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
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Turk, M.: Computer Vision in the Interface. Communications of the ACM 47(1), 61–67 (2004)
Pentland, A.: Perceptual Intelligence. Communications of ACM 43(3), 35–44 (2000)
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)
Pearl, J.H.: Intelligent Search Strategies for Computer Problem Solving. Addison-Wesley Series in Artificial Intelligence (1984)
Cover, T.M., Thomas, J.A., Thomas, J.A.: Elements of Information Theory. John Wiley & Sons Incs, Chichester (1991)
Bar-Shalom, Y., Xiao-Rong, L.: Estimation and Tracking: Principles, Techniques, and Software. Artech House, Boston (1993)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights 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)