Pose Estimation for Non-Central Cameras Using Planes

Abstract

In this paper we study pose estimation for general non-central cameras, using planar targets. The method proposed uses non-minimal data. Using the homography matrix to represent the transformation between the world and camera coordinate systems, we describe a non-iterative algorithm for pose estimation. To improve the accuracy of the solutions, data-set normalization is used. In addition, we propose a parameter optimization to refine the pose estimate. We evaluate the proposed solutions against the state-of-the-art method (for general targets) in terms of both robustness to noise and computation time. From the experiments, we show that the proposed method plus normalization is more accurate against noise and less sensitive to variations of the imaging device. We also show that the numerical results obtained with this method improve with the increasing number of data points. In terms of processing speed, the versions of the algorithm presented are significantly faster than the state-of-the-art algorithm. To further evaluate our method, we performed an experiment of a simple augmented reality application in which we show that our method can be easily applied.

This is a preview of subscription content, access via your institution.

References

  1. 1.

    Aliaga, D.G.: Accurate catadioptric calibration for real-time pose estimation in room-size environments. In: IEEE Proceedings International Conference Computer Vision (ICCV) (2001)

  2. 2.

    Aliakbarpour, H., Tahri, O., Araujo, H.: Visual servoing of mobile robots using non-central catadioptric cameras. In: Robotics and Autonomous Systems (2014)

  3. 3.

    Ansar, A., Daniilidis, K.: Linear pose estimation from points or lines. In: IEEE Transactions on Pattern Analysis and Machine Intelligence (2003)

  4. 4.

    Araujo, H., Carceroni, R.L., Brown, C.M.: A fully projective formulation to improve the accuracy of Lowe’s pose–estimation algorithm. In: Computer Vision and Image Understanding (1998)

  5. 5.

    Baker, S., Nayar, S.K.: A Theory of single-viewpoint catadioptric image formation. In: International Journal on Computer Vision (1999)

  6. 6.

    Cox, D.A., Little, J., O’Shea, D.: Using Algebraic Geometry. Springer Science+Business (2004)

  7. 7.

    Dhome, M., Richetin, M., Lapreste, J.T., Rives, G.: Determination of the attitude of 3d objects from a single perspective view. In: IEEE Transaction on Pattern Analysis and Machine Intelligence (1989)

  8. 8.

    Fischler, M., Bolles, R.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. In: Communication of the Association for Computing Machinery (1981)

  9. 9.

    Gaspar, J., Winters, N., Santos-Victor, J.: Vision-based Navigation and Environmental Representations with an Omni-directional Camera. In: IEEE Transactions on Robotics and Automation (2000)

  10. 10.

    Golub, G.H., Van Loan, C.F.: Matrix Computations (3rd ed.). Johns Hopkins University Press (1996)

  11. 11.

    Grossberg, G., Nayar, S.: A General Imaging Model and a Method for Finding its Parameters. In: Proceedings of the IEEE International Conference Computer Vision (2001)

  12. 12.

    Haralick, R.M., Lee, C.N., Ottenberg, K., Nölle, M.: Review and analysis of solutions of the three point perspective pose estimation problem. In: International Journal on Computer Vision (1994)

  13. 13.

    Hartley, R.: In defense of the eight-point algorithm. In: IEEE Transactions on Pattern Analysis and Machine Intelligence (1997)

  14. 14.

    Hartley, R., Zisserman, A.: Multiple View Geometry. Cambridge University Press, Cambridge (2000)

    MATH  Google Scholar 

  15. 15.

    Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2000)

    MATH  Google Scholar 

  16. 16.

    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: Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition (2011)

  17. 17.

    Ma, Y., Soatto, S., Košecká, J., Sastry, S.S.: An Invitation to 3D Vision: From Images to Geometry Models. Springer Science+Business (2004)

  18. 18.

    Miraldo, P.: General Camera Models: Calibration and Pose. Ph.D. thesis, Department of Electrical and Computer Engineering–University of Coimbra (2013)

  19. 19.

    Miraldo, P., Araujo, H.: Calibration of smooth camera models. In: IEEE Transactions on Pattern Analysis and Machine Intelligence (2013)

  20. 20.

    Miraldo, P., Araujo, H.: Planar pose estimation for general cameras using known 3D lines. In: IEEE/RSJ Pose Estimation for Non-Central Cameras Using Planes (2014)

  21. 21.

    Miraldo, P., Araujo, H.: Pose estimation for general cameras using lines. In: IEEE Transactions on Cybernetics (Systems Man, and Cybernetics, Part B), to be published (2014)

  22. 22.

    Miraldo, P., Araujo, H.: Pose estimation for non-central cameras using planes. In: IEEE International Conference on Autonomous Robot Systems & Competitions – ROBÓTICA 2014 (2014)

  23. 23.

    Nalwa, V.S.: A True Omni-Directional Viewer. Technichal Report, Bell Laboratories (1996)

  24. 24.

    Nayar, S.K., Baker, S.: Catadioptric image formation. In: Proceedings of the 1997 DARPA Image Understanding Workshop (1997)

  25. 25.

    Nistér, D.: A minimal solution to the generalized 3–point pose problem. In: Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition (2004)

  26. 26.

    Moreno Noguer, F., Lepetit, V., Fua, P.: Accurate non–iteractive O(n) solution to the PnP problem. In: Proceedings of the IEEE International Conference on Computer Vision (2007)

  27. 27.

    Oberkampf, D., Dementhon, D.F., Davis, L.S.: Iterative pose estimation using coplanar feature points. In: Computer Vision and Image Understanding (1996)

  28. 28.

    Pégard, C., Mouaddib, E.: A mobile robot using a panoramic view. In: IEEE Proceedings of the International Conference on Robotics and Automation (ICRA) (1996)

  29. 29.

    Pottmann, H., Wallner, J.: Computational line geometry. Springer–Verlag, Berlin Heidelberg (2001)

    MATH  Google Scholar 

  30. 30.

    Ramalingam, S., Bouaziz, S., Sturm, P.: Pose estimation using both points and lines for Geo–localization. In: Proceedings of the IEEE International Conference on Robotics and Automation (2011)

  31. 31.

    Schweighofer, G., Pinz, A.: Robust pose estimation from a planar target. In: IEEE Transactions Pattern Analysis and Machine Intelligence (2006)

  32. 32.

    Schweighofer, G., Pinz, A.: Globally optimal O(n) solution to the PnP problem for general camera models. In: Proceedings of the British Machine Vision Conference (2008)

  33. 33.

    Chu Song, C., Wen Yan, C.: On pose recovery for generalized visual sensers. In: IEEE Transactions on Pattern Analysis and Machine Intelligence (2004)

  34. 34.

    Sturm, J.F.: Using SeDuMi 1.02 a MATLAB toolbox for optimization over symmetric cones (1999)

  35. 35.

    Sturm, P., Ramalingam, S.: A generic concept for camera calibration. In: Proceeding of the European conference computer vision (2004)

  36. 36.

    Swaminathan, R., Grossberg, M.D., Nayar, S.K.: Caustics of Catadioptric Cameras. In: IEEE Proceedings of the international conference on computer vision (ICCV) (2001)

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Pedro Miraldo.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Miraldo, P., Araujo, H. Pose Estimation for Non-Central Cameras Using Planes. J Intell Robot Syst 80, 595–608 (2015). https://doi.org/10.1007/s10846-015-0193-3

Download citation

Keywords

  • Absolute pose estimation
  • General camera models
  • Planar patterns