Abstract
This paper illustrates a novel registration method based on robust estimation of trifocal tensors using point and line correspondences synthetically. The proposed method distinguishes itself in following ways: Firstly, besides feature points, line segments are also used to calculate the needed trifocal tensors. The registration process can still be achieved even under poorly textured scenes. Secondly, to estimate trifocal tensors precisely, we use PROSAC instead of RANSAC algorithm to remove outliers. While improving the accuracy of our system, PROSAC also reduces the computation complexity to a large degree.
Keywords
Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
References
Simon, G., Fitzgibbon, A., Zisserman, A.: Markerless tracking using planar structures in the scene. In: Proc. of the ISAR, pp. 120–128 (2000)
Pang, Y., Yuan, M.L., Nee, A.Y.C., Ong, S.K.: A Markerless Registration Method for Aug-mented Reality based on Affine Properties. In: Proc. of the AUIC, pp. 25–32 (2006)
Simon, G., Berger, M.: Reconstructing while registering: a novel approach for markerless augmented reality. In: Proc. of the ISMAR, pp. 285–294 (2002)
Yuan, M.L., Ong, S.K., Nee, A.Y.C.: Registration Based on Projective Reconstruction Technique for Augmented Reality Systems. IEEE Trans. on Visualization and Computer Graphics 11(3), 254–264 (2005)
Yuan, M.L., Ong, S.K., Nee, A.Y.C.: Registration using natural features for augmented reality systems. IEEE Trans. on Visualization and Computer Graphics 12(4), 569–580 (2006)
Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2000)
Chum, O., Matas, J.: Matching with PROSAC - progressive sample consensus. Proc. of CVPR 1(1), 305–313 (2005)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Guan, T., Li, L., Wang, C. (2007). Registration Based on Online Estimation of Trifocal Tensors Using Point and Line Correspondences. In: Shumaker, R. (eds) Virtual Reality. ICVR 2007. Lecture Notes in Computer Science, vol 4563. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-73335-5_5
Download citation
DOI: https://doi.org/10.1007/978-3-540-73335-5_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-73334-8
Online ISBN: 978-3-540-73335-5
eBook Packages: Computer ScienceComputer Science (R0)