Point Cloud Data Processing Research Articles

Development and Validation of a Point Cloud Data Processing Algorithm for Obstacle Recognition in Double Hull Block

<i>Shipyards have recently been experiencing severe labor shortages, prompting increased adoption of production automation systems to mitigate this issue. This paper introduces a point cloud data acquisition and processing system designed to support automation operations within double-hull block environments. The acquisition system utilizes LiDAR sensors and is built as a portable device capable of conducting 360-degree scans inside double-hull blocks. The processing system integrates the RANSAC algorithm for plane recognition and a voxelization algorithm for object detection, enabling accurate identification of obstacles within the double-hull block. To validate the system, a full-scale test bench was constructed to replicate actual working conditions. Experimental results indicated that the system could detect the positions of various obstacles within the test bench with an accuracy of up to 100 mm, which is sufficient for the implementation of automation systems. The findings from this research are expected to facilitate the adoption of production automation in shipyards, enhancing productivity and addressing labor shortages in the industry.</i>

Massive Point Cloud Processing for Efficient Construction Quality Inspection and Control

The construction of large-scale civil infrastructures requires massive spatiotemporal data to support the management and control of scheduling, quality control, and safety monitoring. Existing artificial-intelligence-based data processing algorithms rely heavily on experienced engineers to adjust the parameters of data processing, which is inefficient and time-consuming when dealing with huge datasets. Limited studies have compared the performance of different algorithms on a unified dataset. This study proposes a framework and evaluation system for comparing different data processing policies for processing huge spatiotemporal data in construction quality control. The proposed method compares the combination of multiple types of algorithms involved in the processing of massive point cloud data. The performance of data processing strategies is evaluated through this framework, and the optimal point cloud processing strategies are explored based on registration accuracy and data fidelity. Results show that a reasonable choice of combinations of point cloud sampling, filtering, and registration algorithms can significantly improve the efficiency of point cloud data processing and satisfy engineering demands for data accuracy and completeness. The proposed method can be applied to the civil engineering problem of processing a large amount of point cloud data and selecting the optimal processing method.

TrajectoryNAS: A Neural Architecture Search for Trajectory Prediction.

Autonomous driving systems are a rapidly evolving technology. Trajectory prediction is a critical component of autonomous driving systems that enables safe navigation by anticipating the movement of surrounding objects. Lidar point-cloud data provide a 3D view of solid objects surrounding the ego-vehicle. Hence, trajectory prediction using Lidar point-cloud data performs better than 2D RGB cameras due to providing the distance between the target object and the ego-vehicle. However, processing point-cloud data is a costly and complicated process, and state-of-the-art 3D trajectory predictions using point-cloud data suffer from slow and erroneous predictions. State-of-the-art trajectory prediction approaches suffer from handcrafted and inefficient architectures, which can lead to low accuracy and suboptimal inference times. Neural architecture search (NAS) is a method proposed to optimize neural network models by using search algorithms to redesign architectures based on their performance and runtime. This paper introduces TrajectoryNAS, a novel neural architecture search (NAS) method designed to develop an efficient and more accurate LiDAR-based trajectory prediction model for predicting the trajectories of objects surrounding the ego vehicle. TrajectoryNAS systematically optimizes the architecture of an end-to-end trajectory prediction algorithm, incorporating all stacked components that are prerequisites for trajectory prediction, including object detection and object tracking, using metaheuristic algorithms. This approach addresses the neural architecture designs in each component of trajectory prediction, considering accuracy loss and the associated overhead latency. Our method introduces a novel multi-objective energy function that integrates accuracy and efficiency metrics, enabling the creation of a model that significantly outperforms existing approaches. Through empirical studies, TrajectoryNAS demonstrates its effectiveness in enhancing the performance of autonomous driving systems, marking a significant advancement in the field. Experimental results reveal that TrajcetoryNAS yields a minimum of 4.8 higger accuracy and 1.1* lower latency over competing methods on the NuScenes dataset.

A novel method for the classification of 3D point clouds based on the improved PointNet++

Abstract In deep learning, point clouds are used as the primary input format for 3D data, which can provide detailed geometric information about objects in the original 3D space. PointNet++ is a deep learning network that uses point cloud data as an input format, which avoids the losses associated with the previous conversion of point cloud into 3D voxelization and a collection of 2D images. Although PointNet++ can directly process point cloud data in various ways, due to the disordered, irregular, and unevenly distributed nature of point cloud data, the effect of extracting point cloud features could be better. The large amount of point cloud data also leads to the training model falling into the local optimal solution, which affects the training results. In recent years, some effective methods and strategies have emerged to address these problems. In this thesis, three methods are proposed based on the PointNet++ network: feature similarity-based attention pooling, small kernel convolution, and diverse branch block method to improve the performance of the PointNet++ network. Experiments show that the improvement methods proposed in this paper effectively improve the feature extraction accuracy, which improves the accuracy of the PointNet++ network for classification on the ModelNet40_Normal_Resampled dataset, with an overall improvement of 1% compared with PointNet++.

Research on New Method for Safety Testing of Steel Structures—Combining 3D Laser Scanning Technology with FEA

This paper introduces a novel approach to assessing structural safety, specifically aimed at evaluating the safety of existing structures. Firstly, a point cloud model of the existing commercial complex was captured utilizing three-dimensional (3D) laser scanning technology. Subsequently, an intelligent method for identifying holes within the point cloud model was proposed, built upon a YOLO v5-based framework, to ascertain the dimensions and locations of holes within the commercial complex. Secondly, Poisson surface reconstruction, coupled with partially self-developed algorithms, was employed to reconstruct the surface of the structure, facilitating the three-dimensional geometric reconstruction of the commercial complex. Lastly, a finite element model of the framed structure with holes was established using the reconstructed 3D model, and a safety analysis was conducted. The research findings reveal that the YOLO v5-based intelligent hole identification method significantly enhances the level of intelligence in point cloud data processing, reducing manual intervention time and boosting operational efficiency. Furthermore, through Poisson surface reconstruction and the self-developed algorithms, we have successfully achieved automated surface reconstruction, where the resulting geometric model accurately reflects the dimensional information of the commercial complex. Additionally, the maximum uniformly distributed surface load that the floor slabs within the framed structure with holes can withstand should not exceed 17.7 kN/m2, and its vertical deformation resistance stiffness is approximately 71.6% of that of a frame without holes.

Gene pointNet for tumor classification

The rising incidence of cancer underscores the imperative for innovative diagnostic and prognostic methodologies. This study delves into the potential of RNA-Seq gene expression data to enhance cancer classification accuracy. Introducing a pioneering approach, we model gene expression data as point clouds, capitalizing on the data's intrinsic properties to bolster classification performance. Utilizing PointNet, a typical technique for processing point cloud data, as our framework's cornerstone, we incorporate inductive biases pertinent to gene expression and pathways. This integration markedly elevates model efficacy, culminating in developing an end-to-end deep learning classifier with an accuracy rate surpassing 99%. Our findings not only illuminate the capabilities of AI-driven models in the realm of oncology but also highlight the criticality of acknowledging biological dataset nuances in model design. This research provides insights into application of deep learning in medical science, setting the stage for further innovation in cancer classification through sophisticated biological data analysis. The source code for our study is accessible at: https://github.com/cialab/GPNet.

Wave-PCT: Wavelet point cloud transformer for point cloud quality assessment

Point cloud representation for real-world objects has seen a surge in interest recently, finding widespread applications in augmented reality, virtual reality, and autonomous driving. However, the process of acquiring, compressing, transmitting, and processing point cloud data often introduces unwanted distortions, highlighting the need for effective no-reference quality assessment methods for distorted point clouds. In this paper, we propose a Wavelet Point Cloud Transformer (Wave-PCT) method to assess the quality of point clouds without reference data. We start by performing patch sampling on a source point cloud, generating an extensive set of patches from the point cloud. These point cloud patches and their 2D projection images are processed using wavelets to produce multiscale local spectral features; moreover, we also extract global features of these patches using Pointnet++. Finally, a self-attention module is performed to fuse these local and global features, resulting in a distortion-sensitive quality score metric. We evaluate the Wave-PCT method on several point cloud quality assessment datasets using various metrics, and the experimental results indicate that the proposed framework exhibits outstanding and reliable performance when compared to various point cloud quality assessment methods.

FLApy: A Python package for evaluating the 3D light availability heterogeneity within forest communities

Abstract Light availability (LAv) dictates a variety of biological and ecological processes across a range of spatiotemporal scales. Quantifying the spatial pattern of LAv in three‐dimensional (3D) space can promote the understanding of microclimates that are critical to fine‐scale species distribution. However, there is still a lack of tools that are robust to evaluate spatiotemporal heterogeneity of LAv in forests. Here, we propose the Forest Light Analyzer python package (FLApy), an open‐source computational tool designed for the analysis of intra‐forest LAv variation across multiple spatial scales. FLApy is freely invoked by Python, facilitating the processing of LiDAR point cloud data into a 3D data container constructed by voxels, as well as traversal calculations related to the LAv regime by high performance synthetic hemispherical algorithm. Furthermore, FLApy incorporates 37 indicators, enabling users to expediently export and visualize LAv patterns and the evaluation of heterogeneity of LAv at two scales (voxel scale and 3D‐cluster scale) for a range of fine‐scale ecological study purposes. To validate the efficacy of the FLApy, we employed a simulated point cloud dataset that simulates forests (varying in canopy closure). Furthermore, to evaluate real world forest, we executed the standard workflow of FLApy utilizing drone‐derived data from three subtropical evergreen broad‐leaved forest dynamics plots within the Ailao Mountain Reserve. Our findings underscore that a series of indices derived from FLApy provide a robust characterization of light availability heterogeneity within diverse forest settings. Additionally, when juxtaposed with conventional monitoring techniques, the metrics offered by FLApy demonstrated better generality in our field assessments. FLApy offers ecologists a solution for rapid quantification of understory light 3D‐regimes across multiple scales, addressing the disparity between traditional manual approaches and the precision required for contemporary ecological studies. Moreover, FLApy provides robust support for the establishment and expansion of heterogeneity indices based on 3D micro‐environments, enhancing our understanding of the largely uncharted 3D structural patterns. Anticipated outcomes suggest that FLApy will enhance our knowledge concerning the intra‐forest climatic conditions into a 3D context, proving pivotal in the delineation of microhabitats and the development of detailed 3D‐scale species distribution models.

Reparation with moving least squares sampling and extraction of body sizes of beef cattle from unilateral point clouds

Body measurements of beef cattle at various growth stages are crucial for assessing breeding quality. To decrease the stress responses of live cattle during measurement, noncontact body size measurement using a deep sensor is conducted. After directly obtaining the point cloud data (PCD) of a unilateral surface, novel point cloud repair and body measurement are proposed. The PCD of beef cattle are first preprocessed using Euclidean clustering, conditional filtering, and Random Sample Consensus. To merge the unilateral PCD into the entire contour, a Euclidean transformation matrix and moving least squares are applied. To address holes caused by stitching due to camera angle restrictions, various upsampling techniques based on least squares deformation are investigated to repair holes in different surfaces with varying growth stages. Finally, polynomial fitting is chosen to be in accordance with the feature point distribution of the body height (BH), chest girth (CG), back height (AH), waist height (WH), ischial tuberosity, and shoulder end of beef cattle. Using the formulas of Euclidean distance and cubic B–spline curve fitting, the values of BH, AH, WH, CG, and body length are obtained and then compared with manual measurement data. The predicted values of the five body sizes of 100 beef cattle had a mean absolute error and mean absolute percentage error of 7.77 cm and 5.42 %, respectively. The largest absolute error was 12.05 cm, and the smallest absolute error was 4.12 cm. A series of PCD processing and repair methods provides a new method for the noncontact automated measurement of beef cattle. This approach promotes more effective practices in livestock welfare and trait assessment compared with traditional management.

Study on Morphometrical Urban Aerodynamic Roughness Multi-Scale Exploration Using LiDAR Remote Sensing

This study proposes the use of light detection and ranging (LiDAR) remote sensing (RS) to support morphometric research for estimating the aerodynamic roughness length (z0 ) of building placement on various scales. A LiDAR three-dimensional point cloud (3DPC) data processing graphical user interface (GUI) was developed to explore the z0 and related urban canopy parameters (UCPs) in the Incheon metropolitan area in South Korea. The results show that multi-scale urban aerodynamic roughness exploration is viable and can address differences in urban building data at various spatial resolutions. Although validating morphological multi-scale UCPs using dense tall towers is challenging, emerging low-cost and efficient methods can serve as substitutes. However, further efforts are required to link the measured z0 to building form regulations, such as floor area ratio, and expand RS research to obtain more quantitative and qualitative knowledge.

Fusion of Multiple Basic Element Features for Airborne LiDAR in-house Surveys

When using airborne LiDAR point clouds for city modelling and road extraction, point cloud classification is a crucial step. There are numerous ways for classifying point clouds, but there are still issues like redundant multi-dimensional feature vector data and poor point cloud classification in intricate situations. A point cloud classification method built on the fusing of multikernel feature vectors is suggested as a solution to these issues. The technique employs random forest to classify point cloud data by merging colour information, and it extracts feature vectors based on point primitives and object primitives, respectively. In this study, a densely populated area was chosen as the study area. Light airborne LIDAR mounted on a delta wing was used to collect point cloud data at a low altitude (170 m) over a dense cross-course. The point cloud data were then combined, corrected, and enhanced with texture data, and the houses were vectorized on the point cloud. The accuracy of the results was then assessed. With a median inaccuracy of 4.8 cm and a point cloud data collection rate of 83.3%, using airborne LIDAR to measure house corners can significantly lighten the labour associated with external house corner measurements.This test extracts the texture information of point cloud data through the efficient processing of high-density point cloud data, providing a reference for the application of texture information of airborne LIDAR data and a clear understanding of its accuracy.

An attention-based bilateral feature fusion network for 3D point cloud.

The widespread use of deep learning in processing point cloud data promotes the development of neural networks designed for point clouds. Point-based methods are increasingly becoming the mainstream in point cloud neural networks due to their high efficiency and performance. However, most of these methods struggle to balance both the geometric and semantic space of the point cloud, which usually leads to unclear local feature aggregation in geometric space and poor global feature extraction in semantic space. To address these two defects, we propose a bilateral feature fusion module capable of combining geometric and semantic data from the point cloud to enhance local feature extraction. In addition, we propose an offset vector attention module for better extraction of global features from point clouds. We provide specific ablation studies and visualizations in the article to validate our key modules. Experimental results show that the proposed method performs superior in both point cloud classification and segmentation tasks.

A Brief Discussion on the Overall Classification Algorithm of Airborne LiDAR Point Cloud

Abstract. Point cloud classification is the most important problem in airborne LiDAR point cloud data processing. In recent years, classification strategies with new theoretical background keep emerging, so it is urgent to make a more systematic and detailed summary of existing point cloud filtering algorithms, so that relevant researchers can have a more macroscopic and clear understanding of various algorithms and their advantages and disadvantages. Based on the characteristics of airborne LiDAR point cloud data, this paper combs the general process of point cloud classification. This paper summarizes the current mainstream classification methods and analyses their application effects in different scenarios, aiming at exploring and customizing suitable point cloud classification methods according to specific purpose objectives or industry standards. The point cloud classification is classified into three-level classification strategy. The first-level classification is gross error elimination, the second-level classification is point cloud filtering, which is to distinguish ground points from non-ground points. The third-level classification is to extract thematic point clouds from non-ground points according to application requirements. At present, the primary and secondary classification methods are relatively diverse and mature, reaching a certain level of application, while the tertiary classification is still in the initial stage of exploration, and large-scale application is not widespread.

AQUA: Analytics-driven quantum neural network (QNN) user assistance for software validation

This paper proposes a novel analytics-driven user assistance software validation approach for quantum neural network (QNN) codes. The proposed analytics-driven QNN user assistance (AQUA) for software validation considers user interactive feedback for constructing efficient QNN software. Our proposed AQUA is based on dynamic software testing and analysis due to undetermined qubit states in QNN which is hard to be tracked via static software analysis. AQUA is for plotting gradient variances to determine whether the QNN software suffers from local minima situations, which are called barren plateaus in QNN. By utilizing AQUA software validation, the stability, feasibility, and explainability of QNN software can be tested. AQUA has been tested using real-world case study with quantum convolutional neural network software for point cloud data processing in autonomous driving applications.

Measuring the profile of aircraft engine blades using spectral confocal sensors

The geometric parameters of aircraft engine blades need to be precisely measured to ensure the quality of the blades for the normal operation of aircraft engines. This study aims to address the challenges of existing measurement systems in balancing efficiency, accuracy, and completeness. Additionally, it aims to enhance the accuracy and robustness of the algorithm for extracting blade profile characteristic parameters. In this paper, a spectral confocal sensor is employed to establish a blade profile measurement system. The design includes a probe sampling strategy, and a standard ball is used to calibrate the sensor probe’s light emission direction and the precise rotation center of the turntable. The paper proposes the use of methods such as partition search algorithm, binary search, and curvature segmentation to process point cloud data of blade body and tenon. We have conducted experimental measurements on the blades of an aircraft engine. The acquired three-dimensional point cloud data of multiple sets of blade cross-sections and dovetail sections were processed. After calculation, the maximum measurement errors for chord length, maximum blade thickness, tenon width, bottom height, top angle, and bottom angle are −0.0036 mm, −0.00721 mm, −0.0102 mm, −0.00928 mm, 0.0086°, and −0.0058°, respectively. This process validates the effectiveness of the proposed method and has high measurement accuracy. Compared with the CMM method, this method is more accurate in measuring small pits and large curvature micro surfaces, with higher measurement integrity and higher measurement efficiency.

Optimizing Performance in Distributed Cloud Architectures: A Review of Optimization Techniques and Tools

This research paper presents a groundbreaking hybrid transactional/analytical processing (HTAP) architecture designed to revolutionize real-time point cloud data processing, particularly in autonomous driving environments. Integrating elements from both columnar and row-based tables within a spatial database, the proposed architecture offers unparalleled efficiency in managing and updating point cloud data in real-time. The architecture's distributed nature operates through a seamless synergy of Edge and Cloud components. The Edge segment operates within the Robot Operating System (ROS) environment of the vehicle, while the Cloud counterpart functions within the PostgreSQL environment of cloud services. The communication between these components is facilitated by Kafka, ensuring rapid and reliable data transmission. A pivotal aspect of the proposed system lies in its ability to autonomously detect changes in point cloud data over time. This is achieved through a sophisticated algorithm that analyzes dissimilarities in the data, triggering real-time updates in areas where high dissimilarity is detected. The system ensures the maintenance of the latest state of point cloud data, contributing significantly to the generation of safe and optimized routes for autonomous vehicles. In terms of optimization, the paper demonstrates how the HTAP architecture achieves real-time online analytical processing through query parallelization in a distributed database cluster. The system's efficacy is evaluated through simulations conducted in the CloudSim framework, showcasing its scalability, adaptability, and robustness in handling point cloud data processing for a single vehicle. While acknowledging the achievement of the proposed architecture, certain limitations are recognized. The study highlights the need for further investigation into the system's performance under simultaneous analysis and updates from multiple vehicles. Additionally, ensuring seamless scalability and robustness for uninterrupted operation and expansion during runtime is identified as an area requiring further development.

Influence of VF and SOR-Filtering Methods on Tree Height Inversion Using Unmanned Aerial Vehicle LiDAR Data

Forests, as the main body of the terrestrial ecosystem, have long been focal points for accurate structural parameter extraction. Among these parameters, tree height is a fundamental measurement factor that plays an important role in monitoring forest structure and biomass. The emergence of unmanned aerial vehicle light detection and ranging (UAV-LiDAR) technology has provided a strong guarantee of the acquisition of forest tree height parameters. However, UAV-LiDAR point cloud data have problems such as a large volume and data redundancy, and different point cloud data processing methods have different effects. Based on voxel filtering (VF) and statistical outlier removal (SOR)point cloud data processing experimental analysis, this study explored the influence of different filtering methods on the forest tree height inversion efficiency and accuracy. First, the point cloud data processed by VF is significantly better than that of SOR in terms of point cloud number, file size, running time, etc. The number of point clouds for VF decreased by an average of 96.91% compared with the original point clouds. Second, the VF tree height inversion accuracy was better than the tree height inversion data using SOR. The average accuracy of VF was 96.24%, while that of SOR was 94.17%. In summary, VF can effectively reduce data redundancy and improve tree height inversion accuracy.

Digital Restoration of Historical Buildings by Integrating 3D PC Reconstruction and GAN Algorithm

Historical architecture is an important carrier of cultural and historical heritage in a country and region, and its protection and restoration work plays a crucial role in the inheritance of cultural heritage. However, the damage and destruction of buildings urgently need to be repaired due to the ancient age of historical buildings and the influence of natural environment and human factors. Therefore, an artificial intelligence repair technology based on three-dimensional (3D) point cloud reconstruction and generative adversarial networks was proposed to improve the precision and efficiency of repair work. Firstly, in-depth research on the principles and algorithms of 3D point cloud data processing and generative adversarial networks should be conducted. Secondly, a digital restoration framework was constructed by combining these two artificial intelligence technologies to achieve precise and efficient restoration of historical buildings through continuous adversarial learning processes. The experimental results showed that the errors in the restoration of palace buildings, defense walls, pagodas, altars, temples, and mausoleums were 0.17, 0.12, 0.13, 0.11, and 0.09, respectively. The technique can significantly reduce the error while maintaining the high precision repair effect. This technology with artificial intelligence as the core has excellent accuracy and stability in the digital restoration. It provides a new technical means for the digital restoration of historical buildings and has important practical significance for the protection of cultural heritage.

ACCURACY RESEARCH OF THE EFFECT OF LOCAL SURFACE MODELING METHODS ON THE GENERATION OF 3D MODELS OF HISTORICAL OBJECTS WITH ROCK-BASED BUILDING STRUCTURES USING OPEN-SOURCE SOFTWARE

Abstract. The paper describes the effect of the local surface modelling methods known as plane, quadric and triangulation on the generation of the 3D mesh models of the historical objects with rock-based building structures using Cloudcompare, an open-source software for point cloud data processing. The methodology begins with data collection of the 3D test objects using terrestrial laser scanning technology, the pre-processing of the point cloud data, the point cloud subsampling process, the process of generating of the local surface modelling data, the process of generating the 3D mesh models and finally, the analysis, which involves the 3D surface deviation analysis between the generated 3D mesh models. The overall results shows that there are no significant differences between the 3D mesh models that was generated from all the three local surface modelling methods. The histogram analysis shows that the plane and the quadric local surface modelling methods is the best methods to be used in the research where the 3D test object to be modelled contains curvy surfaces without sharp edges and corners.

Combined Filtering Method for Offshore Oil and Gas Platform Point Cloud Data Based on KNN_PCF and Hy_WHF and Its Application in 3D Reconstruction.

With the increasing scale of deep-sea oil exploration and drilling platforms, the assessment, maintenance, and optimization of marine structures have become crucial. Traditional detection and manual measurement methods are inadequate for meeting these demands, but three-dimensional laser scanning technology offers a promising solution. However, the complexity of the marine environment, including waves and wind, often leads to problematic point cloud data characterized by noise points and redundancy. To address this challenge, this paper proposes a method that combines K-Nearest-Neighborhood filtering with a hyperbolic function-based weighted hybrid filtering. The experimental results demonstrate the exceptional performance of the algorithm in processing point cloud data from offshore oil and gas platforms. The method improves noise point filtering efficiency by approximately 11% and decreases the total error by 0.6 percentage points compared to existing technologies. Not only does this method accurately process anomalies in high-density areas-it also removes noise while preserving important details. Furthermore, the research method presented in this paper is particularly suited for processing large point cloud data in complex marine environments. It enhances data accuracy and optimizes the three-dimensional reconstruction of offshore oil and gas platforms, providing reliable dimensional information for land-based prefabrication of these platforms.