Multi-Source and Multi-Dimensional Data Fusion of Magnetic Levitation Track Transportation Based on Digital Twin
Yuxin Zhang, Lei Zhang, Guochen Shen · Advances in computer science research · 2022
Digital twin (DT) of large-scale transportation infrastructure plays an important role in the development of intelligent transportation system (ITS), and has become the current research hotspot of ITS.Traditional data fusion has done a lot for intelligent transportation infrastructure.However, it still exists many shortcomings.This paper aims at establishing a multi-source and multidimensional data fusion model of magnetic levitation track based on digital twin.We proposed a data fusion method that can fuse 2D image data and 3D LIDAR point clouds data together, by using Context Capture and Cloud Compare software.This method combines data advantages so that we can optimize the expression of fine particle accuracy.Firstly, we made the aerial triangulation for the image data that was collected with drone, and then reconstructed the dense point clouds and generated the colorful point clouds; next, we fused the colorful point clouds with the LIDAR point clouds data that has been data processed; and finally, we generated the model and accomplished the fusion process of magnetic levitation track model.We compared the digital twin model with the benchmark model from macroscopic to microscopic perspective, the verification results indicated that the error of track flatness is about one centimeter, and the mean distance between the two models is about 0.124 meters, so the digital twin data fusion model fits well.