The rapid development of remote sensing technology has led to a sharp increase in the amount of synthetic aperture radar (SAR) measurements, which put forward higher requirements for remote sensing image processing. As an important application of SAR, fast and accurate ship detection has always been a research hotspot. In this article, an improved lightweight RetinaNet for ship detection in SAR images is proposed. Compared with the standard RetinaNet, the shallow convolutional layers of the backbone are replaced by ghost modules and the number of the deep convolutional layers is reduced. The spatial and channel attention modules are embedded into the model to enhance detectability. K -means clustering algorithm is applied to adjust the initial aspect ratios of the model. The effectiveness and robustness of the proposed method is demonstrated by numerical experiments with SSDD dataset, Gaofen-3 mini dataset, and a large-scale SAR image of Hisea-1 satellite, it is shown that the proposed method can significantly reduce the floating-point operations and the number of parameters without decreasing the detection accuracy and recall ratio. Moreover, the experimental results also show the proposed model's robustness and the ability to detect ship targets in small datasets.

Due to the different imaging mechanisms between optical and polarimetric synthetic aperture radar (PolSAR) images, determining how to effectively use such complementary information has become an interesting and challenging problem. Convolutional neural networks (CNNs) and other deep neural networks have achieved good experimental results in remote sensing land-cover semantic segmentation. However, the CNN convolution structure can extract only the features within the receptive field in the spatial dimension without focusing on the relationship between multiple channels; therefore, it is impossible to realize fusion and complementarity between multiple channels. In this article, we propose a novel spatial dense channel attention fusion network (SDCAFNet), which takes optical and PolSAR images as different inputs and completes feature fusion and semantic segmentation within a neural network. First, SDCAFNet uses a two-stream siamese CNN network to realize the preliminary feature coding of optical and PolSAR images. Then, a spatial dense channel attention module (SDCAM) is proposed. The channel activation values obtained at different positions are combined in the spatial dense matrix, which can describe the attention in the feature fusion process. Finally, we introduce the fused features into the symmetric skip-connection decoder composed of multiple symmetric decoder blocks to realize end-to-end land-cover semantic segmentation. Experimental results show that SDCAFNet can effectively learn the correlation between optical and PolSAR channels and has a better segmentation accuracy than other methods.

Remote sensing is the main technical means for urban researchers and planners to effectively observe targeted urban areas. Generally, it is difficult for only one image to cover a whole urban area and one image cannot support the demands of urban planning tasks for spatial statistical analysis of a whole city. Therefore, people often artificially find multiple images with complementary regions in an urban area on the premise of meeting the basic requirements for resolution, cloudiness, and timeliness. However, with the rapid increase of remote sensing satellites and data in recent years, time-consuming and low performance manual filter results have become more and more unacceptable. Therefore, the issue of efficiently and automatically selecting an optimal image collection from massive image data to meet individual demands of whole urban observation has become an urgent problem. To solve this problem, this paper proposes a large-area full-coverage remote sensing image collection filtering algorithm for individual demands (LFCF-ID). This algorithm achieves a new image filtering mode and solves the difficult problem of selecting a full-coverage remote sensing image collection from a vast amount of data. Additionally, this is the first study to achieve full-coverage image filtering that considers user preferences concerning spatial resolution, timeliness, and cloud percentage. The algorithm first quantitatively models demand indicators, such as cloudiness, timeliness, resolution, and coverage, and then coarsely filters the image collection according to the ranking of model scores to meet the different needs of different users for images. Then, relying on map gridding, the image collection is genetically optimized for individuals using a genetic algorithm (GA), which can quickly remove redundant images from the image collection to produce the final filtering result according to the fitness score. The proposed method is compared with manual filtering and greedy retrieval to verify its computing speed and filtering effect. The experiments show that the proposed method has great speed advantages over traditional methods and exceeds the results of manual filtering in terms of filtering effect.

Superpixel segmentation has been widely used in the field of computer vision. The generations of PolSAR superpixels have also been widely studied for their feasibility and high efficiency. The initial numbers of PolSAR superpixels are usually designed manually by experience, which has a significant impact on the final performance of superpixel segmentation and the subsequent interpretation tasks. Additionally, the effective information of PolSAR superpixels is not fully analyzed and utilized in the generation process. Regarding these issues, a multiobjective evolutionary superpixel segmentation for PolSAR image classification is proposed in this study. It contains two layers, an automatic optimization layer and a fine segmentation layer. Fully considering the similarity information within the superpixels and the difference information among the superpixels simultaneously, the automatic optimization layer can determine the suitable number of superpixels automatically by the multiobjective optimization for PolSAR superpixel segmentation. Considering the difficulty of the search for accurate boundaries of complex ground objects in PolSAR images, the fine segmentation layer can further improve the qualities of superpixels by fully using the boundary information of good-quality superpixels in the evolution process for generating PolSAR superpixels. The experiments on different PolSAR image datasets validate that the proposed approach can automatically generate high-quality superpixels without any prior information.

With continuous improvements in data resolution in recent years, the details and boundaries of various land cover in images have become clearer. A high-resolution image contains abundant detailed information but also generally has considerable noise and redundant information, which interfere with the automatic and high-precision classification of land cover objects. The demand for an automatic land cover/land use classification method that can better handle the detailed information of high-resolution remote sensing images has become increasingly urgent.