A point-to-plane registration algorithm for orthogonal transformations

Makovetskii, Artyom; Voronin, S. M.; Kober, Vitaly; Voronin, Aleksei

doi:10.1117/12.2321396

Cited by 8 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nonetheless, the method is only applicable to the monotonic destination surface, and for non-monotonic surface the approximation leads to the large evaluation error. Makovetskii et al [32]- [34] proposed a point-to-plane registration algorithm based on orthogonal transformation (PTPROT), minimizing the square sum of the distances between the source points and the tangent planes at the destination point by Lagrange multiplier method and the standard SVD method [35]. Nevertheless, the optimization in these methods may generate an improper correspondence in the destination point cloud since the optimization based on the distance function yields the correspondence points far from the proper ones in the area with large fluctuation.…”

Section: Introductionmentioning

confidence: 99%

Modelling and simulation of the contour error evaluation based on spherically-approximated patches for freeform surface

Fan

Kang

Dai

et al. 2023

Preprint

View full text Add to dashboard Cite

The mathematical modelling of contour error evaluation in Computer Aided Manufacture (CAM) system is critical for high-precision measurement and manufacture of free-form surface. The existing methods of evaluating the contour errorfor free-form surface have been developed based on various models. Nevertheless, there still exist some of the shortcomings when applied practically, including the inaccurate distance model between the measured point cloud (MPC) and ideal surface, numerical search required for the correspondence, possible local optimum of solution, the inapplicability to all the surfaces, the huge point cloud required, and heavy computational load in the registration iteration, and so forth. Toovercome those shortcomings, this work proposes the spherically-approximated patch (SAP) registrationmethod for the contour error evaluation of free-form surface. The significance of registration between MPC and the SAP set is theoretically analyzed. The SAP set for the ideal surface is efficiently generated based on the centroid-midpoint search of parametric triangle subdivision (CMSPTS). And the tactics of efficiently computing the shortest distance from the MPC to the SAP set based on a local spreading search function (LSSF) is provided. Finally, the scheme of evaluating contour error based on the Point-To-SAP (PTSAP) registration is developed. The comparative simulation and experiment demonstrate that the proposed method raises the registration level between MPC and the ideal surface and produces the evaluation result closer to the theoretical one with an acceptable efficiency, and reduces the size of ideal point cloud compared with the existing methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Modelling and simulation of the contour error evaluation based on spherically-approximated patches for freeform surface

Fan

Kang

Dai

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The problem of registering point clouds in 3D space is fundamental in computational geometry and computer vision. In most cases, global refinement algorithms first find pairwise transformation parameters using, [2][3][4][5][6][7][8][9][10][11][12][13][14] and then evenly redistribute the errors using 1,15 graphbased optimizations. The graph-based SLAM problem uses a scanned graph, in which each scan corresponds to a vertex and each edge corresponds to a spatial relationship between pairs of nodes.…”

Section: Introductionmentioning

confidence: 99%

Multiple point cloud registration and global consistency condition

Makovetskii,

Voronin,

Kober

et al. 2023

Applications of Digital Image Processing XLVI

View full text Add to dashboard Cite

Point cloud registration is a central problem in many mapping and monitoring applications such as 3D model reconstruction, computer vision, autonomous driving, and others. Generating maps of the environment is often referred to as the Simultaneous Localization and Mapping (SLAM) problem. Note that some point clouds from the considered set may not have intersections. In this paper, we propose an algorithm to align the multiple point clouds based on an effective pairwise registration and a global refinement algorithm. The global refinement algorithm is non-iterative. Computer simulation results are provided to illustrate the performance of the proposed method.

show abstract

“…In this paper, we use for three-dimensional facial reconstruction and face alignment a resampling method based on a non-rigid ICP algorithm [8][9][10][11][12][13][14][15][16][17] instead of network-based methods. First, we convert a 3D scan to the "canonical form".…”

Section: Introductionmentioning

confidence: 99%

Facial recognition and 3D non-rigid registration

Makovetskii

Kober

Voronin

et al. 2020

2020 International Conference on Information Technology and Nanotechnology (ITNT)

Self Cite

View full text Add to dashboard Cite

The most efficient tool for human face recognition is neural networks. However, the result of recognition can be spoiled by facial expressions and other deviation from canonical face representation. In this paper, we propose a resampling method of human faces represented by 3D point clouds. The method is based on non-rigid Iterative Closest Point (ICP) algorithm. To improve the facial recognition performance we use a combination of the method and convolutional neural network (CNN). Computer simulation results are provided to illustrate the performance of the proposed approach.

show abstract

A point-to-plane registration algorithm for orthogonal transformations

Cited by 8 publications

References 9 publications

Modelling and simulation of the contour error evaluation based on spherically-approximated patches for freeform surface

Modelling and simulation of the contour error evaluation based on spherically-approximated patches for freeform surface

Multiple point cloud registration and global consistency condition

Facial recognition and 3D non-rigid registration

Contact Info

Product

Resources

About