No abstract

No abstract

No abstract

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.

The research and development of an intelligent magnetic levitation transportation system has become an important research branch of the current intelligent transportation system (ITS), which can provide technical support for state-of-the-art fields such as intelligent magnetic levitation digital twin. First, we applied unmanned aerial vehicle oblique photography technology to acquire the magnetic levitation track image data and preprocessed them. Then, we extracted the image features and matched them based on the incremental structure from motion (SFM) algorithm, recovered the camera pose parameters of the image data and the 3D scene structure information of key points, and optimized the bundle adjustment to output 3D magnetic levitation sparse point clouds. Then, we applied multiview stereo (MVS) vision technology to estimate the depth map and normal map information. Finally, we extracted the output of the dense point clouds that can precisely express the physical structure of the magnetic levitation track, such as turnout, turning, linear structures, etc. By comparing the dense point clouds model with the traditional building information model, experiments verified that the magnetic levitation image 3D reconstruction system based on the incremental SFM and MVS algorithm has strong robustness and accuracy and can express a variety of physical structures of magnetic levitation track with high accuracy.