Accuracy Of 3D Point Clouds Research Articles

Semantic Segmentation of 3D Point Clouds in Outdoor Environments Based on Local Dual-Enhancement

Semantic segmentation of 3D point clouds in drivable areas is very important for unmanned vehicles. Due to the imbalance between the size of various outdoor scene objects and the sample size, the object boundaries are not clear, and small sample features cannot be extracted. As a result, the semantic segmentation accuracy of 3D point clouds in outdoor environment is not high. To solve these problems, we propose a local dual-enhancement network (LDE-Net) for semantic segmentation of 3D point clouds in outdoor environments for unmanned vehicles. The network is composed of local-global feature extraction modules, and a local feature aggregation classifier. The local-global feature extraction module captures both local and global features, which can improve the accuracy and robustness of semantic segmentation. The local feature aggregation classifier considers the feature information of neighboring points to ensure clarity of object boundaries and the high overall accuracy of semantic segmentation. Experimental results show that provides clearer boundaries between various objects, and has higher identification accuracy for small sample objects. The LDE-Net has good performance for semantic segmentation of 3D point clouds in outdoor environments.

Improving completeness and accuracy of 3D point clouds by using deep learning for applications of digital twins to civil structures

In the Architecture, Engineering, and Construction (AEC) sector, digital twins rely on precise 3D models to convey digital information about physical structures in a virtual space. However, due to the vulnerability to measurement errors in weak-textured regions, 3D point clouds generated by conventional photometric consistency or deep learning-based Multi-View Stereo (MVS) algorithms are often incomplete or inaccurate. Therefore, this paper integrates the consistency constraint across multiple views and the inferential capacity of deep learning to propose a novel approach for refining the missing regions of the depth maps generated by photo-consistency based MVS algorithms. The proposed solution involves a cost volume pyramid-based depth completion (CVP-DC) network with three multi-level pyramid structures, which sequentially estimates and completes depth maps in a coarse-to-fine manner. A dataset that consists of input images and the corresponding depth maps generated by photo-consistency based MVS algorithms, along with output ground truth depth maps, is developed using an open DTU MVS dataset. CVP-DC demonstrates competitive performance when tested on the public DTU MVS dataset, outperforming existing MVS algorithms in terms of both completeness and accuracy. Additionally, experimental studies are conducted utilizing UAV-collected RTK (Real-Time Kinematic) images of an outdoor bridge pier to reconstruct point clouds with absolute scales. Experimental validations demonstrate the effectiveness and applicability of the proposed approach in filling uneven and incomplete depth maps, thereby enhancing the completeness of the generated point clouds. The proposed approach holds promise for establishing precise 3D models for the digital twin of the AEC sector.

3D Point Cloud Classification Method Based on Multiple Attention Mechanism and Dynamic Graph Convolution

In order to solve the problem of uneven density and the low classification accuracy of 3D point cloud, a 3D point cloud classification method fuses multi-attention machine is proposed. It is principally based on the traditional point cloud dynamic graph convolution classification network, into multiple attention mechanisms, including self-attention, spatial attention and channel attention mechanisms. The self-attention mechanism can reduce the dependence on irrelevant points while aligning point clouds, and input the processed point cloud into the classification network. Then the missing geometric information in the classification network is compensated by the integration of spatial and channel attention mechanisms. The experimental results on the public data set ModelNet40 indicate that compared with the DGCNN classification network, the improved network model improves the classification accuracy of the data set by 0.5 % and the average accuracy by 0.9 %. Meantime, the classification accuracy outstrips other contrast classification algorithms.

A digital hologram-based encryption and compression method for 3D models

This study proposes a novel method to compress and decompress the 3D models for safe transmission and storage. The 3D models are first extracted to become 3D point clouds, which would be classified by the K-means algorithm. Then, these nearby 3D point clouds are converted into a computer-generated hologram (CGH) by calculating the point distribution on the hologram plane using the optical wavefront propagation method. The computer-generated hologram (CGH) contains the spatial coordinate information on point clouds, which can be decompressed using the convolutional neural network (CNN) method. The decompression accuracy of 3D point clouds is quantitatively assessed by normalized correlation coefficients (NCCs), reflecting the correlation between two points and influenced by the hologram resolution, the convolution kernel, and the diffraction distance. Numerical simulations have shown that the novel method can reconstruct a high-quality 3D point cloud with an accuracy of 0.1 mm.

A Method for Improving the Measurement Accuracy of 3D Point Cloud of a Geothermal Power Plant Piping by UAV

A Method for Improving the Measurement Accuracy of 3D Point Cloud of a Geothermal Power Plant Piping by UAV

Evaluating the Structure from Motion Technique for Measurement of Bed Morphology in Physical Model Studies

The selection of instrumentation for data acquisition in physical model studies depends on type and resolution of data to be recorded, time frame of the model study, available instrumentation alternatives, availability of skilled personnel and overall budget of the model study. The available instrumentation for recording bed levels or three-dimensional information on geometry of a physical model range from simple manual gauges to sophisticated laser or acoustic sensors. In this study, Structure from Motion (SfM) technique was applied, on three physical model studies of different scales and study objectives, as a cheap, quicker, easy to use and satisfactorily precise alternative for recording 3D point data in form of colour coded dense point cloud representing the model geometry especially the river bed levels in the model. The accuracy of 3D point cloud generated with SfM technique were also assessed by comparing with data obtained from manual measurement using conventional surveying technique in the models and the results were found to be very promising.

Automated shape and pose updating of building information model elements from 3D point clouds

Generating an up-to-date BIM that accurately reflects as-built conditions is becoming necessary for ensuring fit between assemblies and construction sites. If an initial BIM (“proto-BIM”) could be automatically updated to reflect as-built conditions by changing shape and pose of BIM elements, it would be preferable over scan-to-BIM in many instances. An approach is presented herein for creating geometric agency within BIMs by exploiting their parametric capabilities, the accuracy of 3D point clouds, and the dexterity of metaheuristics. The result is a dynamic BIM (“dyna-BIM”) capable of updating its geometry to match a 3D point cloud. A case study for cast-in-place concrete footings shows how the average error between a BIM and the as-built conditions can be reduced from 50.4 mm to 5.69 mm. This paper provides a way to progressively capture accurate as-built conditions in BIM and predict potential assembly conflicts, while maintaining the initial semantics and fidelity of an as-designed BIM.

Multiple Plane Fitting Algorithm to Evaluate the Accuracy of 3D Point Cloud Using Structured Light Measurement

3D shape measurement by structured light is a high-speed method and capable of profiling complex surfaces. In particular, the processing of measuring data also greatly affects the accuracy of obtained point clouds. In this paper, an algorithm to detect multiple planes on point cloud data was developed based on RANSAC algorithm to evaluate the accuracy of point cloud measured by structural light. To evaluate the accuracy of the point cloud obtained, two-step height parts are used. The planes are detected and the distance between them needs to be measured with high accuracy. Therefore, the distance measurement data between the planes found in the point cloud is compared with the data measured by CMM measurement. The experimental results have shown that the proposed algorithm can identify multiple planes at the same time with a maximum standard deviation of 0.068 (mm) and the maximum relative error is 1.46%.

EVALUATION OF MOBILE MAPPING SYSTEMS FOR INDOOR SURVEYS

Abstract. With their high recording rate of hundreds of thousands of points acquired per second, speed of execution and a remote acquisition mode, SLAM based mobile mapping systems (MMS) are a very powerful solution for capturing 3D point clouds in real time, simply by walking in the area of interest. Regarding indoor surveys, these MMS have been integrated in handheld or backpack solutions and become fast scanning sensors. Despite their advantages, the geometric accuracy of 3D point clouds guaranteed with these sensors is lower than the one reachable with static TLS. In this paper the effectiveness of two recent mobile mapping systems namely the GeoSLAM ZEB-REVO RT and the more recent GreenValley LiBackPack C50 is investigated for indoor surveys. In order to perform a reliable assessment study, several datasets produced with each sensor are compared to the high-cost georeferenced point cloud obtained with static laser scanning target-based technique.

Determining the Optimal Number of Ground Control Points for Varying Study Sites through Accuracy Evaluation of Unmanned Aerial System-Based 3D Point Clouds and Digital Surface Models

The rapid development of drone technologies, such as unmanned aerial systems (UASs) and unmanned aerial vehicles (UAVs), has led to the widespread application of three-dimensional (3D) point clouds and digital surface models (DSMs). Due to the number of UAS technology applications across many fields, studies on the verification of the accuracy of image processing results have increased. In previous studies, the optimal number of ground control points (GCPs) was determined for a specific area of a study site by increasing or decreasing the amount of GCPs. However, these studies were mainly conducted in a single study site, and the results were not compared with those from various study sites. In this study, to determine the optimal number of GCPs for modeling multiple areas, the accuracy of 3D point clouds and DSMs were analyzed in three study sites with different areas according to the number of GCPs. The results showed that the optimal number of GCPs was 12 for small and medium sites (7 and 39 ha) and 18 for the large sites (342 ha) based on the overall accuracy. If these results are used for UAV image processing in the future, accurate modeling will be possible with minimal effort in GCPs.

Reconstruction of multi‐balloon copying curved surface based on linear distance field function optimisation

Aiming at the problems of low precision of three-dimensional (3D) curved surface reconstruction and poor surface smoothness of the reconstruction result, a method based on linear distance field function optimisation is proposed for the reconstruction of multi-balloon copying curved surface. First, curvature weighting is conducted for the curved surface point cloud model constructed with the Poisson's equation (PE), and the boundary value limiting condition of average curvature is used to conduct the smoothness processing of the curved surface; second, due to the dynamic deformation characteristic of multi-balloon copying curved surface, the linear distance field function is used to globally register the non-deformable area and the deformable area, and the distance field gradient is used to estimate the non-deformable area. Moreover, self-adaptive weight optimisation is conducted with the matching confidence level for deformable regions, thus to improve the registration accuracy of 3D point clouds. The simulation results show that the method proposed in this study improves the registration accuracy and surface reconstruction smoothness of standard PE.