Advertisement

Conditions for Segmentation of 2D Translations of 3D Objects

  • Shafriza Nisha Basah
  • Alireza Bab-Hadiashar
  • Reza Hoseinnezhad
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5716)

Abstract

Various computer vision applications involve recovery and estimation of multiple motions from images of dynamic scenes. The exact nature of objects’ motions and the camera parameters are often not known a priori and therefore, the most general motion model (the fundamental matrix) is applied. Although the estimation of a fundamental matrix and its use for motion segmentation are well understood, the conditions governing the feasibility of segmentation for different types of motions are yet to be discovered. In this paper, we study the feasibility of separating 2D translations of 3D objects in a dynamic scene. We show that successful segmentation of 2D translations depends on the magnitude of the translations, average distance between the camera and objects, focal length of the camera and level of noise. Extensive set of controlled experiments using both synthetic and real images were conducted to show the validity of the proposed constraints. In addition, we quantified the conditions for successful segmentation of 2D translations in terms of the magnitude of those translations, the average distance between the camera and objects in motions for a given camera. These results are of particular importance for practitioners designing solutions for computer vision problems.

Keywords

Motion segmentation multibody structure-and-motion fundamental matrix robust estimation 

References

  1. 1.
    Armangue, X., Salvi, J.: Overall view regarding fundamental matrix estimation. Image and Vision Computing 21(2), 205–220 (2003)CrossRefGoogle Scholar
  2. 2.
    Bab-Hadiashar, A., Suter, D.: Robust segmentation of visual data using ranked unbiased scale estimate. Robotica 17(6), 649–660 (1999)CrossRefGoogle Scholar
  3. 3.
    Basah, S.N., Hoseinnezhad, R., Bab-Hadiashar, A.: Limits of Motion-Background Segmentation Using Fundamental Matrix Estimation. In: Proceedings of the Digital Image Computing: Techniques and Applications, pp. 250–256. IEEE Computer Society, California (2008)Google Scholar
  4. 4.
    Camera Calibration Toolbox for Matlab, http://www.vision.caltech.edu/bouguetj/calib_doc/index.html
  5. 5.
    Chen, H., Meer, P.: Robust regression with projection based M-estimators. In: Proceedings of the IEEE International Conference on Computer Vision (2003)Google Scholar
  6. 6.
    Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision, 2nd edn. Cambridge University Press, Cambridge (2004)CrossRefzbMATHGoogle Scholar
  7. 7.
    Hoseinnezhad, R., Bab-Hadiashar, A.: Consistency of robust estimators in multi-structural visual data segmentation. Pattern Recognition 40(12), 3677–3690 (2007)CrossRefzbMATHGoogle Scholar
  8. 8.
    Lowe, D.G.: Distinctive image features from scale-invariant keypoints. IJCV 60(2), 91–110 (2004)CrossRefGoogle Scholar
  9. 9.
    Luong, Q.T., Deriche, R., Faugeras, O.D., Papadopoulo, T.: Determining The Fundamental Matrix: Analysis of Different Methods and Experimental Results. INRIA (1993)Google Scholar
  10. 10.
    Schindler, K., Suter, D.: Two-view multibody structure-and-motion with outliers through model selection. PAMI 28(6), 983–995 (2006)CrossRefGoogle Scholar
  11. 11.
    Torr, P.H.S.: Motion Segmentation and Outlier Detection. Phd Thesis, Department of Engineering Science, University of Oxford 28(6), 983–995 (1995)MathSciNetGoogle Scholar
  12. 12.
    Torr, P.H.S., Zisserman, A., Maybank, S.: Robust detection of degenerate configurations while estimating the fundamental matrix. CVIU 71(3), 312–333 (1998)Google Scholar
  13. 13.
    Torr, P.H.S., Murray, D.W.: The Development and Comparison of Robust Methods for Estimating the Fundamental Matrix. IJCV 24(3), 271–300 (1997)CrossRefGoogle Scholar
  14. 14.
    Vidal, R., Ma, Y., Soatto, S., Sastry, S.: Two-view multibody structure from motion. IJCV 68(1), 7–25 (2006)CrossRefGoogle Scholar
  15. 15.
    Wang, H., Suter, D.: Robust adaptive-scale parametric model estimation for computer vision. PAMI 26(11), 1459–1474 (2004)CrossRefGoogle Scholar
  16. 16.
    Zhang, Z.: Determining the Epipolar Geometry and its Uncertainty: A Review. IJCV 27(2), 161–195 (1998)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Shafriza Nisha Basah
    • 1
  • Alireza Bab-Hadiashar
    • 1
  • Reza Hoseinnezhad
    • 2
  1. 1.Faculty of Engineering and Industrial SciencesSwinburne University of TechnologyAustralia
  2. 2.Melbourne School of EngineeringThe University of MelbourneAustralia

Personalised recommendations