|Title:||Heuristic algorithm for computing fast template motion in video streams||Authors:||Sánchez-Nielsen, Elena
Hernández Tejera, Mario
|UNESCO Clasification:||1203 Ciencia de los ordenadores||Issue Date:||2005||Project:||Técnicas Para El Robustecimiento de Procesos en Visión Artificial Para la Interacción [Spanish Government under the Project TIN2004-07087]||Journal:||Lecture Notes in Computer Science||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.||URI:||http://hdl.handle.net/10553/46785||ISBN:||978-3-540-32046-3||ISSN:||0302-9743||DOI:||10.1007/11558484_69||Source:||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|
|Appears in Collections:||Actas de congresos|
checked on May 9, 2021
Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.