Panoramic depth estimation has become a hot topic in 3D reconstruction techniques with its omnidirectional spatial field of view. However, panoramic RGB-D datasets are difficult to obtain due to the lack of panoramic RGB-D cameras, thus limiting the practicality of supervised panoramic depth estimation. Self-supervised learning based on RGB stereo image pairs has the potential to overcome this limitation due to its low dependence on datasets. In this work, we propose the SPDET, an edge-aware self-supervised panoramic depth estimation network that combines the transformer with a spherical geometry feature. Specifically, we first introduce the panoramic geometry feature to construct our panoramic transformer and reconstruct high-quality depth maps. Furthermore, we introduce the pre-filtered depth-image-based rendering method to synthesize the novel view image for self-supervision. Meanwhile, we design an edge-aware loss function to improve the self-supervised depth estimation for panorama images. Finally, we demonstrate the effectiveness of our SPDET with a series of comparison and ablation experiments while achieving the state-of-the-art self-supervised monocular panoramic depth estimation. Our code and models are available at https://github.com/zcq15/SPDET .

The performance of discontinuous deformation analysis (DDA) needs to be improved for large-scale analysis. In this study, the contact detection and open-close iteration, as the bottlenecks of DDA computing, are reimplemented on graphics processing units (GPUs). For contact detection, the proposed parallel method accelerates DDA computing by maintaining a high loading balance and data reuse ratio on the GPU. The open-close iteration is divided into two parts, simultaneous equations solver and interpenetration checker. For the simultaneous equations solver, both the parallel Jacobi method and the block Jacobi preconditioned conjugate gradient (BJPCG) methods are implemented on the GPU to substitute the original successive overrelaxation (SOR) method. The parallel interpenetration checker is improved by optimizing conditional branches on the GPU. Two applications of the new parallel methods are introduced. The results showed that the broad and narrow phases of contact detection showed 18 and 5 times ...

In the fields of 3D modeling, analysis of discontinuities and engineering calculation, surface extraction is of great importance. The rapid development of photogrammetry and Light Detection and Ranging (LiDAR) technology facilitates the study of surface extraction. Automatic extraction of rock surfaces from 3D rock-mass point clouds also becomes the basis of 3D modeling and engineering calculation of rock mass. This paper presents an automated and effective method for extracting rock surfaces from unorganized rock-mass point clouds. This method consists of three stages: (i) clustering based on voxels; (ii) estimating major orientations based on Gaussian Kernel and (iii) rock surface extraction. Firstly, the two-level spatial grid is used for fast voxelization and segmenting the point cloud into three types of voxels, including coplanar, non-coplanar and sparse voxels. Secondly, the coplanar voxels, rather than the scattered points, are employed to estimate major orientations by using a bivariate Gaussian Kernel. Finally, the seed voxels are selected on the basis of major orientations and the region growing method based on voxels is applied to extract rock surfaces, resulting in sets of surface clusters. The sub-surfaces of each cluster are coplanar or parallel. In this paper, artificial icosahedron point cloud and natural rock-mass point clouds are used for testing the proposed method, respectively. The experimental results show that, the proposed method can effectively and accurately extract rock surfaces in unorganized rock-mass point clouds.

Impact craters refer to the most salient features on the moon surface. They are of huge significance for analyzing the moon topography, selecting the lunar landing site and other lunar exploration missions, etc. However, existing methods of impact crater detection have been largely implemented on the optical image data, thereby causing them to be sensitive to the sunlight. Thus, these methods can easily achieve unsatisfactory detection results. In this study, an original two-stage small crater detection method is proposed, which is sufficiently effective in addressing the sunlight effects. At the first stage of the proposed method, a semantic segmentation is conducted to detect small impact craters by fully exploiting the elevation information in the digital elevation map (DEM) data. Subsequently, at the second stage, the detection accuracy is improved under the special post-processing. As opposed to other methods based on DEM images, the proposed method, respectively, increases the new crusher percentage, recall and crusher level $F_1$ by 4.89%, 5.42% and 0.67%.

In respect of rock-mass engineering, the detection of planar structures from the rock-mass point clouds plays a crucial role in the construction of a lightweight numerical model, while the establishment of high-quality models relies on the accurate results of surface analysis. However, the existing techniques are barely capable to segment the rock mass thoroughly, which is attributed to the cluttered and unpredictable surface structures of the rock mass. This paper proposes a high-precision plane detection approach for 3D rock-mass point clouds, which is effective in dealing with the complex surface structures, thus achieving a high level of detail in detection. Firstly, the input point cloud is fast segmented to voxels using spatial grids, while the local coplanarity test and the edge information calculation are performed to extract the major segments of planes. Secondly, to preserve as much detail as possible, supervoxel segmentation instead of traditional region growing is conducted to deal with scattered points. Finally, a patch-based region growing strategy applicable to rock mass is developed, while the completed planes are obtained by merging supervoxel patches. In this paper, an artificial icosahedron point cloud and four rock-mass point clouds are applied to validate the performance of the proposed method. As indicated by the experimental results, the proposed method can make high-precision plane detection achievable for rock-mass point clouds while ensuring high recall rate. Furthermore, the results of both qualitative and quantitative analyses evidence the superior performance of our algorithm.