Spatio-temporal Attention Mechanism for More Complex Analysis to Track Multiple Objects

  • Heungkyu Lee
  • Hanseok Ko
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3704)


This paper proposes the spatio-temporal attentive mechanism to track multiple objects, even occluded objects. The proposed system provides an efficient method for more complex analysis using data association in spatially attentive window and predicted temporal location. When multiple objects are moving or occluded between them in areas of visual field, a simultaneous tracking of multiple objects tends to fail. This is due to the fact that incompletely estimated feature vectors such as location, color, velocity, and acceleration of a target provide ambiguous and missing information. In addition, partial information cannot render the complete information unless temporal consistency is considered when objects are occluded between them or they are hidden in obstacles. Thus, the spatially and temporally considered mechanism using occlusion activity detection and object association with partial probability model is proposed. For an experimental evaluation, the proposed algorithms are applied to real image sequences. Experimental results in a natural environment demonstrate the usefulness of the proposed method.


Mean Absolute Difference Track Multiple Object Minimum Bound Rectangle Validation Region Occlusion Status 
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.
    Cantoni, V., Levialdi, S., Roberto, V.: Artificial Vision: Image description, Recognition and Communication, pp. 3–64. Academic Press, London (1997)Google Scholar
  2. 2.
    Stasse, O., Kuniyoshi, Y., Cheng, G.: Development of a Biologically inspired Real-Time Visual Attention System. In: Bülthoff, H.H., Poggio, T.A., Lee, S.-W. (eds.) BMCV 2000. LNCS, vol. 1811, pp. 150–159. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  3. 3.
    McKenna, S.J., Jabri, S., Duric, Z., Rosenfeld, A., Wechsler, H.: Tracking Groups of people. In: Computer Vision and Image Understanding, pp. 42–56 (2000)Google Scholar
  4. 4.
    Li, W., Salari, E.: Successive elimination algorithm for motion estimation. IEEE Trans. Image processing 4, 105–107 (1995)CrossRefGoogle Scholar
  5. 5.
    Rasmussen, C., Hager, G.D.: Joint probabilistic techniques for tracking multi-part objects. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Proceedings, June 1998, pp. 16–21 (1998)Google Scholar
  6. 6.
    Bar-Shalom, Y., Li, X.R.: Multitarget-multisensor tracking: principles and techniques. YBS Press (1995)Google Scholar
  7. 7.
    Kollnig, H., Nagel, H.-H., Otte, M.: Association of Motion Verbs with Vehicle Movements Extracted from Dense Optical Flow Fields. In: Eklundh, J.-O. (ed.) ECCV 1994. LNCS, vol. 801, pp. 338–350. Springer, Heidelberg (1994)CrossRefGoogle Scholar
  8. 8.
    Tomasi, C., Kanade, T.: Detection and tracking of point features. Tech. Rept. CMUCS- 91132, Pittsburgh: Carnegie Mellon University, School of Computer ScienceGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Heungkyu Lee
    • 1
  • Hanseok Ko
    • 2
  1. 1.Dept. of Visual Information Processing 
  2. 2.Dept. of Electronics and Computer EngineeringKorea UniversitySeoulKorea

Personalised recommendations