Low Level Moving-Feature Extraction Via Heat Flow Analogy

  • Cem Direkoğlu
  • Mark S. Nixon
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4291)


In this paper, an intelligent and automatic moving object edge detection algorithm is proposed, based on heat flow analogy. This algorithm starts with anisotropic heat diffusion in the spatial domain to remove noise and sharpen region boundaries for the purpose of obtaining high quality edge data. Then, isotropic heat diffusion is applied in the temporal domain to calculate the total amount of heat flow. The moving edges are represented as the total amount of heat flow out from the reference frame. The overall process is completed by non-maxima suppression and hysteresis thresholding to obtain binary moving edges. Evaluation results indicate that this approach has advantages in handling noise in the temporal domain because of the averaging inherent of isotropic heat flow. Results also show that this technique can detect moving edges in image sequences.


Heat Flow Active Contour Anisotropic Diffusion Temporal Domain Geometric Active Contour 
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.
    Witkin, A.: Scale-Space Filtering. In: Int. Joint Conf. Artificial Intelligence, Karlsruhe, West Germany, pp. 1019–1021 (1983)Google Scholar
  2. 2.
    Koenderink, J.: The Structure of Images. Biological Cybernetics 50, 363–370 (1984)MATHCrossRefMathSciNetGoogle Scholar
  3. 3.
    Hummel, R.: Representations based on zero-crossings in scale-space. In: Proc. IEEE Computer vision and Pattern Recognition Conf., June 1986, pp. 204–209 (1986)Google Scholar
  4. 4.
    Perona, P., Malik, J.: Scale-Space and Edge Detection using Anisotropic Diffusion. IEEE Trans. Pattern Analysis and Machine Intelligence 22(8), 629–639 (1990)CrossRefGoogle Scholar
  5. 5.
    Kimia, B.B., Siddiqi, K.: Geometric Heat Equation and Nonlinear Diffusion of Shapes and Images. In: Proc. Computer Vision and Pattern Recognition (1994)Google Scholar
  6. 6.
    Zhang, F., Hancock, E.R.: Image Scale-Space from Heat Kernel, Iberoamerican Congress on Pattern Recognition CIARP. In: Sanfeliu, A., Cortés, M.L. (eds.) CIARP 2005. LNCS, vol. 3773, pp. 181–192. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  7. 7.
    Krim, H., Bao, Y.: Nonlinear Diffusion: A Probabilistic View. In: Int. Conference on Image Processing, vol. 2, pp. 21–25 (1999)Google Scholar
  8. 8.
    Scherzer, O., Weickert, J.: Relations between Regularization and Diffusion Filtering. Journal of Mathematical Imaging and Vision 12, 43–63 (2000)MATHCrossRefMathSciNetGoogle Scholar
  9. 9.
    Sze, C.J., Liao, H.Y.M.: A New Image Flux Conduction Model and Its Application to Selective Image Smoothing. IEEE Transaction on Image Processing 10(2) (February 2001)Google Scholar
  10. 10.
    Acton, S.T., Bovik, A.C., Crawford, M.M.: Anisotropic diffusion pyramids for image segmentation. In: Proc. First IEEE Int. Conf. Image Processing, Austin (November 1994)Google Scholar
  11. 11.
    Manay, S., Yezzi, A.: Anti-Geometric Diffusion for Adaptive Thresholding and Fast Segmentation. IEEE Transaction on Image Processing 12(11) (November 2003)Google Scholar
  12. 12.
    Ji, X., Feng, J.: A New Approach to Thinning Based on Time-Reversed Heat Conduction Model. In: IEEE Int. Conf. Image Processing, October 2004, vol. 1, pp. 653–656 (2004)Google Scholar
  13. 13.
    Kass, M., Witkin, A., Terzopoulos, D.: Snakes: Active Contour models. International Journal of Computer Vision, 321–331 (1987)Google Scholar
  14. 14.
    Xu, C., Prince, J.L.: Snakes, Shapes and Gradient Vector Flow. IEEE Transaction on Image Processing 7(3), 359–369 (1998)MATHCrossRefMathSciNetGoogle Scholar
  15. 15.
    Caselles, V., Catte, F., Coll, T., Dibos, F.: A Geometric Model for Active Contours. Numerische Mathematic 66, 1–31 (1993)MATHCrossRefMathSciNetGoogle Scholar
  16. 16.
    Malladi, R., Sethian, J.A., Vemuri, B.C.: Shape Modeling with Front Propagation: A Level Set Approach. IEEE Transaction on Pattern Analysis and Machine Intelligence 17(2), 158–175 (1995)CrossRefGoogle Scholar
  17. 17.
    Horn, B., Schunck, B.: Determining Optical Flow. Artificial Intelligence 17, 185–204 (1981)CrossRefGoogle Scholar
  18. 18.
    Weickert, J., Schnorr, C.: Variational Optic Flow Computation with a Spatio-Temporal Smoothness Constraint. Journal of Mathematical Imaging and Vision 14, 245–255 (2001)MATHCrossRefGoogle Scholar
  19. 19.
    Alvarez, L., Weickert, J., Sanchez, J.: A Scale-Space Approach to Nonlocal Optical Flow Calculations. Scale-Space theories in Computer Vision (1999)Google Scholar
  20. 20.
    Makrogiannis, S.K., Bourbakis, N.G.: Motion Analysis with Application to Assistive Vision Technology. In: 16th IEEE International Conference on Tools with Artificial Intelligence, pp. 344–352 (2004)Google Scholar
  21. 21.
    Lienhard IV, J.H., Lienhard V, J.H.: A Heat Transfer Textbook, 3rd edn. Phlogiston Press, Cambridge, Massachusetts (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Cem Direkoğlu
    • 1
  • Mark S. Nixon
    • 1
  1. 1.Department of Electronics and Computer ScienceUniversity of SouthamptonSouthamptonUK

Personalised recommendations