Text-Enhanced Multimodal Method for SAR Ship Classification With Geometry and Polarization Information

Synthetic aperture radar (SAR) ship classification is crucial for maritime surveillance. Most existing methods primarily focus on visual or polarimetric features, often constrained by a limited feature set and facing challenges in data diversity and multimodal information integration. This study int...

Full description

Saved in:
Bibliographic Details
Main Authors: Jinyue Chen, Youming Wu, Wei Dai, Wenhui Diao, Yang Li, Xin Gao, Xian Sun
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10925632/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850271632217604096
author Jinyue Chen
Youming Wu
Wei Dai
Wenhui Diao
Yang Li
Xin Gao
Xian Sun
author_facet Jinyue Chen
Youming Wu
Wei Dai
Wenhui Diao
Yang Li
Xin Gao
Xian Sun
author_sort Jinyue Chen
collection DOAJ
description Synthetic aperture radar (SAR) ship classification is crucial for maritime surveillance. Most existing methods primarily focus on visual or polarimetric features, often constrained by a limited feature set and facing challenges in data diversity and multimodal information integration. This study introduces a text-enhanced multimodal framework for SAR ship classification (TeMSC), an extensible and unified approach that integrates multimodal information related to SAR ships. It consists of text-form geometry information embedding, polarization and visual information embedding, and a multimodal prediction module. By incorporating ship geometry information in text format, TeMSC leverages text representation to enhance feature expressiveness, compensating for the limited discriminative power of traditional visual and polarization features, especially in low-resolution scenarios. TeMSC effectively processes complementary multimodal information through a multimodal prediction module, while avoiding the complexity associated with traditional decision-level feature fusion strategies. In addition, a classification token mechanism is introduced to streamline the classification process. Through a two-stage training strategy, TeMSC captures information across multiple SAR datasets, enhancing its generalization and adaptability. Extensive experiments on the FUSAR-Ship and OpenSARShip datasets demonstrate the superior performance of TeMSC and highlight the benefits of multimodal integration for SAR ship classification. TeMSC provides a foundation for future research on SAR-focused multimodal learning applications.
format Article
id doaj-art-0789ca224f874a4c8b9ea4e67e92c46a
institution OA Journals
issn 1939-1404
2151-1535
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
spelling doaj-art-0789ca224f874a4c8b9ea4e67e92c46a2025-08-20T01:52:10ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-01188659867110.1109/JSTARS.2025.355123910925632Text-Enhanced Multimodal Method for SAR Ship Classification With Geometry and Polarization InformationJinyue Chen0https://orcid.org/0009-0000-1821-9818Youming Wu1https://orcid.org/0000-0002-5927-364XWei Dai2https://orcid.org/0000-0002-9010-2101Wenhui Diao3https://orcid.org/0000-0002-3931-3974Yang Li4https://orcid.org/0000-0002-2479-2538Xin Gao5Xian Sun6https://orcid.org/0000-0002-0038-9816Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaSynthetic aperture radar (SAR) ship classification is crucial for maritime surveillance. Most existing methods primarily focus on visual or polarimetric features, often constrained by a limited feature set and facing challenges in data diversity and multimodal information integration. This study introduces a text-enhanced multimodal framework for SAR ship classification (TeMSC), an extensible and unified approach that integrates multimodal information related to SAR ships. It consists of text-form geometry information embedding, polarization and visual information embedding, and a multimodal prediction module. By incorporating ship geometry information in text format, TeMSC leverages text representation to enhance feature expressiveness, compensating for the limited discriminative power of traditional visual and polarization features, especially in low-resolution scenarios. TeMSC effectively processes complementary multimodal information through a multimodal prediction module, while avoiding the complexity associated with traditional decision-level feature fusion strategies. In addition, a classification token mechanism is introduced to streamline the classification process. Through a two-stage training strategy, TeMSC captures information across multiple SAR datasets, enhancing its generalization and adaptability. Extensive experiments on the FUSAR-Ship and OpenSARShip datasets demonstrate the superior performance of TeMSC and highlight the benefits of multimodal integration for SAR ship classification. TeMSC provides a foundation for future research on SAR-focused multimodal learning applications.https://ieeexplore.ieee.org/document/10925632/Dual-polarizationgeometry information embeddingmultimodal learningship classificationsynthetic aperture radar (SAR)
spellingShingle Jinyue Chen
Youming Wu
Wei Dai
Wenhui Diao
Yang Li
Xin Gao
Xian Sun
Text-Enhanced Multimodal Method for SAR Ship Classification With Geometry and Polarization Information
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Dual-polarization
geometry information embedding
multimodal learning
ship classification
synthetic aperture radar (SAR)
title Text-Enhanced Multimodal Method for SAR Ship Classification With Geometry and Polarization Information
title_full Text-Enhanced Multimodal Method for SAR Ship Classification With Geometry and Polarization Information
title_fullStr Text-Enhanced Multimodal Method for SAR Ship Classification With Geometry and Polarization Information
title_full_unstemmed Text-Enhanced Multimodal Method for SAR Ship Classification With Geometry and Polarization Information
title_short Text-Enhanced Multimodal Method for SAR Ship Classification With Geometry and Polarization Information
title_sort text enhanced multimodal method for sar ship classification with geometry and polarization information
topic Dual-polarization
geometry information embedding
multimodal learning
ship classification
synthetic aperture radar (SAR)
url https://ieeexplore.ieee.org/document/10925632/
work_keys_str_mv AT jinyuechen textenhancedmultimodalmethodforsarshipclassificationwithgeometryandpolarizationinformation
AT youmingwu textenhancedmultimodalmethodforsarshipclassificationwithgeometryandpolarizationinformation
AT weidai textenhancedmultimodalmethodforsarshipclassificationwithgeometryandpolarizationinformation
AT wenhuidiao textenhancedmultimodalmethodforsarshipclassificationwithgeometryandpolarizationinformation
AT yangli textenhancedmultimodalmethodforsarshipclassificationwithgeometryandpolarizationinformation
AT xingao textenhancedmultimodalmethodforsarshipclassificationwithgeometryandpolarizationinformation
AT xiansun textenhancedmultimodalmethodforsarshipclassificationwithgeometryandpolarizationinformation