With the ongoing developments in laser scanning technology, applications for describing tunnel deformation using rich point cloud data have become a significant topic of investigation. This study ...describes the independently developed CNU-TS-2 mobile tunnel monitoring system for data acquisition, which has an electric system to control its forward speed and is compatible with various laser scanners such as the Faro and Leica models. A comparison with corresponding data acquired by total station data demonstrates that the data collected by CNU-TS-2 is accurate. Following data acquisition, the overall and local deformation of the tunnel is determined by denoising and 360° deformation analysis of the point cloud data. To enhance the expression of the analysis results, this study proposes an expansion of the tunnel point cloud data into a two-dimensional image via cylindrical projection, followed by an expression of the tunnel deformation through color difference to visualize the deformation. Compared with the three-dimensional modeling method of visualization, this method is easier to implement and facilitates storage. In addition, it is conducive to the performance of comprehensive analysis of problems such as water leakage in the tunnel, thereby achieving the effect of multiple uses for a single image.
Sewerages are critical infrastructure assets for wastewater carriage in urban lifelines, but their function can be seriously affected by blockages or deterioration. Existing sewer pipeline inspection ...methods, such as closed-circuit television and sonar detection, have been blamed for low efficiency and considerable noise in the collected data. Therefore, this paper attempts to enhance the blockage and deterioration assessment inside the sewer pipeline by proposing a whale optimization algorithm-based point cloud data (WOAPCD) processing method. The method consists of an improved WOA for data clustering and fitting and a reverse slicing method for modeling the as-is conditions. The applicability of this proposed approach is validated in an actual sewerage system, and the results show that the WOAPCD can accurately and effectively reconstruct the 3D model of the sewer, providing valuable information for quantifying siltation conditions. The proposed method has better performance than PSO and GA in terms of the fitting error and modeling speed.
•Using remote operated vehicle to detect defects of sewers that filled with sewage.•A hybrid point cloud data processing method can effectively remove outliers and high-density noise.•WOAPCD mainly includes point clouds preprocessing, single-layer point clouds clustering and fitting, and 3D reconstruction.•WOAPCD reduce noise with a 1.18% error between the fitted transverse section and the real sewer radius.
Surface defect detection is essential feedback for quality control in manufacturing processes. This paper presents a new defect detection method, Surface Normal Gabor Filter (SNGF), to detect surface ...defects using laser scanning point cloud data. The SNGF method transfers the 3D point cloud data to surface normal vectors to normalize the surface topology geometry. The surface normal vectors are then converted into complex numbers and processed by a Gabor Filter to extract defect-induced geometric features. The feasibility of SNGF is validated in the case of studies for detecting different types of defects on textured surfaces through simulations and experiments. The experimental results show improved stability in detecting defects with different sizes compared to the conventional Region Growing Segmentation Algorithm (RGSA). In addition, test results show the running time of SNGF methods is up to 138 times shorter than the RGSA when processing point cloud data sets with a range of 19,600∼313,600 data points.
This article investigates the problem of acquiring 3D object maps of indoor household environments, in particular kitchens. The objects modeled in these maps include cupboards, tables, drawers and ...shelves, which are of particular importance for a household robotic assistant. Our mapping approach is based on PCD (point cloud data) representations. Sophisticated interpretation methods operating on these representations eliminate noise and resample the data without deleting the important details, and interpret the improved point clouds in terms of rectangular planes and 3D geometric shapes. We detail the steps of our mapping approach and explain the key techniques that make it work. The novel techniques include statistical analysis, persistent histogram features estimation that allows for a consistent registration, resampling with additional robust fitting techniques, and segmentation of the environment into meaningful regions.
Recently, 3D object detection based on deep learning has achieved impressive performance in complex indoor and outdoor scenes. Among the methods, the two-stage detection method performs the best; ...however, this method still needs improved accuracy and efficiency, especially for small size objects or autonomous driving scenes. In this paper, we propose an improved 3D object detection method based on a two-stage detector called the Improved Point-Voxel Region Convolutional Neural Network (IPV-RCNN). Our proposed method contains online training for data augmentation, upsampling convolution and k-means clustering for the bounding box to achieve 3D detection tasks from raw point clouds. The evaluation results on the KITTI 3D dataset show that the IPV-RCNN achieved a 96% mAP, which is 3% more accurate than the state-of-the-art detectors.
Building Information Modelling (BIM) is a globally adapted methodology by government organisations and builders who conceive the integration of the organisation, planning, development and the digital ...construction model into a single project. In the case of a heritage building, the Historic Building Information Modelling (HBIM) approach is able to cover the comprehensive restoration of the building. In contrast to BIM applied to new buildings, HBIM can address different models which represent either periods of historical interpretation, restoration phases or records of heritage assets over time. Great efforts are currently being made to automatically reconstitute the geometry of cultural heritage elements from data acquisition techniques such as Terrestrial Laser Scanning (TLS) or Structure From Motion (SfM) into BIM (Scan-to-BIM). Hence, this work advances on the parametric modelling from remote sensing point cloud data, which is carried out under the Rhino+Grasshopper-ArchiCAD combination. This workflow enables the automatic conversion of TLS and SFM point cloud data into textured 3D meshes and thus BIM objects to be included in the HBIM project. The accuracy assessment of this workflow yields a standard deviation value of 68.28 pixels, which is lower than other author’s precision but suffices for the automatic HBIM of the case study in this research.
Rotary crane systems are commonly utilized to transport heavy loads and hazardous materials from one location to another. Manual operation of a rotary crane is typically difficult for new or ...unskilled operators. Motion trajectory guidance for unskilled operators is necessary to prevent collision and ensure their safety as well as their efficient transfer. An algorithm for trajectory generation is developed by combining the A* algorithm and simple one degree of freedom (DOF) motion. Collision detection and information about the distance between the load and the nearest obstacle are also included in the algorithm to increase the operator’s cautiousness. Point cloud data and octree are implemented to represent the obstacles on the actual crane site. Simulation is implemented to verify the trajectory result with the proposed algorithm. In addition, an experiment combined with load-sway suppression is conducted based on the simulation result to confirm the effectiveness.
•Manually operated rotary cranes by new or unskilled operators.•Simple movements combination for manually operated rotary cranes.•Octree implementation for a rotary crane and surrounding environment.•Trajectory generation using simple movements combined with octree implementation result.
Falls from scaffolds cause the majority of accidents and fatalities at construction sites. A deep learning-based 3D reconstruction technology could provide a solution to prevent such fatalities ...through automated scaffold monitoring. However, when the technology was used at a large-scale construction site, there were limitations, such as the scarcity of point cloud data and the non-uniformity of points. To address this issue, this paper presents a large-scale scaffold reconstruction method using synthetic scaffold datasets and an upsampling adversarial network. The method consists of four steps: 1) data acquisition of scaffold point cloud through a mobile laser scanning (MLS) system, 2) 3D semantic segmentation using synthetic datasets, 3) upsampling of the segmented scaffold points, and 4) automatic generation of a 3D CAD model. The performance of the segmentation model trained with synthetic datasets achieved an 80.83% F1 score, which improved to 94.93% after upsampling.
•The proposed method reconstructs a large-scale scaffold using a MLS system.•A synthetic dataset generation algorithm was developed to overcome data scarcity.•Scaffold points became dense after using an upsampling adversarial network.•An F1 score for scaffold point clouds was 94.93%.
Among digital-based technologies to monitor forest ecosystems, personal laser scanning (PLS) has high potential to characterize even complex deciduous and rainforests. PLS data include a complete and ...detailed 3D representation of forest stands, but tree individuals need to be segmented accurately before retrieving tree characteristics. As manual on-screen segmentation is time-consuming and labor intensive, we suggest an automatic voxel-based region growing crown segmentation algorithm. Diameter at breast height (dbh), tree height, crown base height (cbh), crown projection area (cpa) and crown volume were automatically extracted from single tree point clouds. The methodology was validated on previously published PLS raw data in terms of segmentation accuracy and measurement precision. Manual segmentation, field measurements, and geometrical crown models were used as reference data. The overall segmentation accuracy of the crowns was 87.02%and tree height was accurately measured with a bias of −0.05 m and a root mean square deviation (RMSD) of 1.21 m (6.33%). Existing geometric crown models proved to be a realistic approximation of the true crown architecture and matched the measured tree crown volume with a bias of −4.62 m3 and a RMSD of 63.02 m3 (31.72%). Tree height and cpa were not affected by segmentation accuracy, but a major challenge remained in estimating cbh. The proposed methodology provides an efficient and low-cost solution for a fully automatic and digital forest inventory.
•Personal Laser Scanning is suitable to support forest inventory.•Efficient and accurate measurements on single trees require automatic software.•A region growing algorithm for individual tree segmentation achieved 87% accuracy.•Automatic tree height measurement has the same accuracy as field measurement.
Point cloud registration is an important task in robotics and autonomous driving to estimate the ego-motion of the vehicle. Recent advances following the coarse-to-fine manner show promising ...potential in point cloud registration. However, existing methods rely on good superpoint correspondences, which are hard to be obtained reliably and efficiently, thus resulting in less robust and accurate point cloud registration. In this paper, we propose a novel network, named RDMNet, to find dense point correspondences coarse-to-fine and improve final pose estimation based on such reliable correspondences. Our RDMNet uses a devised 3D-RoFormer mechanism to first extract distinctive superpoints and generates reliable superpoints matches between two point clouds. The proposed 3D-RoFormer fuses 3D position information into the transformer network, efficiently exploiting point clouds' contextual and geometric information to generate robust superpoint correspondences. RDMNet then propagates the sparse superpoints matches to dense point matches using the neighborhood information for accurate point cloud registration. We extensively evaluate our method on multiple datasets from different environments. The experimental results demonstrate that our method outperforms existing state-of-the-art approaches in all tested datasets with a strong generalization ability.
PDF
