An adaptive hybrid harmony search optimization algorithm for point cloud fine registration

Li, Ming, Ma, Xie, Yang, Yang

Full text «Opticheskii Zhurnal»

Full text on elibrary.ru

Publication in Journal of Optical Technology

For Russian citation (Opticheskii Zhurnal):

Yang Yang, Ming Li, Xie Ma An adaptive hybrid harmony search optimization algorithm for point cloud fine registration (Алгоритм адаптивного гибридного оптимизационного поиска соответствия при регистрации облака точек) [на англ. яз.] // Оптический журнал. 2021. Т. 88. № 5. С. 36–51. http://doi.org/10.17586/1023-5086-2021-88-05-36-51

Yang Yang, Ming Li, Xie Ma An adaptive hybrid harmony search optimization algorithm for point cloud fine registration (Алгоритм адаптивного гибридного оптимизационного поиска соответствия при регистрации облака точек) [in English] // Opticheskii Zhurnal. 2021. V. 88. № 5. P. 36–51. http://doi.org/10.17586/1023-5086-2021-88-05-36-51

For citation (Journal of Optical Technology):

Y. Yang, M. Li, and X. Ma, "Adaptive hybrid harmony search optimization algorithm for point cloud fine registration," Journal of Optical Technology. 88(5), 252-263 (2021). https://doi.org/10.1364/JOT.88.000252

Abstract:

The fine registration of point clouds is a key step in point cloud pre-processing. However, the point cloud fine registration algorithm still has problems, such as a low iteration accuracy and slower iteration speed. To further improve the efficiency of the point cloud fine registration algorithm, a point cloud fine registration method based on an adaptive hybrid harmony search algorithm was designed. Firstly, the fine registration mathematical model of the point cloud was established according to iterative closest point algorithm. Secondly, regarding the basic harmony search algorithm, the disadvantages were described through algorithm mechanism analysis, and four strategies — cube chaotic mapping, the shuffled frog leaping algorithm, adaptive parameters andquadratic interpolation — were introduced to improve the algorithm’s computational performance. Finally, the adaptive hybrid harmony search algorithm was validated by benchmark functions and point cloud registration data. Another five traditional algorithms were used for comparative analysis with adaptive hybrid harmony search. The results of the simulation experiment show the effectiveness of the adaptive hybrid harmony search algorithm in point cloud fine registration.

Keywords:

point cloud, fine registration, iterative closest point, adaptive hybrid harmony search

Acknowledgements:

This paper is supported by the Natural Science Foundation of Ningbo, China (Grant No 2016A610039).

OCIS codes: 150.0150, 100.0100

References:

1. Mian S.H., Mannan M.A., Al-Ahmari A. Accuracy of a reverse-engineered mould using contact and noncontact measurement techniques // Int. J. Comput. Integr. Manuf. 2015. V. 28. № 5. P. 419–436.
2. Kumara W.G.C.W., Yen S.H., Hsu H.H., Shih T.K., Chang W.C., Togootogtokh E. Real-time 3D human objects rendering based on multiple camera details // Multimed. Tools. Appl. 2017. V. 76. № 9. P. 11687–11713.
3. Florent P., Romain N., Line V.W., Nys G.A., Billen R. 3D point clouds in archaeology: Advances in acquisition, processing and knowledge integration applied to quasi-planar objects // Geosci.2017. V. 7. № 4. P. 96.
4. Yang X.C., Clements L.W., Luo M., Narasimhan S., Dawant B.M., Miqa M.I. Stereovision-based integrated system for point cloud reconstruction and simulated brain shift validation // J. Med. Imaging. 2017. V. 4. № 3. P. 035002.
5. Besl P.J., McKay H.D. A method for registration of 3-D shapes // IEEE Trans. Pattern. Anal. Mach. Intell. 1992. V. 14. № 2. P. 239–256.
6. Cheng L., Song C., Liu X.Q., Xu H., Wu Y., Li M., Chen Y. Registration of laser scanning point clouds: A Review // Sensors. 2018. V. 18. № 5. P. 1641.
7. Guo H., Pan J.Z., Lin D.J. Registration of point cloud data of multi-population genetic algorithm based on real coding // J. East. China. Univ. Sci. Technol. 2007. V. 33. № 5. P. 733–736.
8. Wang X., Zhang M.M., Yu X., Zhang M.C. Point cloud registration based on improved iterative closet point method // Opt. Precis. Eng. 2012. V. 20. № 9. P. 2068–2077.
9. Senin N., Colosimo B.M., Pacella M. Point set augmentation through fitting for enhanced ICP registration of point clouds in multi-sensor coordinate metrology // Robot. Comput. Integr. Manuf. V. 29. № 1. P. 39–52.
10. Liu J., Zhu J., Yang J., Meng X. L., Zhang H. Three-dimensional point cloud registration based on ICP algorithm employing K-D tree optimization // Int. Conf. Digit. Image. Process, Chengu, 2016. P. 872–876.
11. Huang J.H., Wang Z., Gao J., Huang Y., Towers D.P. High-precision registration of point clouds based on sphere feature constraints // Sensors. 2017. V. 17. № 1. P. 72.
12. Zhao F.Q., Zhou M.Q. Improved probability iterative closest point registration algorithm // J. Graph. V. 38. № 1. P. 15–22.
13. Yang P., Zhou Y.H., Yao J., Tang Y., Chen J.B. Three-dimensional shape reconstruction via an objective function optimization-based point cloud registration method // Opt. Eng. 2017. V. 56. № 11. P. 1.
14. He Y., Liang B., Yang J., Li S.Z., He J. An iterative closest points algorithm for registration of 3D laser scanner point clouds with geometric feature // Sensors. 2017. V. 17. № 8. P. 1862.
15. Lin C.Y., Veneziani A., Ruthotto L. Numerical methods for Polyline-to-Point-Cloud registration with applications to Patient-Specific Stent reconstruction // Int. J. Numer. Method. Biomed. Eng. 2018. V. 34. № 3. P. e2934.

16. Petricek T. and Svoboda T. Point cloud registration from local feature correspondences-evaluation on challenging datasets // Plos. One. 2017. V. 12. № 11. P. e0187943.
17. Yu C.K., Ju D.Y. A maximum feasible subsystem for globally optimal 3D point cloud registration // Sensors. 2018. V. 18. № 2. P. 544.
18. Luo N., Wang Q. Effective outlier matches pruning algorithm for rigid pairwise point cloud registration using distance disparity matrix // IET Comput. Vis. 2017. V. 12. № 2. P. 220–232.
19. Zhang J., Ackland D., Fernandez J. Point-cloud registration using adaptive radial basis functions // Comput. Method. Biomec. 2018. V. 21. № 7. P. 498–502.
20. Zhang X., Jian L., Xu M. Robust 3D point cloud registration based on bidirectional maximum correntropy criterion // Plos. One. 2018. V. 13. № 5. P. e0197542.
21. Sun D.Z., Guo H.S., Li Y.R., Nie L.K. Method of rigid registration based on Poisson reconstruction of local sample points // J. Mech. Eng. 2018. V. 54. № 15. P. 141–149.
22. Tang Z.R., Liu M.Z., Jiang Y., Zhao F.X. Point cloud registration algorithm based on canonical correlation analysis // Chin. J. Laser. 2019. V. 46. № 4. 1–17.
23. Tang Z.R., Liu M.Z., Wang C., Jiang Y. Point cloud registration algorithm based on multi-dimensional mixed Cauchy distribution // Act. Opt. Sin. 2019. V. 39. № 1. 1–21.
24. Liu M., Shu Q., Yang Y.X., Yuan F. Three-dimensional point cloud registration based on independent component // Laser. Opt. Prog. 2019. V. 56. № 1. 1–17.
25. Sun S.F., Li Z., Xia K., Shi Y.F., Yang J.Q., Dong F.M. Variable scale point cloud registration algorithm // J. Syst. Simul. 2018. V. 30. № 7. P. 2465–2474.
26. Li L., Yang M., Wang C.X., Wang B. Robust point set registration using signature quadratic form distance // IEEE Trans. Cybern. 2018. V. 50. № 5. 2097–2109.
27. Naus K., Marchel L. Use of a weighted ICP algorithm to precisely determine USV movement parameters // Appl. Sci. Basel. 2019. V. 9. № 17. P. 3530.
28. Geem Z.W., Kim J.H., Loganathan G.V. A new heuristic optimization algorithm: Harmony Search // Simulation. 2001. V. 2. № 2. P. 60–68.
29. Fourie J., Mills S., Green R. Harmony filter: A robust visual tracking system using the improved harmony search algorithm // Image. Vision. Comput. 2010. V. 28. № 12. P. 1702–1716.
30. Gao M.L., He X.H., Luo D.S., Yu Y.M. Object tracking based on harmony search: Comparative study // J. Electron. Imaging. 2012. V. 21. № 4. P. 3001–3014.
31. Li J., Duan H. Novel biological visual attention mechanism via Gaussian harmony search // Optik. 2014. V. 125. № 10. P. 2313–2319.
32. Talarposhti K.M., Jamei M.K. A secure image encryption method based on dynamic harmony search (DHS) combined with chaotic map // Opt. Laser. Eng. 2016. V. 81. P. 21–34.
33. Salehi M., Granpayeh N. Design of an optical comb generator based on harmony search algorithm // J. Nanophotonics. 2018. V. 12. № 4. P. 046006.
34. Wu Y.L., Zhang X.D., Yan H.M. Focusing light through scattering media using the harmony search algorithm for phase optimization of wavefront shaping // Optik. 2018. V. 158. P. 558–564.
35. Zhang T.H., Geem Z.W. Review of harmony search with respect to algorithm structure // Swarm. Evol. Comput. 2019. V. 48. P. 31–43.
36. Wang X., Gao X.Z., Zenger K. An introduction to harmony search optimization method. Switzerland: Cham, 2015. P. 21.
37. Tao C.H., Yang C.D. Three control strategies for the Lorenz chaotic system // Chaos. Soliton. Fract. 2008. V. 35. № 5. P. 1009–1014.
38. Eusuff M., Lansey K., Pasha F. Shuffled frog-leaping algorithm: A memetic meta-heuristic for discrete optimization // Eng. Optimiz. 2006. V 38. № 2. P. 129–154.
39. Mahdavi M., Fesanghary M., Damangir E. An improved harmony search algorithm for solving optimization problems // Appl. Math. Comput. 2007. V. 188. № 2. P. 1567–1579.
40. Ali M.M., Törnb A. Population set-based global optimization algorithms: Some modifications and numerical studies // Comput. Oper. Res. 2004. V. 31. № 10. P. 1703–1725.
41. Pan Q.K., Suganthan P.N., Liang J.J. A local-best harmony search algorithm with dynamic sub-harmony memories for lot-streaming flow shop scheduling problem // Expert. Syst. Appl. 2011. V. 38. № 4. P. 3252–3259.
42. Holland J. H. Genetic algorithms and the optimal allocation of trials // Siam. J. Comput. 1973. V. 2. № 2. P. 88–105.
43. Mirjalili S. Dragonfly algorithm: A new meta-heuristic optimization technique for solving single-objective discrete, and multi-objective problems // Neural. Comput. Appl. 2016. V. 27. № 4. P. 1053–1073.
44. Mirjalili S. The whale optimization algorithm // Adv. Eng. Softw. 2016. V. 95. № 5. P. 51–67.