Article
Environmental Sciences
Laura Blanco, David Garcia-Selles, Marta Guinau, Thanasis Zoumpekas, Anna Puig, Maria Salamo, Oscar Gratacos, Josep Anton Munoz, Marc Janeras, Oriol Pedraza
Summary: Rock slope monitoring using 3D point cloud data enables the creation of rockfall inventories, and a new methodology with machine learning techniques is proposed to identify rockfalls from compared temporary 3D point clouds.
Review
Chemistry, Analytical
Jinlong Teng, Yufeng Shi, Helong Wang, Jiayi Wu
Summary: This paper discusses the wide applications and advantages of terrestrial laser scanners (TLS) in deformation monitoring, as well as the limitations and future research directions in this field. The methods and precisions of deformation monitoring for different areas, such as ground surface, dams, tunnels, and tall constructions, are summarized. The error sources of TLS point cloud data and error correction models are also analyzed.
Article
Environmental Sciences
Beatrice Tanduo, Andrea Martino, Caterina Balletti, Francesco Guerra
Summary: This research provides a detailed analysis of the potential of MMS (Mobile Mapping Systems) supported by SLAM algorithms in the morphological study of cities. The study compares data obtained from different MMS devices and traditional surveying techniques in a test field in Venice. The results validate the accuracy and completeness of the MMS devices through various quantitative and qualitative analyses.
Article
Construction & Building Technology
Gaozhao Pang, Niannian Wang, Hongyuan Fang, Hai Liu, Fan Huang
Summary: The urban drainage system is an important part of the urban water cycle, but damages to underground pipelines, such as cracks and corrosion, can cause serious consequences like urban waterlogging and road collapse. Present detection methods mainly focus on qualitative identification of pipeline damage, lacking quantitative analysis. This study proposes a method that combines surface segmentation and reconstruction to quantify the damage volume of concrete pipes.
Article
Construction & Building Technology
Francisco J. Ariza-Lopez, Juan F. Reinoso-Gordo, Jose L. Garcia-Balboa, Inigo A. Ariza-Lopez
Summary: This paper applies the ISO 19157 framework to point cloud data and clarifies its application in heritage building information modeling. It proposes a method to evaluate, control, and report the quality of TLS surveys.
AUTOMATION IN CONSTRUCTION
(2022)
Article
Forestry
Chiung Ko, Seunghyun Lee, Jongsu Yim, Donggeun Kim, Jintaek Kang
Summary: This study utilized a LiDAR sensor to estimate tree characteristics in a Cryptomeria japonica forest in Jeju Island, South Korea. Results showed a 100% detection rate of standing trees by LiDAR, with high statistical accuracy in certain pathways and shorter processing times compared to traditional inventory methods. Further research is needed to confirm the efficiency of using backpack personal laser scanning in different forest stands.
Article
Construction & Building Technology
Jose Javier Perez, Maria Senderos, Amaia Casado, Inigo Leon
Summary: The aim of this study is to digitally capture large urban settings quickly. The research design is based on the Design Science Research (DSR) concept, using 3D models to generate solutions. By analyzing and optimizing LiDAR ALS point clouds provided by government bodies, additional TLS capture techniques and UAV-assisted automated photogrammetric techniques, the on-site working time was reduced by more than two thirds, increasing efficiency.
Article
Geochemistry & Geophysics
Yuanzhi Cai, Lei Fan, Peter M. Atkinson, Cheng Zhang
Summary: This research proposes a novel image enhancement method to reveal the local geometric characteristics of point cloud data in images. The method explores various feature channel combinations and achieves improved semantic segmentation accuracy. Experimental results on the Semantic3D benchmark demonstrate the superiority of this image-based approach.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Kai Tan, Tao Ke, Pengjie Tao, Kunbo Liu, Yansong Duan, Weiguo Zhang, Songbo Wu
Summary: A new method based on differences in geometric features is proposed to effectively discriminate leaf and wood components in terrestrial laser scanning (TLS) point clouds with an average accuracy of approximately 93%. The method shows good performance in terms of insensitivity to distance, instrument type, occlusion effect, and forest composition.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Computer Science, Interdisciplinary Applications
Neshat Bolourian, Majid Nasrollahi, Fardin Bahreini, Amin Hammad
Summary: This study created a publicly available point cloud data set for concrete bridge surface defect detection, and developed a point cloud-based semantic segmentation deep learning method to detect different types of concrete surface defects.
JOURNAL OF COMPUTING IN CIVIL ENGINEERING
(2023)
Article
Computer Science, Information Systems
Lei Wang, Jingyu Li, Chuang Jiang, Jinzhong Huang
Summary: This study proposes an automatic extraction method for building deformation in mining areas using TLS point clouds. The results show that the deformation value extracted using this method has negligible difference with the real value. The performance verification also demonstrates the effectiveness of the proposed distance slope filter for noise removal in the complex measurement environment of mining areas.
Article
Geography, Physical
Jing Qiao, Jemil Avers Butt
Summary: This paper presents an autonomous TLS calibration algorithm using planar patches in urban environments. The algorithm estimates and updates calibration parameters by minimizing the normal distances between corresponding planar patches. Compared to target or keypoint-based approaches, it requires only medium-resolution scan data and can estimate a comprehensive set of calibration model parameters. Experimental results with two high-precision scanners show that the proposed algorithm achieves similar calibration performance to traditional methods with subsets of the point cloud.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2023)
Article
Computer Science, Interdisciplinary Applications
Feng Zeng
Summary: This article explores surface reconstruction pattern recognition technology based on scattered point cloud data, achieving surface reconstruction through methods such as extracting candidate feature points and constructing initial grids. Experimental data shows that the search radius for the feature descriptor operator can be adjusted flexibly in reverse engineering, improving reconstruction efficiency.
Article
Environmental Sciences
Adrian Smuleac, Laura Smuleac, Cosmin Alin Popescu, Sorin Herban, Teodor Eugen Man, Florin Imbrea, Adina Horablaga, Simon Mihai, Raul Pascalau, Tamas Safar
Summary: This scientific paper discusses the importance of using 3D scanning technologies in Civil Engineering, Hydrotechnics, and Geomatics for monitoring and evaluating hydrotechnical arrangements and hydroameliorative structures. The researchers utilized mobile scanning technology and terrestrial laser scanning to collect and process point cloud data, and used GPS equipment for ground checkpoints. The results showed that 3D laser scanning technology can provide accurate data in a short period of time, surpassing traditional methods in terms of precision and processing possibilities.
Article
Engineering, Electrical & Electronic
Seyyed Meghdad Hasheminasab, Tian Zhou, Ayman Habib
Summary: This article develops a fully automated image/LiDAR integration framework that can generate accurate 3-D models with color information for stockpiles under challenging environmental conditions. The experimental results show that the developed framework outperforms a classical planar feature-based registration technique in terms of the alignment of acquired point cloud.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2023)
Article
Mechanics
H. Yang, E. Daneshkhah, R. Augello, X. Xu, E. Carrera
Summary: This paper explores the virtual vibration correlation technique for evaluating natural frequency variations in highly flexible thin-walled composite beams, using a refined finite element model. The study highlights the inadequacy of classical beam theories in predicting accurate natural frequencies, emphasizing the necessity of higher-order refined beam theories. Results show a strong correlation between the proposed efficient CUF method and more computationally expensive shell models.
COMPOSITE STRUCTURES
(2022)
Article
Materials Science, Multidisciplinary
Hao Yang, Xuhui He, Xiangyang Xu, Xiaojun Wei, Youwu Wang
Summary: This paper investigates intrusion detection of tunnels and trains based on laser scanning technology, proposing a feature-based registration method. Intrusion analysis is achieved through convex points, generating a complete and comprehensive image for design and decision-making support.
MECHANICS OF ADVANCED MATERIALS AND STRUCTURES
(2022)
Article
Chemistry, Analytical
Xiangyang Xu, Mian Zhao, Peixin Shi, Ruiqi Ren, Xuhui He, Xiaojun Wei, Hao Yang
Summary: The intelligent crack detection method is of great significance for intelligent operation and maintenance as well as traffic safety. This paper investigates the application of deep learning in intelligently detecting road cracks and compares and analyzes Faster R-CNN and Mask R-CNN. The results show that the joint training strategy is effective, but it degrades the effectiveness of the bounding box detected by Mask R-CNN.
Article
Materials Science, Multidisciplinary
Xiangyang Xu, Zihan Wang, Peixin Shi, Wei Liu, Qiang Tang, Xiaohua Bao, Xiangsheng Chen, Hao Yang
Summary: This paper investigates the monitoring method of geometric deformation information of shield tunnels, proposes a method for identifying geometric features of tunnel sections based on the free-form B-spline approximation, and achieves intelligent recognition of common interference targets through the residual classification method. Furthermore, various Root Mean Squared Error (RMSE) distributions are investigated, which successfully realizes and verifies the clustering analysis of certain point cloud features.
MECHANICS OF ADVANCED MATERIALS AND STRUCTURES
(2023)
Article
Materials Science, Multidisciplinary
Ehsan Daneshkhah, Erasmo Carrera, Xiangyang Xu, Hao Yang
Summary: The Carrera Unified Formulation and full Green-Lagrange nonlinear relations are used to investigate the postbuckling behavior of laminated composite panels under in-plane shear and combined loadings. Layerwise refined plate models with efficient Lagrange expansion functions are employed to simulate the laminate thickness. The accuracy of the model is validated based on existing literature. The effects of stiffeners on the nonlinear response of the panels are evaluated, and a comprehensive assessment is provided for the equilibrium curves and stress distributions.
MECHANICS OF ADVANCED MATERIALS AND STRUCTURES
(2023)
Article
Chemistry, Analytical
Mian Zhao, Peixin Shi, Xunqian Xu, Xiangyang Xu, Wei Liu, Hao Yang
Summary: This paper proposes a deep learning-based method for road crack detection, which preprocesses the data using image sparse representation and compressed sensing to improve the accuracy and efficiency of crack identification. The experiments demonstrate that the method has good robustness and high detection efficiency.
Article
Materials Science, Multidisciplinary
Hao Yang, Xunqian Xu, Xiangyang Xu, Wei Liu
Summary: This paper verifies the reliability of deformation analysis of tunnel structures based on finite element method (FEM) simulation and point cloud processing through a combination of numerical simulation and full-field measurement. The result shows that FEM simulation and structural health monitoring analysis are consistent.
MECHANICS OF ADVANCED MATERIALS AND STRUCTURES
(2022)
Article
Engineering, Geological
Wei Liu, Xuan-yang Zhang, Ben Wu, Xiang-yang Xu
Summary: This paper proposes a novel two-dimensional failure mechanism for local stability of tunnel face in c-phi soils. The mechanism involves a hybrid failure with complex movement, incorporating translational and rotational movements. Through spatial discretization, the interface between failure blocks is constructed to meet compatibility requirements. The upper bound analysis considers energy dissipation along discontinuities and within failure blocks, deriving the solution for support pressure. Optimization is performed to select the optimal mechanism, obtain support pressure, and identify the failure mode. Parametric analysis explores the influence of soil shear strength on stability, revealing the significance of frictional angle compared to cohesion. The findings demonstrate the dominance of rotational or translational movement based on soil conditions, supporting previous research conclusions. The paper concludes with validation of the proposed solution through comparisons with analytical solutions and numerical simulations.
Article
Multidisciplinary Sciences
Xinran Li, Wuyin Jin, Xiangyang Xu, Hao Yang
Summary: The transfer learning method based on unsupervised domain adaptation (UDA) has been widely used in fault diagnosis research under different working conditions. In this paper, a domain-adversarial multi-graph convolutional network (DAMGCN) is proposed for UDA. The DAMGCN utilizes a multi-graph convolutional network to extract data structure information and aligns the differences in data structure through domain discriminators and classifiers. The classification and feature extraction ability of DAMGCN is significantly improved compared to other UDA algorithms, achieving effective cross-domain fault diagnosis for rolling bearings.
Article
Multidisciplinary Sciences
Jian Yang, Chen Wang, Jichao Yi, Yuankai Du, Maocheng Sun, Sheng Huang, Wenan Zhao, Shuai Qu, Jiasheng Ni, Xiangyang Xu, Ying Shang
Summary: This paper proposes a railway intrusion event classification and location scheme based on a distributed vibration sensing system. The 1DSE-ResNeXt+SVM method is used to improve accuracy and reliability. The method achieves high accuracy in field experiments, significantly enhancing railway safety.
Article
Multidisciplinary Sciences
Zihan Wang, Peixin Shi, Xunqian Xu, Xiangyang Xu, Feng Xie, Hao Yang
Summary: This paper proposes a new algorithm for the automatic identification of tunnel lining section curves and the optimization of curve geometry features. By combining B-spline and Euclidean clustering methods and comprehensively evaluating the denoising results, including precision, recall, F-score, and rand index (RI), the algorithm achieves automatic extraction and optimization of healthy point cloud data.