Nothing Special   »   [go: up one dir, main page]
Skip to main content
Springer Nature Link
Log in

Heuristic Algorithm for Computing Fast Template Motion in Video Streams

  • Conference paper
Advanced Concepts for Intelligent Vision Systems (ACIVS 2005)

Part of the book series: Lecture Notes in Computer Science ((LNIP,volume 3708))

  • 1186 Accesses

Abstract

Many vision problems require computing fast template motion in dynamic scenes. These problems can be formulated as exploration problems and thus can be expressed as a search into a state space based representation approach. However, these problems are hard to solve because they involve search through a high dimensional space. In this paper, we propose a heuristic algorithm through the space of transformations for computing target 2D motion. Three features are combined in order to compute efficient motion: (1) a quality of function match based on a holistic similarity measurement, (2) Kullback-Leibler measure as heuristic to guide the search process and (3) incorporation of target dynamics into the search process for computing the most promising search alternatives. The paper includes experimental evaluations that illustrate the efficiency and suitability for real-time vision based tasks.

This work has been supported by the Spanish Government and Canary Islands Autonomous Government under the Projects TIN2004-07087 and PI2003/165.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Turk, M.: Computer Vision in the Interface. Communications of the ACM 47(1), 61–67 (2004)

    Article  Google Scholar 

  2. Pentland, A.: Perceptual Intelligence. Communications of ACM 43(3), 35–44 (2000)

    Article  Google Scholar 

  3. Rucklidge, W.: Efficient computation of the minimum Hausdorff distance for visual recognition. In: Rucklidge, W. (ed.) Efficient Visual Recognition Using the Hausdorff Distance. LNCS, vol. 1173. Springer, Heidelberg (1996)

    Chapter  Google Scholar 

  4. Pearl, J.H.: Intelligent Search Strategies for Computer Problem Solving. Addison-Wesley Series in Artificial Intelligence (1984)

    Google Scholar 

  5. Cover, T.M., Thomas, J.A., Thomas, J.A.: Elements of Information Theory. John Wiley & Sons Incs, Chichester (1991)

    Book  MATH  Google Scholar 

  6. Bar-Shalom, Y., Xiao-Rong, L.: Estimation and Tracking: Principles, Techniques, and Software. Artech House, Boston (1993)

    MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Statistics, Operations Research and Computer Science, University of La Laguna, 38271, La Laguna, Spain

    Elena Sánchez-Nielsen

  2. Institute of Intelligent Systems and Numerical Applications in Engineering, Campus Universitario de Tafira, 35017, Gran Canaria, Spain

    Mario Hernández-Tejera

Authors
  1. Elena Sánchez-Nielsen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mario Hernández-Tejera
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. DGA/D4S/MRIS, 94114, Arcueil, France

    Jacques Blanc-Talon

  2. Ghent University, 9000, Gent, Belgium

    Wilfried Philips

  3. Wireless Technologies Lab, CSIRO ICT Centre, NSW 2122, Marsfield, Australia

    Dan Popescu

  4. University of Antwerp, 2610, Wilrijk, Belgium

    Paul Scheunders

Rights and permissions

Reprints and permissions

Copyright information

© 2005 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Sánchez-Nielsen, E., Hernández-Tejera, M. (2005). Heuristic Algorithm for Computing Fast Template Motion in Video Streams. In: Blanc-Talon, J., Philips, W., Popescu, D., Scheunders, P. (eds) Advanced Concepts for Intelligent Vision Systems. ACIVS 2005. Lecture Notes in Computer Science, vol 3708. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11558484_69

Download citation

  • DOI: https://doi.org/10.1007/11558484_69

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-29032-2

  • Online ISBN: 978-3-540-32046-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation