Robust Camera Pose Estimation from Line Correspondences Using GNC

“Robust Camera Pose Estimation from Line Correspondences Using GNC”

Authors: Hans K.R. Holen, Torbjørn Smith and Olav Egeland,
Affiliation: NTNU
Reference: 2024, Vol 45, No 4, pp. 137-146.

Keywords: PnL, PnP, Camera Pose Estimation, Dynamical Pose Estimation, GNC

Abstract: A solution to the Perspective-n-Lines (PnL) problem is proposed where a large fraction of outliers can be handled. The approach estimates camera pose from 2D-3D line correspondences where outliers are in the form of line mismatches. The solution is based on graduated non-convexity (GNC) with truncated least squares with Dynamical Pose Estimation (DAMP) as a solver. The solution is simple to implement and does not require specialized optimization software. The method is compared to 11 state-of-the-art PnL methods using synthetic and real data and evaluated in terms of accuracy, running time, and sensitivity to noise and outliers. The results show that our proposed method scores among the top for accuracy and robustness.

PDF

PDF (845 Kb)        DOI: 10.4173/mic.2024.4.3

References:
[1] Abdellali, H., Frohlich, R., and Kato, Z. (2019). A direct least-squares solution to multi-view absolute and relative pose from 2D-3D perspective line pairs, In 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW). pages 2119--2128. doi:10.1109/ICCVW.2019.00267
[2] Ansar, A. and Daniilidis, K. (2003). Linear pose estimation from points or lines, IEEE Transactions on Pattern Analysis and Machine Intelligence. 25(5):578--589. doi:10.1109/TPAMI.2003.1195992
[3] 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
[4] Black, M.J. and Rangarajan, A. (1996). On the unification of line processes, outlier rejection, and robust statistics with applications in early vision, Intl. J. 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] Cadena, C., Carlone, L., Carrillo, H., Latif, Y., Scaramuzza, D., Neira, J., Reid, I., and Leonard, J.J. (2016). Past, present, and future of simultaneous localization and mapping: Toward the robust-perception age, IEEE Transactions on Robotics. 32(6):1309--1332. doi:10.1109/TRO.2016.2624754
[7] Chin, T.-J. and Suter, D. (2017). The maximum consensus problem: Recent algorithmic advances, In Synthesis Lectures on Computer Vision. 2017. doi:10.2200/S00757ED1V01Y201702COV011
[8] Coughlan, J.M. and Yuille, A.L. (2003). Manhattan world: Orientation and outlier detection by bayesian inference, Neural Computation. 15(5):1063--1088. doi:10.1162/089976603765202668
[9] David, P., DeMenthon, D., Duraiswami, R., and Samet, H. (2003). Simultaneous pose and correspondence determination using line features, In 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Proceedings., volume2. IEEE, pages II--II. doi:10.1109/CVPR.2003.1211499
[10] Ferraz, L., Binefa, X., and Moreno-Noguer, F. (2014). Very fast solution to the PnP problem with algebraic outlier rejection, In 2014 IEEE Conference on Computer Vision and Pattern Recognition. pages 501--508. doi:10.1109/CVPR.2014.71
[11] 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
[12] Hartley, R. and Zisserman, A. (2003). Multiple view geometry in computer vision, Cambridge University Press. doi:10.1017/CBO9780511811685
[13] Kumar, R. and Hanson, A. (1994). Robust methods for estimating pose and a sensitivity analysis, CVGIP: Image Understanding. 60(3):313--342. https://www.sciencedirect.com/science/article/pii/S1049966084710606, doi:https://doi.org/10.1006/ciun.1994.1060
[14] Lepetit, V., Moreno-Noguer, F., and Fua, P. (2009). Epnp: An accurate o(n) solution to the pnp problem, International Journal of Computer Vision. 81(2):155--166. doi:10.1007/s11263-008-0152-6
[15] Li, S., Xu, C., and Xie, M. (2012). A robust O(n) solution to the perspective-n-point problem, IEEE Transactions on Pattern Analysis and Machine Intelligence. 34(7):1444--1450. doi:10.1109/TPAMI.2012.41
[16] Liu, Y., Chen, G., and Knoll, A. (2021). Globally optimal camera orientation estimation from line correspondences by BnB algorithm, IEEE Robotics and Automation Letters. 6(1):215--222. doi:10.1109/LRA.2020.3037843
[17] Liu, Y., Huang, T., and Faugeras, O. (1990). Determination of camera location from 2-D to 3-D line and point correspondences, IEEE Transactions on Pattern Analysis and Machine Intelligence. 12(1):28--37. doi:10.1109/34.41381
[18] Mirzaei, F.M. and Roumeliotis, S.I. (2011). Globally optimal pose estimation from line correspondences, In 2011 IEEE International Conference on Robotics and Automation. pages 5581--5588. doi:10.1109/ICRA.2011.5980272
[19] Morrison, D.R., Jacobson, S.H., Sauppe, J.J., and Sewell, E.C. (2016). Branch-and-bound algorithms: A survey of recent advances in searching, branching, and pruning, Discrete Optimization. 19:79--102. doi:10.1016/j.disopt.2016.01.005
[20] 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
[21] Pottmann, H. and Wallner, J. (2001). Computational Line Geometry, Springer-Verlag, Berlin. doi:10.1007/978-3-642-04018-4
[22] Pribyl, B., Zemcik, P., and Cadik, M. (2016). Camera pose estimation from lines using Plucker coordinates, arXiv preprint arXiv:1608.02824. doi:10.5244/C.29.45
[23] Pribyl, B., Zemcik, P., and Cadik, M. (2017). Absolute pose estimation from line correspondences using direct linear transformation, Computer Vision and Image Understanding. 161:130--144. doi:10.1016/j.cviu.2017.05.002
[24] Silva, M., Ferreira, R., and Gaspar, J. (2012). Camera calibration using a color-depth camera: Points and lines based dlt including radial distortion, In Workshop Color-Depth Camera Fusion in Robotics, held with IROS. 2012. doi:10.1109/IROS.2012.6385509
[25] Smith, T. and Egeland, O. (2022). Dynamical Pose Estimation with Graduated Non-Convexity for Outlier Robustness, Modeling, Identification and Control. 43(2):79--89. doi:10.4173/mic.2022.2.3
[26] Torr, P. and Zisserman, A. (2000). Mlesac: A new robust estimator with application to estimating image geometry, Computer Vision and Image Understanding. 78(1):138--156. https://www.sciencedirect.com/science/article/pii/S1077314299908329, doi:https://doi.org/10.1006/cviu.1999.0832
[27] Wang, K., Liu, D., Liu, Z., Duan, G., Hu, L., and Tan, J. (2020). A fast object registration method for augmented reality assembly with simultaneous determination of multiple 2D-3D correspondences, Robotics and Computer-Integrated Manufacturing. 63:101890. https://www.sciencedirect.com/science/article/pii/S0736584519301644, doi:https://doi.org/10.1016/j.rcim.2019.101890
[28] Wang, P., Xu, G., Cheng, Y., and Yu, Q. (2019). Camera pose estimation from lines: a fast, robust and general method, Machine Vision and Applications. 30(4):603--614. doi:DOI: 10.1007/s00138-019-01012-0
[29] Xu, C., Zhang, L., Cheng, L., and Koch, R. (2017). Pose estimation from line correspondences: A complete analysis and a series of solutions, IEEE Transactions on Pattern Analysis and Machine Intelligence. 39(6):1209--1222. doi:10.1109/TPAMI.2016.2582162
[30] 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. 5(2):1127--1134. doi:10.1109/LRA.2020.2965893
[31] Yang, H., Doran, C., and Slotine, J.-J. (2021). Dynamical pose estimation, In Proceedings of the IEEE/CVF International Conference on Computer Vision. pages 5926--5935. doi:10.48550/arXiv.2103.06182
[32] Yu, H., Zhen, W., Yang, W., and Scherer, S. (2020). Line-based 2-D--3-D registration and camera localization in structured environments, IEEE Transactions on Instrumentation and Measurement. 69(11):8962--8972. doi:10.1109/TIM.2020.2999137
[33] Zhang, L., Xu, C., Lee, K.-M., and Koch, R. (2013). Robust and efficient pose estimation from line correspondences, In K.M. Lee, Y.Matsushita, J.M. Rehg, and Z.Hu, editors, Computer Vision -- ACCV 2012. Springer Berlin Heidelberg, Berlin, Heidelberg, pages 217--230. doi:10.1007/978-3-642-37431-9_17
[34] Zhang, X., Zhang, Z., Li, Y., Zhu, X., Yu, Q., and Ou, J. (2012). Robust camera pose estimation from unknown or known line correspondences, Applied optics. 51(7):936--948. doi:10.1364/AO.51.000936
[35] Zhang, Y., Li, X., Liu, H., and Shang, Y. (2016). Probabilistic approach for maximum likelihood estimation of pose using lines, IET Computer Vision. 10(6):475--482. doi:10.1049/iet-cvi.2015.0099
[36] Zhou, L., Koppel, D., and Kaess, M. (2021). A complete, accurate and efficient solution for the perspective-n-line problem, IEEE Robotics and Automation Letters. 6(2):699--706. doi:10.1109/LRA.2020.3047797
[37] 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

BibTeX:
@article{MIC-2024-4-3,
  title={{Robust Camera Pose Estimation from Line Correspondences Using GNC}},
  author={Holen, Hans K.R. and Smith, Torbjørn and Egeland, Olav},
  journal={Modeling, Identification and Control},
  volume={45},
  number={4},
  pages={137--146},
  year={2024},
  doi={10.4173/mic.2024.4.3},
  publisher={Norwegian Society of Automatic Control}
};

Article

“Robust Camera Pose Estimation from Line Correspondences Using GNC”