Search

Abstract In recent years, the application of real scene 3D technology has become widespread in urban planning and cultural heritage protection. However, there has been relatively little attention paid to the construction of real scene 3D models for special natural landscapes such as caves. Given the global distribution of karst topography and the large number of naturally developed caves with diverse types, unique landscape styles, and significant scientific value, this paper enriches the research in this field. By combining ground-based and aerial remote sensing techniques, and based on 3D laser scanning and photogrammetry, we have successfully constructed a real scene 3D model of the internal structure of a karst cave with a precision better than 4 cm. Utilizing Unmanned Aerial Vehicle (UAV) oblique photography, we established a real scene 3D model of the external karst landform with a precision better than 2 cm. We also integrated the internal and external 3D models of the cave, developing a new, complete, and high-precision method for constructing real scene 3D models of karst cave landscapes. Furthermore, we proposed a method for texture reproduction in the dark environment inside the caves, enhancing the reproduction and visual appeal of the real interior. The establishment of high-precision real scene 3D models can not only serve as an effective tool for scientific research on caves but also, as replicas of the real world, play a crucial role in public dissemination and education, thereby enhancing public understanding of cave geological landscapes.

Geological mapping involves the identification of elements such as rocks, soils, and surface water, which are fundamental tasks in Geological Environment Remote Sensing (GERS) interpretation. High-precision intelligent interpretation technology can not only reduce labor requirements and significantly improve the efficiency of geological mapping but also assist geological disaster prevention assessment and resource exploration. However, the high interclass similarity, high intraclass variability, gradational boundaries, and complex distributional characteristics of GERS elements coupled with the difficulty of manual labeling and the interference of imaging noise, all limit the accuracy of DL-based methods in wide-area GERS interpretation. We propose a Transformer-based multi-stage and multi-scale fusion network, RSWFormer (Rock–Soil–Water Network with Transformer), for geological mapping of spatially large areas. RSWFormer first uses a Multi-stage Geosemantic Hierarchical Sampling (MGHS) module to extract geological information and high-dimensional features at different scales from local to global, and then uses a Multi-scale Geological Context Enhancement (MGCE) module to fuse geological semantic information at different scales to enhance the understanding of contextual semantics. The cascade of the two modules is designed to enhance the interpretation and performance of GERS elements in geologically complex areas. The high mountainous and hilly areas located in western China were selected as the research area. A multi-source geological remote sensing dataset containing diverse GERS feature categories and complex lithological characteristics, Multi-GL9, is constructed to fill the significant gaps in the datasets required for extensive GERS. Using overall accuracy as the evaluation index, RSWFormer achieves 92.15% and 80.23% on the Gaofen-2 and Landsat-8 datasets, respectively, surpassing existing methods. Experiments show that RSWFormer has excellent performance and wide applicability in geological mapping tasks.