Extracting buildings from very high-resolution satellite images is a challenging yet important task for applications such as urban monitoring. Multiscale feature learning proves to be a potential solution toward accurate extraction of buildings. This study exploits a powerful multiscale feature learning module, a hierarchical vision transformer by shifted windows (swin), as a backbone within a building extraction network. To this end, we first designed a general structure for building extraction, consisting of a backbone to extract multiscale features and a head network to fuse and refine features. Then, we integrated swin into the structure as a backbone and utilized channel-wise and spatial-wise enhancement in a head network. Experimental results show that our method achieves improvements regarding both F1-score and intersection over union (IoU) compared to the multiple attending path neural network (MAP-Net), which is the current state-of-the-art (SOTA) algorithm for building extraction from remote sensing images. Our study thus confirms the potential of swin transformers as backbones for semantic segmentation tasks based on satellite images.

As research on large regions of earth progresses, many geographical subdivision grids have been established for various spatial applications by different industries and disciplines. However, there is no clear relationship between the different grids and no consistent spatial reference grid that allows for information exchange and comprehensive application. Sharing and exchange of data across departments and applications are still at a bottleneck. It would represent a significant step forward to build a new grid model that is inclusive of or compatible with most of the existing geodesic grids and that could support consolidation and exchange within existing data services. This study designs a new geographical coordinate global subdividing grid with one dimension integer coding on a 2ⁿ tree (GeoSOT) that has 2ⁿ coordinate subdivision characteristics (global longitude and latitude subdivision) and can form integer hierarchies at degree, minute, and second levels. This grid has the multi-dimensional quadtree hierarchical characteristics of a digital earth grid, but also provides good consistency with applied grids, such as those used in mapping, meteorology, oceanography and national geographical, and three-dimensional digital earth grids. No other existing grid codes possess these characteristics.

Asphalt pavement ages and incurs various distresses due to natural and human factors. Thus, it is crucial to rapidly and accurately extract different types of pavement distress to effectively monitor road health status. In this study, we explored the feasibility of pavement distress identification using low-altitude unmanned aerial vehicle light detection and ranging (UAV LiDAR) and random forest classification (RFC) for a section of an asphalt road that is located in the suburb of Shihezi City in Xinjiang Province of China. After a spectral and spatial feature analysis of pavement distress, a total of 48 multidimensional and multiscale features were extracted based on the strength of the point cloud elevations and reflection intensities. Subsequently, we extracted the pavement distresses from the multifeature dataset by utilizing the RFC method. The overall accuracy of the distress identification was 92.3%, and the kappa coefficient was 0.902. When compared with the maximum likelihood classification (MLC) and support vector machine (SVM), the RFC had a higher accuracy, which confirms its robustness and applicability to multisample and high-dimensional data classification. Furthermore, the method achieved an overall accuracy of 95.86% with a validation dataset. This result indicates the validity and stability of our method, which highway maintenance agencies can use to evaluate road health conditions and implement maintenance.

Extracting buildings from remote sensing (RS) images is an important task with a variety of applications. Considerable attention has focused on achieving new state-of-the-art (SOTA) accuracy with more and more advanced deep learning (DL) models. However, the developed models still hardly generalize across geographical areas, hindering the practical use of SOTA approaches. To attack this problem, we established a baseline for model cross-area generalization ability using available datasets for building extraction (BE). In addition to two popular fully convolutional neural network (FCN) based models, we first adapted two novel transformer-based models, shifted windows (Swin) transformer and SegFormer, which are all able to output SOTA accuracy with no big difference when tested within one area. However, experimental results show that all models fail to generalize to a different area. We then propose to fine-tune pretrained models from one area on a small subset of an unseen area, the effectiveness of which depends on the model choice and the data size for tuning. By jointly taking advantage of the transfer learning idea and the multiscale feature learning ability of SegFormer, a distinct improvement has been achieved compared to results from Swin transformer and FCN-based models trained on the same amount of data. Commonly used metric, Intersection over Union, can be increased from 38.97% to 70.86%, and from 48.36% to 74.51%, when using 10% and 30% subset of the targeting area, respectively. The influence of model choice and data size for tuning has also been investigated. Our work contributes to complementing the algorithm development and within-area model evaluation in the hot field of BE from RS images.

The increasing number of unmanned aerial vehicles (UAVs) has led to challenges related to solving the collision problem to ensure air traffic safety. The traditional approaches employed for collision detection suffer from two main drawbacks: first, the computational burden of a pairwise calculation increases exponentially with an increasing number of spatial entities; second, existing grid-based approaches are unsuitable for complicated scenarios with a large number of objects moving at high speeds. In the proposed model, we first identified UAVs and other spatial objects with GeoSOT-3D grids. Second, the nonrelational spatial database was initialized with a multitable strategy, and spatiotemporal data were inserted with the GeoSOT-3D grid codes as the primary key. Third, the collision detection procedure was transformed from a pairwise calculation to a multilevel query. Four simulation experiments were conducted to verify the feasibility and efficiency of the proposed collision detection model for UAVs in different environments. The results also indicated that 64 m GeoSOT-3D grids are the most suitable basic grid size, and the reduction in the time consumption compared with traditional methods reached approximately 50–80% in different scenarios.