Hole Repairing Algorithm for 3D Point Cloud Model of Symmetrical Objects Grasped by the Manipulator
Abstract
:1. Introduction
1.1. Related Work
1.2. Motivation
1.3. Contribution and Outline
- 1.
- Design an automatic hole repair framework for the point cloud of symmetrical objects grasped by the manipulator, which can repair the mechanical claw holes and the missing surface automatically to obtain the complete point cloud.
- 2.
- Establish the virtual camera coordinate system to correct the pose of the 3D point cloud model and help calculate the bounding boxes to determine the filling regions of the holes.
- 3.
- Classify the hole boundaries automatically to deal with the nesting of the mechanical claw holes and the missing surface in the point cloud, and obtain their complete hole boundaries, respectively, which facilitates the different repair methods for the two kinds of holes.
- 4.
- Experiments on the simulated and real 3D point cloud models verify the hole repair effectiveness and robustness of the proposed framework.
2. Materials and Methods
2.1. Introduction to the Overall Framework
2.2. Hole Detection and Boundary Processing
2.2.1. Hole-Detection Method Based on Edge Detection
- A.
- Project the neighborhood points to the tangent plane.
- B.
- Distinguish inner points, original edge points and hole boundary points.
2.2.2. Hole Boundary Point Connection Method Based on Neighbors
2.2.3. Hole Boundary Classification Method
- A.
- Establish virtual camera coordinate system.
- B.
- Hole boundary classification based on the value in the z-axis.
2.2.4. Hole Boundary Repair Method Based on Spline Curve Fitting and Interpolation
2.3. Hole Repair
2.3.1. Repair Algorithm of Mechanical Claw Holes Based on Surface Reconstruction
2.3.2. Repair Algorithm of Missing Surface Based on Symmetry Completion
3. Results and Discussions
3.1. Evaluation of Hole Repair Effect for Simulated 3D Point Cloud Model
3.1.1. Comparative Experiments among Different Algorithms
3.1.2. Comparative Experiments among Models of Different Sizes
3.1.3. Comparative Experiment in Different Grasping Ways
3.2. Evaluation of Hole Repair Effect for Real 3D Point Cloud Model
4. Conclusions and Discussion
Author Contributions
Funding
Conflicts of Interest
References
- Whelan, T.; Leutenegger, S.; Salas-Moreno†, R.F.; Glocker, B.; Davison, A. ElasticFusion: Dense SLAM without a Pose Graph. In Proceedings of the Robotics: Science & Systems, Rome, Italy, 13–17 July 2015. [Google Scholar]
- Chun-Yen, C.; Kuo-Young, C. A sharpness-dependent filter for recovering sharp features in repaired 3d mesh models. IEEE Trans. Vis. Comput. Graph. 2008, 14, 200–212. [Google Scholar] [CrossRef] [PubMed]
- Wei, Z.; Zhong, Y.; Yuan, C.; Li, R. Research on smooth filling algorithm of large holes in triangular mesh model. China Mech. Eng. 2008, 19, 949–954. [Google Scholar]
- Wang, Y.H.; Wei-Yong, W.U. Holes repairing algorithm of scattered data based on the fitting of partial subdivision curved surface. J. Mach. Des. 2009, 26, 72–74. [Google Scholar]
- Yang, L.; Yan, Q.; Xiao, C. Shape-controllable geometry completion for point cloud models. J. Comput. Graph. 2017, 33, 385–398. [Google Scholar] [CrossRef]
- Lin, H.; Wei, W. Feature preserving holes filling of scattered point cloud based on tensor voting. In Proceedings of the IEEE International Conference on Signal & Image Processing, Beijing, China, 13–15 August 2017; pp. 402–406. [Google Scholar]
- Wang, Y.; Tang, J.; Zhao, Y.; Hao, W.; Lv, K. Point Cloud Hole Filling Based on Feature Lines Extraction. In Proceedings of the 2017 International Conference on Virtual Reality and Visualization (ICVRV), Zhengzhou, China, 21–22 October 2017; pp. 61–66. [Google Scholar]
- Tchapmi, L.P.; Kosaraju, V.; Rezatofighi, H.; Reid, I.; Savarese, S. TopNet: Structural Point Cloud Decoder. In Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, 15–21 June 2019; pp. 383–392. [Google Scholar]
- Huang, Z.; Yu, Y.; Xu, J.; Ni, F.; Le, X. PF-Net: Point Fractal Network for 3D Point Cloud Completion. In Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 14–19 June 2020; pp. 7659–7667. [Google Scholar]
- Chang, A.X.; Funkhouser, T.; Guibas, L.; Hanrahan, P.; Huang, Q.; Li, Z.; Savarese, S.; Savva, M.; Song, S.; Su, H.; et al. ShapeNet: An information-rich 3d model repository. Comput. Sci. 2015, 1512, 03012. [Google Scholar]
- ShapeNet Official Website. Available online: https://shapenet.org/ (accessed on 25 May 2021).
- Sun, D.; Fan, Z.; Li, Y. Automatic extraction of boundary characteristic from scatter data. J. Huazhong Univ. Sci. Technol. 2008, 36, 82–84. [Google Scholar]
- Zou, D.; Pang, M. Algorithm for extracting sharp features from point cloud models. Trans. Chin. Soc. Agric. Mach. 2011, 42, 217–222. [Google Scholar]
- Removing Outliers Using a StatisticalOutlierRemoval Filter. Available online: https://pcl.readthedocs.io/projects/tutorials/en/latest/statistical_outlier.html#statistical-outlier-removal (accessed on 12 June 2021).
- Gu, Y.; Jiang, X.; Zhang, L. Research and implement of hole-repairing technology for scatted point cloud. J. SooChow Univ. 2008, 28, 56–61. [Google Scholar]
- Fischler, M.A.; Bolles, R.C. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography—Sciencedirect. Commun. ACM 1987, 24, 726–740. [Google Scholar] [CrossRef]
- Schnabel, R.; Wahl, R.; Klein, R. Efficient ransac for point-cloud shape detection. Comput. Graph. Forum 2010, 26, 214–226. [Google Scholar] [CrossRef]
- Kazhdan, M.; Bolitho, M.; Hoppe, H. Poisson surface reconstruction. In Proceedings of the Fourth Eurographics Symposium on Geometry Processing, Sardinia, Italy, 26–28 June 2006. [Google Scholar]
- Kazhdan, M.; Hoppe, H. Screened Poisson surface reconstruction. ACM Trans. Graph. (ToG) 2013, 32, 1–13. [Google Scholar] [CrossRef] [Green Version]
- Lorensen, W.E.; Cline, H.E. Marching cubes: A high resolution 3D surface construction algorithm. ACM Siggraph Comput. Graph. 1987, 21, 163–169. [Google Scholar] [CrossRef]
- Newman, T.S.; Yi, H. A survey of the marching cubes algorithm. Comput. Graph. 2006, 30, 854–879. [Google Scholar] [CrossRef]
- Point Cloud Library (PCL)—pcl: Poisson< PointNT > Class Template Reference. Available online: https://pointclouds.org/documentation/classpcl_1_1_poisson.html (accessed on 15 June 2021).
- DISWAY, DC-AB 3D Scanner with High-Precision and Multipurpose. Available online: http://www.hbdc3d.com/smy/91.html (accessed on 23 May 2021).
- Autodesk Meshmixer—Free Software for Making Awesome Stuff. Available online: https://www.meshmixer.com/ (accessed on 6 June 2021).
- Geomagic Releases Geomagic Studio 2012. Available online: https://www.3dsystems.com/press-releases/geomagic/releases-studio-2012?utm_source=geomagic.com&utm_medium=301 (accessed on 6 June 2021).
Shape of Simulated Model | Before Repair | Ours | DC-AB Scanner | Meshmixer | Geomagic |
---|---|---|---|---|---|
Cuboid | 33.81 | 0.045 | 5.72 | 2.28 | 0.25 |
Triangular prism | 8.60 | 0.17 | 0.15 | 0.11 | 0.10 |
Cylinder | 14.73 | 0.14 | 0.36 | 2.84 | 1.57 |
Sphere | 6.40 | 0.026 | 1.08 | 0.071 | 0.088 |
Elliptic cylinder | 37.76 | 0.23 | 41.50 | 40.57 | 0.70 |
Ellipsoid | 9.86 | 0.12 | 4.46 | 0.20 | 0.21 |
Size of Cuboid Model (Unit: cm) | Before Repair | Ours |
---|---|---|
10 × 10 × 20 | 33.81 | 0.045 |
7 × 7 × 14 | 35.61 | 0.049 |
5 × 5 × 10 | 40.59 | 0.15 |
Grasping Way | Before Repair | Ours |
---|---|---|
Top, Straight | 35.61 | 0.049 |
Middle, Straight | 32.76 | 0.057 |
Top, Oblique | 35.89 | 0.071 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Cui, L.; Zhang, G.; Wang, J. Hole Repairing Algorithm for 3D Point Cloud Model of Symmetrical Objects Grasped by the Manipulator. Sensors 2021, 21, 7558. https://doi.org/10.3390/s21227558
Cui L, Zhang G, Wang J. Hole Repairing Algorithm for 3D Point Cloud Model of Symmetrical Objects Grasped by the Manipulator. Sensors. 2021; 21(22):7558. https://doi.org/10.3390/s21227558
Chicago/Turabian StyleCui, Linyan, Guolong Zhang, and Jinshen Wang. 2021. "Hole Repairing Algorithm for 3D Point Cloud Model of Symmetrical Objects Grasped by the Manipulator" Sensors 21, no. 22: 7558. https://doi.org/10.3390/s21227558
APA StyleCui, L., Zhang, G., & Wang, J. (2021). Hole Repairing Algorithm for 3D Point Cloud Model of Symmetrical Objects Grasped by the Manipulator. Sensors, 21(22), 7558. https://doi.org/10.3390/s21227558