Implementing Point Assignment Using Octrees and GPU

2007 ◽  
Author(s):  
Koushik V. Aravalli ◽  
Thomas R. Kurfess ◽  
Thomas M. Tucker
Keyword(s):  
Point Cloud ◽  
Point Clouds ◽  
Computer Hardware ◽  
Model Complexity ◽  
Data Sets ◽  
Cad Model ◽  
Point Set Registration ◽  
Coordinate Metrology ◽  
Point Set ◽  
Processor Unit

Data point set registration is an important operation in coordinate metrology. Registration is the operation by which sampled point clouds are aligned with a CAD model by a 4×4 homogeneous transformation (e.g., rotation and translation). This alignment permits validation of the produced artifact’s geometry. Registration is an iterative nonlinear optimization operation assigning points on the CAD model for the sampled points. The objective is to minimize the sum of the squares of the normal distances between each point in the point cloud and the closest point in the CAD model. State-of-the-art metrology systems are now capable of generating thousands, if not millions, of data points during an inspection operation, resulting in increased computational power to fully utilize these larger data sets. The execution time for assigning the point set in registration process is directly related to the number of points processed and CAD model complexity. A brute force approach to registration, which is often used, is to compute the minimum distance between each sampled point and its normal projection on the CAD model. As the point cloud size and CAD model complexity increase, this approach becomes intractable and inefficient. This paper proposes a new approach to efficiently identify the closest point in the CAD model for a given point. This approach employs a combination of readily available computer hardware, graphical processor unit (GPU) and a formulation of the point assignment problem, using an octree data structure that is suited for execution on the GPU.

scholarly journals 3-D Point Cloud Registration Using Convolutional Neural Networks

2019 ◽  
Vol 9 (16) ◽  
pp. 3273 ◽  
Author(s):  
Wen-Chung Chang ◽  
Van-Toan Pham
Keyword(s):  
Pose Estimation ◽  
Point Cloud ◽  
Full Range ◽  
Point Clouds ◽  
Fixed Time ◽  
Training Data ◽  
Data Sets ◽  
Point Cloud Registration ◽  
Cloud Data ◽  
Model Point

This paper develops a registration architecture for the purpose of estimating relative pose including the rotation and the translation of an object in terms of a model in 3-D space based on 3-D point clouds captured by a 3-D camera. Particularly, this paper addresses the time-consuming problem of 3-D point cloud registration which is essential for the closed-loop industrial automated assembly systems that demand fixed time for accurate pose estimation. Firstly, two different descriptors are developed in order to extract coarse and detailed features of these point cloud data sets for the purpose of creating training data sets according to diversified orientations. Secondly, in order to guarantee fast pose estimation in fixed time, a seemingly novel registration architecture by employing two consecutive convolutional neural network (CNN) models is proposed. After training, the proposed CNN architecture can estimate the rotation between the model point cloud and a data point cloud, followed by the translation estimation based on computing average values. By covering a smaller range of uncertainty of the orientation compared with a full range of uncertainty covered by the first CNN model, the second CNN model can precisely estimate the orientation of the 3-D point cloud. Finally, the performance of the algorithm proposed in this paper has been validated by experiments in comparison with baseline methods. Based on these results, the proposed algorithm significantly reduces the estimation time while maintaining high precision.

Point Cloud to CAD Model Registration Methods in Manufacturing Inspection

2006 ◽  
Vol 6 (4) ◽  
pp. 418-421 ◽  
Author(s):  
Thomas M. Tucker ◽  
Thomas R. Kurfess
Keyword(s):  
Computer Vision ◽  
Virtual World ◽  
Point Cloud ◽  
Physical World ◽  
Coordinate Frame ◽  
Cad Model ◽  
Modern Computer ◽  
Coordinate Metrology ◽  
Flow Of Information

Modern computer vision and coordinate metrology systems provide an ever-increasing flow of information from the physical world we live in to the virtual world inside computer systems. Often the coordinate system of the metrology device has a different coordinate frame from that of the existing objects in the virtual world. To rectify these differences, a process called registration is often applied. This paper uses a case study to highlight the differences between various registration techniques.

Three Dimensional Imaging of LIGA-Made Microcomponents

2004 ◽  
Vol 126 (4) ◽  
pp. 813-821 ◽  
Author(s):  
Douglas Chinn ◽  
Peter Ostendorp ◽  
Mike Haugh ◽  
Russell Kershmann ◽  
Thomas Kurfess ◽  
...  
Keyword(s):  
Computer Aided Design ◽  
High Speed ◽  
Three Dimensional ◽  
Point Clouds ◽  
Three Dimensions ◽  
Cad Model ◽  
Volumetric Imaging ◽  
Data Registration ◽  
Liga Technology ◽  
Coordinate Metrology

Nickel and nickel-alloy microparts sized on the order of 5–1000 microns have been imaged in three dimensions using a new microscopic technique, Digital Volumetric Imaging (DVI). The gears were fabricated using Sandia National Laboratories’ LIGA technology (lithography, molding, and electroplating). The images were taken on a microscope built by Resolution Sciences Corporation by slicing the gear into one-micron thin slices, photographing each slice, and then reconstructing the image with software. The images were matched to the original CAD (computer aided design) model, allowing LIGA designers, for the first time, to see visually how much deviation from the design is induced by the manufacturing process. Calibration was done by imaging brass ball bearings and matching them to the CAD model of a sphere. A major advantage of DVI over scanning techniques is that internal defects can be imaged to very high resolution. In order to perform the metrology operations on the microcomponents, high-speed and high-precision algorithms are developed for coordinate metrology. The algorithms are based on a least-squares approach to data registration the {X,Y,Z} point clouds generated from the component surface onto a target geometry defined in a CAD model. Both primitive geometric element analyses as well as an overall comparison of the part geometry are discussed. Initial results of the micromeasurements are presented in the paper.

scholarly journals INVESTIGATIONS INTO THE QUALITY OF IMAGE-BASED POINT CLOUDS FROM UAV IMAGERY

2019 ◽  
Vol XLII-2/W13 ◽  
pp. 539-545 ◽  
Author(s):  
H.-J. Przybilla ◽  
M. Lindstaedt ◽  
T. Kersten
Keyword(s):  
Point Cloud ◽  
Laser Scanning ◽  
Image Data ◽  
Point Clouds ◽  
Data Sets ◽  
Test Field ◽  
Data Format ◽  
Software Packages ◽  
Dense Point

<p><strong>Abstract.</strong> The quality of image-based point clouds generated from images of UAV aerial flights is subject to various influencing factors. In addition to the performance of the sensor used (a digital camera), the image data format (e.g. TIF or JPG) is another important quality parameter. At the UAV test field at the former Zollern colliery (Dortmund, Germany), set up by Bochum University of Applied Sciences, a medium-format camera from Phase One (IXU 1000) was used to capture UAV image data in RAW format. This investigation aims at evaluating the influence of the image data format on point clouds generated by a Dense Image Matching process. Furthermore, the effects of different data filters, which are part of the evaluation programs, were considered. The processing was carried out with two software packages from Agisoft and Pix4D on the basis of both generated TIF or JPG data sets. The point clouds generated are the basis for the investigation presented in this contribution. Point cloud comparisons with reference data from terrestrial laser scanning were performed on selected test areas representing object-typical surfaces (with varying surface structures). In addition to these area-based comparisons, selected linear objects (profiles) were evaluated between the different data sets. Furthermore, height point deviations from the dense point clouds were determined using check points. Differences in the results generated through the two software packages used could be detected. The reasons for these differences are filtering settings used for the generation of dense point clouds. It can also be assumed that there are differences in the algorithms for point cloud generation which are implemented in the two software packages. The slightly compressed JPG image data used for the point cloud generation did not show any significant changes in the quality of the examined point clouds compared to the uncompressed TIF data sets.</p>

scholarly journals Pointwise Rotation-Invariant Network with Adaptive Sampling and 3D Spherical Voxel Convolution

2020 ◽  
Vol 34 (07) ◽  
pp. 12717-12724
Author(s):  
Yang You ◽  
Yujing Lou ◽  
Qi Liu ◽  
Yu-Wing Tai ◽  
Lizhuang Ma ◽  
...  
Keyword(s):  
Adaptive Sampling ◽  
Point Cloud ◽  
Data Augmentation ◽  
Feature Matching ◽  
State Of The Art ◽  
Point Clouds ◽  
Rotation Invariant ◽  
Learning Framework ◽  
Point Set ◽  
Part Segmentation

Point cloud analysis without pose priors is very challenging in real applications, as the orientations of point clouds are often unknown. In this paper, we propose a brand new point-set learning framework PRIN, namely, Pointwise Rotation-Invariant Network, focusing on rotation-invariant feature extraction in point clouds analysis. We construct spherical signals by Density Aware Adaptive Sampling to deal with distorted point distributions in spherical space. In addition, we propose Spherical Voxel Convolution and Point Re-sampling to extract rotation-invariant features for each point. Our network can be applied to tasks ranging from object classification, part segmentation, to 3D feature matching and label alignment. We show that, on the dataset with randomly rotated point clouds, PRIN demonstrates better performance than state-of-the-art methods without any data augmentation. We also provide theoretical analysis for the rotation-invariance achieved by our methods.

scholarly journals Analysis of the Spatial Differences in Canopy Height Models from UAV LiDAR and Photogrammetry

2020 ◽  
Vol 12 (18) ◽  
pp. 2884
Author(s):  
Qingwang Liu ◽  
Liyong Fu ◽  
Qiao Chen ◽  
Guangxing Wang ◽  
Peng Luo ◽  
...  
Keyword(s):  
Point Cloud ◽  
Forest Canopy ◽  
Point Clouds ◽  
Canopy Height ◽  
Central China ◽  
Data Sets ◽  
Interpolation Algorithm ◽  
Data Set ◽  
Spatial Differences ◽  
Mean Square Errors

Forest canopy height is one of the most important spatial characteristics for forest resource inventories and forest ecosystem modeling. Light detection and ranging (LiDAR) can be used to accurately detect canopy surface and terrain information from the backscattering signals of laser pulses, while photogrammetry tends to accurately depict the canopy surface envelope. The spatial differences between the canopy surfaces estimated by LiDAR and photogrammetry have not been investigated in depth. Thus, this study aims to assess LiDAR and photogrammetry point clouds and analyze the spatial differences in canopy heights. The study site is located in the Jigongshan National Nature Reserve of Henan Province, Central China. Six data sets, including one LiDAR data set and five photogrammetry data sets captured from an unmanned aerial vehicle (UAV), were used to estimate the forest canopy heights. Three spatial distribution descriptors, namely, the effective cell ratio (ECR), point cloud homogeneity (PCH) and point cloud redundancy (PCR), were developed to assess the LiDAR and photogrammetry point clouds in the grid. The ordinary neighbor (ON) and constrained neighbor (CN) interpolation algorithms were used to fill void cells in digital surface models (DSMs) and canopy height models (CHMs). The CN algorithm could be used to distinguish small and large holes in the CHMs. The optimal spatial resolution was analyzed according to the ECR changes of DSMs or CHMs resulting from the CN algorithms. Large negative and positive variations were observed between the LiDAR and photogrammetry canopy heights. The stratified mean difference in canopy heights increased gradually from negative to positive when the canopy heights were greater than 3 m, which means that photogrammetry tends to overestimate low canopy heights and underestimate high canopy heights. The CN interpolation algorithm achieved smaller relative root mean square errors than the ON interpolation algorithm. This article provides an operational method for the spatial assessment of point clouds and suggests that the variations between LiDAR and photogrammetry CHMs should be considered when modeling forest parameters.

scholarly journals Grasp Pose Detection in Point Clouds

2017 ◽  
Vol 36 (13-14) ◽  
pp. 1455-1473 ◽  
Author(s):  
Andreas ten Pas ◽  
Marcus Gualtieri ◽  
Kate Saenko ◽  
Robert Platt
Keyword(s):  
Point Cloud ◽  
Point Clouds ◽  
Sensor Data ◽  
Detection Methods ◽  
Cad Model ◽  
Success Rates ◽  
Pose Detection ◽  
Novel Objects ◽  
Partially Occluded ◽  
Robotic Grasp

Recently, a number of grasp detection methods have been proposed that can be used to localize robotic grasp configurations directly from sensor data without estimating object pose. The underlying idea is to treat grasp perception analogously to object detection in computer vision. These methods take as input a noisy and partially occluded RGBD image or point cloud and produce as output pose estimates of viable grasps, without assuming a known CAD model of the object. Although these methods generalize grasp knowledge to new objects well, they have not yet been demonstrated to be reliable enough for wide use. Many grasp detection methods achieve grasp success rates (grasp successes as a fraction of the total number of grasp attempts) between 75% and 95% for novel objects presented in isolation or in light clutter. Not only are these success rates too low for practical grasping applications, but the light clutter scenarios that are evaluated often do not reflect the realities of real-world grasping. This paper proposes a number of innovations that together result in an improvement in grasp detection performance. The specific improvement in performance due to each of our contributions is quantitatively measured either in simulation or on robotic hardware. Ultimately, we report a series of robotic experiments that average a 93% end-to-end grasp success rate for novel objects presented in dense clutter.

scholarly journals Point Set Multi-Level Aggregation Feature Extraction Based on Multi-Scale Max Pooling and LDA for Point Cloud Classification

2019 ◽  
Vol 11 (23) ◽  
pp. 2846 ◽  
Author(s):  
Tong ◽  
Li ◽  
Zhang ◽  
Chen ◽  
Zhang ◽  
...  
Keyword(s):  
Point Cloud ◽  
Laser Scanning ◽  
Single Point ◽  
Point Clouds ◽  
Max Pooling ◽  
Multi Scale ◽  
Cloud Classification ◽  
Point Set ◽  
Multi Level ◽  
Point Cloud Classification

Accurate and effective classification of lidar point clouds with discriminative features expression is a challenging task for scene understanding. In order to improve the accuracy and the robustness of point cloud classification based on single point features, we propose a novel point set multi-level aggregation features extraction and fusion method based on multi-scale max pooling and latent Dirichlet allocation (LDA). To this end, in the hierarchical point set feature extraction, point sets of different levels and sizes are first adaptively generated through multi-level clustering. Then, more effective sparse representation is implemented by locality-constrained linear coding (LLC) based on single point features, which contributes to the extraction of discriminative individual point set features. Next, the local point set features are extracted by combining the max pooling method and the multi-scale pyramid structure constructed by the point’s coordinates within each point set. The global and the local features of the point sets are effectively expressed by the fusion of multi-scale max pooling features and global features constructed by the point set LLC-LDA model. The point clouds are classified by using the point set multi-level aggregation features. Our experiments on two scenes of airborne laser scanning (ALS) point clouds—a mobile laser scanning (MLS) scene point cloud and a terrestrial laser scanning (TLS) scene point cloud—demonstrate the effectiveness of the proposed point set multi-level aggregation features for point cloud classification, and the proposed method outperforms other related and compared algorithms.

Ground filtering algorithm for mobile LIDAR using order and neighborhood point information

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Siyuan Huang ◽  
Limin Liu ◽  
Jian Dong ◽  
Xiongjun Fu ◽  
Leilei Jia
Keyword(s):  
Point Cloud ◽  
Point Clouds ◽  
Sorting Algorithm ◽  
Data Sets ◽  
Data Set ◽  
Spherical Coordinate ◽  
Content Type ◽  
Cloud Data ◽  
Filtering Algorithm ◽  
Field Environment

Purpose Most of the existing ground filtering algorithms are based on the Cartesian coordinate system, which is not compatible with the working principle of mobile light detection and ranging and difficult to obtain good filtering accuracy. The purpose of this paper is to improve the accuracy of ground filtering by making full use of the order information between the point and the point in the spherical coordinate. Design/methodology/approach First, the cloth simulation (CS) algorithm is modified into a sorting algorithm for scattered point clouds to obtain the adjacent relationship of the point clouds and to generate a matrix containing the adjacent information of the point cloud. Then, according to the adjacent information of the points, a projection distance comparison and local slope analysis are simultaneously performed. These results are integrated to process the point cloud details further and the algorithm is finally used to filter a point cloud in a scene from the KITTI data set. Findings The results show that the accuracy of KITTI point cloud sorting is 96.3% and the kappa coefficient of the ground filtering result is 0.7978. Compared with other algorithms applied to the same scene, the proposed algorithm has higher processing accuracy. Research limitations/implications Steps of the algorithm are parallel computing, which saves time owing to the small amount of computation. In addition, the generality of the algorithm is improved and it could be used for different data sets from urban streets. However, due to the lack of point clouds from the field environment with labeled ground points, the filtering result of this algorithm in the field environment needs further study. Originality/value In this study, the point cloud neighboring information was obtained by a modified CS algorithm. The ground filtering algorithm distinguish ground points and off-ground points according to the flatness, continuity and minimality of ground points in point cloud data. In addition, it has little effect on the algorithm results if thresholds were changed.

Sign in / Sign up

Export Citation Format

Share Document