Imagen de Portada

An Azimuth-Continuously Controllable SAR Image Generation Algorithm Based on GAN

Guardado en:
Publicado en:Remote Sensing vol. 17, no. 22 (2025), p. 3763-3782
Autor principal: Cui Yongjie
Otros Autores: Liu Zhiqu, Ruan Linian, Bowen, Sheng, Wang, Ning, Xiao Xiulai, Bian Xiaolin
Publicado:
MDPI AG
Materias:
United States > US
Deep learning
Datasets
Data acquisition
Training
Interpolation
Generative adversarial networks
Laboratories
Radar imaging
Machine learning
Image processing
Accuracy
Visual discrimination
Data augmentation
Scattering
Continuity (mathematics)
Synthetic aperture radar
Target recognition
Neural networks
Flexibility
Controllability
Image acquisition
Algorithms
Image quality
Azimuth
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> An enhanced GAN for SAR image generation, called Azimuth-Continuously Controllable Generative Adversarial Network (ACC-GAN), is proposed to enable precise interpolation between arbitrary azimuth angles. </list-item> <list-item> ACC-GAN improves the flexibility on angular generation, while maintaining the physical fidelity and angular accuracy of SAR images. </list-item> What are the implications of the main findings? <list list-type="bullet"> <list-item> Since the multi-view SAR images are very scarce and the azimuth characteristics are particularly important for SAR target recognition, the proposed ACC-GAN can provide flexible and accessible augmentation of multi-view SAR images. </list-item> The performance of deep learning models largely depends on the scale and quality of training data. However, acquiring sufficient, high-quality samples for specific observation scenarios is often challenging due to high acquisition costs. Unlike optical imagery, synthetic aperture radar (SAR) target images exhibit strong nonlinear scattering variations with changing azimuth angles, making conventional data augmentation methods such as cropping or rotation ineffective. To tackle these challenges, this paper introduces an Azimuth-Continuously Controllable Generative Adversarial Network (ACC-GAN), which incorporates a continuous azimuth conditional variable to achieve precise azimuth-controllable target generation from dual-input SAR images. Our key contributions are threefold: (1) a continuous azimuth control mechanism that enables precise interpolation between arbitrary azimuth angles; (2) a dual-discriminator framework combining similarity and azimuth supervision to ensure both visual realism and angular accuracy; and (3) conditional batch normalization integrated with adaptive feature fusion to maintain scattering consistency. Experiments on the MSTAR dataset demonstrate that ACC-GAN effectively captures nonlinear azimuth-dependent transformations, generating high-quality images that improve downstream classification accuracy and validate its practical value for SAR data augmentation.
ISSN:2072-4292
DOI:10.3390/rs17223763
Fuente:Advanced Technologies & Aerospace Database