Abstract
Reconstruction of a three-dimensional scene using images taken from two views is possible if the relative pose of the cameras is known. A traditional approach to estimating the pose of the cameras uses eight pairs of corresponding points and involves the solution of a set of homogeneous equations. We propose a multi-layered feedforward network solution. Empirical results demonstrate the feasibility of using the network to recover the relative pose of the cameras in the three-dimensional world.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2003)
Huang, T.S., Faugeras, O.: Some properties of the E matrix in two-view motion estimation. IEEE Trans. Pattern Analysis and Machine Intelligence 11, 1310–1312 (1989)
Ma, Y., Soatto, S., Kosecka, J., Sastry, S.S.: An Invitation to 3-D Vision. Springer, New York (2004)
Zhang, Z.: A Flexible New Technique for Camera Calibration, Microsoft Technical Report MSR-TR-98-81 (1998)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Benton, R.G., Chu, Ch.H. (2006). Camera Pose Estimation by an Artificial Neural Network. In: King, I., Wang, J., Chan, LW., Wang, D. (eds) Neural Information Processing. ICONIP 2006. Lecture Notes in Computer Science, vol 4233. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11893257_68
Download citation
DOI: https://doi.org/10.1007/11893257_68
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-46481-5
Online ISBN: 978-3-540-46482-2
eBook Packages: Computer ScienceComputer Science (R0)