Imagen de Portada

Boosting SAR ATR Trustworthiness via ERFA: An Electromagnetic Reconstruction Feature Alignment Method

Guardado en:
Publicado en:Remote Sensing vol. 17, no. 23 (2025), p. 3855-3882
Autor principal: Gao Yuze
Otros Autores: Li Dongying, Guo Weiwei, Lin, Jianyu, Wang, Yiren, Yu, Wenxian
Publicado:
MDPI AG
Materias:
Feature extraction
Dictionaries
Deep learning
Algorithms
Automatic target recognition
Parameter sensitivity
Image processing
Matched pursuit
Machine learning
Data compression
Transfer learning
Alignment
Physics
Image reconstruction
Fourier transforms
Synthetic aperture radar
Target recognition
Neural networks
Optimization
Crops
Clutter
Robustness (mathematics)
Trustworthiness
Acceso en línea:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Resumen:<sec sec-type="highlights"> What are the main findings? <list list-type="bullet"> <list-item> </list-item>The integration of the frequency-domain electromagnetic reconstruction algorithm with image-domain cropping optimization achieves an effective balance between reconstruction accuracy and computational efficiency. <list-item> The integration of electromagnetic reconstruction and feature alignment effectively enhances model robustness and suppresses background clutter in SAR ATR under varying operating conditions. </list-item> What are the implications of the main findings? <list list-type="bullet"> <list-item> </list-item>Provides a trustworthy deep learning solution for SAR ATR by aligning electromagnetic reconstructions with image features, which helps mitigate overfitting to specific operating conditions. <list-item> Provides evidence that utilizing target-related physical features significantly enhances the robustness, generalization and interpretability of deep learning-based SAR ATR. </list-item> Deep learning-based synthetic aperture radar (SAR) automatic target recognition (ATR) methods exhibit a tendency to overfit specific operating conditions—such as radar parameters and background clutter—which frequently leads to high sensitivity against variations in these conditions. A novel electromagnetic reconstruction feature alignment (ERFA) method is proposed in this paper, which integrates electromagnetic reconstruction with feature alignment into a fully convolutional network, forming the ERFA-FVGGNet. The ERFA-FVGGNet comprises three modules: electromagnetic reconstruction using our proposed orthogonal matching pursuit with image-domain cropping-optimization (OMP-IC) algorithm for efficient, high-precision attributed scattering center (ASC) reconstruction and extraction; the designed FVGGNet combining transfer learning with a lightweight fully convolutional network to enhance feature extraction and generalization; and feature alignment employing a dual-loss to suppress background clutter while improving robustness and interpretability. Experimental results demonstrate that ERFA-FVGGNet boosts trustworthiness by enhancing robustness, generalization and interpretability.
ISSN:2072-4292
DOI:10.3390/rs17233855
Fuente:Advanced Technologies & Aerospace Database