Segregation of Moving Objects Using Elastic Matching

  • Vishal Jain
  • Benjamin B. Kimia
  • Joseph L. Mundy
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3667)


We present a method for figure-ground segregation of moving objects from monocular video sequences. The approach is based on tracking extracted contour fragments, in contrast to traditional approaches which rely on feature points, regions, and unorganized edge elements. Specifically, a notion of similarity between pairs of curve fragments appearing in two adjacent frames is developed and used to find the curve correspondence. This similarity metric is elastic in nature and in addition takes into account both a novel notion of transitions in curve fragments across video frames and an epipolar constraint. This yields a performance rate of 85% correct correspondence on a manually labeled set of frame pairs. The retrieved curve correspondence is then used to group curves in each frame into clusters based on the pairwise similarity of how they transform from one frame to the next. Results on video sequences of moving vehicles show that using curve fragments for tracking produces a richer segregation of figure from ground than current region or feature-based methods.


Video Sequence Video Frame Adjacent Frame Epipolar Line Curve Match 
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.
    Adams, R., Bischof, L.: Seeded region growing. PAMI 16(6), 641–647 (1994)Google Scholar
  2. 2.
    Canny, J.: A computational approach to edge detection. PAMI 8, 679–698 (1986)Google Scholar
  3. 3.
    Comaniciu, D., Ramesh, V., Meer, P.: Real-time tracking of nonrigid objects using mean shift. In: CVPR, Hilton Head Island, South Carolina, pp. 2:142–149 (2000)Google Scholar
  4. 4.
    Deriche, R., Giraudon, G.: A computational approach for corner and vertex detection. In: IJCV, pp. 167–187 (1993)Google Scholar
  5. 5.
    Erdem, C.E., Tekalp, A., Sankur, B.: Video object tracking with feedback of performance measures. In: Proc. IEEE Conf. on CVPR, December 2001, pp. 593–600 (2001)Google Scholar
  6. 6.
    Ferrari, V., Tuytelaars, T., van Gool, L.: Real-time affine region tracking and coplanar grouping. In: Proc. IEEE Conf. on CVPR, Kauai, Hawaii, pp. 226–233 (2001)Google Scholar
  7. 7.
    Folta, F., Eycken, L.V., van Gool, L.: Shape extraction using temporal continuity. In: Proc. European Workshop on Image Analysis for Multimedia Interactive Services of the IEEE conference on CVPR, pp. 69–74 (1997)Google Scholar
  8. 8.
    Freedman, D.: Effective tracking through tree search. IEEE Trans. on Pattern Analysis and Machine Intelligence 25, 604–615 (2003)CrossRefGoogle Scholar
  9. 9.
    Gold, S., Rangarajan, A., Mjolsness, E.: Learning with preknowledge:clustering with point and graph matching distance measures. Neural Computation 8(4), 787–804 (1996)CrossRefGoogle Scholar
  10. 10.
    Hager, G., Belhumeur, P.: Efficient region tracking with parametric models of geometry and illumination. PAMI 20(10), 1025–1039 (1998)Google Scholar
  11. 11.
    Harris, C.: Determination of ego-motion from matched points. In: IJCV, pp. 189–192 (1993)Google Scholar
  12. 12.
    Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2000)zbMATHGoogle Scholar
  13. 13.
    Huttenlocher, D.P., Klanderman, G.A., Rucklidge, W.J.: Comparing images using the Hausdorff distance. PAMI 15, 850–863 (1993)Google Scholar
  14. 14.
    Isard, M., Blake, A.: Condensation - conditional density propagation for visual tracking. In: IJCV, vol. 29, pp. 2–28 (1998)Google Scholar
  15. 15.
    Kass, M., Witkin, A., Terzopoulos, D.: Snakes: Active contour models. International Journal of Computer Vision 1(4), 321–331 (1987)CrossRefGoogle Scholar
  16. 16.
    Koller, D., Weber, J., Malik, J.: Robust multiple car tracking with occlusion reasoning. In: Proceedings of the Third European Conference on Computer Vision, vol. I, Springer, Heidelberg (1994)Google Scholar
  17. 17.
    Lindenberg, T.: Feature detection with automatic scale detection. IJCV 30(2), 77–116 (1998)Google Scholar
  18. 18.
    McBride, J.: Archaeological fragment reassembly using curve matching. Master’s disseration,Brown University,Providence,USA (2003)Google Scholar
  19. 19.
    Moravec, H.P.: Visual mapping by a robot rover. In: Proc. of the 6th International Joint Conference on Artificial Intelligence, pp. 598–600 (1979)Google Scholar
  20. 20.
    Paragios, N., Deriche, R.: A pde-based level set approach for detection and tracking of moving objects. In: Proc. IJCV, Bombay, India, Janurary (1998)Google Scholar
  21. 21.
    Rothwell, C., Mundy, J., Hoffman, W., Nguyen, V.-D.: Driving vision by topology. In: IEEE Intl. Symosium on Computer Vision, pp. 395–400 (1995)Google Scholar
  22. 22.
    Sebastian, T., Klein, P., Kimia, B.: On aligning curves. IEEE Trans. PAMI 25(1), 116–125 (2003)Google Scholar
  23. 23.
    Sharvit, D., Chan, J., Tek, H., Kimia, B.B.: Symmetry-based indexing of image databases. JVCIR 9(4), 366–380 (1998)CrossRefGoogle Scholar
  24. 24.
    Shi, J., Tomasi, C.: Good features to track. In: Proc. of the IEEE conference on CVPR, pp. 593–600 (1994)Google Scholar
  25. 25.
    Younes, L.: Computable elastic distance between shapes. SIAM Journal of Applied Mathematics 58, 565–586 (1998)zbMATHCrossRefMathSciNetGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Vishal Jain
    • 1
  • Benjamin B. Kimia
    • 1
  • Joseph L. Mundy
    • 1
  1. 1.Division of EngineeringBrown UniversityProvidenceUSA

Personalised recommendations