Advertisement

On Fast Point Cloud Matching with Key Points and Parameter Tuning

  • Dániel VargaEmail author
  • Sándor Laki
  • János Szalai-Gindl
  • László Dobos
  • Péter Vaderna
  • Bence Formanek
Conference paper
  • 129 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12046)

Abstract

Nowadays, three dimensional point cloud processing plays a very important role in a wide range of areas: autonomous driving, robotics, cartography, etc. Three dimensional point cloud registration pipelines have high computational complexity, mainly because of the cost of point feature signature calculation. By selecting keypoints and using only them for registration, data points that are interesting in some way, one can significantly reduce the number of points for which feature signatures are needed, hence the running time of registration pipelines. Consequently, keypoint detectors have a prominent role in an efficient processing pipeline. In this paper, we propose to analyze the usefulness of various keypoint detection algorithms and investigate whether and when it is worth to use a keypoint detector for registration. We define the goodness of a keypoint detection algorithm based on the success and quality of registration. Most keypoint detection methods require manual tuning of their parameters for best results. Here we revisit the most popular methods for keypoint detection in 3D point clouds and perform automatic parameter tuning with goodness of registration and run time as primary objectives. We compare keypoint-based registration to registration with randomly selected points and using all data points as a baseline. In contrast to former work, we use point clouds of different sizes, with and without noise, and register objects with different sizes.

Keywords

3D point cloud Keypoint detector Point cloud registration 

References

  1. 1.
    Chetverikov, D., Stepanov, D., Krsek, P.: Robust Euclidean alignment of 3D point sets: the trimmed iterative closest point algorithm. Image Vis. Comput. 23, 299–309 (2005).  https://doi.org/10.1016/j.imavis.2004.05.007CrossRefGoogle Scholar
  2. 2.
    Filipe, S., Alexandre, L.A.: A comparative evaluation of 3D keypoint detectors in a RGB-D object dataset. In: 2014 International Conference on Computer Vision Theory and Applications (VISAPP), vol. 1, pp. 476–483, January 2014Google Scholar
  3. 3.
    Fitzgibbon, A.: Robust registration of 2D and 3D point sets. Image Vis. Comput. 21, 1145–1153 (2002).  https://doi.org/10.1016/j.imavis.2003.09.004CrossRefGoogle Scholar
  4. 4.
    Granger, S., Pennec, X.: Multi-scale EM-ICP: a fast and robust approach for surface registration. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2353, pp. 418–432. Springer, Heidelberg (2002).  https://doi.org/10.1007/3-540-47979-1_28CrossRefGoogle Scholar
  5. 5.
    Harris, C., Stephens, M.: A combined corner and edge detector, p. 50, January 1988Google Scholar
  6. 6.
    Holzer, S., Shotton, J., Kohli, P.: Learning to efficiently detect repeatable interest points in depth data. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7572, pp. 200–213. Springer, Heidelberg (2012).  https://doi.org/10.1007/978-3-642-33718-5_15CrossRefGoogle Scholar
  7. 7.
    Shi, J., Tomasi, C.: Good features to track. In: 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 593–600, June 1994.  https://doi.org/10.1109/CVPR.1994.323794
  8. 8.
    Lai, K., Bo, L., Fox, D.: Unsupervised feature learning for 3D scene labeling. In: 2014 IEEE International Conference on Robotics and Automation (ICRA), pp. 3050–3057, May 2014.  https://doi.org/10.1109/ICRA.2014.6907298
  9. 9.
    Li, J., Lee, G.: USIP: unsupervised stable interest point detection from 3D point clouds, March 2019Google Scholar
  10. 10.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004).  https://doi.org/10.1023/B:VISI.0000029664.99615.94CrossRefGoogle Scholar
  11. 11.
    Mian, A., Bennamoun, M., Owens, R.: On the repeatability and quality of keypoints for local feature-based 3D object retrieval from cluttered scenes. Int. J. Comput. Vis. 89(2), 348–361 (2010).  https://doi.org/10.1007/s11263-009-0296-zCrossRefGoogle Scholar
  12. 12.
    Phillips, J.M., Liu, R., Tomasi, C.: Outlier robust ICP for minimizing fractional RMSD. In: Sixth International Conference on 3-D Digital Imaging and Modeling (3DIM 2007), pp. 427–434, August 2007.  https://doi.org/10.1109/3DIM.2007.39
  13. 13.
    Pomerleau, F., Colas, F., Siegwart, R.: A review of point cloud registration algorithms for mobile robotics. Found. Trends® Robot. 4, 1–104 (2015).  https://doi.org/10.1561/2300000035CrossRefGoogle Scholar
  14. 14.
    Rusu, R., Blodow, N., Beetz, M.: Fast point feature histograms (FPFH) for 3D registration, pp. 3212–3217, June 2009.  https://doi.org/10.1109/ROBOT.2009.5152473
  15. 15.
    Rusu, R., Cousins, S.: 3D is here: point cloud library (PCL), May 2011.  https://doi.org/10.1109/ICRA.2011.5980567
  16. 16.
    Salti, S., Tombari, F., Spezialetti, R., Stefano, L.D.: Learning a descriptor-specific 3D keypoint detector. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 2318–2326, December 2015.  https://doi.org/10.1109/ICCV.2015.267
  17. 17.
    Salti, S., Tombari, F., Stefano, L.D.: A performance evaluation of 3D keypoint detectors. In: 2011 International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission, pp. 236–243, May 2011.  https://doi.org/10.1109/3DIMPVT.2011.37
  18. 18.
    Segal, A., Hähnel, D., Thrun, S.: Generalized-ICP, June 2009.  https://doi.org/10.15607/RSS.2009.V.021
  19. 19.
    Teran, L., Mordohai, P.: 3D interest point detection via discriminative learning. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 159–173. Springer, Cham (2014).  https://doi.org/10.1007/978-3-319-10590-1_11CrossRefGoogle Scholar
  20. 20.
    Tonioni, A., Salti, S., Tombari, F., Spezialetti, R., Stefano, L.D.: Learning to detect good 3D keypoints. Int. J. Comput. Vis. 126(1), 1–20 (2018).  https://doi.org/10.1007/s11263-017-1037-3CrossRefGoogle Scholar
  21. 21.
    Yang, J., Li, H., Campbell, D., Jia, Y.: Go-ICP: a globally optimal solution to 3D ICP point-set registration. IEEE Trans. Pattern Anal. Mach. Intell. 38, 2241–2254 (2015).  https://doi.org/10.1109/TPAMI.2015.2513405CrossRefGoogle Scholar
  22. 22.
    Yew, Z.J., Lee, G.H.: 3DFeat-Net: weakly supervised local 3D features for point cloud registration. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11219, pp. 630–646. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01267-0_37CrossRefGoogle Scholar
  23. 23.
    Zhong, Y.: Intrinsic shape signatures: a shape descriptor for 3D object recognition, pp. 689–696, December 2009.  https://doi.org/10.1109/ICCVW.2009.5457637
  24. 24.
    Zhou, Q.-Y., Park, J., Koltun, V.: Fast global registration. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 766–782. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-46475-6_47CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Dániel Varga
    • 1
    Email author
  • Sándor Laki
    • 1
  • János Szalai-Gindl
    • 1
  • László Dobos
    • 1
  • Péter Vaderna
    • 2
  • Bence Formanek
    • 2
  1. 1.ELTE Eötvös Loránd UniversityBudapestHungary
  2. 2.Ericsson ResearchBudapestHungary

Personalised recommendations