The automation of digital twinning for existing reinforced concrete bridges from point clouds remains an unresolved problem. Whilst current methods can automatically detect bridge objects in point ...clouds in the form of labelled point clusters, the fitting of accurate 3D shapes to point clusters remains largely human dependent largely. 95% of the total manual modelling time is spent on customizing shapes and fitting them correctly. The challenges exhibited in the fitting step are due to the irregular geometries of existing bridges. Existing methods can fit geometric primitives such as cuboids and cylinders to point clusters, assuming bridges are comprised of generic shapes. However, the produced geometric digital twins are too ideal to depict the real geometry of bridges. In addition, none of the existing methods have explicitly demonstrated how to evaluate the resulting Industry Foundation Classes bridge data models in terms of spatial accuracy using quantitative measurements. In this article, we tackle these challenges by delivering a slicing-based object fitting method that can generate the geometric digital twin of an existing reinforced concrete bridge from four types of labelled point cluster. The quality of the generated models is gauged using cloud-to-cloud distance-based metrics. Experiments on ten bridge point cloud datasets indicate that the method achieves an average modelling distance of 7.05 cm (while the manual method achieves 7.69 cm), and an average modelling time of 37.8 s. This is a huge leap over the current practice of digital twinning performed manually.
•An object fitting method that can digitally twin bridges is proposed.•The method can rapidly twin bridge concrete elements.•Local configurations offer characterization to approximate the global topology.•The resulting geometric digital twins are evaluated using quantitative metrics.
Conventional face direction estimation techniques detect the characteristic parts of the face, such as the nose, eyes, and mouth, and estimate the face orientation based on the movements of these ...features. However, these methods cannot accurately estimate the face direction when the characteristic parts of the face are hidden; for example, when the face is turned sideways or a mask is worn. Face detection using point cloud data has been investigated as a solution to these issues. Previous studies applied five classes of face direction estimation for the head using 3D point cloud data. However, considering the practical use of driver assistance systems that verify the driver's status, these five classes are not sufficient for accurately detecting the face direction, and a more precise horizontal wide-range angle detection approach is necessary. In this study, we acquired 3D point cloud data in k (where k > 5) classes while accurately measuring the horizontal angle of the face during the acquisition of the training data using gyroscopic sensors. The training data captured by this depth-gyro sensor integration generates accurate depth data for each direction. As a result, a low number of point cloud data samples for each face direction were sufficient for generating the directional classification model. Therefore, this depth-gyro sensor integrated data capturing significantly reduces the amount of required training data. Furthermore, we applied a weight reduction process for the point cloud data to reduce the training time and performed deep learning to estimate the face direction. The proposed method achieved high performance in face direction detection using deep learning, even with a comparatively small dataset.
Coal-rock recognition is a key technology to realize intelligent shearer and a prerequisite for achieving safe and efficient production in coal mining working face. Based on the analysis of the ...characteristics and defects of the current recognition methods, this article proposes a novel coal-rock recognition method based on laser scanning technology. First, a coal-rock point cloud data simplification method is designed based on feature points preserving. The purpose is to retain abundant information of coal-rock characteristics and simultaneously meet the requirements of simplicity and precision. Then, an improved ant colony optimization (IACO) algorithm is presented by the two strategies to enhance the optimization efficiency and search ability. The strategies are implemented by adaptively adjusting the pheromone volatilization coefficient and the update step of ant colony position. The IACO is combined with the 2-D OTSU (IACO-TOTSU) to determine the optimal intensity threshold of coal-rock point cloud data, which is utilized to consummate the growth rule of the region growing (RG) algorithm. Meanwhile, the initial seed point of RG is optimized through the curvature calculation of each point and an improved region growing algorithm (IACO-TOTSU-RG) is then performed to achieve the segmentation and recognition of coal-rock point cloud data. Experimental test results indicate that the proposed coal-rock recognition method outperforms others and the coal-rock recognition accuracy can reach above 90%. Finally, an industrial application is provided to prove the practicability and feasibility of the proposed method.
3D point cloud data obtained from laser scans, images, and videos are able to provide accurate and fast records of the 3D geometries of construction-related objects. Thus, the construction industry ...has been using point cloud data for a variety of purposes including 3D model reconstruction, geometry quality inspection, construction progress tracking, etc. Although a number of studies have been reported on applying point cloud data for the construction industry in the recent decades, there has not been any systematic review that summaries these applications and points out the research gaps and future research directions. This paper, therefore, aims to provide a thorough review on the applications of 3D point cloud data in the construction industry and to provide recommendations on future research directions in this area. A total of 197 research papers were collected in this study through a two-fold literature search, which were published within a fifteen-year period from 2004 to 2018. Based on the collected papers, applications of 3D point cloud data in the construction industry are reviewed according to three categories including (1) 3D model reconstruction, (2) geometry quality inspection, and (3) other applications. Following the literature review, this paper discusses on the acquisition and processing of point cloud data, particularly focusing on how to properly perform data acquisition and processing to fulfill the needs of the intended construction applications. Specifically, the determination of required point cloud data quality and the determination of data acquisition parameters are discussed with regard to data acquisition, and the extraction and utilization of semantic information and the platforms for data visualization and processing are discussed with regard to data processing. Based on the review of applications and the following discussions, research gaps and future research directions are recommended including (1) application-oriented data acquisition, (2) semantic enrichment for as-is BIM, (3) geometry quality inspection in fabrication phase, and (4) real-time visualization and processing.
Registration performs an individual and deciding role in multiple intelligent transport systems. The advancement of deep-learning-based methods enhances the robustness and effectiveness of the ...preliminary registration stage, although the algorithm will effortlessly fall into local optima when improving the ultimate exactitude. Similarly, traditional method based on optimization has a more reliable performance in terms of precision. However, its performance still counts on the quality of initialization. In order to solve the above problems, we propose a PBNet that combines a point cloud network with a global optimization method. This framework uses the feature information of objects to perform high-precision rough registration and then searches the entire 3D motion space to implement branch-and-bound and iterative nearest point methods. The evaluation results show that PBNet significantly reduce the influence of initial values on registration and has good robustness against noise and outliers.
High-accuracy deformation analysis of composite structures is an important topic in the field of civil engineering and increasing attention is given to geometry-based analytical model, such as ...B-splines where the determination of the parameter values has a great influence on the accuracy of the B-spline approximation. In this paper, B-spline approximation is carried out with point cloud data of an arch structure obtained with terrestrial laser scanner (TLS) and the parameter control point is investigated with the aid of laser tracker (LT) and corner cube reflectors (CCRs). We focused on the discussion about the influence factors of the optimal parameters, such as CCR uncertainty, curvature of object, and order of the B-spline. The innovation of this paper is that we adopt LT to optimize the parameters of B-spline fitting, and the results are compared and verified by Bayesian information criterion.
•This paper proposed a comprehensive framework for parametric semi-automatic BIM and bridge member segmentation.•The parametric algorithm accounted for diverse types of bridge members and produced ...BIM bridge models using shape information automatically extracted per parameter.•The parametrically generated bridge BIM model was converted into PCD, serving as deep learning train data for automatic segmentation of bridge members.•The trained deep learning model showed high accuracy for segmenting superstructures, indicating promise for automated segmentation of bridge members.•The segmentation accuracy increased when accounting for the point density of members corresponding to the different sizes of bridge members.
This paper proposes a comprehensive framework for parametric semi-automatic BIM and bridge member segmentation. For this, a parametric algorithm was developed to accommodate diverse superstructures, piers, abutments, and bearings. Each structural member in a bridge was classified to designate its shape information as parameters. The range of each parameter was defined to account for various dimensions of the shape of the bridge member. Therefore, libraries for each member were established to produce BIM bridge models using shape information automatically extracted per parameter. Then, the framework includes an algorithm that is developed to convert bridge BIM models generated by the parametric algorithm into PCD data. The virtually generated PCD is used as deep learning train data for automatic member segmentation based on the Point-Net algorithm. The trained algorithm using the virtual PCD was applied to a real bridge PCD. The segmentation of the bridge members showed high accuracy for the superstructure but low accuracy for the bearing. The segmentation accuracy of the algorithm including the bearing member could increase by modifying the density of PCD to account for the different sizes of bridge members. Furthermore, the proposed framework was applied to a UK bridge PCD and showed its applicability for use in bridges in different countries.
In this paper, we propose a mesh-free numerical method for solving elliptic PDEs on unknown manifolds, identified with randomly sampled point cloud data. The PDE solver is formulated as a spectral ...method where the test function space is the span of the leading eigenfunctions of the Laplacian operator, which are approximated from the point cloud data. While the framework is flexible for any test functional space, we will consider the eigensolutions of a weighted Laplacian obtained from a symmetric Radial Basis Function (RBF) method induced by a weak approximation of a weighted Laplacian on an appropriate Hilbert space. In this paper, we consider a test function space that encodes the geometry of the data yet does not require us to identify and use the sampling density of the point cloud. To attain a more accurate approximation of the expansion coefficients, we adopt a second-order tangent space estimation method to improve the RBF interpolation accuracy in estimating the tangential derivatives. This spectral framework allows us to efficiently solve the PDE many times subjected to different parameters, which reduces the computational cost in the related inverse problem applications. In a well-posed elliptic PDE setting with randomly sampled point cloud data, we provide a theoretical analysis to demonstrate the convergence of the proposed solver as the sample size increases. We also report some numerical studies that show the convergence of the spectral solver on simple manifolds and unknown, rough surfaces. Our numerical results suggest that the proposed method is more accurate than a graph Laplacian-based solver on smooth manifolds. On rough manifolds, these two approaches are comparable. Due to the flexibility of the framework, we empirically found improved accuracies in both smoothed and unsmoothed Stanford bunny domains by blending the graph Laplacian eigensolutions and RBF interpolator.
•Solving elliptic PDEs on manifolds identified with random point cloud data.•An efficient PDE solver based on Galerkin framework.•Approximate eigenfunctions on manifold using Radial Basis Function approximation.
PDF
