Recently, deep learning-based methods have brought new ideas for ship detection in synthetic aperture radar (SAR) images. However, several challenges still exist: 1) deep models contain millions of parameters, whereas the available annotated samples are not sufficient in number for training. Therefore, most deep detectors have to fine-tune networks pre-trained on ImageNet, which incurs learning bias due to the huge domain mismatch between SAR images and ImageNet images. Furthermore, it has a little flexibility to redesign the network structure; and 2) ships in SAR images are relatively small in size and densely clustered, whereas most deep detectors have poor performance with small objects due to the rough feature map used for detection and the extreme foreground-background imbalance. To address these problems, this paper proposes an effective approach to learn deep ship detector from scratch. First, we design a condensed backbone network, which consists of several dense blocks. Hence, earlier layers can receive additional supervision from the objective function through the dense connections, which makes it easy to train. In addition, feature reuse strategy is adopted to make it highly parameter efficient. Therefore, the backbone network could be freely designed and effectively trained from scratch without using a large amount of annotated samples. Second, we improve the cross-entropy loss to address the foreground-background imbalance and predict multi-scale ship proposals from several intermediate layers to improve the recall rate. Then, position-sensitive score maps are adopted to encode position information into each ship proposal for discrimination. The comparison results on the Sentinel-1 data set show that: 1) learning ship detector from scratch achieved better performance than ImageNet pre-trained model-based detectors and 2) our method is more effective than existing algorithms for detecting the small and densely clustered ships.

The recognition or understanding of the scenes observed with a synthetic aperture radar (SAR) system requires a broader range of cues beyond the spatial context. These encompass but are not limited to the imaging geometry, imaging mode, properties of the Fourier spectrum of the images, or behavior of the polarimetric signatures. In this article, we propose a change of paradigm for explainability in data science for the case of SAR data to ground explainable artificial intelligence (XAI) for SAR. It aims to use explainable data transformations based on well-established models to generate inputs for AI methods, to provide knowledgeable feedback for the training process, and to learn or improve high-complexity unknown or unformalized models from the data.

Convolutional neural networks (CNNs) have found applications in ship detection from synthetic aperture radar (SAR) images. However, there are some challenges hamper their advance. First, the detected bounding boxes are not very compact. Second, there are quite a few missing detections for small and densely clustered ships. Third, objects with analogical scatterings on land are detected as ships by making mistake. This is due to: 1) the CNN-based SAR ship detectors cannot utilize the spatial information very sufficiently; 2) features learned from CNNs only describe SAR images in space domain while neglecting the information hidden in frequency domain; and 3) information contained in the meta-data file, which may link to other sources, is not taken into account. To overcome these problems, in this paper, a cascade coupled CNN-guided (3C2N-guided) visual attention method for SAR ship detection is proposed. This method considers the newly presented 3C2N model as a qualified ship proposal generator because the images’ spatial information is utilized more sufficiently. The 3C2N model, with coupled CNN as the baseline, consists of a sequence of cascade detectors for training. Complementally, a pulse cosine transformation-based visual attention model in frequency domain is operated on the adaptive regions for ship discrimination. This could further refine the proposals’ locations and could significantly reduce the missing detections and false alarms. In addition, the digital elevation model data are adopted to remove ship-like targets on land. Experimental evaluations on 25 Sentinel-1 images demonstrate that the proposed method is superior to the previous state-of-the-art methods.

The Sentinel-1 mission provides a freely accessible opportunity for urban image interpretation based on synthetic aperture radar (SAR) data with a specific resolution, which is of paramount importance for Earth observation. In parallel, with the rapid development of advanced technologies, especially deep learning, we urgently need a large-scale SAR dataset supporting urban image interpretation. This article presents OpenSARUrban: a Sentinel-1 dataset dedicated to the content-related interpretation of urban SAR images, including a well-defined hierarchical annotation scheme, data collection, well-established procedures for dataset compilation and organization as well as properties, visualizations, and applications of this dataset. Particularly, our OpenSARUrban collection provides 33 358 image patches of urban SAR scenes, covering 21 major cities of China, including 10 different target area categories, 4 kinds of data formats, 2 kinds of polarization modes, and owning 5 essential properties: large-scale coverage, diversity, specificity, reliability, and sustainability. These properties guarantee the achievement of several goals for OpenSARUrban. The first one is to support urban target characterization. The second one is to help develop well-applicable and advanced algorithms for Sentinel-1 urban target classification. The third one is to explore content-based image retrieval for these kinds of data. In addition, dataset visualization is implemented from the perspective of manifolds to give an intuitive understanding. Besides a detailed description and visualization of the dataset, we present results of some benchmarking algorithms, demonstrating that this dataset is practical and challenging. Notably, developing algorithms to enhance the classification performance on the whole dataset and considering the data imbalance are especially demanding.

In synthetic aperture radar (SAR) image classification applications, there are three categories of data, including training and benchmark data with fixed classes, as well as actual data in practical applications. A real problem comes that there exist unknown classes not included in training and benchmark data, which is defined as the open set condition. However, little work on recognizing unknown classes and analyzing the separability of SAR datasets has been developed. Motivated by this observation, this article demonstrates the difficulty of practical classification and analyzes SAR dataset separability in open set conditions. In this article, the SAR separability analyzer (SAR-SA) is proposed to model each known class as a multivariate Gaussian distribution. SAR-SA can classify the known classes and recognize the samples locating in each known distribution with low probabilities as unknown. Besides, SAR datasetwise separability index (DSI) and classwise separability index (CSI) are defined to quantify the separability in open set conditions at the dataset level and class level. DSI and CSI are effective indicators of the difficulty of SAR classification datasets. Extensive experimental results demonstrate that the DSI in open set conditions is nearly half of that in supervised conditions. Dataset with low DSI is hard to realize accurate classification in open set conditions. At the class level, even though the SAR image classes are semantically different from each other, there exists more or less overlap between the distributions of supervised known classes and unknown classes. Classes with low CSI are harder to be correctly classified and recognized.