The digital elevation model (DEM) is known as one kind of the most significant fundamental geographical data models. The theory, method and application of DEM are hot research issues in geography, especially in geomorphology, hydrology, soil and other related fields. In this paper, we improve the efficient sub-pixel convolutional neural networks (ESPCN) and propose recursive sub-pixel convolutional neural networks (RSPCN) to generate higher-resolution DEMs (HRDEMs) from low-resolution DEMs (LRDEMs). Firstly, the structure of RSPCN is described in detail based on recursion theory. This paper explores the effects of different training datasets, with the self-adaptive learning rate Adam algorithm optimizing the model. Furthermore, the adding-“zero” boundary method is introduced into the RSPCN algorithm as a data preprocessing method, which improves the RSPCN method’s accuracy and convergence. Extensive experiments are conducted to train the method till optimality. Finally, comparisons are made with other traditional interpolation methods, such as bicubic, nearest-neighbor and bilinear methods. The results show that our method has obvious improvements in both accuracy and robustness and further illustrate the feasibility of deep learning methods in the DEM data processing area.

Radiometric distortion caused by the time-varying gain (TVG), beam patterns, angular responses, and sonar altitude variations, highly degrades the quality of side-scan sonar (SSS) images. Thus, radiometric distortion correction becomes a fundamental step for SSS image processing which holds vital importance for geomorphic applications. However, existing methods cannot take the prior information of the acoustic illumination component as well as the feature of seafloor into consideration well, which would easily cause damage to the image and also always be powerless for residual stripe noise. In this paper, a novel radiometric correction method is proposed. First, we give a detailed analysis of the SSS imaging theory based on the Lambert’s law as well as the prior knowledge about the characteristics of SSS images. Then, incorporating the prior of the SSS imaging process, the low-rank constraint is specifically introduced for the illumination component, while the anisotropic total variation (ATV) constraint is used to constraint the albedo component, combining other constraints, a decomposition model is proposed to correct the radiometric distortion based on the SSS imaging theory. And an alternative minimization method has been adopted to solve the proposed model effectively. Experiments proved the validity of the proposed method.

For inertial navigation systems (INS), as one of the major methods for underwater navigation, errors diverge over time. With the development of geophysical navigation technology, gravity navigation has become an effective method of navigation. Significant changes in the gravity characteristic of the matching region ensure that gravity matching navigation works effectively. In this paper, we combine artificial intelligence algorithms and statistical metrics to classify gravity-matching navigation regions. Firstly, this paper analyzes and extracts gravity anomaly data from a matching region in different ways. Then, a particle swarm optimization (PSO) algorithm is used to optimize the network weights of a back propagation (BP) NN. Finally, based on principal component analysis (PCA) theory and PSO-BP NN, this paper proposes the PPBA method to classify the matching area. Moreover, the Terrain Contour Matching (TERCOM) matching algorithm and gravity anomaly data from the Western Pacific are used to verify the classification performance of the PPBA method. The experiments prove that the PPBA method has a high classification accuracy, and the classification results are consistent with the matching navigation experimental results. This work can provide a reference for designing navigation regions and navigation routes for submarines.