Advertisement

Dynamic Multiple View Geometry with Affine Cameras

  • Cheng WanEmail author
  • Yiquan Wu
  • Jun Sato
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8814)

Abstract

A new multiple view geometry is addressed in this paper, which is obtained in a dynamic environment with a dynamic scene and moving cameras. Multiple affine cameras are considered which move along degree-\(n\) Bezier curves. The new multiple view geometry can represent the multiple view geometry in different dimensions. In the experiments, we show two applications of the new multiple view geometry: view transfer and 3D reconstruction.

Keywords

Multiple view geometry Affine camera Bezier curve Multifocal tensor Dynamic scene 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Faugeras, O., Mourrain, B.: On the geometry and algebra of the point and line correspondences beterrn n images. In: Proc. 5th International Conference on Computer Vision, pp. 951–956 (1995)Google Scholar
  2. 2.
    Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press (2000)Google Scholar
  3. 3.
    Hartley, R.I., Schaffalitzky, F.: Reconstruction from projections using grassmann tensors. Int. J. Comput. Vision 83(3), 274–293 (2009)CrossRefGoogle Scholar
  4. 4.
    Hayakawa, K., Sato, J.: Multiple view geometry in the space-time. In: Proc. 7th Asian Conference on Computer Vision, pp. 437–446 (2006)Google Scholar
  5. 5.
    Heyden, A.: Tensorial properties of multiple view constraints. Mathematical Methods in the Applied Sciences 23, 169–202 (2000)MathSciNetCrossRefzbMATHGoogle Scholar
  6. 6.
    Shashua, A., Wolf, L.: Homography tensors: on algebraic entities that represent three views of static or moving planar points. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1842, pp. 507–521. Springer, Heidelberg (2000) CrossRefGoogle Scholar
  7. 7.
    Sturm, P.: Multi-view geometry for general camera models. In: Proc. Conference on Computer Vision and Pattern Recognition, pp. 206–212 (2005)Google Scholar
  8. 8.
    Wan, C., Sato, J.: Multiple view geometry under projective projection in space-time. IEICE Transactions 91–D(9), 2353–2359 (2008)Google Scholar
  9. 9.
    Wan, C., Sato, J.: Multiple view geometry for curvilinear motion cameras. IEICE Transactions 94–D(7), 1479–1487 (2011)Google Scholar
  10. 10.
    Wan, C., Sato, J.: Multiple view geometry for non-rigid motions viewed from curvilinear motion projective cameras. In: Proc. 20th International Conference on Pattern Recognition, pp. 181–184 (2010)Google Scholar
  11. 11.
    Wan, C., Wu, Y., Sato, J.: Multiple view geometry in dynamic environment. In: Proc. 2nd Asian Conference on Pattern Recognition, pp. 532–536 (2013)Google Scholar
  12. 12.
    Wexler, Y., Shashua, A.: On the synthesis of dynamic scenes from reference views. In: Proc. Conference on Computer Vision and Pattern Recognition, pp. 576–581 (2000)Google Scholar
  13. 13.
    Wolf, L., Shashua, A.: On projection matrices \(p^k\rightarrow p^2\), \(k=3\), \(\cdots \), 6, and their applications in computer vision. In: Proc. 8th International Conference on Computer Vision, vol. 1, pp. 412–419 (2001)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  1. 1.College of Electronic and Information EngineeringNanjing University of Aeronautics and AstronauticsNanjingChina
  2. 2.Department of Electrical and Computer EngineeringNagoya Institute of TechnologyNagoyaJapan

Personalised recommendations