The performance of a deep learning-based Synthetic aperture radar (SAR) automatic target recognition (ATR) model largely relies on the scale and quality of training samples. However, it is time-consuming and expensive to collect sufficient data in practice. Although generative adversarial network (GAN) provides a way for SAR target image generation, existing GAN-based methods cannot confirm what features the generator learns, thus they struggle in generating precise SAR target images. In this paper, we propose an angle transformation GAN (ATGAN) that can generate azimuth-controllable SAR target images while preserving the target details. The key idea of our ATGAN is to reframe the generation task from the perspective of image-to-image translation. To this end, ATGAN consists of two modules, a coarse-to-fine generator that aims to learn the angle transformation in the deep feature space and then apply it to manipulate the representation of an input SAR target image to generate a new one, while a spectral-normalized patch discriminator that tries to estimate the probability that an input SAR target image is real rather than fake using a patch-averaged strategy. Combining with spatial transformer and adversarial training paradigm, ATGAN can generate precise SAR target images for ATR. Extensive experiments verify the effectiveness of the proposed ATGAN, and our method outperforms the state-of-the-art method qualitatively and quantitatively.
14 October 2021 in IEEE Transactions on Geoscience and Remote Sensing
Synthetic aperture radar raw data simulation (SAR-RDS) is beneficial to the SAR system design, signal processing method verification, and radar parameter optimization. Most SAR-RDS methods are based on the flat terrain assumption. However, the fluctuant terrain in real scene will induce severe SAR beam occlusion effect and produce radar shadow, leading to incorrect RDS results. Thus, a dynamic elevation angle interpolation (DEAI) algorithm is proposed for SAR shadow judgment by considering the actual SAR working process. The key of the proposed DEAI algorithm is the 1-D EAI and shadow visualization update, which avoids the problem that the existing methods cannot judge the shadow of partial areas due to the insufficiently refined mesh grid or the mismatch of the judgment model. Moreover, an evaluation framework named as joint image and signal criteria (JISC) is proposed from the perspectives of SAR imaging and signal processing results to objectively evaluate the SAR-RDS results and solve the problem that the existing evaluation methods cannot be compatible with fluctuant terrain. Finally, the numerical experiment verified our theoretical analyses.
Despite the in-depth understanding of the synthetic aperture-radar (SAR) speckle and its characteristics, despeckling remains an open issue far from being solved. Deep-learning methods with supervised training have made great progress. However, reliable reference images are inconveniently accessible or even non-existent. In this paper, we propose an end-to-end self-supervised method named Speckle2Self for SAR image despeckling, which learns mapping from noisy input to clean output using only the input noisy image itself for training. We formulate the image despeckling as a masked pixel-estimation problem, where a set of masks is carefully designed. The masked pixel values are predicted by the queries of complementary masks indicating the positions of masked pixels through an attention mechanism. Transformer architecture is employed as the network backbone. In addition, a novel loss function is also derived based on the statistics of SAR images, and meanwhile, image downsampling is used to provide guarantees on the white noise assumption involved in our Speckle2Self. We compare the proposed Speckle2Self with reference methods on both synthetic and real images. Experimental results demonstrate that the proposed Speckle2Self achieves comparable despeckling performance with supervised methods, suppressing noise while maintaining structural details. Even compared with self-supervised methods, the proposed Speckle2Self still has significant advantages in SAR image-despeckling metrics.
This paper proposes a synthetic aperture radar (SAR) ship detection method based on wavelet-domain deformable convolution (WDC) and multi-head attention, built upon the Sparse R-CNN framework. First, a wavelet-domain convolution module is introduced to enhance the modeling of ship targets with diverse scales and shapes while incorporating frequency-domain information. Deformable convolution adaptively adjusts sampling locations, overcoming the limitations of traditional convolution in capturing target edges and blurred boundaries. Next, a position encoding module is employed to normalize candidate bounding box coordinates and integrate them into region-of-interest features. By providing spatial context, position encoding strengthens spatial perception and enables the subsequent multi-head attention mechanism to more effectively capture associations between targets and candidate regions, thereby improving localization accuracy under arbitrary spatial distributions. Furthermore, the original dynamic head is replaced with a multi-head attention mechanism. Through position-encoded multi-head attention, the model more accurately emphasizes regions with spatial and semantic correlations to the target, enhancing both focus and discrimination for sparse targets. Extensive experiments conducted on two benchmark datasets (SSDD and HRSID) demonstrate the effectiveness and superiority of the proposed method. Overall, the method significantly improves the detection of sparse, multi-scale, and randomly distributed ship targets in SAR images.