A SAR Image Classification Algorithm Based on Multi-Feature Polarimetric Parameters Using FOA and LS-SVM

This paper presents a Synthetic Aperture Radar (SAR) image classification algorithm based on multi-feature using Fruit Fly Optimization Algorithm (FOA) and Least Square Support Vector Machine (LS-SVM). First, pixel-based information derived from three elements of coherency matrix, six parameters obt...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Shiyu Luo, Kamal Sarabandi, Ling Tong, Leland Pierce
Formato: article
Lenguaje:EN
Publicado: IEEE 2019
Materias:
FOA
Acceso en línea:https://doaj.org/article/6174aab3b64340b9b6283a7aaa8914a4
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:6174aab3b64340b9b6283a7aaa8914a4
record_format dspace
spelling oai:doaj.org-article:6174aab3b64340b9b6283a7aaa8914a42021-11-19T00:03:17ZA SAR Image Classification Algorithm Based on Multi-Feature Polarimetric Parameters Using FOA and LS-SVM2169-353610.1109/ACCESS.2019.2957547https://doaj.org/article/6174aab3b64340b9b6283a7aaa8914a42019-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/8922629/https://doaj.org/toc/2169-3536This paper presents a Synthetic Aperture Radar (SAR) image classification algorithm based on multi-feature using Fruit Fly Optimization Algorithm (FOA) and Least Square Support Vector Machine (LS-SVM). First, pixel-based information derived from three elements of coherency matrix, six parameters obtained by <inline-formula> <tex-math notation="LaTeX">$H/\alpha /A$ </tex-math></inline-formula> decomposition and Freeman decomposition techniques, and three polarimetric parameters including the total receive power (SPAN), pedestal height, and Radar Vegetation Index (RVI), as well as region-based information derived from eight texture parameters obtained by Grey Level Co-occurrence Matrix (GLCM) are combined to use as the features of land cover. Second, Kernel Principal Component Analysis (KPCA) is used to reduce the dimensionality of the multi-feature data derived from the integration of the pixel-based and region-based information. Third, LS-SVM is used as the classifier in this study due to its fast solving speed and desirable classification capability. Since the input parameters of LS-SVM significantly affect the classification performance, we employ FOA to obtain the optimized input parameters. Finally, the experiments on two fully polarimetric SAR images of various crops with a limited number of samples are implemented by the proposed method and other commonly used methods, respectively. The results show that the proposed method can attain better classification performances compared with other methods.Shiyu LuoKamal SarabandiLing TongLeland PierceIEEEarticlePolarimetric SAR imageclassificationmulti-featureFOAElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 7, Pp 175259-175276 (2019)
institution DOAJ
collection DOAJ
language EN
topic Polarimetric SAR image
classification
multi-feature
FOA
Electrical engineering. Electronics. Nuclear engineering
TK1-9971
spellingShingle Polarimetric SAR image
classification
multi-feature
FOA
Electrical engineering. Electronics. Nuclear engineering
TK1-9971
Shiyu Luo
Kamal Sarabandi
Ling Tong
Leland Pierce
A SAR Image Classification Algorithm Based on Multi-Feature Polarimetric Parameters Using FOA and LS-SVM
description This paper presents a Synthetic Aperture Radar (SAR) image classification algorithm based on multi-feature using Fruit Fly Optimization Algorithm (FOA) and Least Square Support Vector Machine (LS-SVM). First, pixel-based information derived from three elements of coherency matrix, six parameters obtained by <inline-formula> <tex-math notation="LaTeX">$H/\alpha /A$ </tex-math></inline-formula> decomposition and Freeman decomposition techniques, and three polarimetric parameters including the total receive power (SPAN), pedestal height, and Radar Vegetation Index (RVI), as well as region-based information derived from eight texture parameters obtained by Grey Level Co-occurrence Matrix (GLCM) are combined to use as the features of land cover. Second, Kernel Principal Component Analysis (KPCA) is used to reduce the dimensionality of the multi-feature data derived from the integration of the pixel-based and region-based information. Third, LS-SVM is used as the classifier in this study due to its fast solving speed and desirable classification capability. Since the input parameters of LS-SVM significantly affect the classification performance, we employ FOA to obtain the optimized input parameters. Finally, the experiments on two fully polarimetric SAR images of various crops with a limited number of samples are implemented by the proposed method and other commonly used methods, respectively. The results show that the proposed method can attain better classification performances compared with other methods.
format article
author Shiyu Luo
Kamal Sarabandi
Ling Tong
Leland Pierce
author_facet Shiyu Luo
Kamal Sarabandi
Ling Tong
Leland Pierce
author_sort Shiyu Luo
title A SAR Image Classification Algorithm Based on Multi-Feature Polarimetric Parameters Using FOA and LS-SVM
title_short A SAR Image Classification Algorithm Based on Multi-Feature Polarimetric Parameters Using FOA and LS-SVM
title_full A SAR Image Classification Algorithm Based on Multi-Feature Polarimetric Parameters Using FOA and LS-SVM
title_fullStr A SAR Image Classification Algorithm Based on Multi-Feature Polarimetric Parameters Using FOA and LS-SVM
title_full_unstemmed A SAR Image Classification Algorithm Based on Multi-Feature Polarimetric Parameters Using FOA and LS-SVM
title_sort sar image classification algorithm based on multi-feature polarimetric parameters using foa and ls-svm
publisher IEEE
publishDate 2019
url https://doaj.org/article/6174aab3b64340b9b6283a7aaa8914a4
work_keys_str_mv AT shiyuluo asarimageclassificationalgorithmbasedonmultifeaturepolarimetricparametersusingfoaandlssvm
AT kamalsarabandi asarimageclassificationalgorithmbasedonmultifeaturepolarimetricparametersusingfoaandlssvm
AT lingtong asarimageclassificationalgorithmbasedonmultifeaturepolarimetricparametersusingfoaandlssvm
AT lelandpierce asarimageclassificationalgorithmbasedonmultifeaturepolarimetricparametersusingfoaandlssvm
AT shiyuluo sarimageclassificationalgorithmbasedonmultifeaturepolarimetricparametersusingfoaandlssvm
AT kamalsarabandi sarimageclassificationalgorithmbasedonmultifeaturepolarimetricparametersusingfoaandlssvm
AT lingtong sarimageclassificationalgorithmbasedonmultifeaturepolarimetricparametersusingfoaandlssvm
AT lelandpierce sarimageclassificationalgorithmbasedonmultifeaturepolarimetricparametersusingfoaandlssvm
_version_ 1718420670450237440