“Dynamical Pose Estimation with Graduated Non-Convexity for Outlier Robustness”

Authors: Torbjørn Smith and Olav Egeland,
Affiliation: NTNU
Reference: 2022, Vol 43, No 2, pp. 79-89.

Keywords: Pose estimation, Outlier rejection, Dynamical Pose Estimation, Graduated Non-Convexity

Abstract: In this paper we develop a method for relative pose estimation for two sets of corresponding geometric primitives in 3D with a significant outlier fraction. This is done by using dynamical pose estimation as a solver in registration problems formulated with graduated non-convexity for truncated least squares (GNC-TLS). Dynamical pose estimation provides a unifying solver that can be used for point cloud registration, primitive registration, and absolute pose estimation. The solver is straightforward to implement, and it does not require specialized software for optimization. The main contribution of this paper is to show how the dynamical pose estimation method can be extended to fit into the GNC-TLS framework so that high outlier fractions can be handled. The proposed method is validated for point cloud registration, primitive registration, and absolute pose estimation. The accuracy and robustness to outliers is shown to be on the level of existing GNC-TLS methods.

PDF PDF (713 Kb)        DOI: 10.4173/mic.2022.2.3

DOI forward links to this article:
[1] Antonio Boccuto, Ivan Gerace and Valentina Giorgetti (2023), doi:10.3390/app13105861
[2] Giulio Biondi, Antonio Boccuto and Ivan Gerace (2023), doi:10.1007/978-3-031-37117-2_44
[3] Giulio Biondi, Antonio Boccuto and Ivan Gerace (2023), doi:10.1007/978-3-031-37117-2_45
[4] Liangzu Peng, Christian Kummerle and Rene Vidal (2023), doi:10.1109/CVPR52729.2023.01708
[1] Agostinho, S., Gomes, J., and DelBue, A. (2019). CvxPnPL: A unified convex solution to the absolute pose estimation problem from point and line correspondences, ArXiv preprint arXiv:1907.10545 [cs.
[2] Antonante, P., Tzoumas, V., Yang, H., and Carlone, L. (2022). Outlier-robust estimation: Hardness, minimally tuned algorithms, and applications, IEEE Transactions on Robotics (T-RO). 38(1):281--301. doi:10.1109/TRO.2021.3094984
[3] Arun, K., Huang, T., and Blostein, S. (1987). Least-squares filtering of two 3-D point sets, IEEE Trans. Pattern Analysis and Machine Intelligence. PAMI-9(5):698 -- 700. doi:10.1109/TPAMI.1987.4767965
[4] Black, M.J. and Rangarajan, A. (1996). On the unification of line processes, outlier rejection, and robust statistics with applications in early vision, International Journal of Computer Vision. 19(1):57--91. doi:10.1007/BF00131148
[5] Blake, A. and Zisserman, A. (1987). Visual Reconstruction, The MIT Press. doi:10.7551/mitpress/7132.001.0001
[6] Briales, J. and Gonzalez-Jimenez, J. (2017). Convex global 3D registration with Lagrangian duality, In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pages 5612--5621. doi:10.1109/CVPR.2017.595
[7] Curless, B. and Levoy, M. (1996). A volumetric method for building complex models from range images, In Proceedings of the 23rd Annual Conference on Computer Graphics and Interactive Techniques, SIGGRAPH '96. Association for Computing Machinery, New York, NY, USA, page 303–312. doi:10.1145/237170.237269
[8] Egeland, O. and Gravdahl, J.T. (2002). Modeling and Simulation for Automatic Control, Marine Cybernetics.
[9] Fischler, M.A. and Bolles, R.C. (1981). Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography, Communications of the ACM. 24(6):381--395. doi:10.1145/358669.358692
[10] Hartley, R. and Kahl, F. (2009). Global optimization through rotation space search, International Journal of Computer Vision. 82(1):64--79. doi:10.1007/s11263-008-0186-9
[11] Hartley, R.I. and Zisserman, A. (2004). Multiple View Geometry in Computer Vision, Cambridge University Press, second edition. doi:10.1017/CBO9780511811685
[12] Horn, B. K.P. (1987). Closed-form solution of absolute orientation using unit quaternions, Journal of the Optical Society of America. 4(4):629--642. doi:10.1364/JOSAA.4.000629
[13] Khalil, H.K. (2002). Nonlinear Systems, Pearson Education. Prentice Hall.
[14] Kneip, L., Li, H., and Seo, Y. (2014). UPnP: An optimal O(n) solution to the absolute pose problem with universal applicability, In Proceedings of the European Conf. on Computer Vision (ECCV). Springer, pages 127–--142. doi:10.1007/978-3-319-10590-1_9
[15] Olsson, C., Kahl, F., and Oskarsson, M. (2009). Branch-and-bound methods for Euclidean registration problems, IEEE Transactions on Pattern Analysis and Machine Intelligence. 31(5):783--794. doi:10.1109/TPAMI.2008.131
[16] ParraBustos, A. and Chin, T.J. (2018). Guaranteed outlier removal for point cloud registration with correspondences, IEEE Transactions on Pattern Analysis and Machine Intelligence. 40(512):2868--2882. doi:10.1109/TPAMI.2017.2773482
[17] Xiang, Y., Mottaghi, R., and Savarese, S. (2014). Beyond PASCAL: A benchmark for 3D object detection in the wild, In IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE, pages 75--82. doi:10.1109/WACV.2014.6836101
[18] Yang, H., Antonante, P., Tzoumas, V., and Carlone, L. (2020). Graduated non-convexity for robust spatial perception: From non-minimal solvers to global outlier rejection, IEEE Robotics and Automation Letters (RA-L). 5(2):1127--1134. doi:10.1109/LRA.2020.2965893
[19] Yang, H. and Carlone, L. (2019). A polynomial-time solution for robust registration with extreme outlier rates, In Proceedings of Robotics: Science and Systems (RSS). Freiburg im Breisgau, Germany. doi:10.15607/RSS.2019.XV.003
[20] Yang, H., Doran, C., and Slotine, J.-J. (2021). Dynamical pose estimation, In 2021 IEEE/CVF International Conference on Computer Vision (ICCV). pages 5906--5915, 2021. doi:10.1109/ICCV48922.2021.00587
[21] Yang, H., Shi, J., and Carlone, L. (2021). TEASER: Fast and certifiable point cloud registration, IEEE Transactions on Robotics, 2021. 37(2):314 -- 333. doi:10.1109/TRO.2020.3033695
[22] Zhou, Q., Park, J., and Koltun, V. (2016). Fast global registration, In European Conference on Computer Vision (ECCV). Springer, pages 766--782. doi:10.1007/978-3-319-46475-6_47
[23] Zhou, X., Zhu, M., Leonardos, S., and Daniilidis, K. (2017). Sparse representation for 3D shape estimation: A convex relaxation approach, IEEE Transactions on Pattern Analysis and Machine Intelligence. 39(8):1648--1661. doi:10.1109/TPAMI.2016.2605097

  title={{Dynamical Pose Estimation with Graduated Non-Convexity for Outlier Robustness}},
  author={Smith, Torbjørn and Egeland, Olav},
  journal={Modeling, Identification and Control},
  publisher={Norwegian Society of Automatic Control}