Camera Pose Estimation by an Artificial Neural Network

  • Ryan G. Benton
  • Chee-hung Henry Chu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4233)


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.


Rotation Angle Image Point Hide Unit Output Unit Point Pair 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2003)Google Scholar
  2. 2.
    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)CrossRefGoogle Scholar
  3. 3.
    Ma, Y., Soatto, S., Kosecka, J., Sastry, S.S.: An Invitation to 3-D Vision. Springer, New York (2004)MATHGoogle Scholar
  4. 4.
    Zhang, Z.: A Flexible New Technique for Camera Calibration, Microsoft Technical Report MSR-TR-98-81 (1998)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Ryan G. Benton
    • 1
  • Chee-hung Henry Chu
    • 1
  1. 1.Center for Advanced Computer StudiesThe University of Louisiana at LafayetteLafayetteU.S.A.

Personalised recommendations