Over the recent years, deep-learning technology has been widely used. However, in research based on Synthetic Aperture Radar (SAR) ship target detection, it is difficult to support the training of a deep-learning network model because of the difficulty in data acquisition and the small scale of the samples. This paper provides a SAR ship detection dataset with a high resolution and large-scale images. This dataset comprises 31 images from Gaofen-3 satellite SAR images, including harbors, islands, reefs, and the sea surface in different conditions. The backgrounds include various scenarios such as the near shore and open sea. We conducted experiments using both traditional detection algorithms and deep-learning algorithms and observed the densely connected end-to-end neural network to achieve the highest average precision of 88.1%. Based on the experiments and performance analysis, corresponding benchmarks are provided as a basis for further research on SAR ship detection using this dataset.

The multi-platform-borne Synthetic Aperture Radar (SAR) has become one of the most explored research directions in the domain of SAR. This study discusses the imaging algorithms in multi-platform-borne SARs such as airborne SAR, missile-borne SAR, and spaceborne SAR. First, the establishment of the radar echo model is briefly introduced, including two main points: slant range-model and imaging mode. Subsequently, the imaging algorithms of the aforementioned multi-platform-borne SARs developed and used in recent years are summarized. In addition, the inherent characteristics and challenges are described. Finally, the future development trends of the research are discussed.

Synthetic Aperture Radar three-dimensional (SAR 3D) imaging technology can eliminate severe overlap in 2D images, and improve target recognition and 3D modeling capabilities, which have become an important trend in SAR development. After decades of development of SAR 3D imaging technology, many types of 3D imaging methods have been proposed. In this study, the history of SAR 3D imaging technology is systematically reviewed and the characteristics of existing SAR 3D imaging technology are analyzed. Given that the 3D information contained in SAR echo and images is not fully used by existing techniques, a new concept of SAR microwave vision 3D imaging has been proposed for the first time. This new concept is integrated with microwave scattering mechanism and image visual semantics to realize three-dimensional reconstruction, which form the theory and method of SAR microwave vision 3D imaging and can achieve high-efficiency and low-cost SAR 3D imaging. This study also analyzes the concept, goal and key scientific problems of SAR microwave vision 3D imaging and provides a preliminary solution, which will contribute in several ways to our understanding of SAR 3D imaging and provide the basis for further research.

This paper analyzes the multi-directional evolution of radar ground imaging technology from the aspects of the representation of imaging results, aperture manifolds, signal channels, system morphologies, observation directions, processing methods, realization mechanisms, and target recognition. Attempts are made to analyze and understand the internal and external factors as well as the development law of radar ground imaging technology from a macroscopic perspective over a long time scale, and to predict the direction of future development. Alternative observation perspective and thinking method are proposed with a view to advance the understanding of the times veins and macro trends of radar ground imaging technology, meet practical needs, lead innovation efforts, and promote development and applications.

With the development of artificial intelligence, Synthetic-Aperture Radar (SAR) ship detection using deep learning technology can effectively avoid traditionally complex feature design and thereby greatly improve detection accuracy. However, most existing detection models often improve detection accuracy at the expense of detection speed that limits some real-time applications of SAR such as emergency military deployment, rapid maritime rescue, and real-time marine environmental monitoring. To solve this problem, a high-speed and high-accuracy SAR ship detection method called SARShipNet-20 based on a Depthwise Separable Convolution Neural Network (DS-CNN) has been proposed in this paper, that replaces the Traditional Convolution Neural Network (T-CNN) and combines Channel Attention (CA) and Spatial Attention (SA). As a result, high-speed and high-accuracy SAR ship detection can be simultaneously achieved. This method has certain practical significance in the field of real-time SAR application, and its lightweight model is helpful for future FPGA or DSP hardware transplantation.

As an important tool for acquiring remote sensing information, Synthetic Aperture Radar (SAR) has various modes, including high-resolution wide-swath, multi-angle information acquisition, high temporal observation, and three-dimensional topographic mapping. For any spaceborne SAR system, obtaining high-quality images is a prerequisite for improving the performance of SAR applications. In this paper, we analyze the factors affecting spaceborne SAR imaging and image quality with respect to orbit, platform, payload, and signal processing. We describe high-precision data acquisition techniques, including amplitude-phase compensation, the dynamic adjustment of the central electronic equipment, and antenna pattern estimation. We then present imaging compensation methods based on the improved motion model and tropospheric delay correction, which can achieve resolutions better than 0.3 m. Lastly, we summarize and compare SAR image processing techniques such as speckle noise suppression, azimuth ambiguity suppression, and sidelobe suppression, whereby the equivalent number of looks can be increased to more than 25 and the azimuth ambiguity and sidelobes can both be suppressed by 20 dB.

The development of multimode high-resolution Synthetic Aperture Radar (SAR) poses new challenges to information perception and feature abstraction of the space, ground, sea, and environment targets. The intersection of spatial remote sensing big data and artificial intelligence information technology is a new scientific research domain and major application area in Automatic Target Recognition (ATR). We emphasize that research on artificial intelligence information technology needs to be conducted under the physical background of the interaction between electromagnetic waves and targets, i.e., physical intelligence, to develop microwave vision of information perception on the electromagnetic spectrum that cannot be recognized by human eyes. This study is based on a keynote speech presented by author at the Fifth Young Scientists Forum of Journal of Radars on August 15, 2019.