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.

Deep learning such as deep neural networks has revolutionized the computer vision area. Deep learning-based algorithms have surpassed conventional algorithms in terms of performance by a significant margin. This paper reviews our works in the application of deep convolutional neural networks to target recognition and terrain classification using the SAR image. A convolutional neural network is employed to automatically extract a hierarchic feature representation from the data, based on which the target recognition and terrain classification can be conducted. Experimental results on the MSTAR benchmark dataset reveal that deep convolutional network could achieve a state-of-the-art classification accuracy of 99% for the 10-class task. For a polarimetric SAR image classification, we propose complex-valued convolutional neural networks for complex SAR images. This algorithm achieved a state-of-the-art accuracy of 95% for the 15-class task on the Flevoland benchmark dataset.

Multi-temporal Interferometric Synthetic Aperture Radar (MT-InSAR) is one of the most powerful Earth observation techniques, especially useful for measuring highly detailed ground deformation over large ground areas. Much research has been carried out to apply MT-InSAR to monitor ground and infrastructure deformation in urban areas related to land reclamation, underground construction and groundwater extraction. This paper reviews the progress in the research and identifies challenges in applying the technology, including the inconsistency in coherent point identification when different approaches are used, the reliability issue in parameter estimation, difficulty in accurate geolocation of measured points, the one-dimensional line-of-sight nature of InSAR measurements, the inability of making complete measurements over an area due to geometric distortions, especially the shadowing effects, the challenges in processing large SAR datasets, the decrease of the number of coherent points with the increase of the length of SAR time series, and the difficulty in quality control of MT-InSAR results.