Measured Point Cloud Research Articles

Research on laser measurement point cloud preprocessing and 3D reconstruction technology for free-form surfaces.

Surface morphology measurement and reconstruction technology based on point cloud data is one of the key technologies for 3D information processing in the digital manufacturing industry and has been widely applied in fields such as reverse engineering, computer vision, and unmanned driving system navigation. A method for 3D modeling of aircraft-engine blade profiles based on laser measurement point cloud data is proposed to address the difficulties in measuring the 3D morphology of aircraft-engine blades and the low modeling accuracy. This method first preprocesses the measured point cloud and then uses Poisson's algorithm to reconstruct the blade surface in three dimensions based on the calculation of the point cloud normal. Through error statistical analysis, the overall reconstruction effect is good. The experimental results further validated the generality and effectiveness of this method.

Arch dam point cloud segmentation based on deep feature learning and normal vector data optimization

Separating the dam body, spillway, and other structures from the point cloud in the dam area is an important step in dam deformation monitoring. Manual segmentation is time consuming and inaccurate. This study proposes a point cloud segmentation neural network model based on normal vector optimization suitable for dam environment: (1) This model utilizes the voxel uniform sampling method of equal length cubes to solve the problem of uneven point cloud density caused by wide range and long-distance measurement during point cloud measurement in dam areas. (2) Designed block input and combined output modules in the model, achieving efficient input of large volume point cloud and eliminating the impact of interpolation points offset during seq2seq model decoding process. (3) In response to the diverse characteristics of point cloud normal vectors presented by vegetation, rock mass, and complex dam structures in the dam area, this paper proposes an adaptive radius plane fitting vector estimation method based on eigenvalue method to improve the accuracy of segmentation. The experiment on the prototype arch dam shows that the proposed normal estimation method improves the classification accuracy of PointNet + + from 96.26 to 98.27%. Compared with the other three normal estimation methods (2-jets, Hough CNN, iterative PCA), the overall accuracy is improved by 0.82%, 1.22%, and 0.22%, and the joint average intersection is improved by 0.0293, 0.0325, and 0.0104. The prototype arch dam experiment shows that our proposed method has a segmentation accuracy of 98.27%. Compared with 2-jets, Hough CNN, and iterative PCA, the overall accuracy has been improved by 0.82%, 1.22%, and 0.22%. This study provides a high-precision segmentation scheme for applications such as deformation detection of dam components based on point clouds.

Research on the Method for Recognizing Bulk Grain-Loading Status Based on LiDAR.

Grain is a common bulk cargo. To ensure optimal utilization of transportation space and prevent overflow accidents, it is necessary to observe the grain's shape and determine the loading status during the loading process. Traditional methods often rely on manual judgment, which results in high labor intensity, poor safety, and low loading efficiency. Therefore, this paper proposes a method for recognizing the bulk grain-loading status based on Light Detection and Ranging (LiDAR). This method uses LiDAR to obtain point cloud data and constructs a deep learning network to perform target recognition and component segmentation on loading vehicles, extract vehicle positions and grain shapes, and recognize and make known the bulk grain-loading status. Based on the measured point cloud data of bulk grain loading, in the point cloud-classification task, the overall accuracy is 97.9% and the mean accuracy is 98.1%. In the vehicle component-segmentation task, the overall accuracy is 99.1% and the Mean Intersection over Union is 96.6%. The results indicate that the method has reliable performance in the research tasks of extracting vehicle positions, detecting grain shapes, and recognizing loading status.

Point Cloud Measurement of Rubber Tread Dimension Based on RGB-Depth Camera

To achieve an accurate measurement of tread size after fixed-length cutting, this paper proposes a point-cloud-based tread size measurement method. Firstly, a mathematical model of corner points and a reprojection error is established, and the optimal solution of the number of corner points is determined by the non-dominated sorting genetic algorithm II (NSGA-II), which reduces the reprojection error of the RGB-D camera. Secondly, to address the problem of the low accuracy of the traditional pixel metric ratio measurement method, the random sampling consensus point cloud segmentation algorithm (RANSAC) and the oriented bounding box (OBB) collision detection algorithm are introduced to complete the accurate detection of the tread size. By comparing the absolute error and relative error data of several groups of experiments, the accuracy of the detection method in this paper reaches 1 mm, and the measurement deviation is between 0.14% and 2.67%, which is in line with the highest accuracy standard of the national standard. In summary, the RGB-D visual inspection method constructed in this paper has the characteristics of low cost and high inspection accuracy, which is a potential solution to enhance the pickup guidance of tread size measurement.

Mathematical Modeling for Robot 3D Laser Scanning in Complete Darkness Environments to Advance Pipeline Inspection

This paper introduces an autonomous robot designed for in-pipe structural health monitoring of oil/gas pipelines. This system employs a 3D Optical Laser Scanning Technical Vision System (TVS) to continuously scan the internal surface of the pipeline. This paper elaborates on the mathematical methodology of 3D laser surface scanning based on dynamic triangulation. This paper presents the mathematical framework governing the combined kinematics of the Mobile Robot (MR) and TVS. It discusses the custom design of the MR, adjusting it to use of robustized mathematics, and incorporating a laser scanner produced using a 3D printer. Both experimental and theoretical approaches are utilized to illustrate the formation of point clouds during surface scanning. This paper details the application of the simple and robust mathematical algorithm RANSAC for the preliminary processing of the measured point clouds. Furthermore, it contributes two distinct and simplified criteria for detecting defects in pipelines, specifically tailored for computer processing. In conclusion, this paper assesses the effectiveness of the proposed mathematical and physical method through experimental tests conducted under varying light conditions.

Bridging Formal Shape Models and Deep Learning: A Novel Fusion for Understanding 3D Objects

This article describes a novel fusion of a generative formal model for three-dimensional (3D) shapes with deep learning (DL) methods to understand the geometric structure of 3D objects and the relationships between their components, given a collection of unorganized point cloud measurements. Formal 3D shape models are implemented as shape grammar programs written in Procedural Shape Modeling Language (PSML). Users write PSML programs to describe complex objects, and DL networks estimate the configured free parameters of the program to generate 3D shapes. Users write PSML programs to enforce fundamental rules that define an object class and encode object attributes, including shapes, components, size, position, etc., into a parametric representation of objects. This fusion of the generative model with DL offers artificial intelligence (AI) models an opportunity to better understand the geometric organization of objects in terms of their components and their relationships to other objects. This approach allows human-in-the-loop control over DL estimates by specifying lists of candidate objects, the shape variations that each object can exhibit, and the level of detail or, equivalently, dimension of the latent representation of the shape. The results demonstrate the advantages of the proposed method over competing approaches.

Filtering the results of measurements three-dimensional geometry of objects by the phase triangulation method under non-stationary lighting conditions

The issues of improving the metrological characteristics of the phase triangulation method for measuring three-dimensional geometry are considered. In practice, external lighting is usually non-stationary, which affects the stability of measurement results. The paper proposes a method for filtering data received by a photodetector during measurements using the phase triangulation method under non-stationary lighting conditions. The method is based on frequency analysis of received data and filtering according to the criterion of the amplitude of the first harmonic in the frequency decomposition of the signal. The proposed method is implemented in the form of an algorithm for filtering the measured point cloud in a measuring complex that implements the phase triangulation method. The proposed method has been experimentally tested. A comparison was made of the filtering results obtained by the developed method based on frequency analysis of received data and the filtering method based on the analysis of amplitude modulation of the signal intensity recorded by a photodetector. Based on the results of a comparative analysis of the results of filtration by two methods, an increased (more than eight times) efficiency of the proposed filtration method was established. The results of the work will be useful in the field of processing and analysis of experimental results and for the development of optical methods for measuring three-dimensional geometry.

Research on 3D point cloud alignment algorithm based on SHOT features.

To overcome the problem of the high initial position of the point cloud required by the traditional Iterative Closest Point (ICP) algorithm, in this paper, we propose a point cloud registration method based on normal vector and directional histogram features (SHOT). Firstly, a hybrid filtering method based on the voxel idea is proposed and verified using the measured point cloud data, and the noise removal rates of 97.5%, 97.8%, and 93.8% are obtained. Secondly, in terms of feature point extraction, the original algorithm is optimized, and the optimized algorithm can better extract the missing part of the point cloud. Finally, a fine alignment method based on normal vector and directional histogram features (SHOT) is proposed, and the improved algorithm is compared with the existing algorithm. Taking the Stanford University point cloud data and the self-measured point cloud data as examples, the plotted iteration-error plots can be concluded that the improved method can reduce the number of iterations by 40.23% and 37.62%, respectively.

Fast Extraction Algorithm of Planar Targets Based on Point Cloud Data for Monitoring the Synchronization of Bridge Jacking Displacements

Transverse synchronization of vertical displacements of all jacking-up points is an important monitoring indicator to replace bearings in assembled multigirder bridges during the jacking phase. Currently, using target paper to identify the 3D coordinates of control points reduces the complexity of monitoring operations and improves the stability of data precision. However, the existing planar target locating methods have low accuracy, inefficiency, and subjectivity, which seriously hinders the construction process of bearing replacement. Accurately obtaining the center coordinates of multiple targets from a point cloud in a short monitoring period remains a challenge. This study proposes a high-precision automated algorithm to extract target center points in low-density point clouds to quickly calculate real target center points. First, we construct a standard point cloud model of the target papers for scanning, including color and geometric features. Then, we extract the measured point cloud of the typical jacking operation phase based on the reflection intensity and size information. Next, we map the intensity values of the measured point cloud into the color channel and register the measured point cloud with its standard point cloud model using the normal vector estimation and colored ICP algorithms. Finally, we extract the center point of the measured targets. Numerical experiments and engineering test results show that the proposed method converges quickly with high precision and good robustness, which saves 91.4% of the time compared with the traditional method. In general, this research can provide effective technical support for 3D laser scanning in monitoring the operation phase of bridge jacking.

Curvature generation based on weight-updated boosting using shoe last point-cloud measurements

Lasts are foot-shaped forms made of plastic, wood, aluminum, or 3D-printed plastic. The last of a shoe determines not only its shape and style but also how well it fits and protects the foot. A weight-updated boosting-based ensemble learning (WUBEL) algorithm is presented in this paper to extract critical features (points) from plantar pressure imaging to optimize the shoe's last surface to satisfy a comfortable shoe's last surface optimization design. An enhanced last design is constructed from the foot measurement data of the bottom surface of the base last, the critical control lines (points) of the shoe's last body, and the running-in degree of the pressure-sensitive area lattice data. Using a Likert scale (LS) and relevant evaluation indicators, we conducted an experimental evaluation and comparative study of our enhanced last design. With a point-cloud dataset, the proposed method performs highly effectively in constructing shoes, which will help diabetes patients find comfortable and customized shoes.

Assessing the spatial distribution of positional error associated to dense point cloud measurements using regional Gaussian random fields

Being able to assess the amount of uncertainty locally associated to dense point clouds generated by measurement can help investigate the relations between the metrological performance of a chosen measuring technology, and the local geometric and surface properties of the measurand geometry. In previous research it was demonstrated that spatial statistics based on Gaussian Random Fields and measurement repeats could be used to obtain spatial maps capturing both local dispersion and local bias associated to the position of points within measured clouds. However, the previous method had scalability limitations when handling very dense point clouds, due to it requiring the resolution of a global, increasingly larger, covariance matrix in order to solve the random field fitting problem. This work presents a variant to the previous method, where the covariance matrix is solved only locally, making the method better scalable to handle denser point clouds. Despite the new method not being able to return an equally rich information content in relation to spatial covariance, it still allows to obtain almost equally accurate information on local bias and variance, with significant gains in terms of processing speed and, importantly, making it now possible to handle very dense clouds which would be unviable to process with the original method.

A Framework for Synchronous Extraction of Multitype Steel Mesh Features Based on Measured Point Clouds

A Framework for Synchronous Extraction of Multitype Steel Mesh Features Based on Measured Point Clouds

Point Cloud Data Extraction Combining Surface Variation and Ransac for Digital Archiving of Shell Structures

The importance of digitally archiving existing architectures for cultural and research purposes is continuously increasing. Therefore, there are growing needs to extract significant data and reduce the amount of data in 3D measurements. Point clouds obtained from 3D surveys of entire buildings are expected to be used as a digital archive for various applications, such as structural analysis and renovation planning. However, effectively managing the vast amount of data from these surveys remains a challenge. Building point-clouds are typically massive and often contain unnecessary points and missing parts. This paper presents a novel method that combines surface variation and Random Sample Consensus (RANSAC) for determining the shape parameters of point clouds with curved surfaces. Our approach is efficient, not only in reconstructing surfaces of individual shells but also in handling combined and interpenetrated ones. The approach is also effective in processing the point cloud from actual measurement, demonstrating resilience to outliers and missing parts. Additionally, when applied to the measured point cloud for an example structure composed of seven intersecting domes, our approach accurately estimates the surface with an error margin of 0.06%–0.24%. Significant reduction in data volume, from 6.69 GB to 33 KB, is also achieved.

Blade profile extraction and edge completion method based on structured light measurement point cloud

Blade characteristic parameters evaluation plays an important role in quality monitoring and processing. In this research, a new blade profile extraction and edge completion strategy is proposed to deal with structured light measurement steam turbine blade. To handle the point cloud discretization and local data missing, the blade cross-sectional profiles are extracted adaptively at different heights, providing accurate and non-redundant data. Using NURBS and circular curves, the missing edge completion combines actual measurement curve trends and blade design geometric constraints, achieving a higher success rate and accuracy. Compared with the Perproj method and Virtual Edge method, the profile extraction accuracy of the proposed method is improved by 65 % and 36 % respectively, and the whole process of a sampled blade with additional noise is simulated to verify the effectiveness. Finally, more than two hundred blades are verified on the structured light measurement system, and the average absolute error of all parameters is less than 0.120 mm, which meets the accuracy requirements of blade quality evaluation in engineering applications.

Adaptive Drilling of Film Cooling Holes of Turbine Vanes Based on Registration of Point Clouds

The manufacture of film cooling holes on turbine guide vanes of an aero engine suffers from the contour errors resulting from a casting process. It is therefore necessary to adjust positions and orientations of cooling holes for each vane. This paper proposes an adaptive compensation machining method based on a combination of a principal component analysis iterative closest point (PCA-ICP) registration method and an orthocenter mapping method. Firstly, a registration is carried out between an ideal point cloud and a measured point cloud by a laser measurement machine to obtain a transformation matrix. Then, the exit center of a cooling hole is obtained by an orthocenter mapping method. Simulation results show that the machining errors of vanes can be improved from <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\pm$</tex-math></inline-formula> 0.1 mm to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\pm$</tex-math></inline-formula> 0.03 mm. Machining tests show that with a combination of the PCA-ICP registration and orthocenter mapping methods, the cooling holes are drilled adaptively to meet the machining requirements.

Quatro++: Robust global registration exploiting ground segmentation for loop closing in LiDAR SLAM

Global registration is a fundamental task that estimates the relative pose between two viewpoints of 3D point clouds. However, there are two issues that degrade the performance of global registration in LiDAR SLAM: one is the sparsity issue and the other is degeneracy. The sparsity issue is caused by the sparse characteristics of the 3D point cloud measurements in a mechanically spinning LiDAR sensor. The degeneracy issue sometimes occurs because the outlier-rejection methods reject too many correspondences, leaving less than three inliers. These two issues have become more severe as the pose discrepancy between the two viewpoints of 3D point clouds becomes greater. To tackle these problems, we propose a robust global registration framework, called Quatro++. Extending our previous work that solely focused on the global registration itself, we address the robust global registration in terms of the loop closing in LiDAR SLAM. To this end, ground segmentation is exploited to achieve robust global registration. Through the experiments, we demonstrate that our proposed method shows a higher success rate than the state-of-the-art global registration methods, overcoming the sparsity and degeneracy issues. In addition, we show that ground segmentation significantly helps to increase the success rate for the ground vehicles. Finally, we apply our proposed method to the loop closing module in LiDAR SLAM and confirm that the quality of the loop constraints is improved, showing more precise mapping results. Therefore, the experimental evidence corroborated the suitability of our method as an initial alignment in the loop closing. Our code is available at https://quatro-plusplus.github.io.

Reconstruction of Smooth Skin Surface Based on Arbitrary Distributed Sparse Point Clouds

Adaptively reconstruction of the skin surface covering the skeletons of aircrafts, ships, high-speed trains, buildings with steel frames, etc. based on on-site measured point clouds is an important issue in both industry and construction. However, the skeleton has the characteristics of long and narrow shape and variable structure, resulting in a narrow and sparse distribution of measured point cloud on its surface with variable shape in different areas, which brings great challenges to the reconstruction of skin surface. In this paper, a method for accurately reconstructing the skin surface covering the skeleton structures based on the arbitrary distributed sparse on-site measured points of the skeleton surface is proposed. At first, a robust B-spline curve fitting method based on the least square principle is proposed to construct the boundary curves of the point cloud. Then, a Coons-B-spline surface fitting method based on the generated boundary curves is proposed to generate an initial skin surface. Next, the initial skin surface is considered as a curved thin plate with stiffness, and a method of surface deformation considering the target points of deformation and the tensile and shear stiffness of the surface is proposed to obtain the surface with high accuracy and good smoothness. To show the feasibility of the proposed method, simulations and experiments are carried out. It is proved that the proposed method can achieve better accuracy while maintaining smoothness.

AN ASSESSMENT OF POINT CLOUD DATA ACQUISITION TECHNIQUES FOR AGGREGATE STOCKPILES AND VOLUMETRIC SURVEYS

Abstract. Stockpiling aggregate materials is a common practice within the construction industry and with the demand for aggregates rapidly increasing, stockpile owners have taken a greater interest in the effective determination of volumes of inventory to optimize profit and limit waste. Historically, traditional stockpile measurement techniques were inaccurate but with the increase in demand, a higher quality and more reliable assessment of resources is necessary.The evolution of point cloud measurement and mapping technology, such as UAV and Terrestrial Laser Scanning (TLS), now means these techniques can be utilized for stockpile measurements. While some of the advantages over traditional techniques have been well documented, there is still a need to ascertain which of these methods is more applicable for volumetric surveys of different types of aggregate stockpiles.This study involved data collection and analysis from TLS and UAV photogrammetry for volumetric surveys and comparisons with Total Station (TS) measurement of the stockpiles for sharp sand, coarse (gravel) and finer aggregates.The research suggested that TS surveys could only be effectively utilized on sharp sand and coarse aggregates and was impractical for finer aggregates, and their results produced a general under-reporting of stockpile volumes. TLS and UAV provide non-contact collection with increased accuracy. There are differences in accuracy and appropriateness dependent on the aggregate type. It was observed that the TLS outperformed the TS approach whereas UAV demonstrated promise particularly at a lower altitude with greater overlap.Additional recommendations are shared to potentially improve productivity and inventory maintenance for Stockpiling Operations.

Self-Supervised Depth Correction of Lidar Measurements From Map Consistency Loss

Depth perception is considered an invaluable source of information in the context of 3D mapping and various robotics applications. However, point cloud maps acquired using consumer-level <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">light detection and ranging</i> sensors (lidars) still suffer from bias related to local surface properties such as measuring beam-to-surface incidence angle. This fact has recently motivated researchers to exploit traditional filters, as well as the deep learning paradigm, in order to suppress the aforementioned depth sensors error while preserving geometric and map consistency details. Despite the effort, depth correction of lidar measurements is still an open challenge mainly due to the lack of clean 3D data that could be used as ground truth. In this paper, we introduce two novel point cloud map consistency losses, which facilitate self-supervised learning on real data of lidar depth correction models. Specifically, the models exploit multiple point cloud measurements of the same scene from different view-points in order to learn to reduce the bias based on the constructed map consistency signal. Complementary to the removal of the bias from the measurements, we demonstrate that the depth correction models help to reduce localization drift. Additionally, we release a data set that contains point cloud scans captured in an indoor corridor environment with precise localization and ground truth mapping information <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$^{1}$</tex-math></inline-formula> .

Method for detecting pipeline spatial attitude using point cloud alignment

This paper introduces a new method for detecting the spatial attitude of pipeline welding based on point cloud registration. The method aligns the measured point cloud of the pipeline with the CAD model point cloud using point cloud registration and guides the pipeline adjustment accordingly. This automated measurement method has resolved the inefficiencies and potential for rework that can arise from manual instrument operation during pipeline pose detection, and has subsequently improved detection efficiency and accuracy. In addition, we propose a coarse registration algorithm based on the axial line of pipeline point clouds to help facilitate the alignment process. We conducted simulation experiments using 3D CAD models, which demonstrated that our coarse registration algorithm outperformed the other three compared methods in terms of accuracy. The simulation experiments also proved that the absolute value of the overall method's relative error was less than 0.1%.