A Modified SOFM Method for Point Cloud Segmentation in Reverse Engineering

The purpose of reverse engineering is to convert a large point cloud into a CAD model. In reverse engineering, the key issue is segmentation, i.e. studying how to subdivide the point cloud into smaller regions, where each of them can be approximated by a single surface. Segmentation is relatively simple, if regions are bounded by sharp edges and small blends; problems arise when smoothly connected regions need to be separated. In this paper, a modified self-organizing feature map neural network （SOFM） is used to solve segmentation problem. Eight dimensional feature vectors （3-dimensional coordinates, 3-dimensional normal vectors, Gaussian curvature and mean curvature） are taken as input for SOFM. The weighted Euclidean distance measure is used to improve segmentation result. The method not only can deal with regions bounded by sharp edges, but also is very efficient to separating smoothly connected regions. The segmentation method using SOFM is robust to noise, and it operates directly on the point cloud. An examples is given to show the effect of SOFM algorithm.

Effect of Lumbar Spinal Point Injection on Sitting Function in Children with Cerebral Palsy

Objective: To observe the effect of lumbar spinal point injection on sitting function in children with cerebral palsy. Method: Sixty-two children with post-confirmed cerebral palsy were randomly divided into control group and treatment group, 31 each. The control group was given conventional rehabilitation treatment, and the treatment group was given lumbar chiropspinal acupoint injection on the basis of the treatment method of the control group. After 3 consecutive courses of treatment, the sitting score of the two groups before and after treatment (GMFM88) was used to evaluate the sitting score before and after treatment. Outcome: Before treatment, the two groups were evaluated and the differences were not statistically significant (p > 0.05), which was comparable. The two groups (GMFM88) after treatment had significantly increased the differential values, and the difference was statistically significant compared with the same group before treatment (p Conclusion: Conventional rehabilitation combined with lumbar spinal point injection can effectively improve the sitting motor function of children with cerebral palsy.

3D reconstruction and defect pattern recognition of bonding wire based on stereo vision

Non-destructive detection of wire bonding defects in integrated circuits(IC)is critical for ensuring product quality after packaging.Image-processing-based methods do not provide a detailed evaluation of the three-dimensional defects of the bonding wire.Therefore,a method of 3D reconstruction and pattern recognition of wire defects based on stereo vision,which can achieve non-destructive detection of bonding wire defects is proposed.The contour features of bonding wires and other electronic components in the depth image is analysed to complete the 3D reconstruction of the bonding wires.Especially to filter the noisy point cloud and obtain an accurate point cloud of the bonding wire surface,a point cloud segmentation method based on spatial surface feature detection(SFD)was proposed.SFD can extract more distinct features from the bonding wire surface during the point cloud segmentation process.Furthermore,in the defect detection process,a directional discretisation descriptor with multiple local normal vectors is designed for defect pattern recognition of bonding wires.The descriptor combines local and global features of wire and can describe the spatial variation trends and structural features of wires.The experimental results show that the method can complete the 3D reconstruction and defect pattern recognition of bonding wires,and the average accuracy of defect recognition is 96.47%,which meets the production requirements of bonding wire defect detection.

Three Dimensional Laser Point Cloud Slicing Method for Calculating Irregular Volume

Volume parameter is the basic content of a spatial body object morphology analysis.However,the challenge lies in the volume calculation of irregular objects.The point cloud slicing method proposed in this study effectively works in calculating the volume of the point cloud of the spatial object obtained through three-dimensional laser scanning(3DLS).In this method,a uniformly spaced sequent slicing process is first conducted in a specific direction on the point cloud of the spatial object obtained through 3DLS.A series of discrete point cloud slices corresponding to the point cloud bodies are then obtained.Subsequently,the outline boundary polygon of the point cloud slicing is searched one by one in accordance with the slicing sequence and areas of the polygon.The point cloud slice is also calculated.Finally,the individual point cloud section volume is calculated through the slicing areas and the adjacent slicing gap.Thus,the total volume of the scanned spatial object can be calculated by summing up the individual volumes.According to the results and analysis of the calculated examples,the slice-based volume-calculating method for the point cloud of irregular objects obtained through 3DLS is correct,concise in process,reliable in results,efficient in calculation methods,and controllable on accuracy.This method comes as a good solution to the volume calculation of irregular objects.

Density‑Based Road Segmentation Algorithm for Point Cloud Collected by Roadside LiDAR

This paper proposes a novel density-based real-time segmentation algorithm,to extract ground point cloud in real time from point cloud data collected by roadside LiDAR.The algorithm solves the problems such as the large amount of original point cloud data collected by LiDAR,which leads to heavy computational burden in ground point search.First,point cloud data is filtered by straight-through filtering method and rasterized to improve the real-time performance of the algorithm.Then,the density of the point cloud in horizontal plane is calculated,and the threshold of the density is selected to extract the low-density regional point cloud according to the density statistical histogram and 95%loci.Finally,the low-density regional point cloud is used as the initial ground seeds for iterative optimization of ground parameters,and the ground point cloud is extracted by the fitted ground model to realize road point cloud extraction.The experimental results on 1055 frames of continuous data collected on real scenes show that the average time consumption of the proposed method is 0.11 s,and the average segmentation precision is 92.48%.This shows that the density-based road segmentation algorithm can reduce the time of point cloud traversal in the process of ground parameter fitting and improve the real-time performance of the algorithm while maintaining the accuracy of ground extraction.

A point cloud segmentation method for power lines and towersbased on a combination of multiscale density features andpoint-based deep learning

The point segmentation of power lines and towers aims to use unmanned aerial vehicles(UAVs)for the inspection of power facilities,risk detection and modelling.Because of the unclear spatial relationship between the point clouds,the point segmentation of power lines and towers is challenging.In this paper,the power line and tower point datasets are constructed using Light Detection and Ranging(LiDAR)and a point segmentation method is proposed based on multiscale density features and a point-based deep learning network.First,the data are blocked and the neighbourhood is constructed.Second,the point clouds are downsampled to produce sparse point clouds.The point clouds before and after sampling are rotated,and their density is calculated.Next,a direct mapping method is selected to fuse the density information;a lightweight network is built to learn the features.Finally,the point clouds are segmented by concatenating the local features provided by PointCNN.The algorithm performs effectively on different types of power lines and towers.The mean interaction over union is 82.73%,and the overall accuracy can reach 91.76%.This approach can achieve the end-to-end integration of segmentation and provide theoretical support for the segmentation of large scenic point clouds.

Fast Estimation of Loader’s Shovel Load Volume by 3D Reconstruction of Material Piles

Fast and accurate measurement of the volume of earthmoving materials is of great signifcance for the real-time evaluation of loader operation efciency and the realization of autonomous operation. Existing methods for volume measurement, such as total station-based methods, cannot measure the volume in real time, while the bucket-based method also has the disadvantage of poor universality. In this study, a fast estimation method for a loader’s shovel load volume by 3D reconstruction of material piles is proposed. First, a dense stereo matching method (QORB–MAPM) was proposed by integrating the improved quadtree ORB algorithm (QORB) and the maximum a posteriori probability model (MAPM), which achieves fast matching of feature points and dense 3D reconstruction of material piles. Second, the 3D point cloud model of the material piles before and after shoveling was registered and segmented to obtain the 3D point cloud model of the shoveling area, and the Alpha-shape algorithm of Delaunay triangulation was used to estimate the volume of the 3D point cloud model. Finally, a shovel loading volume measurement experiment was conducted under loose-soil working conditions. The results show that the shovel loading volume estimation method (QORB–MAPM VE) proposed in this study has higher estimation accuracy and less calculation time in volume estimation and bucket fll factor estimation, and it has signifcant theoretical research and engineering application value.

Predictive cruise control for heavy trucks based on slope information under cloud control system

With the advantage of fast calculation and map resources on cloud control system(CCS), cloud-based predictive cruise control(CPCC) for heavy trucks has great potential to improve energy efficiency, which is significant to achieve the goal of national carbon neutrality. However, most investigations focus on the on-board predictive cruise control(PCC) system,lack of research on CPCC architecture under CCS. Besides, the current PCC algorithms have the problems of a single control target and high computational complexity, which hinders the improvement of the control effect. In this paper, a layered architecture based on CCS is proposed to effectively address the realtime computing of CPCC system and the deployment of its algorithm on vehicle-cloud. In addition, based on the dynamic programming principle and the proposed road point segmentation method(RPSM), a PCC algorithm is designed to optimize the speed and gear of heavy trucks with slope information. Simulation results show that the CPCC system can adaptively control vehicle driving through the slope prediction, with fuel-saving rate of 6.17% in comparison with the constant cruise control. Also,compared with other similar algorithms, the PCC algorithm can make the engine operate more in the efficient zone by cooperatively optimizing the gear and speed. Moreover, the RPSM algorithm can reconfigure the road in advance, with a 91% roadpoint reduction rate, significantly reducing algorithm complexity.Therefore, this study has essential research significance for the economic driving of heavy trucks and the promotion of the CPCC system.

View suggestion for interactive segmentation of indoor scenes

Point cloud segmentation is a fundamental problem. Due to the complexity of real-world scenes and the limitations of 3D scanners, interactive segmentation is currently the only way to cope with all kinds of point clouds. However, interactively segmenting complex and large-scale scenes is very time-consuming.In this paper, we present a novel interactive system for segmenting point cloud scenes. Our system automatically suggests a series of camera views, in which users can conveniently specify segmentation guidance. In this way, users may focus on specifying segmentation hints instead of manually searching for desirable views of unsegmented objects, thus significantly reducing user effort. To achieve this, we introduce a novel view preference model, which is based on a set of dedicated view attributes, with weights learned from a user study. We also introduce support relations for both graph-cut-based segmentation and finding similar objects. Our experiments show that our segmentation technique helps users quickly segment various types of scenes, outperforming alternative methods.