Nothing Special   »   [go: up one dir, main page]
Skip to main content
Springer Nature Link
Log in

SingleMatch: a point cloud coarse registration method with single match point and deep-learning describer

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Point cloud registration is a necessary step of object digitization. In this paper, we propose a coarse registration method with a single match point. To achieve the purpose, feature points with stable orientation are recognized firstly, then descriptors of these points are generated with our Convolution Neural Network (CNN) named PFNet. Finally, candidate solutions are obtained by descriptors matching and the accurate registration is given by a RANSAC-based optimization strategy. As the feature points used are highly directional, a stable Local Coordinate System (LCS) can be constructed by combining the orientation and the normal vector, and thus, the registration can be realized by LCS mapping with single match point. Experiment results show that our algorithm achieves good registration effects in challenging scenes, and is robust to noise, outliers, non-uniform sampling.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19

Similar content being viewed by others

References

  1. Ai S, Jia L, Zhuang C, Ding H (2017) A registration method for 3D point clouds with convolutional neural network. In: Huang Y., Wu H., Liu H., Yin Z. (eds) Intelligent Robotics and Applications. ICIRA. Lecture notes in computer science, vol 10464. Springer, Cham.

  2. Aoki Y, Goforth H, Srivatsan RA, et al. (2019). PointNetLK: Robust & efficient point cloud registration using PointNet. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp. 7156–7165

  3. Bai X, Luo Z, Zhou L, et al. (2020). D3Feat: Joint learning of dense detection and description of 3D local features. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp. 6358–6366

  4. Besl PJ (1992) A method for registration 3D shapes. IEEE Trans Pattern Anal Mach Intell 14(2):193–200

    Article  Google Scholar 

  5. Chopra S, Hadsell R, Lecun Y (2005) Learning a similarity metric discriminatively, with application to face verification. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp. 539–546

  6. Feng X, Tan T, Yuan Y, Yin C (2019) Aligning point clouds with an effective local feature descriptor. In: Ning H. (eds) Cyberspace Data and Intelligence, and Cyber-Living, Syndrome, and Health. CyberDI, CyberLife 2019. Communications in Computer and Information Science, vol 1138. Springer, Singapore.

  7. Gao QH, Wan TR, Tang W, … Chen L (2019) Object registration in semi-cluttered and partial-occluded scenes for augmented reality. Multimed Tools Appl 78(11):15079–15099

    Article  Google Scholar 

  8. Geng N, Ma F, Yang H, … Zhang Z (2016) Neighboring constraint-based pairwise point cloud registration algorithm. Multimed Tools Appl 75(24):16763–16780

    Article  Google Scholar 

  9. Gojcic Z, Zhou C, Wegner JD, et al. (2019). The Perfect Match: 3D point cloud matching with smoothed densities. In: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp. 5540–5549

  10. Guerrero P, Kleiman Y, Ovsjanikov M, … Mitra NJ (2017) PCPNet: learning local shape properties from raw point clouds. Computer Graphics Forum 37(2):75–85

    Article  Google Scholar 

  11. Gumhold S, Wang X, Mcleod R (2001). Feature extraction from point clouds. In: Inter- national Meshing Roundtable. IEEE Computer Society Press, pp. 293–305

  12. Hussnain Z, Elberink SO, Vosselman G (2016). Automatic feature detection, description and matching from mobile laser scanning data and aerial imagery. Int Arch Photogrammetry Remote Sensing & S XLI-B1:609–616

  13. Iger D, Mitra NJ, Cohen-or D (2008) 4-points congruent sets for robust pairwise surface registration. ACM Trans Graph 27(3):1–10

    Article  Google Scholar 

  14. Jiao Z, Liu R, Yi P, Zhou D (2019) A point cloud registration algorithm based on 3D-SIFT. In: pan Z., Cheok a., Müller W., Zhang M., El Rhalibi a., Kifayat K. (eds) transactions on edutainment XV. Lecture notes in computer science, vol 11345. Springer, Berlin, Heidelberg.

  15. Johnson AE, Hebert M (1999) Using spin images for efficient object recognition in cluttered 3D scenes. IEEE Trans Pattern Anal Mach Intell 21(5):433–449

    Article  Google Scholar 

  16. Lai K, Bo L, Fox D (2014) Unsupervised feature learning for 3d scene labeling. In 2014 IEEE International Conference on Robotics and Automation (ICRA). 3050–3057

  17. Lebeda K, Matas J, Chum O (2012) Fixing locally optimized RANSAC full experimental evaluation. In: British Machine Vision Conference on Neural Information Processing Systems.Curran Associates Inc, pp. 1–11

  18. Li C, Zhong F, Zhang Q, … Qin X (2018) Accurate and fast 3D head pose estimation with noisy RGBD images. Multimed Tools Appl 77(6):14605–14624

    Article  Google Scholar 

  19. Li RZ, Yang M, Tian Y, Liu YY, Zhang HH (2017) Point cloud registration algorithm based on the ISS feature points combined with improved ICP algorithm. Laser Optoelectronics Progress 54(11):111503

    Article  Google Scholar 

  20. Lin D, Jarzabek-Rychard M, Tong X, … Maas HG (2019) Fusion of thermal imagery with point clouds for building facade thermal attribute mapping. ISPRS J Photogramm Remote Sens 151(5):162–175

    Article  Google Scholar 

  21. Lowe DG (1999) Object recognition from local scale-invariant features. In: IEEE International Conference on Computer Vision. IEEE, pp. 1150–1157

  22. Lu J, Wang W, Shao H, Su L (2019) Point cloud registration algorithm fusing of super 4PCS and ICP based on the key points. Chinese control conference (CCC), Guangzhou. China 2019:4439–4444

    Google Scholar 

  23. Mellado N, Aiger D, Mitra NJ (2015) Super4PCS: fast global pointcloud registration via smart indexing. Comput Graphics Forum 33(5):205–215

    Article  Google Scholar 

  24. Mohamad M, Ahmed MT, Rappaport D, Greenspan M (2015) Super generalized 4PCS for 3D registration. International conference on 3D vision, Lyon. France 2015:598–606

    Google Scholar 

  25. Nie J (2016) Extracting feature lines from point clouds based on smooth shrink and iterative thinning. Graph Model 84(5):38–49

    Article  MathSciNet  Google Scholar 

  26. Nie J, Ye L, Hao G et al (2015) Feature line detection from point cloud based on signed surface variation and region segmentation. J Comp Aided Design Graphics 27(12):2332–2339 in Chinese

    Google Scholar 

  27. Nießner M, Zollhofer M, Izadi S, Stamminger M (2013) Real-time 3D reconstruction at scale using voxel hashing. ACM Trans Graphics (TOG) 32(6CD):1–11

  28. Noh H, Araujo A, Sim J, Weyand T, Han B (2017). Large-scale image retrieval with attentive deep local features. In: IEEE International Conference on Computer Vision (ICCV), pp. 3476–3485

  29. Pauly M, Keiser R, Gross M (2003) Multi-scale feature extraction on point-sampled surfaces. Comput Graph Forum 22(3):281–289

    Article  Google Scholar 

  30. Pavel FA, Wang Z, Feng DD (2009) Reliable object recognition using sift features. In: IEEE International Workshop on Multimedia Signal Processing (MMSP), pp. 1–6.

  31. Prakhya SM, Liu B, Lin W, … Guntuku SC (2017) B-SHOT: a binary 3D feature descriptor for fast Keypoint matching on 3D point clouds. Auton Robot 41:1501–1520

    Article  Google Scholar 

  32. Qi CR, Su H, Mo K, et al. (2017) PointNet: Deep learning on point sets for 3D classification and segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp. 77–85

  33. Rusinkiewicz S, Levoy M (2001) Efficient variants of the ICP algorithm. In: International Conference on 3-D Digital Imaging and Modeling. 145–152

  34. Rusu RB, Blodow N, Marton ZC, Beetz M (2008) Aligning point cloud views using persistent feature histograms. In: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3384–3391

  35. Rusu RB, Blodow N, Beetz M (2009) Fast point feature histograms (FPFH) for 3D registration. In: IEEE International Conference on Robotics and Automation. IEEE, pp. 3212–3217

  36. Sharp GC, Lee SW, Wehe DK (2002) ICP registration using invariant features. IEEE Trans Pattern Anal Mach Intell 24(1):90–102

    Article  Google Scholar 

  37. Shi W, Zhu D, Du L, Zhang G, Li J, Zhang X (2019) A hierarchical attention fused descriptor for 3D point matching. In IEEE Access 7:77436–77447

    Article  Google Scholar 

  38. Sipiran I, Bustos B (2011) Harris 3D: a robust extension of the Harris operator for interest point detection on 3D meshes. Vis Comput 27:963–976. https://doi.org/10.1007/s00371-011-0610-y

    Article  Google Scholar 

  39. Theiler PW, Wegner JD, Schindler K (2014) Keypointbased 4-points congruent sets–automated marker-less registration of laser scans. ISPRS J Photogramm Remote Sens 96:149–163

    Article  Google Scholar 

  40. Tombari F, Salti S, Stefano LD (2010) Unique signatures of histograms for local surface description. In: Daniilidis K., Maragos P., Paragios N. (eds) Computer Vision – ECCV 2010. ECCV. Lecture Notes Comput Sci. vol 6313. Springer, Berlin, Heidelberg. 356–369. https://doi.org/10.1007/978-3-642-15558-1_26

  41. Tombari F, Salti S, Stefano LD (2011) A combined texture-shape descriptor for enhanced 3D feature matching. In: 18th IEEE International Conference on Image Processing, pp. 809–812.

  42. Wan T, Du S, Xu Y et al (2019) RGB-D point cloud registration via infrared and color camera. Multimed Tools Appl 78(5):33223–33246

    Article  Google Scholar 

  43. Wang CY, Kiani H, Lin CH, Lucey S (2018) Deep-LK for efficient adaptive object tracking. In: IEEE International Conference on Robotics and Automation (ICRA). IEEE, pp. 627–634

  44. Wang X, Chen H, Wu L (2020) Feature extraction of point clouds based on region clustering segmentation. Multimed Tools Appl 79:11861–11889

    Article  Google Scholar 

  45. Wu NZ, Song S, Khosla A, et al. (2015). 3D ShapeNets: A deep representation for volumetric shapes. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp. 1912–1920

  46. Xu Z, Xu E, Zhang Z, … Wu L (2018) Multiscale sparse features embedded 4-points congruent sets for global registration of TLS point clouds. IEEE Geosci Remote Sens Lett 16(2):286–290

    Article  Google Scholar 

  47. Yang J, Li H, Jia Y (2013) Go-ICP: Solving 3D registration efficiently and globally optimally. In: IEEE International Conference on Computer Vision. IEEE, pp. 1457–1464

  48. Yew ZJ, Lee GH (2018) 3DFeat-net: weakly supervised local 3D features for point cloud registration. In: Ferrari V., Hebert M., Sminchisescu C., Weiss Y. (eds) Computer Vision – ECCV 2018.Lecture notes in computer science, vol 11219. Springer, Cham.

  49. Zeng A,Song S, Nießner M, et al. (2017). 3DMatch: Learning local geometric descriptors from RGB-D reconstructions. In: IEEE Conference on Computer Vision and Pattern Recognition.IEEE Computer Society, pp. 199–208

  50. Zhong Y (2009). Intrinsic shape signatures: A shape descriptor for 3D object recognition. In: IEEE International Conference on Computer Vision Workshops. IEEE. 689–696

  51. Zhou QY, Park J, Koltun V (2016) Fast global registration. In: European Conference on Computer Vision. Springer, Cham, pp 766–782

Download references

Author information

Authors and Affiliations

  1. School of Automation & Artificial Intelligence, Nanjing University of Posts and Telecommunications, Nanjing, China

    Rui Wu, Jianhui Nie, Hao Gao, Ye Liu & Haotian Lu

Authors
  1. Rui Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jianhui Nie
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hao Gao
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Ye Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Haotian Lu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jianhui Nie.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wu, R., Nie, J., Gao, H. et al. SingleMatch: a point cloud coarse registration method with single match point and deep-learning describer. Multimed Tools Appl 81, 16967–16986 (2022). https://doi.org/10.1007/s11042-022-12704-7

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-022-12704-7

Keywords

Search

Navigation