scholarly journals HIERARCHICAL PROXIMITY-BASED OVER-SEGMENTATION OF 3-D POINT CLOUDS FOR EFFICIENT GRAPH FEATURE DETECTION

2020 ◽  
Vol V-2-2020 ◽  
pp. 273-280
Author(s):  
Z. Shtain ◽  
S. Filin
Keyword(s):  
Point Cloud ◽  
Surface Characterization ◽  
Feature Detection ◽  
Point Clouds ◽  
Free Form ◽  
Natural Scenes ◽  
General Strategy ◽  
Computationally Efficient ◽  
Definition Of ◽  
Point Cloud Simplification

Abstract. Point cloud simplification is empowered by the definition of similarity metrics which we aim to identify homogeneous regions within the point-cloud. Nonetheless, the variety of shapes and clutter in natural scenes, along with the significant resolution variations, occlusions, and noise, contribute to inconsistencies in the geometric properties, thereby making the homogeneity measurement challenging. Thus, the objective of this paper is to develop a point-cloud simplification model by means of data segmentation and to extract information in a better-suited way. The literature shows that most approaches either apply volumetric data strategies and/or resort to simplified planar geometries, which relate to only part of the entities found within a natural scene. To provide a more general strategy, we propose a proximity-based approach that allows an efficient and reliable surface characterization with no limitation on the number or shape of the primitives which in turn, enables detecting free-form objects. To achieve this, a local, computationally efficient and scalable metric is developed, which captures resolution variation and allows for short processing time. Our proposed scheme is demonstrated on datasets featuring a variety of surface types and characteristics. Experiments show high precision rates while exhibiting robustness to the varying resolution, texture, and occlusions that exist within the sets.

scholarly journals Worm Selector: Volume Selection in a 3D Point Cloud Through Adaptive Modelling

2017 ◽  
Vol 17 (1) ◽  
pp. 1-20 ◽  
Author(s):  
Emmanuel Dubois ◽  
Adrien Hamelin
Keyword(s):  
Point Cloud ◽  
User Study ◽  
Point Clouds ◽  
Ease Of Use ◽  
Free Form ◽  
3D Point Cloud ◽  
3D Point Clouds ◽  
3D Scanners ◽  
Definition Of ◽  
Straight Lines

3D point clouds are more and more widely used, especially because of the proliferation of manual and cheap 3D scanners and 3D printers. Due to the large size of the 3D point clouds, selecting part of them is very often required. Existing interaction techniques include ray/cone casting and predefined or free-form selection volume. In order to cope with the traditional trade-off between accuracy, ease of use and flexibility of these different forms of selection techniques in a 3D point cloud, we present the Worm Selector. It allows to select complex shapes while remaining simple to use and accurate. Using the Worm Selector relies on three principles: 1) points are selected by progressively constructing a cylinder-like shape (the adaptative worm) through the sequential definition of several sections; 2) a section is defined as a set of two contours linked together with straight lines; 3) each contour is a freely drawn closed shape. A user study reveals that the Worm Selector is significantly faster than a classical selection mechanism based on predefined volumes such as spheres or cuboids, while maintaining a comparable level of precision and recall.

scholarly journals SEMANTIC SEGMENTATION OF BUILDING ELEMENTS USING POINT CLOUD HASHING

2018 ◽  
Vol XLII-2 ◽  
pp. 241-250 ◽  
Author(s):  
M. Chizhova ◽  
A. Gurianov ◽  
M. Hess ◽  
T. Luhmann ◽  
A. Brunn ◽  
...  
Keyword(s):  
Point Cloud ◽  
Semantic Segmentation ◽  
Point Clouds ◽  
Probabilistic Networks ◽  
Component Design ◽  
Semantic Modelling ◽  
Segmentation Approach ◽  
Novel Method ◽  
Human Interpretation ◽  
Definition Of

For the interpretation of point clouds, the semantic definition of extracted segments from point clouds or images is a common problem. Usually, the semantic of geometrical pre-segmented point cloud elements are determined using probabilistic networks and scene databases. The proposed semantic segmentation method is based on the psychological human interpretation of geometric objects, especially on fundamental rules of primary comprehension. Starting from these rules the buildings could be quite well and simply classified by a human operator (e.g. architect) into different building types and structural elements (dome, nave, transept etc.), including particular building parts which are visually detected. The key part of the procedure is a novel method based on hashing where point cloud projections are transformed into binary pixel representations. A segmentation approach released on the example of classical Orthodox churches is suitable for other buildings and objects characterized through a particular typology in its construction (e.g. industrial objects in standardized enviroments with strict component design allowing clear semantic modelling).

scholarly journals An Automatic 3D Point Cloud Registration Method Based on Biological Vision

2021 ◽  
Vol 11 (10) ◽  
pp. 4538
Author(s):  
Jinbo Liu ◽  
Pengyu Guo ◽  
Xiaoliang Sun
Keyword(s):  
Point Cloud ◽  
Feature Detection ◽  
Surface Deformation ◽  
Point Clouds ◽  
Transformation Matrix ◽  
Point Cloud Registration ◽  
Biological Vision ◽  
Registration Method ◽  
Shape Fitting ◽  
Initial Values

When measuring surface deformation, because the overlap of point clouds before and after deformation is small and the accuracy of the initial value of point cloud registration cannot be guaranteed, traditional point cloud registration methods cannot be applied. In order to solve this problem, a complete solution is proposed, first, by fixing at least three cones to the target. Then, through cone vertices, initial values of the transformation matrix can be calculated. On the basis of this, the point cloud registration can be performed accurately through the iterative closest point (ICP) algorithm using the neighboring point clouds of cone vertices. To improve the automation of this solution, an accurate and automatic point cloud registration method based on biological vision is proposed. First, the three-dimensional (3D) coordinates of cone vertices are obtained through multi-view observation, feature detection, data fusion, and shape fitting. In shape fitting, a closed-form solution of cone vertices is derived on the basis of the quadratic form. Second, a random strategy is designed to calculate the initial values of the transformation matrix between two point clouds. Then, combined with ICP, point cloud registration is realized automatically and precisely. The simulation results showed that, when the intensity of Gaussian noise ranged from 0 to 1 mr (where mr denotes the average mesh resolution of the models), the rotation and translation errors of point cloud registration were less than 0.1° and 1 mr, respectively. Lastly, a camera-projector system to dynamically measure the surface deformation during ablation tests in an arc-heated wind tunnel was developed, and the experimental results showed that the measuring precision for surface deformation exceeded 0.05 mm when surface deformation was smaller than 4 mm.

scholarly journals A Saliency-Based Sparse Representation Method for Point Cloud Simplification

Sensors ◽  
2021 ◽  
Vol 21 (13) ◽  
pp. 4279
Author(s):  
Esmeide Leal ◽  
German Sanchez-Torres ◽  
John W. Branch-Bedoya ◽  
Francisco Abad ◽  
Nallig Leal
Keyword(s):  
Point Cloud ◽  
Feature Vector ◽  
Sparse Matrix ◽  
Point Clouds ◽  
Reconstruction Error ◽  
Normal Vector ◽  
Surface Simplification ◽  
Two Measures ◽  
Representation Method ◽  
Point Cloud Simplification

High-resolution 3D scanning devices produce high-density point clouds, which require a large capacity of storage and time-consuming processing algorithms. In order to reduce both needs, it is common to apply surface simplification algorithms as a preprocessing stage. The goal of point cloud simplification algorithms is to reduce the volume of data while preserving the most relevant features of the original point cloud. In this paper, we present a new point cloud feature-preserving simplification algorithm. We use a global approach to detect saliencies on a given point cloud. Our method estimates a feature vector for each point in the cloud. The components of the feature vector are the normal vector coordinates, the point coordinates, and the surface curvature at each point. Feature vectors are used as basis signals to carry out a dictionary learning process, producing a trained dictionary. We perform the corresponding sparse coding process to produce a sparse matrix. To detect the saliencies, the proposed method uses two measures, the first of which takes into account the quantity of nonzero elements in each column vector of the sparse matrix and the second the reconstruction error of each signal. These measures are then combined to produce the final saliency value for each point in the cloud. Next, we proceed with the simplification of the point cloud, guided by the detected saliency and using the saliency values of each point as a dynamic clusterization radius. We validate the proposed method by comparing it with a set of state-of-the-art methods, demonstrating the effectiveness of the simplification method.

scholarly journals VAULT MODELING WITH NEURAL NETWORKS

2019 ◽  
Vol XLII-2/W9 ◽  
pp. 81-86
Author(s):  
L. Barazzetti ◽  
M. Previtali
Keyword(s):  
Neural Networks ◽  
Point Cloud ◽  
Laser Scanning ◽  
Point Clouds ◽  
3D Models ◽  
Information Modeling ◽  
Free Form ◽  
Mathematical Representation ◽  
Mathematical Functions ◽  
Digital Reconstruction

<p><strong>Abstract.</strong> Nowadays, the digital reconstruction of vaults is carried out using photogrammetric and laser scanning techniques able to capture the visible surface with dense point clouds. Then, different modeling strategies allow the generation of 3D models in various formats, such as meshes that interpolates the acquired point cloud, NURBS-based reconstructions based on manual, semi-automated, or automated procedures, and parametric objects for Building Information Modeling. This paper proposes a novel method that reconstructs the visible surface of a vault using neural networks. It is based on the assumption that vaults are not irregular free-form objects, but they can be reconstructed by mathematical functions calculated from the acquired point clouds. The proposed approach uses the point cloud to train a neural network that approximates vault surface. The achieved solution is not only able to consider the basic geometry of the vault, but also its irregularities that cannot be neglected in the case of accurate and detailed modeling projects of historical vaults. Considerations on the approximation capabilities of neural networks are illustrated and discussed along with the advantages of creating a mathematical representation encapsulated into a function.</p>

scholarly journals Feature-Preserved Point Cloud Simplification Based on Natural Quadric Shape Models

2019 ◽  
Vol 9 (10) ◽  
pp. 2130 ◽  
Author(s):  
Kun Zhang ◽  
Shiquan Qiao ◽  
Xiaohong Wang ◽  
Yongtao Yang ◽  
Yongqiang Zhang
Keyword(s):  
Point Cloud ◽  
Shape Operator ◽  
Point Clouds ◽  
Data Set ◽  
Cloud Data ◽  
Shape Models ◽  
Huge Data ◽  
Key Points ◽  
Data Volume ◽  
Point Cloud Simplification

With the development of 3D scanning technology, a huge volume of point cloud data has been collected at a lower cost. The huge data set is the main burden during the data processing of point clouds, so point cloud simplification is critical. The main aim of point cloud simplification is to reduce data volume while preserving the data features. Therefore, this paper provides a new method for point cloud simplification, named FPPS (feature-preserved point cloud simplification). In FPPS, point cloud simplification entropy is defined, which quantifies features hidden in point clouds. According to simplification entropy, the key points including the majority of the geometric features are selected. Then, based on the natural quadric shape, we introduce a point cloud matching model (PCMM), by which the simplification rules are set. Additionally, the similarity between PCMM and the neighbors of the key points is measured by the shape operator. This represents the criteria for the adaptive simplification parameters in FPPS. Finally, the experiment verifies the feasibility of FPPS and compares FPPS with other four-point cloud simplification algorithms. The results show that FPPS is superior to other simplification algorithms. In addition, FPPS can partially recognize noise.

scholarly journals Increasing Spatio-Temporal Resolution for Monitoring Alpine Solifluction Using Terrestrial Laser Scanners and 3D Vector Fields

2021 ◽  
Vol 13 (6) ◽  
pp. 1192
Author(s):  
Christoph Holst ◽  
Jannik Janßen ◽  
Berit Schmitz ◽  
Martin Blome ◽  
Malte Dercks ◽  
...  
Keyword(s):  
Temporal Resolution ◽  
Point Cloud ◽  
Vector Fields ◽  
Feature Detection ◽  
Water Saturation ◽  
Point Clouds ◽  
Deformation Monitoring ◽  
The Arctic ◽  
High Mountain ◽  
Mountain Areas

This article investigates the usage of terrestrial laser scanner (TLS) point clouds for monitoring the gradual movements of soil masses due to freeze–thaw activity and water saturation, commonly referred to as solifluction. Solifluction is a geomorphic process which is characteristic for hillslopes in (high-)mountain areas, primarily alpine periglacial areas and the arctic. The movement can reach millimetre-to-centimetre per year velocities, remaining well below the typical displacement mangitudes of other frequently monitored natural objects, such as landslides and glaciers. Hence, a better understanding of solifluction processes requires increased spatial and temporal resolution with relatively high measurement accuracy. To that end, we developed a workflow for TLS point cloud processing, providing a 3D vector field that can capture soil mass displacement due to solifluction with high fidelity. This is based on the common image-processing techniques of feature detection and tracking. The developed workflow is tested on a study area placed in Hohe Tauern range of the Austrian Alps with a prominent assemblage of solifluction lobes. The derived displacements were compared with the established geomonitoring approach with total station and signalized markers and point cloud deformation monitoring approaches. The comparison indicated that the achieved results were in the same accuracy range as the established methods, with an advantage of notably higher spatial resolution. This improvement allowed for new insights considering the solifluction processes.

Registration of 3-D Shape with Free-Form Surface Using Imageware and Genetic Algorithm

2012 ◽  
Vol 472-475 ◽  
pp. 317-322 ◽  
Author(s):  
Xiao Yi Wang ◽  
Jing Chen ◽  
Jiang Zhu ◽  
Yoshio Saito ◽  
Tomohisa Tanaka
Keyword(s):  
Genetic Algorithm ◽  
Point Cloud ◽  
Point Clouds ◽  
Free Form ◽  
Work Piece ◽  
Cad Model ◽  
Manufacturing Accuracy ◽  
Free Form Surface ◽  
Point Data ◽  
Fine Registration

Registration of 3-D shape is significant in quantizing the error between the part and its CAD model and evaluating the part's manufacturing accuracy. In the past, various improved methods of the iterative closest point (ICP) had been proposed in registration. However, without fine initial pose of point clouds, the ICP algorithm often could not converge to the best (or near best) solution. According to the characteristics of 3-D shape with free-form surface, a new method for registration of 3-D shape with free-form surface is given, by which there are not rigid requests in initial pose of point data and the 3-D shape model could be in arbitrary positions and orientations in space. To improve the efficiency and accuracy of solving, this method is divided into general registration and fine registration. General registration is to fit rapidly and roughly the measured point cloud to designing point cloud from CAD model by Imageware. Fine registration is to further accurately fit the two group points using genetic algorithm (GA). Case study is finally given for a work piece with free-form surface to show the effectiveness of the above method.

scholarly journals LOCALIZATION OF PATHOLOGY ON COMPLEX ARCHITECTURE BUILDING SURFACES

2017 ◽  
Vol XLII-2/W3 ◽  
pp. 617-621 ◽  
Author(s):  
A. A. Sidiropoulos ◽  
K. N. Lakakis ◽  
V. K. Mouza
Keyword(s):  
Point Cloud ◽  
Laser Scanning ◽  
Principal Component ◽  
Point Clouds ◽  
Normal Vector ◽  
Northern Greece ◽  
Complex Building ◽  
Building Surfaces ◽  
Definition Of ◽  
Complex Architecture

The technology of 3D laser scanning is considered as one of the most common methods for heritage documentation. The point clouds that are being produced provide information of high detail, both geometric and thematic. There are various studies that examine techniques of the best exploitation of this information. In this study, an algorithm of pathology localization, such as cracks and fissures, on complex building surfaces is being tested. The algorithm makes use of the points’ position in the point cloud and tries to distinguish them in two groups-patterns; pathology and non-pathology. The extraction of the geometric information that is being used for recognizing the pattern of the points is being accomplished via Principal Component Analysis (PCA) in user-specified neighborhoods in the whole point cloud. The implementation of PCA leads to the definition of the normal vector at each point of the cloud. Two tests that operate separately examine both local and global geometric criteria among the points and conclude which of them should be categorized as pathology. The proposed algorithm was tested on parts of the Gazi Evrenos Baths masonry, which are located at the city of Giannitsa at Northern Greece.

Robust Initial Matching of Free-Form Objects Represented by Point Clouds

2012 ◽  
Vol 134 (2) ◽  
Author(s):  
Daoshan OuYang ◽  
Hsi-Yung Feng ◽  
Nimun A. Jahangir ◽  
Hao Song
Keyword(s):  
Point Cloud ◽  
Distance Measure ◽  
Point Clouds ◽  
Matching Condition ◽  
Surface Shape ◽  
Free Form ◽  
Data Sets ◽  
Point Cloud Data ◽  
Cloud Data ◽  
Geometric Inspection

The problem of best matching two point cloud data sets or, mathematically, identifying the best rigid-body transformation matrix between them, arises in many application areas such as geometric inspection and object recognition. Traditional methods establish the correspondence between the two data sets via the measure of shortest Euclidean distance and rely on an iterative procedure to converge to the solution. The effectiveness of such methods is highly dependent on the initial condition for the numerical iteration. This paper proposes a new robust scheme to automatically generate the needed initial matching condition. The initial matching scheme undertakes the alignment in a global manner and yields a rough match of the data sets. Instead of directly minimizing the distance measure between the data sets, the focus of the initial matching is on the alignment of shape features. This is achieved by evaluating Delaunay pole spheres for the point cloud data sets and analyzing their distributions to map out the intrinsic features of the underlying surface shape. The initial matching result is then fine-tuned by the final matching step via the traditional iterative closest point method. Case studies have been performed to validate the effectiveness of the proposed initial matching scheme.

Sign in / Sign up

Export Citation Format

Share Document