DSpace Repository

Dynamic visual attention model in image sequences

Show simple item record

dc.contributor.author López Bonal, María Teresa es_ES
dc.contributor.author Mira Mira, José es_ES
dc.contributor.author Delgado García, Ana Esperanza es_ES
dc.contributor.author Fernández Graciani, Miguel Ángel es_ES
dc.contributor.author Fernández Caballero, Antonio es_ES
dc.date.accessioned 2012-03-21T07:13:12Z
dc.date.available 2012-03-21T07:13:12Z
dc.date.issued 2007 es_ES
dc.identifier.citation Image and Vision Computing, 2007, 25(5): 297-613 es_ES
dc.identifier.issn 0262-8856 es_ES
dc.identifier.uri http://hdl.handle.net/10578/2152
dc.description.abstract A new computational architecture of dynamic visual attention is introduced in this paper. Our approach defines a model for the generation of an active attention focus on a dynamic scene captured from a still or moving camera. The aim is to obtain the objects that keep the observer?s attention in accordance with a set of predefined features, including color, motion and shape. The solution proposed to the selective visual attention problem consists in decomposing the input images of an indefinite sequence of images into its moving objects, by defining which of these elements are of the user?s interest, and by keeping attention on those elements through time. Thus, the three tasks involved in the attention model are introduced. The Feature-Extraction task obtains those features (color, motion and shape features) necessary to perform object segmentation. The Attention-Capture task applies the criteria established by the user (values provided through parameters) to the extracted features and obtains the different parts of the objects of potential interest. Lastly, the Attention-Reinforcement task maintains attention on certain elements (or objects) of the image sequence that are of real interest. es_ES
dc.format text/plain en_US
dc.language.iso es en_US
dc.rights info:eu-repo/semantics/openAccess en_US
dc.subject Ingenierías es_ES
dc.title Dynamic visual attention model in image sequences es_ES
dc.type info:eu-repo/semantics/article en_US

Files in this item

This item appears in the following Collection(s)

Show simple item record

Search DSpace

Advanced Search


My Account