Reverse engineering (RE) is a technology used to create three-dimensional (3D) models by scanning structures and can be used to examine the current condition of structures. Applying RE to the maintenance of railroad facilities with a high proportion of safety accidents can be an alternative to increase the efficiency of railroad facilities. However, most tasks while constructing Building Information Modeling (BIM) after 3D scanning and extracting two-dimensional (2D) drawings are still performed manually. In particular, denoising, registration, and 3D modeling based on point clouds are labor-intensive and time-consuming tasks, and their efficiency needs to be enhanced by introducing automation technology. In this study, we selected point clouds-based representative parameters for ballasted tracks of a straight single-line section for automating railroad maintenance. Scan data and a BIM of a ballasted track were compared using the selected representative parameters. In addition, the types of damage to ballasted track requiring maintenance were examined. And a testbed was consisted of ballasted a track was selected, and 3D scanning was performed to obtain point cloud data of a testbed. Then, a BIM model was created by measuring the numerical values corresponding to the representative parameters on the scan data. The feasibility of constructing a railroad maintenance BIM based on representative 3D object detection parameters during RE work on the ballasted track was evaluated.
3D point cloud data (PCD) can accurately and efficiently capture the 3D geometric information of a target and exhibits significant potential for construction applications. Although one of the most common approaches for generating PCD is the use of unmanned aerial vehicles (UAV), UAV photogrammetry-based point clouds are erroneous. This study proposes a novel framework for automatically improving the coordinate accuracy of PCD. Image-based deep learning and PCD analysis methods are integrated into a framework that includes the following four phases: GCP (Ground Control Point) detection, GCP global coordinate extraction, transformation matrix estimation, and fine alignment. Two different experiments, as follows, were performed in the case study to validate the proposed framework: (1) experiments on the fine alignment performance of the developed framework, and (2) performance and run time comparison between the fine alignment framework and common registration algorithms such as ICP (Iterative Closest Points). The framework achieved millimeter-level accuracy for each axis. The run time was less than 30 s, which indicated the feasibility of the proposed framework.
Extracting information from scanned invoices and other commercial documents, a critical component of corporate function, typically requires significant manual processing. Much research has been conducted in the field of automated information extraction and document processing to alleviate the manual resources used for document analysis, but resultant literature and commercially available products have demonstrated limitations in customizability for identifying specific information. In this paper, we propose a customized machine learning-based pipeline for extracting and tabulating relevant key–value pairs from commercial invoice documents. Specifically, the pipeline combines general document understanding, OCR extraction, and key–value matching with custom rules pertaining to a provided invoice dataset. Then, we demonstrate that the pipeline greatly outperforms a commercially available product and can significantly reduce the amount of manual labor required to process invoice documents. Future work will focus on generalizing the pipeline, so as to apply it on more varied datasets.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.