Skip to main content
SpringerLink
Log in

Planar Fitting Transformation: A Rapid Point Cloud Registration for Real-time Applications

  • Conference paper
  • First Online:
Robot Intelligence Technology and Applications 7 (RiTA 2022)

Part of the book series: Lecture Notes in Networks and Systems ((LNNS,volume 642))

  • 767 Accesses

Abstract

This paper presents Planar Fitting Transformation (PFT), a highly efficiency-oriented 3D point cloud registration. Based on Normal Distribution Transformation (NDT), we replace the gaussian approximation with least-squared planar fitting, dramatically increasing the FPS to 500 Hz with CPU (18 threads). As an alternative to the time-consuming neighbor search, we propose octomerge voxelization to enhance robustness without compromising efficiency. As a result, our work significantly outperforms all state-of-the-art methods in execution time, while retaining a comparable level of accuracy.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 189.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 249.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    GitHub repository: https://github.com/Leohsieh57/pft_matcher.

  2. 2.

    Since \(\textbf{T}_0\) also denotes the Taylor expansion point, although less consistent with (1), we alternatively denote the initial guess by \(\textbf{T}_{init}\) to avoid confusion.

  3. 3.

    GitHub repository: https://github.com/koide3/ndt_omp.

  4. 4.

    GitHub repository: https://github.com/SMRT-AIST/fast_gicp.

  5. 5.

    The common suffix -10k is omitted.

References

  1. Barnes, D., Gadd, M., Murcutt, P., Newman, P., Posner, I.: The oxford radar robotcar dataset: a radar extension to the oxford robotcar dataset. In: Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), Paris (2020)

    Google Scholar 

  2. Bentley, J.L.: Multidimensional binary search trees used for associative searching. Commun. ACM 18(9), 509–517 (1975)

    Google Scholar 

  3. Besl, P., McKay, H.D.: A method for registration of 3-d shapes. IEEE Trans. Pattern Anal. Mach. Intell. 14, 239–256 (1992)

    Article  Google Scholar 

  4. Geiger, A., Lenz, P., Urtasun, R.: Are we ready for autonomous driving? the kitti vision benchmark suite. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2012)

    Google Scholar 

  5. Horn, B.: Closed-form solution of absolute orientation using unit quaternions. J. Opt. Soc. A 4, 629–642 (1987)

    Article  Google Scholar 

  6. Kato, S., Takeuchi, E., Ishiguro, Y., Ninomiya, Y., Takeda, K., Hamada, T.: An open approach to autonomous vehicles. IEEE Micro 35(6), 60–68 (2015)

    Article  Google Scholar 

  7. Koide, K., Yokozuka, M., Oishi, S., Banno, A.: Voxelized gicp for fast and accurate 3D point cloud registration. In: 2021 IEEE International Conference on Robotics and Automation (ICRA), pp. 11054–11059 (2021)

    Google Scholar 

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

    Google Scholar 

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

    Google Scholar 

  10. Segal, A., Hähnel, D., Thrun, S.: Generalized-icp (2009)

    Google Scholar 

  11. Serafin, J., Grisetti, G.: Nicp: dense normal based point cloud registration. In: 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 742–749 (2015)

    Google Scholar 

  12. Stoyanov, T., Magnusson, M., Andreasson, H., Lilienthal, A.: Fast and accurate scan registration through minimization of the distance between compact 3D NDT representations. Int. J. Rob. Res. 31, 1377–1393 (2012)

    Article  Google Scholar 

  13. Streiff, D., Bernreiter, L., Tschopp, F., Fehr, M., Siegwart, R.: 3d3l: deep learned 3D keypoint detection and description for lidars. In: 2021 IEEE International Conference on Robotics and Automation (ICRA), pp. 13064–13070 (2021)

    Google Scholar 

  14. Sturm, J., Engelhard, N., Endres, F., Burgard, W., Cremers, D.: A benchmark for the evaluation of rgb-d slam systems. In: Proceedings of the International Conference on Intelligent Robot Systems (IROS) (2012)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Industrial Technology Research Institute, Hsinchu, Taiwan

    Weiyuan Hsieh

Authors
  1. Weiyuan Hsieh
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Weiyuan Hsieh .

Editor information

Editors and Affiliations

  1. School of Information and Communication Technology, Griffith University, Southport, Australia

    Jun Jo

  2. Department of Aerospace Engineering, KAIST, Daejeon, Korea (Republic of)

    Han-Lim Choi

  3. School of Information and Communication Technology, Griffith University, Southport, Australia

    Marde Helbig

  4. Department of Mechanical Engineering, Ulsan National Institute of Science and Technology (UNIST), Ulsan, Korea (Republic of)

    Hyondong Oh

  5. Department of Mechanical Engineering, KAIST, Daejeon, Korea (Republic of)

    Jemin Hwangbo

  6. Department of Mechanical Engineering, KAIST, Daejeon, Korea (Republic of)

    Chang-Hun Lee

  7. School of Information and Communication Technology, Griffith University, Southport, Australia

    Bela Stantic

Appendices

A Experiment Configurations

1.1 A.1 GPS/INS Interpolation

Let \(\textbf{T}_t\) denote the INS pose at time t, for an instance \(\beta \) between two consecutive INS occurrences \(\textbf{T}_\alpha \) and \(\textbf{T}_\gamma \), the interpolation \(\textbf{T}_\beta \) is:

$$\begin{aligned} \textbf{T}_\beta =\textbf{T}_\alpha \times \exp \left( \frac{(\beta -\alpha ) \log \left( \textbf{T}_\alpha ^{-1}\textbf{T}_\gamma \right) ^{\wedge }}{\gamma -\alpha } \right) \end{aligned}$$
(17)

A LiDAR scan would be excluded from RobotCar (INS) if it arrives after the last or before the first INS instance, since \(\alpha \le \beta \le \gamma \) no longer holds.

1.2 A.2 Configuration Details

Source clouds are downsampled by voxel-grid filters with grid size listed in Table 2. Initial guesses \(\textbf{T}_{init}\) are generated according to (13), except for RobotCar (INS), which uses (17) instead.

Table 2. Configuration details
Full size table

B Tested Sequences of Datasets

1.1 B.1 RobotCar

Footnote 5

figure d

1.2 B.2 KITTI

Sequence 00-10, all sequences with public ground truth.

1.3 B.3 TUM-RGBD

figure e

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Hsieh, W. (2023). Planar Fitting Transformation: A Rapid Point Cloud Registration for Real-time Applications. In: Jo, J., et al. Robot Intelligence Technology and Applications 7. RiTA 2022. Lecture Notes in Networks and Systems, vol 642. Springer, Cham. https://doi.org/10.1007/978-3-031-26889-2_23

Download citation

Publish with us

Policies and ethics

Search

Navigation