Efficient Egocentric Visual Perception Combining Eye-tracking, a Software Retina and Deep Learning

Hristozova, N., Ozimek, P. and Siebert, J. P. (2018) Efficient Egocentric Visual Perception Combining Eye-tracking, a Software Retina and Deep Learning. Third International Workshop on Egocentric Perception, Interaction and Computing (EPIC@ECCV18), Munich, Germany, 09 Sep 2018.

183354.pdf - Accepted Version



We present ongoing work to harness biological approaches to achieving highly efficient egocentric perception by combining the space- variant imaging architecture of the mammalian retina with Deep Learn- ing methods. By pre-processing images collected by means of eye-tracking glasses to control the fixation locations of a software retina model, we demonstrate that we can reduce the input to a DCNN by a factor of 3, reduce the required number of training epochs and obtain over 98% clas- sification rates when training and validating the system on a database of over 26,000 images of 9 object classes.

Item Type:Conference or Workshop Item
Keywords:Data efficiency, deep learning, retina, foveated vision, biological vision, egocentric perception, robot vision, visual cortex.
Glasgow Author(s) Enlighten ID:Ozimek, Peter and Siebert, Dr Paul and Hristozova, Nina
Authors: Hristozova, N., Ozimek, P., and Siebert, J. P.
Subjects:Q Science > QA Mathematics
Q Science > QA Mathematics > QA75 Electronic computers. Computer science
R Medicine > RZ Other systems of medicine
T Technology > TK Electrical engineering. Electronics Nuclear engineering
College/School:College of Science and Engineering > School of Computing Science
Research Group:Computer Vision for Autonomous Systems
Copyright Holders:Copyright © 2018 The Authors
Publisher Policy:Reproduced in accordance with the publisher copyright policy
Related URLs:

University Staff: Request a correction | Enlighten Editors: Update this record