Towards Contextual Action Recognition and Target Localization with Active Allocation of Attention
File(s)ognibene_living_machines.pdf (642.61 KB)
Accepted version
Author(s)
Ognibene, D
Chinellato, E
Sarabia, M
Demiris, Y
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 partner’s 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.
Date Issued
2012-07-12
Date Acceptance
2012-07-09
Citation
First International Conference, Living Machines 2012, Barcelona, Spain, July 9-12, 2012. Proceedings, 2012, 7375, pp.192-203
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
Source
Living Machines
Subjects
active vision
social interaction
humanoid robots
attentive systems
information gain
Publication Status
Published
Start Date
2012-07-09
Finish Date
2012-07-12
Coverage Spatial
Barcelona, Spain