TY - GEN
T1 - Building representations of proto-objects with exploration of the effect on fixation times
AU - Braud, Raphaël
AU - Giagkos, Alexandros
AU - Shaw, Patricia
AU - Lee, Mark
AU - Shen, Qiang
PY - 2018/4/2
Y1 - 2018/4/2
N2 - During development, infants rapidly build models of the world around them, segmenting the visual scene into clusters of features that can be indexed as proto-objects. These proto-objects form the foundation of more specialised object perception later on, but also act as a means for generalising, comparing and recognising similar objects. This paper takes inspiration from psychological studies to present an approach for building representations of proto-objects that can be learned on-line on a robotic platform and used for object recognition. In particular, from our previous studies of infant visual development, we first identify four types of features; brightness, motion, colour and edges, and then apply heuristics to cluster them into proto-object representations. When correlations of the observed features are made, pairs of features are used to construct graphs that encapsulate information of the observed phenomena. By a three-phase experiment we demonstrate the robot's ability of effectively learn proto-object representations and then, by utilising the graphs, to recognise what is presented to it and report on the impact uncertainties in object recognition have on fixation times.
AB - During development, infants rapidly build models of the world around them, segmenting the visual scene into clusters of features that can be indexed as proto-objects. These proto-objects form the foundation of more specialised object perception later on, but also act as a means for generalising, comparing and recognising similar objects. This paper takes inspiration from psychological studies to present an approach for building representations of proto-objects that can be learned on-line on a robotic platform and used for object recognition. In particular, from our previous studies of infant visual development, we first identify four types of features; brightness, motion, colour and edges, and then apply heuristics to cluster them into proto-object representations. When correlations of the observed features are made, pairs of features are used to construct graphs that encapsulate information of the observed phenomena. By a three-phase experiment we demonstrate the robot's ability of effectively learn proto-object representations and then, by utilising the graphs, to recognise what is presented to it and report on the impact uncertainties in object recognition have on fixation times.
UR - http://www.scopus.com/inward/record.url?scp=85050345012&partnerID=8YFLogxK
UR - https://ieeexplore.ieee.org/document/8329821
U2 - 10.1109/DEVLRN.2017.8329821
DO - 10.1109/DEVLRN.2017.8329821
M3 - Conference publication
AN - SCOPUS:85050345012
SN - 978-1-5386-3716-6
T3 - 7th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics, ICDL-EpiRob 2017
SP - 296
EP - 303
BT - 7th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics, ICDL-EpiRob 2017
PB - IEEE
T2 - 7th Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics, ICDL-EpiRob 2017
Y2 - 18 September 2017 through 21 September 2017
ER -