Towards Contextual Action Recognition and Target Localization with Active Allocation of Attention

File Description SizeFormat 
ognibene_living_machines.pdfAccepted version642.61 kBAdobe PDFView/Open
Title: Towards Contextual Action Recognition and Target Localization with Active Allocation of Attention
Authors: Ognibene, D
Chinellato, E
Sarabia, M
Demiris, Y
Item Type: Conference Paper
Abstract: Exploratory gaze movements are fundamental for gathering the most relevant information regarding the partner during social interactions. We have designed and implemented a system for dynamic attention allocation which is able to actively control gaze movements during a visual action recognition task. During the observation of a partners reaching movement, the robot is able to contextually estimate the goal position of the partner hand and the location in space of the candidate targets, while moving its gaze around with the purpose of optimizing the gathering of information relevant for the task. Experimental results on a simulated environment show that active gaze control provides a relevant advantage with respect to typical passive observation, both in term of estimation precision and of time required for action recognition. © 2012 Springer-Verlag.
Issue Date: 12-Jul-2012
Date of Acceptance: 9-Jul-2012
URI: http://hdl.handle.net/10044/1/26617
DOI: https://dx.doi.org/10.1007/978-3-642-31525-1_17
ISBN: 978-3-642-31524-4
ISSN: 0302-9743
Publisher: Springer
Start Page: 192
End Page: 203
Journal / Book Title: First International Conference, Living Machines 2012, Barcelona, Spain, July 9-12, 2012. Proceedings
Volume: 7375
Copyright Statement: The final publication is available at Springer via https://dx.doi.org/10.1007/978-3-642-31525-1_17
Conference Name: Living Machines
Keywords: active vision
social interaction
humanoid robots
attentive systems
information gain
Publication Status: Published
Start Date: 2012-07-09
Finish Date: 2012-07-12
Conference Place: Barcelona, Spain
Appears in Collections:Electrical and Electronic Engineering



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commons