3D point cloud data processing with machine learning for construction and infrastructure applications: A comprehensive review

Mirzaei, Kaveh; Arashpour, Mehrdad; Asadi, Ehsan; Masoumi, Hossein; Bai, Yu; Behnood, Ali

doi:10.1016/j.aei.2021.101501

Cited by 83 publications

(26 citation statements)

References 149 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ALS point clouds are commonly classified according to their basic features and geometric features. The basic features of point clouds include 3D coordinate information, intensity information, echo information and GPS time [ 34 , 35 ]. The echo information represents the penetration ability of the laser.…”

Section: Methodsmentioning

confidence: 99%

A Classification Method of Point Clouds of Transmission Line Corridor Based on Improved Random Forest and Multi-Scale Features

Tang

Zhang

Lan

et al. 2023

Sensors

View full text Add to dashboard Cite

Classification of airborne laser scanning (ALS) point clouds of power lines is of great importance to their reconstruction. However, it is still a difficult task to efficiently and accurately classify the ground, vegetation, power lines and power pylons from ALS point clouds. Therefore, in this paper, a method is proposed to improve the accuracy and efficiency of the classification of point clouds of transmission lines, which is based on improved Random Forest and multi-scale features. The point clouds are filtered by the optimized progressive TIN densification filtering algorithm, then the elevations of the filtered point cloud are normalized. The features of the point cloud at different scales are calculated according to the basic features of the point cloud and the characteristics of transmission lines. The Relief F and Sequential Backward Selection algorithm are used to select the best subset of features to estimate the parameters of the learning model, then an Improved Random Forest classification model is built to classify the point clouds. The proposed method is verified by using three different samples from the study area and the results show that, compared with the methods based on Support Vector Machines, AdaBoost or Random Forest, our method can reduce feature redundancy and has higher classification accuracy and efficiency.

show abstract

Section: Methodsmentioning

confidence: 99%

A Classification Method of Point Clouds of Transmission Line Corridor Based on Improved Random Forest and Multi-Scale Features

Tang

Zhang

Lan

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Earthwork construction is characterized by a large area, which brings difficulties in scene perception and challenges for man-machine interaction between operators and construction machinery. The 3D modeling of the construction site can obtain the terrain and texture information of the whole construction site (Mirzaei et al, 2022), which can improve the safety of teleoperation.…”

Section: Three-dimensional Modeling Of the Construction Sitementioning

confidence: 99%

Earthwork digital twin for teleoperation of an automated bulldozer in edge dumping

You

Zhou

Ding

et al. 2023

Journal of Field Robotics

View full text Add to dashboard Cite

The unstructured construction site with a complex and changeable environment brings challenges to human–machine interaction. In this study, the earthwork digital twin (DT) is proposed to realize accurate and real‐time perception, which can support the teleoperation of an automated bulldozer. The overall framework includes anterior‐time DT, real‐time DT, and posterior‐time DT, which integrates three‐dimensional modeling, edge detection, and blade trajectory algorithms. Multidimensional heterogeneous data in bulldozer teleoperation can be displayed in real‐time to ensure construction safety. Big data during teleoperation of the construction process can be collected, stored, and analyzed. The DT proposed in this study was successfully applied in a major construction project in China, and testing results show its universality, robustness, and advanced performance. The key technologies proposed in this study can be applied to solve the common problems in the construction industry, which is promising for future intelligent construction.

show abstract

“…New measurement methods for evaluating products and equipment facilities have also emerged. In addition to product quality inspection, from global mapping to small area inspection, from basic science to public service, all point cloud data figures appear, and it plays an important role in global change, smart city, 8 resource survey, environmental inspection, basic mapping and many other fields, such as unmanned high-precision map generation in real time, 9 power corridor safety inspection, 10 cultural heritage digital protection, 11 urban morphology analysis, 12 forest resource survey, digital ground model establishment, and has been widely used in many engineering and typical fields.…”

Section: Introductionmentioning

confidence: 99%

Review: Research on product surface quality inspection technology based on 3D point cloud

Huo

Liu

Yang

et al. 2023

Advances in Mechanical Engineering

View full text Add to dashboard Cite

In recent years, machine vision has played an important role in product surface quality detection. The promotion and use of this technology have largely avoided the subjectivity caused by human detection and improved detection efficiency and accuracy. Different from the image data commonly used in machine vision, point cloud can describe the spatial structure of an object, provide more information than image data, and have the ability to expand the data to build multi-dimensional data models. Due to the strong anti-interference ability of point cloud sensors and the high accuracy of three-dimensional positioning information point cloud, nondestructive testing technology based on point cloud has received more and more attention. This paper summarizes the research progress of product surface quality detection methods based on 3D point cloud in recent years. According to different data processing methods, the detection research is divided into five categories: based on point cloud contour, based on local geometric feature, based on template matching, based on multimodal point cloud, and based on deep learning. The five methods are reviewed and summarized respectively. Finally, the key problems of each detection method and the future trend of product surface quality detection technology based on 3D point cloud are discussed.

show abstract

3D point cloud data processing with machine learning for construction and infrastructure applications: A comprehensive review

Cited by 83 publications

References 149 publications

A Classification Method of Point Clouds of Transmission Line Corridor Based on Improved Random Forest and Multi-Scale Features

A Classification Method of Point Clouds of Transmission Line Corridor Based on Improved Random Forest and Multi-Scale Features

Earthwork digital twin for teleoperation of an automated bulldozer in edge dumping

Review: Research on product surface quality inspection technology based on 3D point cloud

Contact Info

Product

Resources

About