Multi-view point cloud registration with adaptive convergence threshold and its application in 3D model retrieval

  • Yaochen LiEmail author
  • Ying Liu
  • Rui Sun
  • Rui Guo
  • Li Zhu
  • Yong Qi


Multi-view point cloud registration is a hot topic in the communities of artificial intelligence and multimedia technology. In this paper, we propose a novel framework to reconstruct 3D models with a multi-view point cloud registration algorithm with adaptive convergence threshold, and apply it to 3D model retrieval subsequently. The iterative closest point (ICP) algorithm is implemented with an adaptive convergence threshold, and further combines with a motion average algorithm for the registration of multi-view point cloud data. After the registration process, the applications are designed for 3D model retrieval. The geometric saliency map is computed based on the vertex curvatures. The test facial triangles are selected to compare with the standard facial triangle. The face and non-face models are then discriminated. The experiments and comparisons demonstrate the effectiveness of the proposed framework.


Point cloud registration ICP algorithm Convergence threshold Geometric saliency 3D model retrieval 



This work was supported in part by the National Natural Science Foundation of China under Grant no. 61803298, Natural Science Foundation of Jiangsu Province under Grant no. BK20180236.


  1. 1.
    Akagunduz E, Ulusoy I (2010) 3D face detection using transform invariant features. Electron Lett 46(13):905–907CrossRefGoogle Scholar
  2. 2.
    Bergevin R, Soucy M, Gagnon H, et al. (1996) Towards a genral multi-view registration technique. IEEE Trans Pattern Anal Mach Intell 18(5):540–547CrossRefGoogle Scholar
  3. 3.
    Boukamcha H, Elhallek M, Smach F (2015) 3D face landmark auto detection. In: World symposium on computer networks and information security, pp 1–6Google Scholar
  4. 4.
    Chane CS, Schutze R, Krsek P (2013) Registration of arbitrary multi-view 3D acquisitions. Comput Ind 64(9):1082–1089CrossRefGoogle Scholar
  5. 5.
    Chen Y, Medioni G (1992) Object modeling by registration of multiple range images. Image Vis Comput 10(3):145–155CrossRefGoogle Scholar
  6. 6.
    Chetverikov D, Stepanov D, Krsek P (2006) Robust Euclidean alignment of 3D point sets: the trimmed iterative closet point algorithm. Image Vis Comput 27 (11):1201–1208Google Scholar
  7. 7.
    Creusot C, Pear N, Austin J (2011) Automatic keypoint detection on 3D faces using a dictionary of local shapes. In: International conference on 3D imaging, modeling, processing, visualization and transmission, pp 204–211Google Scholar
  8. 8.
    Fantoni S, Castellani U, Fusiello A (2012) Accurate and automatic alignment of range surfaces. In: International conference on 3D imaging, modeling, processing, visualization and transmission, pp 73–80Google Scholar
  9. 9.
    Guo YL, Sohel F, Bennamoun M, et al. (2014) An accurate and robust range image registration algorithm for 3D object modeling. IEEE Trans Multimedia 16 (5):1377–1390CrossRefGoogle Scholar
  10. 10.
    Guo R, Zhu JH, Li YC et al (2018) Weighted motion averaging for the registration of multi-view range scans. Multimed Tools Appl 77(1):10651–10668CrossRefGoogle Scholar
  11. 11.
    Jin X, Wu Z, Song C et al (2016) 3D point cloud encryption through chaotic mapping. In: The Pacific-rim conference on multimedia, pp 119–129Google Scholar
  12. 12.
    Jin X, Zhu S, Xiao C et al (2017) 3D textured model encryption via 3D Lu Chaotic Mapping. Sci China Inf Sci 60(12):1–9Google Scholar
  13. 13.
    Lee CH, Varshney A, Jacobs DW (2005) Mesh saliency. ACM Trans Graph 24(3):659–666CrossRefGoogle Scholar
  14. 14.
    Lei J, Zhou J, Mottaleb MA, et al. (2013) Detection, localization and pose classification of ear in 3D face images. In: IEEE international conference on image processing, pp 4200–4204Google Scholar
  15. 15.
    Li YJ, Lu HM, Kihara K et al (2017) Motor anomaly detection for aerial unmanned vehicles using temperature sensor. Artif Intell Robot 752(1):295–304Google Scholar
  16. 16.
    Lomonosov E, Chetverikov D, Ekart A (2006) Pre-registration of arbitrary oriented 3D surfaces using a genetic algorithm. Pattern Recogn Lett 27(11):1201–1208CrossRefGoogle Scholar
  17. 17.
    Lu HM, Li YJ, Chen M (2018) Brain intelligence: go beyond artificial intelligence. Mobile Netw Appl 23(2):368–375CrossRefGoogle Scholar
  18. 18.
    Rabiu H, Saripan M, Marhaban MH (2013) 3D-based face segmentation using adaptive radius. In: IEEE international conference on signal and image processing applications, pp 237–240Google Scholar
  19. 19.
    Sandhu R, Dambreville S, Tannenbaum A (2010) Point set registration via particle filtering and stochastic dynamics. IEEE Trans Pattern Anal Mach Intell 32 (8):1459–1473CrossRefGoogle Scholar
  20. 20.
    Shi SW, Chuang YT, Yu TY (2009) An efficient and accurate method for the relaxation of multiview registration error. IEEE Trans Image Process 17(6):968–981MathSciNetGoogle Scholar
  21. 21.
    Wang Y, Wang F, Wang TF et al (2016) The registration of array laser point clouds based on the adaptive threshold. Acta Physica Sinica 65(24):267–277Google Scholar
  22. 22.
    Xu X, He L, Lu HM et al (2019) Deep adversarial metric learning for cross-modal retrieval. World Wide Web 22(2):657–672CrossRefGoogle Scholar
  23. 23.
    Zhu JH, Meng DY, Li ZY et al (2014) Robust registration of partially overlapping point sets via genetic algorithm with growth operator. IET Image Process 8(10):582–590CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  • Yaochen Li
    • 1
    Email author
  • Ying Liu
    • 1
  • Rui Sun
    • 1
  • Rui Guo
    • 1
  • Li Zhu
    • 1
  • Yong Qi
    • 2
  1. 1.School of Software EngineeringXi’an Jiaotong UniversityXi’anChina
  2. 2.Department of Computer Science and TechnologyXi’an Jiaotong UniversityXi’anChina

Personalised recommendations