A Review of Point Cloud Registration Algorithms for Laser Scanners: Applications in Large-Scale Aircraft Measurement
Source abstract
Abstract
As 3D acquisition equipment picks up steam, point cloud registration has been applied in ever-increasing fields. This paper provides an exhaustive survey of the field of point cloud registration for laser scanners and examines its application in large-scale aircraft measurement. We first researched the existing representative point cloud registration algorithms, such as hierarchical optimization, stochastic and probability distribution, and feature-based methods, for analysis. These methods encompass as many point cloud registration algorithms as possible; typical algorithms of each method are suggested respectively, and their strengths and weaknesses are compared. Lastly, the application of point cloud registration algorithms in large-scale aircraft measurement is introduced. We discovered that despite the significant progress of point cloud registration combining deep learning and traditional methods, it is still difficult to meet realistic needs, and the main challenges are in the direction of robustness and generalization. Furthermore, it is impossible to extract accurate and comparable features for alignment from large-scale aircraft surfaces due to their relative smoothness, lack of obvious features, and abundance of point clouds. It is necessary to develop lightweight and effective dedicated algorithms for particular application scenarios. As a result, with the development of point cloud registration technology and the deepening into the aerospace field, the particularity of the aircraft shape and structure poses higher challenges to point cloud registration technology.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: 3D Surveying and Cultural Heritage · Remote Sensing and LiDAR Applications · Robotics and Sensor-Based Localization
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of General Aviation and Flight, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China
Funding
Fundamental Research Funds for the Central Universities · Ministry of Education · Nanjing University of Aeronautics and Astronautics
References (100+)
Show source-provided references
1. Image-guided registration of unordered terrestrial laser scanning point clouds for urban scenes10.1109/TGRS.2011.2161613 ↗
2. Marker-Free Registration of Forest Terrestrial Laser Scanner Data Pairs with Embedded Confidence Metrics10.1109/TGRS.2016.2539219 ↗
3. Learning a constrained conditional random field for enhanced segmentation of fallen trees in ALS point clouds10.1016/j.isprsjprs.2017.04.001 ↗
4. Use of LIDAR in landslide investigations: A review10.1007/s11069-010-9634-2 ↗
5. Landslide monitoring using multitemporal terrestrial laser scanning for ground displacement analysis10.1080/19475705.2013.863808 ↗
6. Determination of possible failure surfaces in an open-pit slope caused by underground production
7. Landslide detection and characterization using terrestrial 3D laser scanning (LiDAR)
8. Preface LIDAR and DEM techniques for landslides monitoring and characterization10.5194/nhess-10-1877-2010 ↗
9. The Mount Pizzuto earth flow: Deformational pattern and recent thrusting evolution10.1080/17445647.2016.1145150 ↗
10. Image-based correlation of Laser Scanning point cloud time series for landslide monitoring
11. Assessing the capability of terrestrial laser scanning for monitoring slow moving landslides10.5194/nhess-9-1921-2009 ↗
12. Fast pairwise coarse registration between point clouds of construction sites using 2d projection-based phase correlation10.5194/isprs-archives-XLII-2-W13-1015-2019 ↗
13. Terrestrial laser scanning in forest ecology: Expanding the horizon10.1016/j.rse.2020.112102 ↗
14. Individual tree point clouds and tree measurements from multi-platform laser scanning in German forests10.5194/essd-14-2989-2022 ↗
15. Mapping tropical forest trees across large areas with lightweight cost-effective terrestrial laser scanning10.1007/s13595-021-01113-9 ↗
16. Laser scanning of forest resources: The nordic experience10.1080/02827580410019553 ↗
17. Morgan, M., and Habib, A. (2002, January 19–26). Interpolation of lidar data and automatic building extraction. Proceedings of the ACSM-ASPRS Annual Conference, Washington, DC, USA.
18. Indoor scene reconstruction using feature sensitive primitive extraction and graph-cut10.1016/j.isprsjprs.2014.02.004 ↗
19. An efficient global energy optimization approach for robust 3D plane segmentation of point clouds10.1016/j.isprsjprs.2018.01.013 ↗
20. Montuori, A., Luzi, G., Stramondo, S., Casula, G., Bignami, C., Bonali, E., Bianchi, M.G., and Crosetto, M. (2014, January 13–18). Combined use of ground-based systems for Cultural Heritage conservation monitoring. Proceedings of the 2014 IEEE Geoscience and Remote Sensing Symposium, Quebec City, QC, Canada.10.1109/IGARSS.2014.6947384 ↗
21. Improving the Accuracy of Laser Scanning for 3D Model Reconstruction Using Dithering Technique10.1016/j.protcy.2013.12.498 ↗
22. Boardman, C., Bryan, P., McDougall, L., Reuter, T., Payne, E., Moitinho, V., Rodgers, T., Honkova, J., O’Connor, L., and Blockley, C. (2018). 3D Laser Scanning for Heritage. Advice and Guidance on the Use of Laser Scanning in Archaeology and Architecture, Historic England.
23. Wu, C., Yuan, Y., Tang, Y., and Tian, B. (2021). Application of Terrestrial Laser Scanning (TLS) in the Architecture, Engineering and Construction (AEC) Industry. Sensors, 22.10.3390/s22010265 ↗
24. Application of 3D laser scanning technology for image data processing in the protection of ancient building sites through deep learning10.1016/j.imavis.2020.103969 ↗
25. Huo, P., Hou, M., Dong, Y., Li, A., Ji, Y., and Li, S. (2020). A Method for 3D Reconstruction of the Ming and Qing Official-Style Roof Using a Decorative Components Template Library. ISPRS Int. J. Geo-Inf., 9.10.3390/ijgi9100570 ↗
26. A Review of Point Cloud Registration Algorithms for Mobile Robotics
27. A Qualitative Review on 3D Coarse Registration Methods
28. Cheng, L., Chen, S., Liu, X., Xu, H., Wu, Y., Li, M., and Chen, Y. (2018). Registration of Laser Scanning Point Clouds: A Review. Sensors, 18.10.3390/s18051641 ↗
29. Registration of large-scale terrestrial laser scanner point clouds: A review and benchmark10.1016/j.isprsjprs.2020.03.013 ↗
30. Huang, X., Mei, G., Zhang, J., and Abbas, R. (2021). A comprehensive survey on point cloud registration. arXiv.
31. A method for registration of 3-D shapes10.1109/34.121791 ↗
32. Registering multiview range data to create 3D computer objects10.1109/34.400574 ↗
33. Pulli, K. (1999, January 4–8). Multiview registration for large data sets. Proceedings of the Second International Conference on 3D Digital Imaging and Modeling, Ottawa, Canada.
34. Rusinkiewicz, S., and Levoy, M. (June, January 28). Efficient variants of the ICP algorithm. Proceedings of the 3rd International Conference on 3-D Digital Imaging and Modeling, Quebec City, Canada.
35. ICP registration using invariant features10.1109/34.982886 ↗
36. Robust Registration of 2D and 3D Point Sets10.1016/j.imavis.2003.09.004 ↗
37. A method for automated registration of unorganized point clouds10.1016/j.isprsjprs.2007.05.012 ↗
38. Censi, A. (2008, January 19–23). An ICP variant using a point-to-line metric. Proceedings of the IEEE International Conference on Robotics and Automation, Pasadena, CA, USA.10.1109/ROBOT.2008.4543181 ↗
39. Segal, A., Haehnel, D., and Thrun, S. (2009). Generalized-ICP. Robotics: Science and Systems, University of Washington.10.15607/RSS.2009.V.021 ↗
40. A Scale Stretch Method Based on ICP for 3D Data Registration10.1109/TASE.2009.2021337 ↗
41. Sparse Iterative Closest Point10.1111/cgf.12178 ↗
42. Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration10.1109/TPAMI.2015.2513405 ↗
43. He, Y., Liang, B., Yang, J., Li, S., and He, J. (2017). An Iterative Closest Points Algorithm for Registration of 3D Laser Scanner Point Clouds with Geometric Features. Sensors, 17.10.3390/s17081862 ↗
44. Wang, Y., and Solomon, J. (2019, January 16–17). Deep Closest Point: Learning Representations for Point Cloud Registration. Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/ICCV.2019.00362 ↗
45. Wang, Y., and Solomon, J.M. (2020, January 6–12). PRNet: Self-Supervised Learning for Partial-to-Partial Registration. Proceedings of the 33rd Conference on Neural Information Processing Systems, Online.
46. Koide, K., Yokozuka, M., Oishi, S., and Banno, A. (June, January 30). Voxelized GICP for Fast and Accurate 3D Point Cloud Registration. Proceedings of the IEEE International Conference on Robotics and Automation, Xi’an, China.
47. An eigen decomposition approach to weighted graph matching problems10.1109/34.6778 ↗
48. Structural graph matching using the EM algorithm and singular value decomposition10.1109/34.954602 ↗
49. An eigenspace projection clustering method for inexact graph matching10.1109/TPAMI.2004.1265866 ↗
50. Leordeanu, M., and Hebert, M. (2005, January 17–21). A spectral technique for correspondence problems using pairwise constraints. In Proceeding of the Tenth IEEE International Conference on Computer Vision (ICCV’05), Beijing, China.10.1109/ICCV.2005.20 ↗
51. Cour, T., Srinivasan, P., and Shi, J. (2006, January 4–7). Balanced graph matching. Proceedings of the Conference on Advances in Neural Information Processing Systems, Vancouver, BC, Canada.
52. A graduated assignment algorithm for graph matching10.1109/34.491619 ↗
53. Feature Correspondence Via Graph Matching: Models and Global Optimization
54. Zhou, F., and de la Torre, F. (2016, January 27–30). Factorized Graph Matching. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.
55. Lagrange relaxation graph matching10.1016/j.patcog.2016.07.021 ↗
56. Fu, K., Liu, S., Luo, X., and Wang, M. (2021, January 20–25). Robust Point Cloud Registration Framework Based on Deep Graph Matching. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.10.1109/CVPR46437.2021.00878 ↗
57. Global Registration of Multiple Point Clouds Using Semidefinite Programming10.1137/130935458 ↗
58. Point registration via efficient convex relaxation10.1145/2897824.2925913 ↗
59. Le, H.M., Do, T.-T., Hoang, T., and Cheung, N.-M. (2019, January 16–20). SDRSAC: Semidefinite-Based Randomized Approach for Robust Point Cloud Registration Without Correspondences. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.10.1109/CVPR.2019.00021 ↗
60. TEASER: Fast and Certifiable Point Cloud Registration10.1109/TRO.2020.3033695 ↗
61. Sun, L. (2022). IRON: Invariant-based highly robust point cloud registration. arXiv.
62. Zass, R., and Shashua, A. (2008, January 24–26). Probabilistic graph and hypergraph matching. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, AK, USA.10.1109/CVPR.2008.4587500 ↗
63. A Tensor-Based Algorithm for High-Order Graph Matching10.1109/TPAMI.2011.110 ↗
64. Lee, J., Cho, M., and Lee, K.M. (2011, January 20–25). Hyper-graph matching via reweighted random walks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Colorado Springs, CO, USA.10.1109/CVPR.2011.5995387 ↗
65. Ngoc, Q.N., Gautier, A., and Hein, M. (2015, January 7–12). A flexible tensor block coordinate ascent scheme for hypergraph matching. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA.
66. Second- and High-Order Graph Matching for Correspondence Problems10.1109/TCSVT.2017.2718225 ↗
67. Pavlov, A.L., Ovchinnikov, G.W., Derbyshev, D.Y., Tsetserukou, D., and Oseledets, I.V. (2018, January 21–25). AA-ICP: Iterative Closest Point with Anderson Acceleration. Proceedings of the 2018 IEEE International Conference on Robotics and Automation (ICRA), Brisbane, QLD, Australia.10.1109/ICRA.2018.8461063 ↗
68. Li, G., Cui, Y., Wang, L., and Meng, L. (2022). Automatic Registration Algorithm for the Point Clouds Based on the Optimized RANSAC and IWOA Algorithms for Robotic Manufacturing. Appl. Sci., 12.10.3390/app12199461 ↗
69. A survey for the quadratic assignment problem10.1016/j.ejor.2005.09.032 ↗
70. Tian, Y., Yan, J., Zhang, H., Zhang, Y., Yang, X., and Zha, H. (2012, January 7–13). On the Convergence of Graph Matching: Graduated Assignment Revisited. Proceedings of the 12th European Conference on Computer Vision, Florence, Italy.10.1007/978-3-642-33712-3_59 ↗
71. Lai-Dang, Q.-V., Nengroo, S.H., and Jin, H. (2022). Learning Dense Features for Point Cloud Registration Using a Graph Attention Net-work. Appl. Sci., 12.10.3390/app12147023 ↗
72. Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography10.1145/358669.358692 ↗
73. Myatt, D.R., Torr, P.H.S., Nasuto, S.J., Bishop, J.M., and Craddock, R. (2002, January 2–5). NAPSAC: High noise, high dimensional robust estimation-It’s in the bag. Proceedings of the British Machine Vision Conference, Cardiff, UK.10.5244/C.16.44 ↗
74. Locally optimized RANSAC10.1007/978-3-540-45243-0_31 ↗
75. Chum, O., and Matas, J. (2005, January 20–25). Matching with PROSAC-Progressive Sample Consensus. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, San Diego, CA, USA.
76. Ma, S., Ma, X., You, H., Tang, T., Wang, J., and Wang, M. (2021, January 6–8). SC-PROSAC: An Improved Progressive Sample Consensus Algorithm Based on Spectral Clustering. Proceedings of the 3rd International Conference on Robotics and Computer Vision, Beijing, China.10.1109/ICRCV52986.2021.9546964 ↗
77. 4-points congruent sets for robust pairwise surface registration10.1145/1360612.1360684 ↗
78. Super 4PCS: Fast global point cloud registration via smart indexing10.1111/cgf.12446 ↗
79. Sattler, T., Leibe, B., and Kobbelt, L. (October, January 29). SCRAMSAC: Improving RANSAC’s efficiency with a spatial consistency filter. Proceedings of the 12th IEEE International Conference on Computer Vision, Kyoto, Japan.
80. Ni, K., Jin, H., and Dellaert, F. (October, January 29). GroupSAC: Efficient consensus in the presence of groupings. Proceedings of the 12th IEEE International Conference on Computer Vision, Kyoto, Japan.
81. Registration of point clouds using sample-sphere and adaptive distance restriction10.1007/s00371-011-0580-0 ↗
82. Point Cloud Registration Based on One-Point RANSAC and Scale-Annealing Biweight Estimation10.1109/TGRS.2020.3045456 ↗
83. RANSIC: Fast and Highly Robust Estimation for Rotation Search and Point Cloud Registration Using Invariant Compatibility10.1109/LRA.2021.3116313 ↗
84. Biber, P. (2003, January 27–31). The Normal Distributions Transform: A New Approach to Laser Scan Matching. Proceedings of the 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems, Las Vegas, NV, USA.
85. Magnusson, M. (2006). 3D Scan Matching for Mobile Robots with Application to Mine Mapping, Örebro University.
86. A 3D Scan Matching Method Based on Multi-Layered Normal Distribution Transform
87. Das, A., and Waslander, S.L. (2012, January 7–12). Scan registration with multi-scale k-means normal distributions transform. Proceedings of the 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems, Vilamoura, Portugal.10.1109/IROS.2012.6386185 ↗
88. Scan registration using segmented region growing NDT10.1177/0278364914539404 ↗
89. Lu, J., Liu, W., Dong, D.L., and Shao, Q. (2015, January 28–30). Point cloud registration algorithm based on NDT with variable size voxel. Proceedings of the 34th Chinese Control Conference, Hangzhou, China.
90. A Method of Generating Multi-Scale Disc-Like Distributions for NDT Registration Algorithm
91. Zaganidis, A., Magnusson, M., Duckett, T., and Cielniak, G. (2017, January 24–28). Semantic-assisted 3D normal distributions transform for scan registration in environments with limited structure. Proceedings of the IEEE International Conference on Intelligent Robots and Systems, Vancouver, BC, Canada.10.1109/IROS.2017.8206262 ↗
92. Point Set Registration: Coherent Point Drift10.1109/TPAMI.2010.46 ↗
93. Jian, B., and Vemuri, B. (2005, January 17–20). A robust algorithm for point set registration using mixture of Gaussians. Proceedings of the 10th IEEE International Conference on Computer Vision, Beijing, China.
94. Evangelidis, G.D., Kounades-Bastian, D., Horaud, R., and Psarakis, E.Z. (2014, January 6–12). A Generative Model for the Joint Registration of Multiple Point Sets. Proceedings of the 13th European Conference on Computer Vision, Zurich, Switzerland.10.1007/978-3-319-10584-0_8 ↗
95. Convex hull indexed Gaussian mixture model (CH-GMM) for 3D point set registration10.1016/j.patcog.2016.02.023 ↗
96. Ben, E., Kim, K., Troccoli, A., Kelly, A., and Kautz, J. (2016, January 27–30). Accelerated generative models for 3D point cloud data. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.
97. Min, Z., Wang, J., and Meng, M.Q.H. (2018, January 21–25). Robust Generalized Point Cloud Registration Using Hybrid Mixture Model. Proceedings of the IEEE International Conference on Robotics and Automation, Brisbane, Australia.10.1109/ICRA.2018.8460825 ↗
98. Eckart, B., Kim, K., and Kautz, J. (2018, January 8–14). HGMR: Hierarchical Gaussian Mixtures for Adaptive 3D Registration. Proceedings of the 15th European Conference on Computer Vision, Munich, Germany.10.1007/978-3-030-01267-0_43 ↗
99. Yuan, W., Eckart, B., Kim, K., Jampani, V., Fox, D., and Kautz, J. (2020, January 23–28). Deepgmr: Learning latent gaussian mixture models for registration. Proceedings of the European Conference on Computer Vision, Glasgow, UK.10.1007/978-3-030-58558-7_43 ↗
100. Randomized RANSAC with T (d, d) test10.1016/j.imavis.2004.02.009 ↗