PolSAR-SFCGN: An End-to-End PolSAR Superpixel Fully Convolutional Generation Network

Polarimetric Synthetic Aperture Radar (PolSAR) image classification is one of the most important applications in remote sensing. The impressive superpixel generation approaches can improve the efficiency of the subsequent classification task and restrain the influence of the speckle noise to an exte...

Full description

Saved in:
Bibliographic Details
Main Authors: Mengxuan Zhang, Jingyuan Shi, Long Liu, Wenbo Zhang, Jie Feng, Jin Zhu, Boce Chu
Format: Article
Language:English
Published: MDPI AG 2025-08-01
Series:Remote Sensing
Subjects:
Online Access:https://www.mdpi.com/2072-4292/17/15/2723
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849406168463572992
author Mengxuan Zhang
Jingyuan Shi
Long Liu
Wenbo Zhang
Jie Feng
Jin Zhu
Boce Chu
author_facet Mengxuan Zhang
Jingyuan Shi
Long Liu
Wenbo Zhang
Jie Feng
Jin Zhu
Boce Chu
author_sort Mengxuan Zhang
collection DOAJ
description Polarimetric Synthetic Aperture Radar (PolSAR) image classification is one of the most important applications in remote sensing. The impressive superpixel generation approaches can improve the efficiency of the subsequent classification task and restrain the influence of the speckle noise to an extent. Most of the classical PolSAR superpixel generation approaches use the features extracted manually and even only consider the pseudocolor images. They do not make full use of polarimetric information and do not necessarily lead to good enough superpixels. The deep learning methods can extract effective deep features but they are difficult to combine with superpixel generation to achieve true end-to-end training. Addressing the above issues, this study proposes an end-to-end fully convolutional superpixel generation network for PolSAR images. It integrates the extraction of polarization information features and the generation of PolSAR superpixels into one step. PolSAR superpixels can be generated based on deep polarization feature extraction and need no traditional clustering process. Both the performance and efficiency of generations of PolSAR superpixels can be enhanced effectively. The experimental results on various PolSAR datasets show that the proposed method can achieve impressive superpixel segmentation by fitting the real boundaries of different types of ground objects effectively and efficiently. It can achieve excellent classification performance by connecting a very simple classification network, which is helpful to improve the efficiency of the subsequent PolSAR image classification tasks.
format Article
id doaj-art-35be7a3051334b2f83367a674cc34be0
institution Kabale University
issn 2072-4292
language English
publishDate 2025-08-01
publisher MDPI AG
record_format Article
series Remote Sensing
spelling doaj-art-35be7a3051334b2f83367a674cc34be02025-08-20T03:36:30ZengMDPI AGRemote Sensing2072-42922025-08-011715272310.3390/rs17152723PolSAR-SFCGN: An End-to-End PolSAR Superpixel Fully Convolutional Generation NetworkMengxuan Zhang0Jingyuan Shi1Long Liu2Wenbo Zhang3Jie Feng4Jin Zhu5Boce Chu6Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi’an 710071, ChinaKey Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi’an 710071, ChinaSchool of Engineering, Xidian University, Xi’an 710071, ChinaSchool of Engineering, Xidian University, Xi’an 710071, ChinaKey Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, School of Artificial Intelligence, Xidian University, Xi’an 710071, China54th Research Institute of China Electronics Technology Group Corporation, Shijiazhuang 050081, China54th Research Institute of China Electronics Technology Group Corporation, Shijiazhuang 050081, ChinaPolarimetric Synthetic Aperture Radar (PolSAR) image classification is one of the most important applications in remote sensing. The impressive superpixel generation approaches can improve the efficiency of the subsequent classification task and restrain the influence of the speckle noise to an extent. Most of the classical PolSAR superpixel generation approaches use the features extracted manually and even only consider the pseudocolor images. They do not make full use of polarimetric information and do not necessarily lead to good enough superpixels. The deep learning methods can extract effective deep features but they are difficult to combine with superpixel generation to achieve true end-to-end training. Addressing the above issues, this study proposes an end-to-end fully convolutional superpixel generation network for PolSAR images. It integrates the extraction of polarization information features and the generation of PolSAR superpixels into one step. PolSAR superpixels can be generated based on deep polarization feature extraction and need no traditional clustering process. Both the performance and efficiency of generations of PolSAR superpixels can be enhanced effectively. The experimental results on various PolSAR datasets show that the proposed method can achieve impressive superpixel segmentation by fitting the real boundaries of different types of ground objects effectively and efficiently. It can achieve excellent classification performance by connecting a very simple classification network, which is helpful to improve the efficiency of the subsequent PolSAR image classification tasks.https://www.mdpi.com/2072-4292/17/15/2723superpixel generationend-to-endfully convolutional networkpolarimetric informationPolarimetric Synthetic Aperture Radar image classification
spellingShingle Mengxuan Zhang
Jingyuan Shi
Long Liu
Wenbo Zhang
Jie Feng
Jin Zhu
Boce Chu
PolSAR-SFCGN: An End-to-End PolSAR Superpixel Fully Convolutional Generation Network
Remote Sensing
superpixel generation
end-to-end
fully convolutional network
polarimetric information
Polarimetric Synthetic Aperture Radar image classification
title PolSAR-SFCGN: An End-to-End PolSAR Superpixel Fully Convolutional Generation Network
title_full PolSAR-SFCGN: An End-to-End PolSAR Superpixel Fully Convolutional Generation Network
title_fullStr PolSAR-SFCGN: An End-to-End PolSAR Superpixel Fully Convolutional Generation Network
title_full_unstemmed PolSAR-SFCGN: An End-to-End PolSAR Superpixel Fully Convolutional Generation Network
title_short PolSAR-SFCGN: An End-to-End PolSAR Superpixel Fully Convolutional Generation Network
title_sort polsar sfcgn an end to end polsar superpixel fully convolutional generation network
topic superpixel generation
end-to-end
fully convolutional network
polarimetric information
Polarimetric Synthetic Aperture Radar image classification
url https://www.mdpi.com/2072-4292/17/15/2723
work_keys_str_mv AT mengxuanzhang polsarsfcgnanendtoendpolsarsuperpixelfullyconvolutionalgenerationnetwork
AT jingyuanshi polsarsfcgnanendtoendpolsarsuperpixelfullyconvolutionalgenerationnetwork
AT longliu polsarsfcgnanendtoendpolsarsuperpixelfullyconvolutionalgenerationnetwork
AT wenbozhang polsarsfcgnanendtoendpolsarsuperpixelfullyconvolutionalgenerationnetwork
AT jiefeng polsarsfcgnanendtoendpolsarsuperpixelfullyconvolutionalgenerationnetwork
AT jinzhu polsarsfcgnanendtoendpolsarsuperpixelfullyconvolutionalgenerationnetwork
AT bocechu polsarsfcgnanendtoendpolsarsuperpixelfullyconvolutionalgenerationnetwork