Abstract
Camera pose estimation known as Perspective-n-Point (PnP) problem has essential applications in different fields such as robotics and augmented reality. In this paper, we propose a novel method for PnP problem called Geometric and Simple PnP (GSPnP) using coplanar feature points. Some characteristics of our proposed algorithm are non-iterativity, simplicity, ease-of-implementation on planer markers, and better accuracy. Our method reaches a very fast solution, beyond any complicated calculations just by relying on the projection geometry. We compare our proposed method with the available methods in solvePnP function of OpenCV library using AR.Drone 2.0 quadcopter simulation in Gazebo world and ArUco markers with the help of ROS. Moreover, we practically make some experiments using a real AR.Drone 2.0 quadcopter fitted in the table of a milling machine. The results show that GSPnP method is the fastest method (specifically, 13 times in simulation case and five times in experimental case faster than the current fastest method) with almost the same accuracy and even better results in some cases (e.g., a higher accuracy in the camera’s height estimation) compared to the other methods.
Similar content being viewed by others
References
Ansar, A., Daniilidis, K.: Linear pose estimation from points or lines. IEEE Trans. Pattern Anal. Mach. Intell. 25, 578–589 (2003)
ArUco: A Minimal Library for Augmented Reality Applications Based on OpenCV. https://www.uco.es/investiga/grupos/ava/node/26
Bacik, J., Durovsky, F., Fedor, P., Perdukova, D.: Autonomous flying with quadrocopter using fuzzy control and ArUco markers. J. Intell. Serv. Robot. 10, 185–194 (2017)
Carreira, T. G.: Quadcopter automatic landing on a docking station (2013)
Ferraz, L., Binefa, X., Moreno-Noguer, F.: Leveraging feature uncertainty in PnP problem. In: Proceedings of the British Machine Vision Conference (BMVC) (2014)
Ferraz, L., Binefa, X., Moreno-Noguer, F.: Very fast solution to the PnP problem with algebraic outlier rejection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 501–508 (2014)
Fiore, P.D.: Efficient linear solution of exterior orientation. IEEE. Trans. Pattern Anal. Mach. Intell. 23(2), 140–148 (2001)
Gao, X., Hou, X., Tang, J., Cheng, H.: Complete solution classification for the perspectivr-three-point problem. IEEE Trans. Pattern Anal. Mach. Intell. 25, 930–943 (2003)
Garro, V., Crosilla, F., Fuesiello, A.: Solving the PnP problem with anisotropic orthogonal procrustes analysis. In: Second International Conference on 3D Imaging, Modeling, Processing, Visualization and Transmission, pp. 262–269 (2012)
Hesch, J.A., Roumeliotis, S.I.: A direct lesat-squares (DLS) Method for PnP. In: Proceedings of ICCV, pp. 383–390 (2011)
Kneip, L., Scaramuzza, D., Sigwart, R.: A novel parameterization of the perspective-three-point problem for a direct computation of absolute camera position and orientation. In: Proceedings of the IEEE Conference on Computer and Pattern Recognition (CVPR) (2011)
Lepetit, V., Moreno-Noguer, F., Fua, P.: Epnp: An accurate O(n) solution to the pnp problem. Int. J. Comput. Vis. 81, 155–166 (2008)
Li, S., Xu, C., Xie, M.: A robust O(n) solution to the perspective-n-point problem. IEEE Trans. Pattern Anal. Mach. Intell. 34, 1444–1450 (2012)
Liu, Y., Chen, X., Gu, T., Zhang, Y., Xing, G.: Real-time camera pose estimation via line tracking. Vis. Comput. 34, 899–909 (2018)
Lu, C., Hager, G., Mjolsness, E.: Fast and globally convergent pose estimation from video images. IEEE Trans. Pattern Anal. Mach. Intell 22, 610–622 (2000)
OpenCV: Open Source Computer Vision Library. https://opencv.org/
Parrot AR.Drone 2.0. http://ardrone2.parrot.com/
Penate-Sanchez, A., Andrade-Cetto, J., Moreno-Noguer, F.: Exhaustive linearization for robust camera pose and focal length estimation. IEEE Trans. Pattern Anal. Mach. Intell. 35, 2387–2400 (2013)
Pi, C.-H., Sheng, V. B., Cheng, S.: A dual-loop approach with visual servoing fuzzy control for marker navigation quadcopter. In: Proceeding of the 4th IIAE International Conference on Intelligent Systems and Image Processing (2016)
Reif, R., Walch, D.: Augmented & Virtual Reality application in the field of logistics. Vis. Comput. 24, 987–994 (2008)
ROS: Robot Operating System. http://www.ros.org/
Roweis, S.: Levenberg-marquardt optimization. http://www.cs.nyu.edu/~roweis/notes/lm.pdf. Retrieved 20 Oct 2018
Siltanen, S.: Diminished reality for augmented reality interior design. Vis. Comput. 33, 193–208 (2017)
Wang, G., Jonathan, Q.M., Ji, Z.: Pose Estimation from circle or parallel lines in a single image. In: Asian Conference on Computer Vision (ACCV), pp. 363–372 (2007)
Zehng, Y., Kuang, Y., Sugimoto, S., Astrom, K., Okutomi, M.: Revisiting the PnP problem: a fast, general and optimal solution. In: Proceedings of the International Conference on Computer Vision (ICCV), pp. 2344–2351 (2013)
Zheng, Y., Sugimonto, S., Okutomi, M.: ASPnP: an accurate and scalable solution to the perspective-n-point problem. In: IEICE transactions on information and systems, pp. 1525–1535 (2013)
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
Eivazi Adli, S., Shoaran, M. & Sayyed Noorani, S.M. GSPnP: simple and geometric solution for PnP problem. Vis Comput 36, 1549–1557 (2020). https://doi.org/10.1007/s00371-019-01747-x
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00371-019-01747-x