A Coarse-to-Fine Registration Approach for Point Cloud Data with Bipartite Graph Structure

Alignment is a critical aspect of point cloud data (PCD) processing, and we propose a coarse-to-fine registration method based on bipartite graph matching in this paper. After data pre-processing, the registration progress can be detailed as follows: Firstly, a top-tail (TT) strategy is designed to normalize and estimate the scale factor of two given PCD sets, which can combine with the coarse alignment process flexibly. Secondly, we utilize the 3D scale-invariant feature transform (3D SIFT) method to extract point features and adopt fast point feature histograms (FPFH) to describe corresponding feature points simultaneously. Thirdly, we construct a similarity weight matrix of the source and target point data sets with bipartite graph structure. Moreover, the similarity weight threshold is used to reject some bipartite graph matching error-point pairs, which determines the dependencies of two data sets and completes the coarse alignment process. Finally, we introduce the trimmed iterative closest point (TrICP) algorithm to perform fine registration. A series of extensive experiments have been conducted to validate that, compared with other algorithms based on ICP and several representative coarse-to-fine alignment methods, the registration accuracy and efficiency of our method are more stable and robust in various scenes and are especially more applicable with scale factors.

Download Full-text

On the Generation of Point Cloud Data Sets: Step One in the Knowledge Discovery Process

Interactive Knowledge Discovery and Data Mining in Biomedical Informatics - Lecture Notes in Computer Science ◽

10.1007/978-3-662-43968-5_4 ◽

2014 ◽

pp. 57-80 ◽

Cited By ~ 8

Author(s):

Andreas Holzinger ◽

Bernd Malle ◽

Marcus Bloice ◽

Marco Wiltgen ◽

Massimo Ferri ◽

...

Keyword(s):

Knowledge Discovery ◽

Point Cloud ◽

Data Sets ◽

Point Cloud Data ◽

Discovery Process ◽

Cloud Data

Download Full-text

GPU assisted processing of point cloud data sets for ground segmentation in autonomous vehicles

2013 IEEE Conference on Technologies for Practical Robot Applications (TePRA) ◽

10.1109/tepra.2013.6556352 ◽

2013 ◽

Cited By ~ 3

Author(s):

Stuart P. Baker ◽

Robert W. Sadowski

Keyword(s):

Autonomous Vehicles ◽

Point Cloud ◽

Data Sets ◽

Point Cloud Data ◽

Cloud Data ◽

Ground Segmentation

Download Full-text

Detection of geophysical features in InSAR point cloud data sets using spatiotemporal models

International Journal of Remote Sensing ◽

10.1080/01431161.2013.833357 ◽

2013 ◽

Vol 34 (22) ◽

pp. 8215-8234 ◽

Cited By ~ 10

Author(s):

Andrea Vaccari ◽

Michael Stuecheli ◽

Brian Bruckno ◽

Edward Hoppe ◽

Scott T. Acton

Keyword(s):

Point Cloud ◽

Data Sets ◽

Point Cloud Data ◽

Cloud Data ◽

Spatiotemporal Models ◽

Geophysical Features

Download Full-text

Topological pattern recognition for point cloud data

Acta Numerica ◽

10.1017/s0962492914000051 ◽

2014 ◽

Vol 23 ◽

pp. 289-368 ◽

Cited By ~ 73

Author(s):

Gunnar Carlsson

Keyword(s):

Pattern Recognition ◽

Algebraic Topology ◽

Point Cloud ◽

Metric Spaces ◽

Persistent Homology ◽

Topological Spaces ◽

Data Sets ◽

Point Cloud Data ◽

Cloud Data ◽

Finite Metric Spaces

In this paper we discuss the adaptation of the methods of homology from algebraic topology to the problem of pattern recognition in point cloud data sets. The method is referred to aspersistent homology, and has numerous applications to scientific problems. We discuss the definition and computation of homology in the standard setting of simplicial complexes and topological spaces, then show how one can obtain useful signatures, called barcodes, from finite metric spaces, thought of as sampled from a continuous object. We present several different cases where persistent homology is used, to illustrate the different ways in which the method can be applied.

Download Full-text

A NOVEL TIE POINT BASED STRATEGY FOR POINT CLOUD AND IMAGERY DATA FINE REGISTRATION

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-archives-xlii-4-w18-331-2019 ◽

2019 ◽

Vol XLII-4/W18 ◽

pp. 331-334

Author(s):

M. Eslami ◽

M. Saadatseresht

Keyword(s):

Point Cloud ◽

Laser Scanner ◽

Normal Vector ◽

Point Cloud Data ◽

Object Space ◽

Cloud Data ◽

Conditional Equation ◽

Novel Strategy ◽

Orientation Parameters ◽

Fine Registration

Abstract. Laser scanner generated point cloud and photogrammetric imagery are complimentary data for many applications and services. Misalignment between imagery and point cloud data is a common problem, which causes to inaccurate products and procedures. In this paper, a novel strategy is proposed for coarse to fine registration between close-range imagery and terrestrial laser scanner point cloud data. In such a case, tie points are extracted and matched from photogrammetric imagery and preprocessing is applied on generated tie points to eliminate non-robust ones. At that time, for every tie point, two neighbor pixels are selected and matched in all overlapped images. After that, coarse interior orientation parameters (IOPs) and exterior orientation parameters (EOPs) of the images are employed to reconstruct object space points of the tie point and its two neighbor pixels. Then, corresponding nearest points to the object space photogrammetric points are estimated in the point cloud data. Estimated three point cloud points are used to calculate a plane and its normal vector. Theoretically, every object space tie point should be located on the aforementioned plane, which is used as conditional equation alongside the collinearity equation to fine register the photogrammetric imagery network. Attained root mean square error (RMSE) results on check points, have been shown less than 2.3 pixels, which shows the accuracy, completeness and robustness of the proposed method.

Download Full-text

A Robust Initial Matching Scheme for Free-Form Object Geometry

Volume 2: 29th Computers and Information in Engineering Conference, Parts A and B ◽

10.1115/detc2009-86431 ◽

2009 ◽

Author(s):

Hsi-Yung Steve Feng ◽

Daoshan OuYang ◽

Nimun A. Jahangir ◽

Hao Song

Keyword(s):

Point Cloud ◽

Distance Measure ◽

Matching Condition ◽

Surface Shape ◽

Free Form ◽

Data Sets ◽

Point Cloud Data ◽

Cloud Data ◽

Numerical Iteration ◽

Rigid Body Transformation

The problem of matching two point cloud data sets, or identifying the correct rigid-body transformation between them, arises in various areas such as manufacturing inspection and object recognition. Existing 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 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 existing methods such as the iterative closest point method. Extensive case studies have shown that the proposed initial matching scheme is able to significantly improve the matching accuracy.

Download Full-text

BIM RECONSTRUCTION: AUTOMATED PROCEDURAL MODELING FROM POINT CLOUD DATA

ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences ◽

10.5194/isprs-archives-xlii-2-w17-53-2019 ◽

2019 ◽

Vol XLII-2/W17 ◽

pp. 53-60

Author(s):

M. Bassier ◽

L. Mattheuwsen ◽

M. Vergauwen

Keyword(s):

Point Cloud ◽

Reconstruction Algorithm ◽

Information Modeling ◽

Data Sets ◽

Point Cloud Data ◽

Ongoing Research ◽

Cloud Data ◽

Structure Information ◽

Wide Range ◽

Building Information

Abstract. The reconstruction of Building Information Modeling objects for as-built modeling is currently the subject of ongoing research. A popular method is to extract structure information from point cloud data to create a set of parametric objects. This requires the interpretation of the point cloud data which currently is a manual and labor intensive procedure. Automated processes have to cope with excessive occlusions and clutter in the data sets. To create an as-built BIM, it is vital to reconstruct the building’s structure i.e. wall geometry prior to the reconstruction of other objects.In this work, a novel method is presented to automatically reconstruct as-built BIM for generic buildings. We presented an unsupervised method that procedurally models the geometry of the walls based on point cloud data. A bottom-up process is defined where consecutively higher level information is extracted from the point cloud data using pre-trained machine learning models. Prior to the reconstruction, the data is segmented, classified and clustered to retrieve all the available observations of the walls. The resulting geometry is processed by the reconstruction algorithm. First, the necessary information is extracted from the observations for the creation of parametric solid objects. Subsequently, the final walls are created by updating their topology. The method is tested on a variety of scenes and shows promising results to reliably and accurately create as-built models. The accuracy of the generated geometry is similar to the precision of expert modelers. A key advantage is that that the algorithm creates Revit and Rhino native objects which makes the geometry directly applicable to a wide range of applications.

Download Full-text

Three-Dimensional Reconstruction of Single Input Image Based on Point Cloud

Photogrammetric Engineering & Remote Sensing ◽

10.14358/pers.87.7.479 ◽

2021 ◽

Vol 87 (7) ◽

pp. 479-484

Author(s):

Yu Hou ◽

Ruifeng Zhai ◽

Xueyan Li ◽

Junfeng Song ◽

Xuehan Ma ◽

...

Keyword(s):

Point Cloud ◽

Large Scale ◽

Three Dimensional ◽

Data Sets ◽

Point Cloud Data ◽

Three Dimensional Reconstruction ◽

Data Set ◽

Cloud Data ◽

Dimensional Reconstruction ◽

Institute Of Technology

Three-dimensional reconstruction from a single image has excellent future prospects. The use of neural networks for three-dimensional reconstruction has achieved remarkable results. Most of the current point-cloud-based three-dimensional reconstruction networks are trained using nonreal data sets and do not have good generalizability. Based on the Karlsruhe Institute of Technology and Toyota Technological Institute at Chicago ()data set of large-scale scenes, this article proposes a method for processing real data sets. The data set produced in this work can better train our network model and realize point cloud reconstruction based on a single picture of the real world. Finally, the constructed point cloud data correspond well to the corresponding three-dimensional shapes, and to a certain extent, the disadvantage of the uneven distribution of the point cloud data obtained by light detection and ranging scanning is overcome using the proposed method.

Download Full-text

NormNet: Point-wise normal estimation network for three-dimensional point cloud data

International Journal of Advanced Robotic Systems ◽

10.1177/1729881419857532 ◽

2019 ◽

Vol 16 (4) ◽

pp. 172988141985753 ◽

Cited By ~ 2

Author(s):

Janghun Hyeon ◽

Weonsuk Lee ◽

Joo Hyung Kim ◽

Nakju Doh

Keyword(s):

Point Cloud ◽

Nearest Neighbor ◽

Three Dimensional ◽

Local Feature ◽

Data Sets ◽

Point Cloud Data ◽

K Nearest Neighbor ◽

Cloud Data ◽

Normal Estimation ◽

Local Feature Extraction

In this article, a point-wise normal estimation network for three-dimensional point cloud data called NormNet is proposed. We propose the multiscale K-nearest neighbor convolution module for strengthened local feature extraction. With the multiscale K-nearest neighbor convolution module and PointNet-like architecture, we achieved a hybrid of three features: a global feature, a semantic feature from the segmentation network, and a local feature from the multiscale K-nearest neighbor convolution module. Those features, by mutually supporting each other, not only increase the normal estimation performance but also enable the estimation to be robust under severe noise perturbations or point deficiencies. The performance was validated in three different data sets: Synthetic CAD data (ModelNet), RGB-D sensor-based real 3D PCD (S3DIS), and LiDAR sensor-based real 3D PCD that we built and shared.

Download Full-text