Evaluation and Improvement of Generalization Performance of SAR Ship Recognition Algorithms

Zhang, Chi; Zhang, Xi; Zhang, Jie; Gao, Gui; Dai, Yongshou; Liu, Genwang; Jia, Yongjun; Wang, Xiaochen; Zhang, Yi; Meng, Bo

doi:10.1109/jstars.2022.3216623

Cited by 12 publications

(5 citation statements)

References 83 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…10(a), it is noteworthy that when λ g is smaller than 4, the PSNR gradually increases with the increase of λ g . When λ g comes to [4,5], PSNR is at the highest value. Then, in most cases, when λ g is greater than 4, the PSNR will be in a relatively stable state.…”

Section: A Some Key Parameters In Sar-orientated Gbfmentioning

confidence: 99%

“…Therefore, we introduce a similarity measurement for SAR images. Like (5) in Section II, the patches similarity criterion adapted to speckle noise is…”

Section: B Nonlocal Self-similarity Measurement Of Sar Imagementioning

confidence: 99%

“…S YNTHETIC aperture radar (SAR) could obtain the information covered by the ground or vegetation without concerning weather conditions. The corresponding imaging analysis is popular in forest monitoring [1], urban feature extraction [2], [3], [4], ship surveillance [5], and many other fields. Nevertheless, due to the speckle produced by coherent mechanisms, SAR images usually suffer from information attenuation, resulting in huge challenges in their analysis, interpretation, or applications [6].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Novel SAR Image Despeckling Method Based on Local Filter With Nonlocal Preprocessing

Wang

Guo

2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Owing to the characteristics of long distance and strong penetration, a synthetic aperture radar (SAR) imaging system could provide ground information with high resolution under a poor climate environment. Nevertheless, speckle is still a common interference of the output that deteriorates the content of SAR images and further affects the recognition of real objects. In this article, a new speckle suppression method is proposed from the perspective of exploring nonlocal and local SAR image features. Considering the statistical distribution of SAR images, a novel local filter termed SAR-orientated guided bilateral filter is proposed to characterize the range and spatial similarity of SAR images. Meanwhile, an optimized nonlocal filter based on the weight Schatten-p norm is introduced to characterize the nonlocal self-similarity of SAR images by a low-rank model. As a preprocessing step, it yields nonlocal filtering features as the guidance image of the proposed SAR-oriented guided bilateral filter. By incorporating the nonlocal filtering feature into the local filter, the structured method could achieve desirable despeckling results. Extensive experiments on real SAR images demonstrate that the proposed method outperforms several state-of-the-art methods in terms of both visual satisfaction and quantitative metrics.

show abstract

Section: A Some Key Parameters In Sar-orientated Gbfmentioning

confidence: 99%

“…Therefore, we introduce a similarity measurement for SAR images. Like (5) in Section II, the patches similarity criterion adapted to speckle noise is…”

Section: B Nonlocal Self-similarity Measurement Of Sar Imagementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Novel SAR Image Despeckling Method Based on Local Filter With Nonlocal Preprocessing

Wang

Guo

2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…SAR plays an important role in the military defense and civil economy as an indispensable means of marine information acquisition and surveillance. SAR ship target recognition is an important development prospect, especially in the aspects of marine monitoring, target surveillance, ecological protection, and disaster forecasting [1]- [6].…”

Section: Introductionmentioning

confidence: 99%

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

Zhang,

Feng,

Zhao

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

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 multi-scale global scattering feature association network (MGSFA-Net) for SAR ship target recognition is proposed in this paper. In the network, the SAR ship target is firstly 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 k-Nearest Neighbors (KNN) algorithm. The local graph structures are associated by the scattering center feature association (SCFA) module and enhanced by the multi-scale feature enhancement (MSFE) module to produce the multi-scale global scattering features. Moreover, the deep features of the targets are extracted by the multi-kernel deep feature extraction (MKDFE) 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 multi-scale global scattering association features.

show abstract

“…Since ships are the primary mode of maritime transportation, monitoring their movements is crucial for the regulation and management of maritime traffic. Compared to conventional optical remote sensing technologies, SAR can penetrate adverse weather conditions and provide high-resolution images, making it an optimal instrument for marine monitoring [2]. However, analyzing SAR images can be challenging due to the complex nature of sea surface backgrounds, the presence of clutter interference, and the blurred features of ship targets in the images.…”

Section: Introductionmentioning

confidence: 99%

MSSD-Net: Multi-Scale SAR Ship Detection Network

Wang,

Xu,

Huang

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

In recent years, the development of neural networks has significantly advanced their application in Synthetic Aperture Radar (SAR) ship target detection for maritime traffic control and ship management. However, traditional neural network architectures are often complex and resource intensive, making them unsuitable for deployment on artificial satellites. To address this issue, this paper proposes a lightweight neural network: the Multi-Scale SAR Ship Detection Network (MSSD-Net). Initially, the MobileOne network module is employed to construct the backbone network for feature extraction from SAR images. Subsequently, a Multi-Scale Coordinate Attention (MSCA) module is designed to enhance the network’s capability to process contextual information. This is followed by the integration of features across different scales using an FPN + PAN structure. Lastly, an Anchor-Free approach is utilized for the rapid detection of ship targets. To evaluate the performance of MSSD-Net, we conducted extensive experiments on the Synthetic Aperture Radar Ship Detection Dataset (SSDD) and SAR-Ship-Dataset. Our experimental results demonstrate that MSSD-Net achieves a mean average precision (mAP) of 98.02% on the SSDD while maintaining a compact model size of only 1.635 million parameters. This indicates that MSSD-Net effectively reduces model complexity without compromising its ability to achieve high accuracy in object detection tasks.

show abstract

Evaluation and Improvement of Generalization Performance of SAR Ship Recognition Algorithms

Cited by 12 publications

References 83 publications

A Novel SAR Image Despeckling Method Based on Local Filter With Nonlocal Preprocessing

A Novel SAR Image Despeckling Method Based on Local Filter With Nonlocal Preprocessing

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

MSSD-Net: Multi-Scale SAR Ship Detection Network

Contact Info

Product

Resources

About