MGSFA-Net: Multiscale Global Scattering Feature Association Network for SAR Ship Target Recognition

Deep learning has offered new ideas in SAR ship target recognition. Although many methods improve the recognition performance through the improvement of loss function and migration of deep networks, scattering features as the important intrinsic features of SAR targets, need to be considered in the...

Full description

Bibliographic Details
Main Authors: Xianghui Zhang, Sijia Feng, Chenxi Zhao, Zhongzhen Sun, Siqian Zhang, Kefeng Ji
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10412205/
_version_ 1827349076587315200
author Xianghui Zhang
Sijia Feng
Chenxi Zhao
Zhongzhen Sun
Siqian Zhang
Kefeng Ji
author_facet Xianghui Zhang
Sijia Feng
Chenxi Zhao
Zhongzhen Sun
Siqian Zhang
Kefeng Ji
author_sort Xianghui Zhang
collection DOAJ
description Deep learning has offered new ideas in SAR ship target recognition. Although many methods improve the recognition performance through the improvement of loss function and migration of deep networks, scattering features as the important intrinsic features of SAR targets, need to be considered in the SAR ship recognition tasks. To introduce the scattering features into the deep network and characterize the features of ship targets more comprehensively, a multiscale global scattering feature association network (MGSFA-Net) for SAR ship target recognition is proposed in this article. In the network, the SAR ship target is first separated from the background by fine target segmentation. Then, the scattering centers (SCs) of ship targets are extracted and converted to local graph structures based on the <inline-formula><tex-math notation="LaTeX">$k$</tex-math></inline-formula>-nearest neighbors algorithm. The local graph structures are associated by the scattering center feature association module and enhanced by the multiscale feature enhancement module to produce the multiscale global scattering features. Moreover, the deep features of the targets are extracted by the multikernel deep feature extraction module to characterize the high-dimensional information. Finally, the scattering features and deep features are fused by weighted integration to enrich the diversity of features. The experimental results on the FUSAR-Ship and OpenSARShip dataset show that the MGSFA-Net can significantly improve the recognition performance, even on a few-shot condition with the accuracy increasing over 2&#x0025;&#x2013;3&#x0025;. The feature distribution and visualization show the effectiveness of the MGSFA-Net to characterize the multiscale global scattering association features.
first_indexed 2024-03-08T00:25:16Z
format Article
id doaj.art-d8c7dbb407824960a7a453e2db04ec94
institution Directory Open Access Journal
issn 2151-1535
language English
last_indexed 2024-03-08T00:25:16Z
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj.art-d8c7dbb407824960a7a453e2db04ec942024-02-16T00:00:19ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352024-01-01174611462510.1109/JSTARS.2024.335717110412205MGSFA-Net: Multiscale Global Scattering Feature Association Network for SAR Ship Target RecognitionXianghui Zhang0https://orcid.org/0009-0008-4295-0051Sijia Feng1https://orcid.org/0000-0002-1321-082XChenxi Zhao2https://orcid.org/0000-0002-4031-355XZhongzhen Sun3https://orcid.org/0000-0001-6400-1481Siqian Zhang4https://orcid.org/0000-0001-8108-9278Kefeng Ji5https://orcid.org/0000-0001-5261-0220State Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System, the College of Electronic Science and Technology, National University of Defense Technology, Changsha, ChinaState Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System, the College of Electronic Science and Technology, National University of Defense Technology, Changsha, ChinaState Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System, the College of Electronic Science and Technology, National University of Defense Technology, Changsha, ChinaState Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System, the College of Electronic Science and Technology, National University of Defense Technology, Changsha, ChinaState Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System, the College of Electronic Science and Technology, National University of Defense Technology, Changsha, ChinaState Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System, the College of Electronic Science and Technology, National University of Defense Technology, Changsha, ChinaDeep learning has offered new ideas in SAR ship target recognition. Although many methods improve the recognition performance through the improvement of loss function and migration of deep networks, scattering features as the important intrinsic features of SAR targets, need to be considered in the SAR ship recognition tasks. To introduce the scattering features into the deep network and characterize the features of ship targets more comprehensively, a multiscale global scattering feature association network (MGSFA-Net) for SAR ship target recognition is proposed in this article. In the network, the SAR ship target is first separated from the background by fine target segmentation. Then, the scattering centers (SCs) of ship targets are extracted and converted to local graph structures based on the <inline-formula><tex-math notation="LaTeX">$k$</tex-math></inline-formula>-nearest neighbors algorithm. The local graph structures are associated by the scattering center feature association module and enhanced by the multiscale feature enhancement module to produce the multiscale global scattering features. Moreover, the deep features of the targets are extracted by the multikernel deep feature extraction module to characterize the high-dimensional information. Finally, the scattering features and deep features are fused by weighted integration to enrich the diversity of features. The experimental results on the FUSAR-Ship and OpenSARShip dataset show that the MGSFA-Net can significantly improve the recognition performance, even on a few-shot condition with the accuracy increasing over 2&#x0025;&#x2013;3&#x0025;. The feature distribution and visualization show the effectiveness of the MGSFA-Net to characterize the multiscale global scattering association features.https://ieeexplore.ieee.org/document/10412205/Deep learningmultiscalescattering feature associationship recognitionsynthetic aperture radar (SAR)
spellingShingle Xianghui Zhang
Sijia Feng
Chenxi Zhao
Zhongzhen Sun
Siqian Zhang
Kefeng Ji
MGSFA-Net: Multiscale Global Scattering Feature Association Network for SAR Ship Target Recognition
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Deep learning
multiscale
scattering feature association
ship recognition
synthetic aperture radar (SAR)
title MGSFA-Net: Multiscale Global Scattering Feature Association Network for SAR Ship Target Recognition
title_full MGSFA-Net: Multiscale Global Scattering Feature Association Network for SAR Ship Target Recognition
title_fullStr MGSFA-Net: Multiscale Global Scattering Feature Association Network for SAR Ship Target Recognition
title_full_unstemmed MGSFA-Net: Multiscale Global Scattering Feature Association Network for SAR Ship Target Recognition
title_short MGSFA-Net: Multiscale Global Scattering Feature Association Network for SAR Ship Target Recognition
title_sort mgsfa net multiscale global scattering feature association network for sar ship target recognition
topic Deep learning
multiscale
scattering feature association
ship recognition
synthetic aperture radar (SAR)
url https://ieeexplore.ieee.org/document/10412205/
work_keys_str_mv AT xianghuizhang mgsfanetmultiscaleglobalscatteringfeatureassociationnetworkforsarshiptargetrecognition
AT sijiafeng mgsfanetmultiscaleglobalscatteringfeatureassociationnetworkforsarshiptargetrecognition
AT chenxizhao mgsfanetmultiscaleglobalscatteringfeatureassociationnetworkforsarshiptargetrecognition
AT zhongzhensun mgsfanetmultiscaleglobalscatteringfeatureassociationnetworkforsarshiptargetrecognition
AT siqianzhang mgsfanetmultiscaleglobalscatteringfeatureassociationnetworkforsarshiptargetrecognition
AT kefengji mgsfanetmultiscaleglobalscatteringfeatureassociationnetworkforsarshiptargetrecognition