將一個給定原始點雲和一個目標點雲進行配准，使這兩點雲可以快速又準確的對齊是現今許多人研究的重要題目，且可應用於攝影測量、遙感、機器人技術和 3D 視覺領域中。在本文中，首先提出了一種去除異常值的方法，用於刪除大量特徵不一致的雙共面對應關係，從而構建一個由三個特徵一致的雙共面對應關係子集組成的數量較少集合。接下來，提出了一種快速方法來解決每個特徵一致的雙共面對應關係子集的代表配準解。然
後，提出了一種穩健的融合方法來將這三個代表配準解融合成為最終的配準解。透過對幾個典型的點雲集進行實驗，從實驗結果可以看的出來，本文提出的配准法可以擁有不錯的配准率，且在執行時間上比其他現有方法
分別提升了 98％、87％、98％和 61％的速度。

Given a source point cloud and a target point cloud, it is an important and challenging issue to register the two point clouds such that the estimated registration solution can approach the best alignment effect and the least execution time requirement, leading to practical applications of photogrammetry, remote sensing, robotics, and 3D vision. In this paper, an outlier removal approach is first proposed to delete numerous feature-inconsistent coplane-pair correspondences for constructing a reduced coplane-pair correspondence set which consists of three feature-consistent coplane-pair correspondence subsets. Next, a fast method is proposed to solve the representative registration solution of each feature-consistent coplane-pair correspondence subset. Then, a robust fusion approach is proposed to integrate the three representative registration solutions as the final registration solution. Based on typical testing datasets, comprehensive experimental results demonstrated that with good registration accuracy, in average, the proposed registration method achieves 98%, 87%, 98%, and 61% execution time improvement ratios when compared with the state-of-the-art methods.

[1] Z. Wang, S. Yan, L. Wu, X. Zhang, and B. Chen, “Robust point clouds registration with point-to-
point lp distance constraints in large-scale metrology,” ISPRS Journal of Photogrammetry and Remote
Sensing, vol. 189, pp. 23–35, 2022.
[2] D. Hong, L. Gao, N. Yokoya, J. Yao, J. Chanussot, Q. Du, and B. Zhang, “More diverse means bet-
ter: Multimodal deep learning meets remote-sensing imagery classification,” IEEE Transactions on
Geoscience and Remote Sensing, vol. 59, no. 5, pp. 4340–4354, 2021.
[3] J. Yang, K. Xian, P. Wang, and Y. Zhang, “A performance evaluation of correspondence grouping
methods for 3d rigid data matching,” IEEE Transactions on Pattern Analysis and Machine Intelli-
gence, vol. 43, no. 6, pp. 1859–1874, 2021.
[4] J. Heo, S. Jeong, H.-K. Park, J. Jung, S. Han, S. Hong, and H.-G. Sohn, “Productive high-complexity
3d city modeling with point clouds collected from terrestrial lidar,” Computers, Environment and
Urban Systems, vol. 41, pp. 26–38, 2013.
[5] J. Li, R. Zhong, Q. Hu, and M. Ai, “Feature-based laser scan matching and its application for indoor
mapping,” Sensors, vol. 16, no. 8, 2016.
[6] K. Favre, M. Pressigout, E. Marchand, and L. Morin, “A plane-based approach for indoor point clouds
registration,” in 2020 25th International Conference on Pattern Recognition (ICPR), pp. 7072–7079,
2021.
[7] G. Li, Y. Gan, G. Liu, and F. Chen, “High-accuracy point cloud registration for 3d shape measurement
based on double constrained intersurface mutual projections,” Measurement, vol. 194, p. 111050,
2022.
[8] P. J. Besl and N. D. McKay, “A Method for Registration of 3-D Shapes,” IEEE Transactions on Pattern
Analysis and Machine Intelligence, vol. 14, no. 2, pp. 239–256, 1992.
[9] B. K. Horn, “Closed-form solution of absolute orientation using unit quaternions,” Josa a, vol. 4,
no. 4, pp. 629–642, 1987.
[10] K. S. Arun, T. S. Huang, and S. D. Blostein, “Least-Squares Fitting of Two 3-D Point Sets,” IEEE
Transactions on pattern analysis and machine intelligence, no. 5, pp. 698–700, 1987.
[11] C. S. Chua and R. Jarvis, “3d free-form surface registration and object recognition,” International
journal of computer vision, vol. 17, no. 1, pp. 77–99, 1996.
[12] J. Wyngaerd, L. Van Gool, R. Kock, and M. Proesmans, “Invariant-based registration of surface
patches,” in Proceedings of the Seventh IEEE International Conference on Computer Vision, vol. 1,
pp. 301–306 vol.1, 1999
[13] J. Jiang, J. Cheng, and X. Chen, “Registration for 3-d point cloud using angular-invariant feature,”
Neurocomputing, vol. 72, no. 16, pp. 3839–3844, 2009. Financial Engineering Computational and
Ambient Intelligence (IWANN 2007).
[14] R. B. Rusu, N. Blodow, and M. Beetz, “Fast point feature histograms (fpfh) for 3d registration,” in
2009 IEEE International Conference on Robotics and Automation, pp. 3212–3217, 2009.
[15] M. A. Fischler and R. C. Bolles, “Random sample consensus: a paradigm for model fitting with
applications to image analysis and automated cartography,” Communications of the ACM, vol. 24,
no. 6, pp. 381–395, 1981.
[16] S. Bouaziz, A. Tagliasacchi, and M. Pauly, “Sparse iterative closest point,” in Computer graphics
forum, vol. 32, pp. 113–123, Wiley Online Library, 2013.
[17] G. Marjanovic and V. Solo, “On lq optimization and matrix completion,” IEEE Transactions on Signal
Processing, vol. 60, no. 11, pp. 5714–5724, 2012.
[18] N. Mellado, D. Aiger, and N. J. Mitra, “Super 4pcs fast global pointcloud registration via smart in-
dexing,” Computer Graphics Forum, vol. 33, no. 5, pp. 205–215, 2014.
[19] D. Aiger, N. J. Mitra, and D. Cohen-Or, “4-points congruent sets for robust pairwise surface regis-
tration,” in ACM SIGGRAPH 2008 Papers, SIGGRAPH ’08, (New York, NY, USA), Association for
Computing Machinery, 2008.
[20] H. Yang and L. Carlone, “A polynomial-time solution for robust registration with extreme outlier
rates,” arXiv preprint arXiv:1903.08588, 2019.
[21] H. Yang, J. Shi, and L. Carlone, “TEASER: Fast and Certifiable Point Cloud Registration,” IEEE
Transactions on Robotics, vol. 37, no. 2, pp. 314–333, 2021.
[22] J. Yang, H. Li, D. Campbell, and Y. Jia, “Go-icp: A globally optimal solution to 3d icp point-set regis-
tration,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 38, no. 11, pp. 2241–
2254, 2016.
[23] H. Yang, P. Antonante, V. Tzoumas, and L. Carlone, “Graduated non-convexity for robust spatial
perception: From non-minimal solvers to global outlier rejection,” IEEE Robotics and Automation
Letters, vol. 5, no. 2, pp. 1127–1134, 2020.
[24] J. Li, Q. Hu, and M. Ai, “Gesac: Robust graph enhanced sample consensus for point cloud registra-
tion,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 167, pp. 363–374, 2020.
[25] R. Huang, Y. Xu, W. Yao, L. Hoegner, and U. Stilla, “Robust global registration of point clouds
by closed-form solution in the frequency domain,” ISPRS Journal of Photogrammetry and Remote
Sensing, vol. 171, pp. 310–329, 2021.
[26] Z. Yao, Q. Zhao, X. Li, and Q. Bi, “Point cloud registration algorithm based on curvature feature
similarity,” Measurement, vol. 177, p. 109274, 2021.
[27] Y. C. K. Wang, F. Chen, “Directly compute curvatures on point-based surface,” Mini-Micro Syst.,
vol. 26, no. 5, pp. 813–817, 2005.
[28] N. Amenta and Y. J. Kil, “Defining point-set surfaces,” ACM Trans. Graph., vol. 23, p. 264–270,
aug 2004.
[29] J. Li, J. Zhan, T. Zhou, V. A. Bento, and Q. Wang, “Point cloud registration and localization based on
voxel plane features,” ISPRS Journal of Photogrammetry and Remote Sensing, vol. 188, pp. 363–379,
2022.
[30] H. Samet, The design and analysis of spatial data structures, vol. 85. Addison-wesley Reading, MA,
1990.
[31] S. Chen, L. Nan, R. Xia, J. Zhao, and P. Wonka, “Plade: A plane-based descriptor for point cloud
registration with small overlap,” IEEE Transactions on Geoscience and Remote Sensing, vol. 58,
no. 4, pp. 2530–2540, 2020.
[32] H. Hoppe, T. DeRose, T. Duchamp, J. McDonald, and W. Stuetzle, “Surface reconstruction from un-
organized points,” in Proceedings of the 19th annual conference on computer graphics and interactive
techniques, pp. 71–78, 1992.
[33] R. Schnabel, R. Wahl, and R. Klein, “Efficient ransac for point-cloud shape detection,” Computer
Graphics Forum, vol. 26, no. 2, pp. 214–226, 2007.
[34] T. H. Cormen, C. E. Leiserson, R. L. Rivest, and C. Stein, Introduction to algorithms. MIT press,
4 ed., 2022.