Spatial Visualization Based on Geodata Fusion Using an Autonomous Unmanned Vessel

Abstract

The visualization of riverbeds and surface facilities on the banks is crucial for systems that analyze conditions, safety, and changes in this environment. Hence, in this paper, we propose collecting, and processing data from a variety of sensors—sonar, LiDAR, multibeam echosounder (MBES), and camera—to create a visualization for further analysis. For this purpose, we took measurements from sensors installed on an autonomous, unmanned hydrographic vessel, and then proposed a data fusion mechanism, to create a visualization using modules under and above the water. A fusion contains key-point analysis on classic images and sonars, augmentation/reduction of point clouds, fitting data and mesh creation. Then, we also propose an analysis module that can be used to compare and extract information from created visualizations. The analysis module is based on artificial intelligence tools for the classification tasks, which helps in further comparison to archival data. Such a model was tested using various techniques to achieve the fastest and most accurate visualizations possible in simulation and real case studies.