Skip to Main content Skip to Navigation

Modèle computationnel d'attention pour la vision adaptative

Abstract : Providing real time analysis of the huge amount of data generated by computer vision algorithms in interactive applications is still an open problem. It promises great advances across a wide variety of fields : robotics, distance education, or new mouse-less and keyboard-less human computer interaction.When using scene analysis algorithms for computer vision, a trade-off must be found between the quality of the results expected, and the amount of computer resources allocated for each task. It is usually a design time decision, implemented through the choice of pre-defined algorithms and parameters. However, this way of doing limits the generality of the system. Using an adaptive vision system provides a more flexible solution as its analysis strategy can be changed according to the information available concerning the execution context. As a consequence, such a system requires some kind of guiding mechanism to explore the scene faster and more efficiently.In human, the mechanisms of evolution have generated the visual attention system which selects the most important information in order to reduce both cognitive load and scene understanding ambiguity.In this thesis, we propose a visual attention system tailored for interacting with a vision system (whose theoretical architecture is given) so that it adapts its processing according to the interest (or salience) of each element of the scene.Somewhere in between hierarchical salience based (ex: [Koch1985], then [Itti1998]) and competitive distributed (ex: [Desimone1995], then [Deco2004, Rolls2006]) models, we propose a hierarchical yet competitive and non salience based model. Our original approach allows the generation of attentional focus points without the need of neither saliency map nor explicit inhibition of return mechanism. This new real-time computational model is based on a preys / predators system. The use of this kind of dynamical system is justified by an adjustable trade-off between nondeterministic attentional behavior and properties of stability, reproducibility and reactiveness.Our experiments shows that despite the non deterministic behavior of preys / predators equations, the system exhibits interesting properties of stability, reproducibility and reactiveness while allowing a fast and efficient exploration of the scene. These properties are useful for addressing different kinds of applications, ranging from image complexity evaluation, to object detection and tracking. Finally, while it is designed for computer vision, we compare our model to human visual attention. We show that it is equally as plausible as existing models (or better, depending on its configuration).
Document type :
Complete list of metadata

Cited literature [57 references]  Display  Hide  Download
Contributor : ABES STAR :  Contact
Submitted on : Friday, March 4, 2011 - 6:44:09 PM
Last modification on : Friday, June 3, 2022 - 10:24:30 AM
Long-term archiving on: : Sunday, June 5, 2011 - 3:00:36 AM


Version validated by the jury (STAR)


  • HAL Id : tel-00573844, version 1



Matthieu Perreira da Silva. Modèle computationnel d'attention pour la vision adaptative. Autre. Université de La Rochelle, 2010. Français. ⟨NNT : 2010LAROS317⟩. ⟨tel-00573844⟩



Record views


Files downloads