{e85-b_12_2934,
author={Junyi XU, Jian YANG, Yingning PENG, Chao WANG, Yuei-An LIOU, },
journal={IEICE TRANSACTIONS on Communications},
title={Using Similarity Parameters for Supervised Polarimetric SAR Image Classification},
year={2002},
volume={E85-B},
number={12},
pages={2934-2942},
abstract={In this paper, a new method is proposed for supervised classification of ground cover types by using polarimetric synthetic aperture radar (SAR) data. The concept of similarity parameter between two scattering matrices is introduced for characterizing target scattering mechanism. Four similarity parameters of each pixel in image are used for classification. They are the similarity parameters between a pixel and a plane, a dihedral, a helix and a wire. The total received power of each pixel is also used since the similarity parameter is independent of the spans of target scattering matrices. The supervised classification is carried out based on the principal component analysis. This analysis is applied to each data set in image in the feature space for getting the corresponding feature transform vector. The inner product of two vectors is used as a distance measure in classification. The classification result of the new scheme is shown and it is compared to the results of principal component analysis with other decomposition coefficients, to demonstrate the effectiveness of the similarity parameters.},
keywords={},
doi={},
ISSN={},
month={December},}
Copiar
TY - JOUR
TI - Using Similarity Parameters for Supervised Polarimetric SAR Image Classification
T2 - IEICE TRANSACTIONS on Communications
SP - 2934
EP - 2942
AU - Junyi XU
AU - Jian YANG
AU - Yingning PENG
AU - Chao WANG
AU - Yuei-An LIOU
PY - 2002
DO -
JO - IEICE TRANSACTIONS on Communications
SN -
VL - E85-B
IS - 12
JA - IEICE TRANSACTIONS on Communications
Y1 - December 2002
AB - In this paper, a new method is proposed for supervised classification of ground cover types by using polarimetric synthetic aperture radar (SAR) data. The concept of similarity parameter between two scattering matrices is introduced for characterizing target scattering mechanism. Four similarity parameters of each pixel in image are used for classification. They are the similarity parameters between a pixel and a plane, a dihedral, a helix and a wire. The total received power of each pixel is also used since the similarity parameter is independent of the spans of target scattering matrices. The supervised classification is carried out based on the principal component analysis. This analysis is applied to each data set in image in the feature space for getting the corresponding feature transform vector. The inner product of two vectors is used as a distance measure in classification. The classification result of the new scheme is shown and it is compared to the results of principal component analysis with other decomposition coefficients, to demonstrate the effectiveness of the similarity parameters.
ER -