Abstract
Pairwise rigid registration can be developed by comparing local geometry encoded by intrinsic second-order orientation tensors which allows to model the registration problem using the associated Riemannian geometry or related group structures. Everything starts by representing those tensor fields as multivariate normal models that permit us to manipulate Gaussians in two ways: using the Riemannian manifold elements, that can be embedded into matrix spaces with geometric structures, or through Lie group/algebra techniques. In this paper we discuss some points behind these approaches in the context of rigid registration problems. Firstly, they are not equivalent since, in general, there is no isometry linking them. Secondly, embedding methodologies are not invariant with respect to rigid motion. We discuss these points using two variants of the Iterative Closest Point that use the comparative tensor shape factor (CTSF) to match orientation tensors. We replace the CTSF to different criteria computed through geodesic distance and algebraic embeddings and compare the registration algorithms showing that the latter is more efficient for registration of point clouds.
Similar content being viewed by others
References
Almeida, L.R., Giraldi, G.A., Vieira, M.B.: Applying lie groups approaches for rigid registration of point clouds. Technical report, Laboratório Nacional de Computação Científica (2018). arXiv:2006.13341
Almeida, L.R., Giraldi, G.A., Vieira, M.B.: Rigid registration of point clouds based on indirect lie group approach. In: 21st Symposium on Virtual and Augmented Reality (SVR), Rio de Janeiro, RJ, pp. 130–139 (2019)
Amari, S.: Information Geometry and Its Applications, 1st edn. Springer, Berlin (2016)
Baker, A.: Matrix Groups: An Introduction to Lie Group Theory. Springer Undergraduate Mathematics Series. Springer, London (2002)
Berger, M., Tagliasacchi, A., Seversky, L.M., Alliez, P., Guennebaud, G., Levine, J.A., Sharf, A., Silva, C.T.: A survey of surface reconstruction from point clouds. In: Computer Graphics Forum. Wiley Online Library (2016)
Besl, P.J., McKay, N.D.: A method for registration of 3-d shapes. IEEE Trans. Pattern Anal. Mach. Intell. 14(2), 239–256 (1992)
Bridger, M.: Real Analysis: A Constructive Approach Through Interval Arithmetic. American Mathematical Society, Providence (2019)
Calvo, M., Oller, J.M.: A distance between multivariate normal distributions based on an embedding into the Siegel group. J. Multivar. Anal. 35(2), 223–242 (1990)
Carmo, M.P.D.: Riemannian Geometry: Theory & Applications, 1st edn. Birkhauser, Boston (1992)
Cejnog, L.W.X., Yamada, F.A.A., Vieira, M.B.: Wide angle rigid registration using a comparative tensor shape factor. Int. J. Image Graph. 17(01), 1–34 (2017)
Chetverikov, D., Svirko, D., Stepanov, D., Krsek, P.: The trimmed iterative closest point algorithm. In: Proceedings of 16th International Conference on Pattern Recognition, vol. 3, pp 545–548 (2002)
Clark, W., Ghaffari, M., Bloch, A.: Nonparametric continuous sensor registration. (2020) arXiv:2001.04286
Deng, Y., Rangarajan, A., Eisenschenk, S., Vemuri, B.C.: A riemannian framework for matching point clouds represented by the schrödinger distance transform. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 3756–3761 (2014). https://doi.org/10.1109/CVPR.2014.486
de Araujo Yamada, FA: A shape-based strategy applied to the covariance estimation on the ICP. Master’s thesis, Post-Graduation Program on Computer Science, Federal University of Juiz de Fora, Juiz de Fora, MG, Brazil (2016)
de Araujo Yamada, FA., Giraldi, GA., Vieira, MB., Almeida Jr., L.R.: Frame-to-frame rigid registration of point clouds extracted from depth sequences: Comparing different strategies. Technical report, Laboratório Nacional de Computação Científica, virtual01.lncc.br/\(\sim \)giraldi/extended-svr-paper2017/Relatorio-Registration-27-03-2017.pdf (2017)
de Araujo Yamada, F.A., Giraldi, G., Vieira, M., Almeida, L., Apolinario, A.L.: Comparing seven methodogies for rigid alignment of point clouds with focus on frame-to-frame registration in depth sequences. SBC J. Interact. Syst. 9, 82–104 (2018)
Department of Statistics, Stanford University (SUD), Lene Theil Skovgaard, National Science Foundation (US) (1981) A Riemannian Geometry of the Multivariate Normal Model. Statistical Research Unit, https://books.google.com.br/books?id=VQpfGwAACAAJ
Díez, Y., Roure, F., Lladó, X., Salvi, J.: A qualitative review on 3d coarse registration methods. ACM Comput. Surv. 47(3), 45 (2015)
do Carmo, M.P.: Differential Geometry of Curves and Surfaces. Prentice Hall, Hoboken (1976)
Dong, J., Peng, Y., Ying, S., Hu, Z.: Lietricp: an improvement of trimmed iterative closest point algorithm. Neurocomputing 140, 67–76 (2014)
Dryden, I.L., Koloydenko, A., Zhou, D.: Non-Euclidean statistics for covariance matrices, with applications to diffusion tensor imaging. Ann Appl Stat 3(3), 1102–1123 (2009). https://doi.org/10.1214/09-AOAS249
Gao, Q.H., Wan, T.R., Tang, W., Chen, L.: Object registration in semi-cluttered and partial-occluded scenes for augmented reality. Multimed. Tools Appl. 78(11), 15079–15099 (2019)
Gojcic, Z., Zhou, C., Wegner, J., Wieser, A.: The perfect match: 3d point cloud matching with smoothed densities. In: 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 5540–5549 (2019)
Gong, L., Wang, T., Liu, F.: Shape of Gaussians as feature descriptors. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp 2366–2371 (2009)
Group, C.V.: RGB-D SLAM dataset and benchmark. Technical report, https://vision.in.tum.de/data/datasets/rgbd-dataset/download (2012)
Handa, A., Whelan, T., McDonald, J., Davison, A.J.: A benchmark for RGB-D visual odometry, 3D reconstruction and SLAM. In: 2014 IEEE International Conference on Robotics and Automation (ICRA), pp. 1524–1531 (2014). https://doi.org/10.1109/ICRA.2014.6907054
Horn, B.K.: Closed-form solution of absolute orientation using unit quaternions. JOSA A 4(4), 629–642 (1987)
Huynh, D.Q.: Metrics for 3d rotations: comparison and analysis. J. Math. Imaging Vis. 35(2), 155–164 (2009)
Levoy, M., Gerth, J., Curless, B., Pull, K.: Bunny model (1994). https://graphics.stanford.edu/data/3Dscanrep/
Li, P., Wang, Q., Zeng, H., Zhang, L.: Local log-Euclidean multivariate Gaussian descriptor and its application to image classification. IEEE Trans. Pattern Anal. Mach. Intell. 39, 803–817 (2017)
Lima, E.: Variedades diferenciáveis. Monografias de matemática. Instituto Matemática Puro e Aplicada, Conselho Nacional de Pesquisas (1973)
Lovrić, M., Min-Oo, M.: Multivariate normal distributions parametrized as a Riemannian symmetric space. J. Multivar. Anal. 74(1), 36–48 (2000)
Luong, H.Q., Vlaminck, M., Goeman, W., Philips, W.: Consistent ICP for the registration of sparse and inhomogeneous point clouds. In: 2016 IEEE Sixth International Conference on Communications and Electronics (ICCE), pp 262–267 (2016). https://doi.org/10.1109/CCE.2016.7562647
Olver, P.J.: Applications of Lie Groups to Differential Equations, p. 1986. Springer-Verlag, Berlin (1986)
Rusu, R.B., Blodow, N., Marton, Z.C., Beetz, M.: Aligning point cloud views using persistent feature histograms. In: 2008 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 3384–3391 (2008) https://doi.org/10.1109/IROS.2008.4650967
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)
Salvi, J., Matabosch, C., Fofi, D., Forest, J.: A review of recent range image registration methods with accuracy evaluation. Image Vis. Comput. 25(5), 578–596 (2007)
Set, D.: File formats. Technical report (2012) https://vision.in.tum.de/data/datasets/rgbd-dataset/file_formats
Sharp, G.C., Lee, S.W., Wehe, D.K.: ICP registration using invariant features. IEEE Trans. Pattern Anal. Mach. Intell. 24(1), 90–102 (2002)
Shih, S., Chuang, Y., Yu, T.: An efficient and accurate method for the relaxation of multiview registration error. IEEE Trans. Image Process. 17(6), 968–981 (2008). https://doi.org/10.1109/TIP.2008.921987
Skovgaard, L.T.: A Riemannian geometry of the multivariate normal model. Scand. J. Stat. 11(4), 211–223 (1984)
Sturm, J., Engelhard, N., Endres, F., Burgard, W., Cremers, D.: A benchmark for the evaluation of RGB-D SLAM systems. In: International Conference on Intelligent Robot Systems (IROS) (2012)
Tam, G., Cheng, Z.Q., Lai, Y.K., Langbein, F., Liu, Y., Marshall, D., Martin, R., Sun, X.F., Rosin, P.: Registration of 3D point clouds and meshes: a survey from rigid to nonrigid. IEEE Trans. Vis. Comput. Graph. 19(7), 1199–1217 (2013)
Wang, Y., Solomon, M.J..: Deep closest point: learning representations for point cloud registration. In: International Conference on Computer Vision, pp. 3523–3532 (2019)
Xiong, H., Szedmak, S., Piater, J.: A study of point cloud registration with probability product kernel functions. In: International Conference on 3D Vision, pp. 207–214. IEEE (2013). https://doi.org/10.1109/3DV.2013.35, https://iis.uibk.ac.at/public/papers/Xiong-2013-3DV.pdf
Yamada, F.A., Giraldi, G.A., Vieira, M.B., Almeida Jr., L.R.: Comparing seven methodologies for rigid alignment of point clouds with focus on frame-to-frame registration in depth sequences. SBC J. Interact. Syst. 9(2), 82–104 (2018)
Yang, H., Shi, J., Carlone, L.: Teaser: fast and certifiable point cloud registration (2020). arXiv:2001.07715
Yang, J., Li, H., Jia, Y.: Go-icp: Solving 3d registration efficiently and globally optimally. In: 2013 IEEE International Conference on Computer Vision (ICCV), pp. 1457–1464. IEEE (2013)
Ying, S., Peng, J., Du, S., Qiao, H.: Lie group framework of iterative closest point algorithm for n-d data registration. Int. J. Pattern Recognit. Artif. Intell. 23, 1201–1220 (2009). https://doi.org/10.1142/S0218001409007533
Zeng, A., Song, S., Nießner, M., Fisher, M., Xiao, J., Funkhouser, T.: 3dmatch: learning local geometric descriptors from rgb-d reconstructions. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 199–208 (2017)
Zhang, B., Li, Y.F.: Automatic Calibration and Reconstruction for Active Vision Systems. Springer, Berlin (2014)
Zhou, Y., Li, H., Kneip, L.: Canny-vo: visual odometry with rgb-d cameras based on geometric 3-d 2-d edge alignment. IEEE Trans. Robot. 35(1), 184–199 (2019). https://doi.org/10.1109/TRO.2018.2875382
Acknowledgements
We thanks PCI-LNCC for the financial support.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
de Almeida, L.R., Giraldi, G.A., Vieira, M.B. et al. Pairwise Rigid Registration Based on Riemannian Geometry and Lie Structures of Orientation Tensors. J Math Imaging Vis 63, 894–916 (2021). https://doi.org/10.1007/s10851-021-01037-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10851-021-01037-z