AQPnP: an accurate and quaternion-based solution for the Perspective-n-Point problem
Abstract
In this work, we present an accurate and quaternion-based solution for the Perspective-n-Point method for determining the position and orientation of a calibrated camera from a set of n 3D points and their corresponding 2D projections on the image plane referred to as AQPnP. Most of the previous PnP methods have not handled the uncertainty of image feature points directly. In the proposed method, uncertainty of image points is integrated into PnP method. This is achieved by mapping the covariance (uncertainty) matrices of the image points to PnP method. It then uses the alternating direction method of multipliers (ADMM) method to minimize the modeled cost function, which has the ability to find the desired solution in real time. The ADMM method solves the system of equations in a manner that is convergent to the global optimal. The ADMM, a widely used operator splitting technique, has drawn significant attention due to its excellent performance in various applications. Quaternion-based rotation parameterization allows AQPnP to be highly accurate in estimating the rotation matrix. We compared AQPnP method with the state-of-the-art PnP methods, and pose estimation results show that our proposed method outperforms better than other methods.
References
[1]
Adli SE, Shoaran M, and Noorani SMS Gspnp: simple and geometric solution for pnp problem Vis. Comput. 2019 36 1549-1557
[2]
Garro, V., Crosilla, F., Fusiello, A.: Solving the pnp problem with anisotropic orthogonal procrustes analysis. Second International Conference on 3D Imaging Modeling Processing Visualization Transmission pp. 262–269 (2012).
[3]
Chen, H., Wang, P., Wang, F., Tian, W., Xiong, L., Li, H.: Epro-pnp: generalized end-to-end probabilistic perspective-n-points for monocular object pose estimation. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2022)
[4]
Lu C, Hager GD, and Mjolsness E Fast and globally convergent pose estimation from video images IEEE Trans. Pattern Anal. Mach. Intell. 2000 22 6 610-622
[5]
Zhou B, Chen Z, and Liu Q An efficient solution to the perspective-n-point problem for camera with unknown focal length IEEE Access 2020 8 162838-162846
[6]
Fischler M and Robert C Random sample consensus a paradigm for model fitting with apphcatlons to image analysis and automated cartography Commun. ACM 1981
[7]
Vakhitov, A., Colomina, L.F., Agudo, A., Moreno-Noguer, F.: Uncertainty-aware camera pose estimation from points and lines. In: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 4657–4666 (2021)
[8]
Shi, J., Xu, G.: An angle parameterization method for the perspective-n-point problem. In: 2020 IEEE 5th International Conference on Signal and Image Processing (ICSIP) pp. 407–414 (2020).
[9]
Boyd S, Parikh N, Chu E, and Peleato B Eckstein, J,: Distributed optimization and statistical learning via the alternating direction method of multipliers Found. Trends Mach. Learn. 2011
[10]
Stellato B, Banjac G, Goulart P, et al. Osqp: an operator splitting solver for quadratic programs Math. Program. Comput. 2020
[11]
Lepetit V, Noguer FM, and Fua P Epnp: an accurate on solution to the pnp problem Int. J. Comput. Vis. 2009 81 55
[12]
Ferraz, L., Binefa, X., Noguer, F.M.: Very fast solution to the pnp problem with algebraic outlier rejection. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition pp. 501–508 (2014).
[13]
Ferraz, L., Binefa, X., Noguer, F.M.: Leveraging feature uncertainty in the pnp problem. In: Proceedings of the British Machine Vision Conference (2014).
[14]
Urban, S., Leitloff, J., Hinz, S.: Mlpnp a real time maximum likelihood solution to the perspectiv n point problem. ISPRS Ann. Photogramm Remote Sens. Spat. Inf. Sci. 3, 131–138 (2016).
[15]
Hesch, J.A., Roumeliotis, S.I.: A direct least squares dls method for pnp. In: 2011 International Conference on Computer Vision pp. 383–390 (2011).
[16]
Zheng Y, Sugimoto S, and Okutomi M Aspnp an accurate and scalable solution to the perspective n point problem IEICE Trans. Inf. Syst. 2013 96 7 1525-1535
[17]
Zheng, Y., Kuang, Y., Sugimoto, S., Åström, K., Okutomi, M.: Revisiting the pnp problem a fast general and optimal solution. In: IEEE International Conference on Computer Vision pp. 2344–2351 (2013).
[18]
Li S, Xu C, and Xie M A robust o(n) solution to the perspective n point problem IEEE Trans. Pattern Anal. Mach. Intell. 2012 34 7 1444-1450
[19]
Terzakis G, Culverhouse P, Bugmann G, Sharma S, and Sutton R On quaternion based methods for the parameterization of orientation in iterative optimization J. Eng. Sci. Technol. Rev. 2014 6 15-24
[20]
Schmidt, J., Niemann, H.: Using quaternions for parametrizing 3-d rotations in unconstrained nonlinear optimization. In: Proceedings of the Vision Modeling and Visualization Conference pp. 21–23 (2001)
[21]
Pitchandi N and Subramanian S Image uncertainty based absolute camera pose estimation with fibonacci outlier elimination J. Intell. Robot Syst. 2019 96 65-81
[22]
Banjac G, Goulart P, Stellato B, and Boyd S Infeasibility detection in the alternating direction method of multipliers for convex optimization J. Optim. Theory Appl. 2019
Recommendations
Fast and robust absolute camera pose estimation with known focal length
Some 3D computer vision techniques such as structure from motion (SFM) and augmented reality (AR) depend on a specific perspective-n-point (PnP) algorithm to estimate the absolute camera pose. However, existing PnP algorithms are difficult to achieve a ...
RETRACTED ARTICLE: Fast and robust absolute camera pose estimation with known focal length
AbstractSome 3D computer vision techniques such as structure from motion (SFM) and augmented reality (AR) depend on a specific perspective-n-point (PnP) algorithm to estimate the absolute camera pose. However, existing PnP algorithms are difficult to ...
Analysing the attributes of fiducial markers for robust tracking in augmented reality applications
Tracking the position and orientation pose of camera is a critical challenge for different modern applications like augmented reality, robot navigation, robot localisation, and 3D modelling and surveillance systems. Marker-based tracking is the most ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
© The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 11 July 2023
Accepted: 11 June 2023
Author Tags
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 05 Mar 2025