Fast and reliable object pose estimation from line correspondences
In this paper, we describe a fast object pose estimation method from 3-D to 2-D line correspondences using a perspective camera model. The principle consists in iteratively improving the pose computed with an affine camera model (either weak perspective or paraperspective) to converge, at the limit, to a pose estimation computed with a perspective camera model. Thus, the advantage of the method is to reduce the problem to solving a linear system at each iteration step. The iterative algorithms that we describe in detail in this paper can deal with non coplanar or coplanar object models and have interesting properties both in terms of speed and rate of convergence.
Unable to display preview. Download preview PDF.
- 4.P. Gros. Matching and clustering: Two steps towards automatic model generation in computer vision. In Proceedings of the AAAI Fall Symposium Series: Machine Learning in Computer Vision: What, Why, and How?, Raleigh, North Carolina, USA, pages 40–44, October 1993.Google Scholar
- 5.R. Horaud, S. Christy, F. Dornaika, and B. Lamiroy. Object pose: Links between paraperspective and perspective. In Proceedings of the 5th International Conference on Computer Vision, Cambridge, Massachusetts, USA, pages 426–433, Cambridge, Mass., June 1995. IEEE Computer Society Press.Google Scholar
- 6.D. Oberkampf, D.F. Dementhon, and L.S. Davis. Iterative pose estimation using coplanar feature points. Computer Vision, Graphics and Image Processing, 63(3):495–511, May 1996.Google Scholar
- 7.T.Q. Phong, R. Horaud, A. Yassine, and P.D. Tao. Object pose from 2D to 3D point and line correspondences. In International Journal of Computer Vision, pages 225–243. Kluwer Academic Publishers, July 1995.Google Scholar
- 8.C.J. Poelman and T. Kanade. A paraperspective factorization method for shape and motion recovery. In J.O. Eklundh, editor, Proceedings of the 3rd European Conference on Computer Vision, Stockholm, Sweden, pages 97–108, May 1994.Google Scholar