Deep learning has been widely used in the field of SAR ship detection. However, current SAR ship detection still faces many challenges, such as complex scenes, multiple scales, and small targets. In order to promote the solution to the above problems, this article releases a high-resolution SAR ship detection dataset which can be used for rotating frame target detection. The dataset contains six categories of ships. In total, 30 panoramic SAR tiles of the Chinese Gaofen-3 of port areas with a 1-m resolution were cropped to slices, each with 1024 × 1024 pixels. In addition, most of the images in the dataset contain nearshore areas with complex background interference. Eight state-of-the-art rotated detectors and a CFAR-based method were used to evaluate the dataset. Experimental results revealed that the complex background will have a great impact on the performance of detectors.

The Gaofen-3 (GF-3) data processor was developed as a workstation-based GF-3 synthetic aperture radar (SAR) data processing system. The processor consists of two vital subsystems of the GF-3 ground segment, which are referred to as data ingesting subsystem (DIS) and product generation subsystem (PGS). The primary purpose of DIS is to record and catalogue GF-3 raw data with a transferring format, and PGS is to produce slant range or geocoded imagery from the signal data. This paper presents a brief introduction of the GF-3 data processor, including descriptions of the system architecture, the processing algorithms and its output format.

Synthetic aperture radar (SAR) image simulation can provide SAR target images under different scenes and imaging conditions at a low cost. These simulation images can be applied to SAR target recognition, image interpretation, 3-D reconstruction, and many other fields. With the accumulation of high-resolution SAR images of targets under different imaging conditions, the simulation process should be benefited from these real images. Accurate simulation parameters are one of the keys to obtain high-quality simulation images. However, it takes a lot of time, energy, and resources to get simulation parameters from actual target measurement or adjusting manually. It is difficult to derive the analytical form of the relation between a SAR image and its simulation parameter, so nowadays the abundant real SAR images can hardly help the SAR simulation. In this article, a framework is proposed to obtain the relationship between SAR images and simulation parameters by training the deep neural network (DNN), so as to extract the simulation parameters from the real SAR image. Two DNNs, convolutional neural network (CNN), and generative adversarial network (GAN) are used to implement this framework. By modifying the network structures and setting reasonable training data, our DNNs can learn the relationship between image and simulation parameters more effectively. Experimental results show that the DNNs can extract the simulation parameters from the real SAR image, which can further improve the similarity of the simulation image while automating the setting of simulation parameters. Compared with CNN, the simulation parameters extracted by GAN can achieve better results at multiple azimuth angles.

Ship detection in synthetic aperture radar (SAR) images has attracted widespread attention due to its significance and challenges. In recent years, numerous detectors based on deep learning have achieved good performance in the field of SAR ship detection. However, ship targets of the same type always have various representations in SAR images under different imaging conditions, while different types of ships may have a high degree of similarity, which considerably complicates SAR target recognition. Meanwhile, the ship target in the SAR image is also obscured by background and noise. To address these issues, this paper proposes a novel oriented ship detection method in SAR images named SPG-OSD. First, we propose an oriented two-stage detection module based on the scattering characteristics. Second, to reduce false alarms and missing ships, we improve the performance of the network by incorporating SAR scattering characteristics in the first stage of the detector. A scattering-point-guided region proposal network (RPN) is designed to predict possible key scattering points and make the regression and classification stages of RPN increase attention to the vicinity of key scattering points and reduce attention to background and noise. Third, supervised contrastive learning is introduced to alleviate the problem of minute discrepancies among SAR object classes. Region-of-Interest (RoI) contrastive loss is proposed to enhance inter-class distinction and diminish intra-class variance. Extensive experiments are conducted on the SAR ship detection dataset from the Gaofen-3 satellite, and the experimental results demonstrate the effectiveness of SPG-OSD and show that our method achieves state-of-the-art performance.

Multi-sensor remote sensing applications require the registration of optical and Synthetic Aperture Radar (SAR) images, which presents challenges due to significant radiometric and geometric differences resulting from distinct imaging mechanisms. Although various algorithms have been proposed, including hand-crafted features and deep learning networks, most of them focus on matching radiometric-invariant features while ignoring geometric differences. Furthermore, these algorithms often achieve promising results on datasets that use manually labeled ground truths that may be less reliable for high-resolution SAR images affected by speckle noise. To address these issues, we propose a robust global-to-local registration algorithm consisting of four modules: geocoding, global matching, local matching, and refinement. We generate a geometry-invariant mask in the geocoding module to help the local matching module focus on valid areas, introduce a fast global matching method to solve large offsets, and use matching confidence to guide subsequent local matching based on the accuracy of global matching. We propose a feature based on multi-directional anisotropic Gaussian derivatives (MAGD) and embed it into the confidence-aware local matching with the geometry-invariant mask to reduce the effect of geometric differences. Finally, we refine correspondence positions and remove outliers. We also build a high-accuracy evaluation dataset with hundreds of image pairs, where the ground truth is obtained by meta poles, which have clear and reliable structures in both optical and SAR images. Experimental results on this dataset demonstrate the superiority of our proposed algorithm compared to several state-of-the-art methods.

In recent years, the stereo positioning technology based on multiview spaceborne synthetic aperture radar (SAR) images has been widely applied in digital surface model extraction. In this letter, problems of the existing methods based on the range–Doppler (RD) model in a multiview stereo solution are pointed out. A robust stereo positioning solution for multiview spaceborne SAR images based on the RD model is proposed. In the proposed method, the traditional RD model is normalized to reduce the model errors caused by the different scales of the range equation and Doppler equation. A weighting strategy is also proposed to improve the positioning accuracy. This strategy is useful for multiview stereo positioning when using images of different satellites with orbital data of different accuracies. The experiments based on GaoFen-3 and TerraSAR-X satellite data sets validate the effectiveness of the proposed method.