Copyright © 2007 The Institute of Electronics, Information and Communication Engineers
Regular Section -- Papers -- Image Recognition, Computer Vision |
Uncalibrated Factorization Using a Variable Symmetric Affine Camera
1 The authors are with the Department of Computer Science, Okayama University, Okayama-shi, 700–8530 Japan. E-mail: kanatani{at}suri.it.okayama-u.ac.jp, 2 The author is with the Department of Information and Computer Sciences, Toyohashi University of Technology, Toyohashi-shi, 441–8580 Japan.
In order to reconstruct 3-D Euclidean shape by the Tomasi-Kanade factorization, one needs to specify an affine camera model such as orthographic, weak perspective, and paraperspective. We present a new method that does not require any such specific models. We show that a minimal requirement for an affine camera to mimic perspective projection leads to a unique camera model, called symmetric affine camera, which has two free functions. We determine their values from input images by linear computation and demonstrate by experiments that an appropriate camera model is automatically selected.
Key Words: factorization, structure from motion, affine camera, self-calibration, video image analysis
Manuscript received February 16, 2006. Manuscript revised October 12, 2006.
References
[1] R. Basri, "Paraperspective 
affine," Int. J. Comput. Vis., vol.19, no.2, pp.169–179, Aug. 1996.
[2] K. Deguchi, T. Sasano, H. Arai, and H. Yoshikawa, "3-D shape reconstruction from endoscope image sequences by the factorization method," IEICE Trans. Inf. & Syst., vol.E79-D, no.9, pp.1329–1336, Sept. 1996.
[3] R. Hartley and A. Zisserman, Multiple View Geometry in Computer Vision, Cambridge University Press, Cambridge, U.K., 2000.
[4] K. Kanatani, Group-Theoretical Methods in Image Understanding, Springer-Verlag, Berlin, Germany, 1990.
[5] K. Kanatani, Geometric Computation for Machine Vision, Oxford University Press, Oxford, U.K., 1993.
[6] K. Kanatani, "Motion segmentation by subspace separation: Model selection and reliability evaluation," Int. J. Image Graphics, vol.2, no.2, pp.179–197, April 2002.
[7] K. Kanatani, "Evaluation and selection of models for motion segmentation," Proc. 7th Euro. Conf. Comput. Vision, pp.335–349, Copenhagen, Denmark, June 2002.
[8] K. Kanatani and Y. Sugaya, "Factorization without factorization: Complete recipe," Mem. Fac. Eng. Okayama Univ., vol.38, nos.1/2, pp.61–72, March 2004.
[9] K. Kanatani, Y. Sugaya, and H. Ackermann, "Uncalibrated factorization using a variable symmetric affine camera," Mem. Fac. Eng. Okayama Univ., vol.40, pp.53–63, Jan. 2006.
[10] C.J. Poelman and T. Kanade, "A paraperspective factorization method for shape and motion recovery," IEEE Trans. Pattern Anal. Mach. Intell., vol.19, no.3, pp.206–218, March 1997.
[11] L. Quan, "Self-calibration of an affine camera from multiple views," Int. J. Comput. Vis., vol.19, no.1, pp.93–105, July 1996.
[12] L.S. Shapiro, A. Zisserman, and M. Brady, "3D motion recovery via affine epipolar geometry," Int. J. Comput. Vis., vol.16, no.2, pp.147–182, Oct. 1995.
[13] Y. Sugaya and K. Kanatani, "Outlier removal for motion tracking by subspace separation," IEICE Trans. Inf. & Syst., vol.E86-D, no.6, pp.1095–1102, June 2003.
[14] Y. Sugaya and K. Kanatani, "Extending interrupted feature point tracking for 3-D affine reconstruction," IEICE Trans. Inf. & Syst., vol.E87-D, no.4, pp.1031–1038, April 2004.
[15] Y. Sugaya and K. Kanatani, "Multi-stage optimization for multi-body motion segmentation," IEICE Trans. Inf. & Syst., vol.E87-D, no.7, pp.1935–1942, July 2004.
[16] A. Sugimoto, "Object recognition by combining paraperspective images," Int. J. Comput. Vis., vol.19, no.2, pp.181–201, Aug. 1996.
[17] C. Tomasi and T. Kanade, "Shape and motion from image streams under orthography—A factorization method," Int. J. Comput. Vis., vol.9, no.2, pp.137–154, Oct. 1992.
CiteULike 
Connotea 
Del.icio.us What's this?
| ||||||||||||||||||||||||||||||||||||||||||||||||||