Building Facade Point Clouds Segmentation Based on Optimal Dual-Scale Feature Descriptors

To address the current issues of inaccurate segmentation and the limited applicability of segmentation methods for building facades in point clouds, we propose a facade segmentation algorithm based on optimal dual-scale feature descriptors. First, we select the optimal dual-scale descriptors from a range of feature descriptors. Next, we segment the facade according to the threshold value of the chosen optimal dual-scale descriptors. Finally, we use RANSAC (Random Sample Consensus) to fit the segmented surface and optimize the fitting result. Experimental results show that, compared to commonly used facade segmentation algorithms, the proposed method yields more accurate segmentation results, providing a robust data foundation for subsequent 3D model reconstruction of buildings.

Aggregate Point Cloud Geometric Features for Processing

As 3D acquisition technology develops and 3D sensors become increasingly affordable,large quantities of 3D point cloud data are emerging.How to effectively learn and extract the geometric features from these point clouds has become an urgent problem to be solved.The point cloud geometric information is hidden in disordered,unstructured points,making point cloud analysis a very challenging problem.To address this problem,we propose a novel network framework,called Tree Graph Network(TGNet),which can sample,group,and aggregate local geometric features.Specifically,we construct a Tree Graph by explicit rules,which consists of curves extending in all directions in point cloud feature space,and then aggregate the features of the graph through a cross-attention mechanism.In this way,we incorporate more point cloud geometric structure information into the representation of local geometric features,which makes our network perform better.Our model performs well on several basic point clouds processing tasks such as classification,segmentation,and normal estimation,demonstrating the effectiveness and superiority of our network.Furthermore,we provide ablation experiments and visualizations to better understand our network.

Point Cloud Processing Methods for 3D Point Cloud Detection Tasks

Light detection and ranging(LiDAR)sensors play a vital role in acquiring 3D point cloud data and extracting valuable information about objects for tasks such as autonomous driving,robotics,and virtual reality(VR).However,the sparse and disordered nature of the 3D point cloud poses significant challenges to feature extraction.Overcoming limitations is critical for 3D point cloud processing.3D point cloud object detection is a very challenging and crucial task,in which point cloud processing and feature extraction methods play a crucial role and have a significant impact on subsequent object detection performance.In this overview of outstanding work in object detection from the 3D point cloud,we specifically focus on summarizing methods employed in 3D point cloud processing.We introduce the way point clouds are processed in classical 3D object detection algorithms,and their improvements to solve the problems existing in point cloud processing.Different voxelization methods and point cloud sampling strategies will influence the extracted features,thereby impacting the final detection performance.

Regression Method for Rail Fastener Tightness Based on Center-Line Projection Distance Feature and Neural Network

In the railway system,fasteners have the functions of damping,maintaining the track distance,and adjusting the track level.Therefore,routine maintenance and inspection of fasteners are important to ensure the safe operation of track lines.Currently,assessment methods for fastener tightness include manual observation,acoustic wave detection,and image detection.There are limitations such as low accuracy and efficiency,easy interference and misjudgment,and a lack of accurate,stable,and fast detection methods.Aiming at the small deformation characteristics and large elastic change of fasteners from full loosening to full tightening,this study proposes high-precision surface-structured light technology for fastener detection and fastener deformation feature extraction based on the center-line projection distance and a fastener tightness regression method based on neural networks.First,the method uses a 3D camera to obtain a fastener point cloud and then segments the elastic rod area based on the iterative closest point algorithm registration.Principal component analysis is used to calculate the normal vector of the segmented elastic rod surface and extract the point on the centerline of the elastic rod.The point is projected onto the upper surface of the bolt to calculate the projection distance.Subsequently,the mapping relationship between the projection distance sequence and fastener tightness is established,and the influence of each parameter on the fastener tightness prediction is analyzed.Finally,by setting up a fastener detection scene in the track experimental base,collecting data,and completing the algorithm verification,the results showed that the deviation between the fastener tightness regression value obtained after the algorithm processing and the actual measured value RMSE was 0.2196 mm,which significantly improved the effect compared with other tightness detection methods,and realized an effective fastener tightness regression.

A Gradient-Domain Based Geometry Processing Framework for Point Clouds

The use of point clouds is becoming increasingly popular. We present a general framework for performing geometry filtering on point-based surface through applying the meshless local Petrol-Galelkin （MLPG） to obtain the solution of a screened Poisson equation. The enhancement or smoothing of surfaces is controlled by a gradient scale parameter. Anisotropic filtering is supported by the adapted Riemannian metric. Contrary to the other approaches of partial differential equation for point-based surface, the proposed approach neither needs to construct local or global triangular meshes, nor needs global parameterization. It is only based on the local tangent space and local interpolated surfaces. Experiments demonstrate the efficiency of our approach.

Research on 3D Laser Scanning Reconstruction of Ancient Buildings Combined with BIM Technology

After more than 30 years of scientific and social development, surveying and mapping technology by leaps and bounds, engineering surveying technology has undergone tremendous changes. In the process of protecting ancient buildings, it is necessary to obtain the precise dimensions of architectural details. In this study, the path of 3D laser scanning combined with BIM technology is explored. Taking the observation and protection of the ancestral hall of the Liu family as an example, this study aims to draw drawings that reflect the relevant information about the ancient buildings, the accurate three-dimensional model of ancient buildings is established with BIM technology, which provides new methods and ideas for the research and protection of ancient buildings. .

Dynamic A^*path finding algorithm and 3D lidar based obstacle avoidance strategy for autonomous vehicles

This paper presents a novel dynamic A^*path finding algorithm and 3D lidar based local obstacle avoidance strategy for an autonomous vehicle.3D point cloud data is collected and analyzed in real time.Local obstacles are detected online and a 2D local obstacle grid map is constructed at 10 Hz/s.The A^*path finding algorithm is employed to generate a local path in this local obstacle grid map by considering both the target position and obstacles.The vehicle avoids obstacles under the guidance of the generated local path.Experiment results have shown the effectiveness of the obstacle avoidance navigation algorithm proposed.

Assessment of handheld mobile terrestrial laser scanning for estimating tree parameters

Sustainable forest management heavily relies on the accurate estimation of tree parameters.Among others,the diameter at breast height(DBH) is important for extracting the volume and mass of an individual tree.For systematically estimating the volume of entire plots,airborne laser scanning(ALS) data are used.The estimation model is frequently calibrated using manual DBH measurements or static terrestrial laser scans(STLS) of sample plots.Although reliable,this method is time-consuming,which greatly hampers its use.Here,a handheld mobile terrestrial laser scanning(HMTLS) was demonstrated to be a useful alternative technique to precisely and efficiently calculate DBH.Different data acquisition techniques were applied at a sample plot,then the resulting parameters were comparatively analysed.The calculated DBH values were comparable to the manual measurements for HMTLS,STLS,and ALS data sets.Given the comparability of the extracted parameters,with a reduced point density of HTMLS compared to STLS data,and the reasonable increase of performance,with a reduction of acquisition time with a factor of5 compared to conventional STLS techniques and a factor of3 compared to manual measurements,HMTLS is considered a useful alternative technique.

Comparison of heuristic and deep learning-based methods for ground classification from aerial point clouds

The automatic definition of the ground from 3D point clouds has been a common process for the last two decades,with many different approaches and applications that can be found in a vast literature.This paper presents a comparison of three different methodological concepts for ground classification,in order to establish the advantages and drawbacks of each method.First,a heuristic method,based on previous knowledge of the geometry and context of the 3D data.Secondly,a Deep Convolutional Network based on SegNet that classifies 2D images generated from the 3D point cloud.Finally,the third method applies a Deep Learning classification based on PointNet,which takes 3D points directly as inputs.To validate each method and compare them,public and labelled point clouds from the Actueel Hoogtebestand Nederland dataset are employed.Furthermore,the three methods are validated against the ISPRS 3D Semantic Labeling Contest benchmark.The results obtained show that the deep learning-based approaches outperform the heuristic method,with F-scores above 96%.The best results were obtained using a shallower version of SegNet,with F-score above 97%.

PCT:Point cloud transformer

The irregular domain and lack of ordering make it challenging to design deep neural networks for point cloud processing.This paper presents a novel framework named Point Cloud Transformer(PCT)for point cloud learning.PCT is based on Transformer,which achieves huge success in natural language processing and displays great potential in image processing.It is inherently permutation invariant for processing a sequence of points,making it well-suited for point cloud learning.To better capture local context within the point cloud,we enhance input embedding with the support of farthest point sampling and nearest neighbor search.Extensive experiments demonstrate that the PCT achieves the state-of-the-art performance on shape classification,part segmentation,semantic segmentation,and normal estimation tasks.

Two-sided ultrasonic surface rolling process of aeroengine blades based on on-machine noncontact measurement

As crucial parts of an aeroengine,blades are vulnerable to damage from long-term operation in harsh environments.The ultrasonic surface rolling process(USRP)is a novel surface treatment technique that can highly improve the mechanical behavior of blades.During secondary machining,the nominal blade model cannot be used for secondary machining path generation due to the deviation between the actual and nominal blades.The clamping error of the blade also affects the precision of secondary machining.This study presents a two-sided USRP(TS-USRP)machining for aeroengine blades on the basis of on-machine noncontact measurement.First,a TS-USRP machining system for blade is developed.Second,a 3D scanning system is used to obtain the point cloud of the blade,and a series of point cloud processing steps is performed.A local point cloud automatic extraction algorithm is introduced to extract the point cloud of the strengthened region of the blade.Then,the tool path is designed on the basis of the extracted point cloud.Finally,an experiment is conducted on an actual blade,with results showing that the proposed method is effective and efficient.

Skyline-Based Registration of 3D Laser Scans

Acquisition and registration of terrestrial 3D laser scans is a fundamental task in mapping and modeling of cities in three dimensions. To automate this task marker-flee registration methods are required. Based on the existence of skyline features, this paper proposes a novel method. The skyline features are extracted from panoramic 3D scans and encoded as strings enabling the use of string matching for merging the scans. Initial results of the proposed method in the old city center of Bremen are presented.