Semantic Place Recognition based on Deep Belief Networks and Tiny Images
Ahmad Hasasneh, Emmanuelle Frenoux, Philippe Tarroux
2012
Abstract
This paper presents a novel approach for robot semantic place recognition (SPR) based on Restricted Boltzmann Machines (RBMs) and a direct use of tiny images. RBMs are able to code images as a superposition of a limited number of features taken from a larger alphabet. Repeating this process in a deep architecture leads to an efficient sparse representation of the initial data in the feature space. A complex problem of classification in the input space is thus transformed into an easier one in the feature space. In this article, we show that SPR can thus be achieved using tiny images instead of conventional Bag-of-Words (BoW) methods. After appropriate coding, a softmax regression in the feature space suffices to compute the probability to be in a given place according to the input image.
DownloadPaper Citation
in Harvard Style
Hasasneh A., Frenoux E. and Tarroux P. (2012). Semantic Place Recognition based on Deep Belief Networks and Tiny Images . In Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO, ISBN 978-989-8565-22-8, pages 236-241. DOI: 10.5220/0004029902360241
in Bibtex Style
@conference{icinco12,
author={Ahmad Hasasneh and Emmanuelle Frenoux and Philippe Tarroux},
title={Semantic Place Recognition based on Deep Belief Networks and Tiny Images},
booktitle={Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,},
year={2012},
pages={236-241},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004029902360241},
isbn={978-989-8565-22-8},
}
in EndNote Style
TY - CONF
JO - Proceedings of the 9th International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,
TI - Semantic Place Recognition based on Deep Belief Networks and Tiny Images
SN - 978-989-8565-22-8
AU - Hasasneh A.
AU - Frenoux E.
AU - Tarroux P.
PY - 2012
SP - 236
EP - 241
DO - 10.5220/0004029902360241