SAR Target Image Generation Method Using Azimuth-Controllable Generative Adversarial Network

Abstract

Sufficient synthetic aperture radar (SAR) target images are very important for the development of researches. However, available SAR target images are often limited in practice, which hinders the progress of SAR application. In this paper, we propose an azimuth-controllable generative adversarial network to generate precise SAR target images with an intermediate azimuth between two given SAR images' azimuths. This network mainly contains three parts: generator, discriminator, and predictor. Through the proposed specific network structure, the generator can extract and fuse the optimal target features from two input SAR target images to generate SAR target image. Then a similarity discriminator and an azimuth predictor are designed. The similarity discriminator can differentiate the generated SAR target images from the real SAR images to ensure the accuracy of the generated, while the azimuth predictor measures the difference of azimuth between the generated and the desired to ensure the azimuth controllability of the generated. Therefore, the proposed network can generate precise SAR images, and their azimuths can be controlled well by the inputs of the deep network, which can generate the target images in different azimuths to solve the small sample problem to some degree and benefit the researches of SAR images. Extensive experimental results show the superiority of the proposed method in azimuth controllability and accuracy of SAR target image generation.

From Coarse to Fine: ISAR Object View Interpolation via Flow Estimation and GAN

“…In the field of SAR image interpolation, a deep convolutional generative adversarial network (DCGAN) is modified and employed to generate intermediate azimuth SAR images by utilizing two SAR images [15]. After that, a Self-Attention GAN (SAGAN) is designed based on DCGAN to solve the problem of azimuth expansion [16], [17]. The sine and cosine of the azimuth are introduced into the generator's input as conditions, which are concatenated with random Gaussian noise to ensure diversity in the generated results.…”

SAR ATR under Limited Training Data Via MobileNetV3

“…Using the invariant risk minimization (IRM) concept, we provide a loss L d to enable X v accumulation in Eq. (2). By minimizing L d , our CIATR models achieve precise recognition with limited SAR data.…”

“…Next, we apply a hybrid similarity measure for feature discrimination, calculating the effect of different conditions on a SAR image. Using the invariant risk minimization (IRM) concept, we provide a loss L d to enable X v accumulation in Eq (2)…”

A Two-Stage SAR Image Generation Algorithm Based on GAN with Reinforced Constraint Filtering and Compensation Techniques

“…Methods like dual discriminator and high frequency pass filter (DH-GAN) [40] attempt to combine physical characteristics with a GAN generation procedure to generate realistic images. Recently, there has also been a series of GAN methods which concentrate on generating SAR images of designated azimuth angles, including pose estimator and auxiliary classifier GAN (PeaceGAN) [41], azimuth-controllable GAN (AG-GAN) [42], and angle transformation GAN (ATGAN) [43].…”