Towards a Bayesian Approach to Robust Finding Correspondences in Multiple View Geometry Environments

  • Cristian Canton-Ferrer
  • Josep R. Casas
  • Montse Pardàs
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3515)


This paper presents a new Bayesian approach to the problem of finding correspondences of moving objects in a multiple calibrated camera environment. Moving objects are detected and segmented in multiple cameras using a background learning technique. A Point Based Feature (PBF) of each foreground region is extracted, in our case, the top. This features will be the support to establish the correspondences. A reliable, efficient and fast computable distance, the symmetric epipolar distance, is proposed to measure the closeness of sets of points belonging to different views. Finally, matching the features from different cameras originating from the same object is achieved by selecting the most likely PBF in each view under a Bayesian framework. Results are provided showing the effectiveness of the proposed algorithm even in case of severe occlusions or with incorrectly segmented foreground regions.


Camera View Epipolar Line Epipolar Geometry Foreground Region Correspondence Algorithm 
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.


  1. 1.
    Black, J., Ellis, T.: Multi Camera Image Tracking. In: Proc. IEEE Work. on Performance Evaluation of Tracking and Surveillance (2001)Google Scholar
  2. 2.
    Boyd, S., Vandenberghe, L.: Convex Optimization, 1st edn. Cambridge University Press, Cambridge (2004)zbMATHGoogle Scholar
  3. 3.
    Eisert, P., Steinbach, E., Girod, B.: Multi-hypothesis, volumetric reconstruction of 3D objects from multiple calibrated camera views. In: Proc. IEEE Int. Conf. on Acoustics Speech and Signal Processing, pp. 3509–3512 (1999)Google Scholar
  4. 4.
    Faugeras, O., Luong, Q.T.: The geometry of multiple views, 1st edn. MIT Press, Cambridge (2001)Google Scholar
  5. 5.
    Figueras, R.M.: Image Coding with Matching Pursuit. MS Thesis, EPFL (2000)Google Scholar
  6. 6.
    Focken, D., Stiefelhagen, R.: Towards vision-based 3D people tracking in a smart room. In: Proc. IEEE Int. Conf. on Multimodal Interfaces, pp. 400–405 (2002)Google Scholar
  7. 7.
    Fuentes, L.M., Velastin, S.A.: People Tracking in Surveillance Applications. In: Proc. IEEE Work. on Performance Evaluation of Tracking and Surveillance (2001)Google Scholar
  8. 8.
    Gavrila, D.M., Davis, L.S.: 3D Model Based tracking of humans in action: a multi-view approach. In: Proc. of Computer Vision and Pattern Recognition, vol. 73–80 (1996)Google Scholar
  9. 9.
    Hartley, R.I., Zisserman, A.: Multiple View Geometry in Computer Vision, 2nd edn. Cambridge University Press, Cambridge (2004)zbMATHGoogle Scholar
  10. 10.
    Landabaso, J.L., Xu, L.Q., Pardàs, M.: Robust Tracking and Object Classification Towards Automated Video Surveillance. In: Proc. Int. Conf. on Image Analysis and Recognition, vol. 463–470 (2004)Google Scholar
  11. 11.
    Mikic, I., Santini, S., Jain, R.: Tracking Objects in 3D using Multiple Camera Views. In: Proc. Asian Conf. on Computer Vision, pp. 234–239 (2000)Google Scholar
  12. 12.
    Stauffer, C., Grimson, W.E.L.: Adaptive background mixture models for real-time tracking. In: Proc. IEEE Int. Conf. on Computer Vision and Pattern Recognition, pp. 252–259 (1999)Google Scholar
  13. 13.
    Triggs, B.: Joint Feature Distributions for Image Correspondence. In: Proc. IEEE Int. Conf. on Computer Vision, pp. 201–208 (2001)Google Scholar
  14. 14.
    Zhang, Z.: Determining the epipolar geometry and its uncertainty-a review. Int. Jour. of Computer Vision 27(2), 161–195 (1998)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Cristian Canton-Ferrer
    • 1
  • Josep R. Casas
    • 1
  • Montse Pardàs
    • 1
  1. 1.Image Processing GroupTechnical University of CataloniaBarcelonaSpain

Personalised recommendations