Abstract
Pose Estimation is an important component of many real-world computer vision systems. Most existing pose estimation algorithms need a large number of point correspondences to accurately determine the pose of an object. Since the number of point correspondences depends on the object’s appearance, lighting and other external conditions, detecting many points may not be feasible. In many real-world applications, movement of objects is limited due to gravity. Hence, detecting objects with only three degrees of freedom is usually sufficient. This allows us to improve the accuracy of pose estimation by changing the underlying equation of the perspective-n-point problem to allow only three variables instead of six. By using the improved equations, our algorithm is more robust against detection errors with limited point correspondences. In this paper, we specify two scenarios where such constraints apply. The first one is about parking a vehicle on a specific spot, while the second scenario describes a camera observing objects from a birds-eye view. In both scenarios, objects can only move in the ground plane and rotate around the vertical axis. Experiments with synthetic data and real-world photographs have shown that our algorithm outperforms state-of-the-art pose estimation algorithms. Depending on the scenario, our algorithm usually achieves 50% better accuracy, while being equally fast.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bujnak, M., Kukelova, Z., Pajdla, T.: A general solution to the P4P problem for camera with unknown focal length. In: CVPR (2008). https://doi.org/10.1109/CVPR.2008.4587793
Burke, J.V., Ferris, M.C.: A gauss–newton method for convex composite optimization. Math. Program. 71, 179–194 (1995). https://doi.org/10.1007/BF01585997
Chen, J., Zhang, L., Liu, Y., Xu, C.: Survey on 6D pose estimation of rigid object. In: CCC (2020). https://doi.org/10.23919/CCC50068.2020.9189304
Collins, T., Bartoli, A.: Infinitesimal plane-based pose estimation. Int. J. Comput. Vis. 109(3), 252–286 (2014). https://doi.org/10.1007/s11263-014-0725-5
Dhall, A., Dai, D., Van Gool, L.: Real-time 3D traffic cone detection for autonomous driving. In: IV (2019). https://doi.org/10.1109/IVS.2019.8814089
Einsiedler, J., Becker, D., Radusch, I.: External visual positioning system for enclosed carparks. In: WPNC (2014). https://doi.org/10.1109/WPNC.2014.6843287
Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24, 381–395 (1981). https://doi.org/10.1145/358669.358692
Fragoso, V., DeGol, J., Hua, G.: gDLS*: generalized pose-and-scale estimation given scale and gravity priors. In: CVPR (2020). https://doi.org/10.1109/CVPR42600.2020.00228
Gao, X.S., Hou, X.R., Tang, J., Cheng, H.F.: Complete solution classification for the perspective-three-point problem. In: TPAMI (2003)
Garro, V., Crosilla, F., Fusiello, A.: Solving the PnP problem with anisotropic orthogonal procrustes analysis. In: 3DIMPVT (2012). https://doi.org/10.1109/3DIMPVT.2012.40
Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: the KITTI dataset. Int. J. Robot. Res. 32, 1231–1237 (2013). https://doi.org/10.1177/0278364913491297
Grafarend, E.W., Shan, J.: Closed-form solution of P4P or the three-dimensional resection problem in terms of Möbius barycentric coordinates. J. Geodesy 71, 217–231 (1997). https://doi.org/10.1007/s001900050089
Grunert, J.A.: Das Pothenot’sche Problem, in erweiterter Gestalt; nebst Bemerkungen über seine Anwendung in der Geodäsie. Archiv der Mathematik und Physik (1841)
Gu, R., Wang, G., Hwang, J.N.: Efficient multi-person hierarchical 3D pose estimation for autonomous driving. In: MIPR (2019). https://doi.org/10.1109/MIPR.2019.00036
Hagelskjær, F., Savarimuthu, T.R., Krüger, N., Buch, A.G.: Using spatial constraints for fast set-up of precise pose estimation in an industrial setting. In: CASE (2019). https://doi.org/10.1109/COASE.2019.8842876
Hajder, L., Barath, D.: Least-squares optimal relative planar motion for vehicle-mounted cameras. In: ICRA (2020). https://doi.org/10.1109/ICRA40945.2020.9196755
Hesch, J.A., Roumeliotis, S.I.: A direct least-squares (DLS) method for PnP. In: ICCV (2011). https://doi.org/10.1109/ICCV.2011.6126266
IAM, Universität Duisburg-Essen: Taxiladekonzept für Elektrotaxis im öffentlichen Raum. talako.uni-due.de (2022). Accessed 14 Jan 2022
Jiao, Y., et al.: Robust localization for planar moving robot in changing environment: a perspective on density of correspondence and depth. In: ICRA (2021). https://doi.org/10.1109/ICRA48506.2021.9561539
Kim, I.S., Jung, T.W., Jung, K.D.: Augmented reality service based on object pose prediction using PnP algorithm. IJACT 9, 295–301 (2021)
Kim, S.T., Fan, M., Jung, S.W., Ko, S.J.: External vehicle positioning system using multiple fish-eye surveillance cameras for indoor parking lots. IEEE Syst. J. 15, 5107–5118 (2021). https://doi.org/10.1109/JSYST.2020.3019296
Kneip, L., Li, H., Seo, Y.: UPnP: an optimal O(n) solution to the absolute pose problem with universal applicability. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 127–142. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10590-1_9
Kneip, L., Scaramuzza, D., Siegwart, R.: A novel parametrization of the perspective-three-point problem for a direct computation of absolute camera position and orientation. In: CVPR (2011). https://doi.org/10.1109/CVPR.2011.5995464
Lee, S., Moon, Y.K.: Camera pose estimation using voxel-based features for autonomous vehicle localization tracking. In: ITC-CSCC (2022). https://doi.org/10.1109/ITC-CSCC55581.2022.9895071
Lee, T.E., et al.: Camera-to-robot pose estimation from a single image. In: ICRA (2020). https://doi.org/10.1109/ICRA40945.2020.9196596
Lepetit, V., Moreno-Noguer, F., Fua, P.: EPnP: an accurate o(n) solution to the PnP problem. IJCV 81, 155–166 (2009). https://doi.org/10.1007/s11263-008-0152-6
Levenberg, K.: A method for the solution of certain non-linear problems in least squares. Q. Appl. Math. 2, 164–168 (1944)
Li, C., Wang, X.: On convergence of the gauss-newton method for convex composite optimization. Math. Program. 91, 349–356 (2002)
Lin, Y., Tremblay, J., Tyree, S., Vela, P.A., Birchfield, S.: Multi-view fusion for multi-level robotic scene understanding. In: IROS (2021). https://doi.org/10.1109/IROS51168.2021.9635994
Lu, X.X.: A review of solutions for perspective-n-point problem in camera pose estimation. In: Journal of Physics: Conference Series (2018). https://doi.org/10.1088/1742-6596/1087/5/052009
Marchand, E., Uchiyama, H., Spindler, F.: Pose estimation for augmented reality: a hands-on survey. TVCG 22, 2633–2651 (2016). https://doi.org/10.1109/TVCG.2015.2513408
Marquardt, D.W.: An algorithm for least-squares estimation of nonlinear parameters. J. Soc. Ind. Appl. Math. 11, 431–441 (1963)
Martull, S., Peris, M., Fukui, K.: Realistic CG stereo image dataset with ground truth disparity maps. Technical report of IEICE, PRMU (2012)
Nelder, J.A., Mead, R.: A simplex method for function minimization. Comput. J. 7, 308–313 (1965). https://doi.org/10.1093/comjnl/7.4.308
Ortín, D., Montiel, J.M.M.: Indoor robot motion based on monocular images. Robotica 19, 331–342 (2001). https://doi.org/10.1017/S0263574700003143
Pan, S., Wang, X.: A survey on perspective-n-point problem. In: CCC (2021). https://doi.org/10.23919/CCC52363.2021.9549863
Parameshwara, C.M., Hari, G., Fermüller, C., Sanket, N.J., Aloimonos, Y.: DiffPoseNet: direct differentiable camera pose estimation. In: CVPR (2022). https://doi.org/10.1109/CVPR52688.2022.00672
Persson, M., Nordberg, K.: Lambda twist: an accurate fast robust perspective three point (P3P) solver. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 334–349. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01225-0_20
Pošík, P., Huyer, W.: Restarted local search algorithms for continuous black box optimization. Evol. Comput. 20, 575–607 (2012). https://doi.org/10.1162/EVCO_a_00087
Qingxuan, J., Ping, Z., Hanxu, S.: The study of positioning with high-precision by single camera based on p3p algorithm. In: ICII (2006). https://doi.org/10.1109/INDIN.2006.275618
Roch, P., Shahbaz Nejad, B., Handte, M., Marrón, P.J.: Car pose estimation through wheel detection. In: Bebis, G., et al. (eds.) ISVC 2021. LNCS, vol. 13017, pp. 265–277. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-90439-5_21
Rublee, E., Rabaud, V., Konolige, K., Bradski, G.: Orb: An efficient alternative to sift or surf. In: ICCV (2011). https://doi.org/10.1109/ICCV.2011.6126544
Scaramuzza, D.: 1-point-RANSAC structure from motion for vehicle-mounted cameras by exploiting non-holonomic constraints. IJCV 95, 74–85 (2011). https://doi.org/10.1007/s11263-011-0441-3
Schweighofer, G., Pinz, A.: Globally optimal O(n) solution to the PnP problem for general camera models. In: BMVC (2008)
Sturm, J., Engelhard, N., Endres, F., Burgard, W., Cremers, D.: A benchmark for the evaluation of RGB-D SLAM systems. In: IROS (2012). https://doi.org/10.1109/IROS.2012.6385773
Sweeney, C., Flynn, J., Nuernberger, B., Turk, M., Höllerer, T.: Efficient computation of absolute pose for gravity-aware augmented reality. In: ISMAR (2015). https://doi.org/10.1109/ISMAR.2015.20
Terzakis, G., Lourakis, M.: A consistently fast and globally optimal solution to the perspective-n-point problem. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 478–494. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58452-8_28
Tremblay, J., To, T., Sundaralingam, B., Xiang, Y., Fox, D., Birchfield, S.: Deep object pose estimation for semantic robotic grasping of household objects. CoRR (2018). https://doi.org/10.48550/arXiv.1809.10790
Urban, S., Leitloff, J., Hinz, S.: MLPnP - a real-time maximum likelihood solution to the perspective-n-point problem. ISPRS (2016). https://doi.org/10.5194/isprs-annals-iii-3-131-2016
Velichkovsky, B.M., Kotov, A., Arinkin, N., Zaidelman, L., Zinina, A., Kivva, K.: From social gaze to indirect speech constructions: how to induce the impression that your companion robot is a conscious creature. Appl. Sci. 11, 10255 (2021). https://doi.org/10.3390/app112110255
Wang, Z., Yang, X.: V-head: face detection and alignment for facial augmented reality applications. In: Amsaleg, L., Guðmundsson, G.Þ, Gurrin, C., Jónsson, B.Þ, Satoh, S. (eds.) MMM 2017. LNCS, vol. 10133, pp. 450–454. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-51814-5_40
Zhang, B., Zhang, Q., Wang, Y., Tian, Z.: The method of solving the non-coplanar perspective-four-point (P4P) problem. In: CCC (2014). https://doi.org/10.1109/ChiCC.2014.6896771
Zhou, G., Wang, H., Chen, J., Huang, D.: PR-GCN: a deep graph convolutional network with point refinement for 6D pose estimation. In: ICCV (2021). https://doi.org/10.1109/ICCV48922.2021.00279
Acknowledgments
This research is funded by the Bundesministerium für Wirtschaft und Energie as part of the TALAKO project (“Taxiladekonzept für Elektrotaxis im öffentlichen Raum” tr. “Taxi Charging Concept for Public Spaces”) [18] (grant number 01MZ19002A).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Roch, P., Shahbaz Nejad, B., Handte, M., Marrón, P.J. (2023). Optimizing PnP-Algorithms for Limited Point Correspondences Using Spatial Constraints. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2023. Lecture Notes in Computer Science, vol 14362. Springer, Cham. https://doi.org/10.1007/978-3-031-47966-3_17
Download citation
DOI: https://doi.org/10.1007/978-3-031-47966-3_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-47965-6
Online ISBN: 978-3-031-47966-3
eBook Packages: Computer ScienceComputer Science (R0)