IEICE Transactions on Information and Systems

IEICE Transactions on Information and Systems 2008 E91-D(1):114-123; doi:10.1093/ietisy/e91-d.1.114

This Article Abstract Full Text (PDF) Alert me when this article is cited Alert me if a correction is posted Services Email this article to a friend Similar articles in this journal Alert me to new issues of the journal Add to My Personal Archive Download to citation manager Request Permissions Google Scholar Articles by HWANG, Y. Articles by HONG, H. Search for Related Content Social Bookmarking          What's this?

Copyright © 2008 The Institute of Electronics, Information and Communication Engineers

Regular Section -- Papers -- Image Recognition, Computer Vision

Key-Frame Selection and an LMedS-Based Approach to Structure and Motion Recovery

Yongho HWANG¹, Jungkak SEO¹ and Hyunki HONG^1,2

¹ The authors are with the Computer Graphics & Media Laboratory, Department of Image Engineering, Graduate School of Advanced Imaging Science, Multimedia and Film, Chung-Ang University, Seoul 156–756, Korea. E-mail: honghk{at}cau.ac.kr, ² Correspondence author.

Auto-calibration for structure and motion recovery can be used for match move where the goal is to insert synthetic 3D objects into real scenes and create views as if they were part of the real scene. However, most auto-calibration methods for multi-views utilize bundle adjustment with non-linear optimization, which requires a very good starting approximation. We propose a novel key-frame selection measurement and LMedS (Least Median of Square)-based approach to estimate scene structure and motion from image sequences captured with a hand-held camera. First, we select key-frames considering the ratio of number of correspondences and feature points, the homography error and the distribution of corresponding points in the image. Then, by using LMedS, we reject erroneous frames among the key-frames in absolute quadric estimation. Simulation results demonstrated that the proposed method can select suitable key-frames efficiently and achieve more precise camera pose estimation without non-linear optimization.

Key Words: auto-calibration, key-frames selection, corresponding points, absolute quadric estimation, least median of square

---

Manuscript received May 18, 2007. Manuscript revised September 7, 2007.

Reference

[1] H.S. Sawhney, Y. Guo, J. Asmuth, and R. Kumar, "Multi-view 3D estimation and applications to match move," Proc. IEEE Multi-view Modeling & Analysis of Visual Scenes, pp.21–28, 1999.

[2] O. Faugeras, Q.T. Luong, and S. Maybank, "Camera self-calibration: theory and experiments," LNCS 588, pp.321–334, 1992.

[3] W. Triggs, "Auto-calibration and the absolute quadric," Proc. IEEE Computer Vision and Pattern Recognition, pp.609–614, 1997.

[4] M. Pollefeys and L.V. Gool, "Self-calibration from the absolute conic on the plane at infinity," LNCS 1296, pp.175–182, 1997.

[5] K. Cornelis, M. Pollefeys, M. Vergauwen, and L.V. Gool, "Augmented reality from un-calibrated video sequences," LNCS 2018, pp.144–160, 2001.

[6] S. Gibson, J. Cook, T. Howard, R. Hubbold, and D. Oram, "Accurate camera calibration for off-line, video-based augmented reality," Proc. IEEE and ACM International Symposium on Mixed and Augmented Reality, pp.37–46, 2002.

[7] P. Sturm and B. Triggs, "A factorization based algorithm for muti-Image projective structure and motion," LNCS 1065, pp.709–720, 1996.

[8] A. Chiuso, P. Favaro, H. Jin, and S. Soatto, "Motion and structure causally integrated over time," IEEE Trans. Pattern Anal. Mach. Intell., vol.24, no.4, pp.523–535, 2002.

[9] A. Fitzgibbon and A. Zisserman, "Automatic camera recovery for closed or open image sequences," LNCS 1406, pp.311–326, 1998.

[10] D. Nister, "Frame decision for structure and motion," LNCS 2018, pp.17–34, 2001.

[11] Z. Zhang, R. Deriche, O. Faugeras, and Q. Loung, "A robust technique for matching two uncalibrated images through the recovery of the unknown epipolar geometry," Technical Report of INRIA, vol.2273, 1994.

[12] R. Hartley and A. Zisserman, Mutiple View Geometry in Computer Vision, Cambrige Univ. Press, 2000.

[13] R. Hartley, "In defense of the 8-Point algorithm," Proc. IEEE International Conference on Computer Vision, pp.1064–1070, 1995.

[14] J. Seo, H. Hong, C. Jho, and M. Choi, "Two quantitative measures of inlier distributions for precise fundamental matrix estimation," Pattern Recognit. Lett., vol.25, no.6, pp.733–741, 2004.

[15] P.J. Rousseeuw and A.M. Leroy, Robust Regression and Outlier Detection, John Wiley & Sons, New York, 1987.

[16] Z. Zhang, "Computing rectifying homographies for stereo vision," Proc. IEEE Computer Vision and Pattern Recognition, pp.125–131, 1999.

[17] C. Tsai and A.K. Katsaggelos, "Dense disparity estimation with a divide-and-conquer disparity space image technique," IEEE Trans. Multimed., vol.1, no.1, pp.18–29, 1999.

[18] S.S. Intille and A.F. Bobick, "Disparity-space images and large occlusion stereo," Proc. European Conference on Computer Vision, pp.179–186, 1994.

CiteULike    Connotea    Del.icio.us    What's this?

This Article Abstract Full Text (PDF) Alert me when this article is cited Alert me if a correction is posted Services Email this article to a friend Similar articles in this journal Alert me to new issues of the journal Add to My Personal Archive Download to citation manager Request Permissions Google Scholar Articles by HWANG, Y. Articles by HONG, H. Search for Related Content Social Bookmarking          What's this?