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...
Main Authors: | , , , , , |
---|---|
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%–3%. 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%–3%. 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 |