Egocentric Perception using a Biologically Inspired Software Retina Integrated with a Deep CNN

Ozimek, P., Balog, L., Wong, R., Esparon, T. and Siebert, J. P. (2017) Egocentric Perception using a Biologically Inspired Software Retina Integrated with a Deep CNN. International Conference on Computer Vision 2017, ICCV 2017, Second International Workshop on Egocentric Perception, Interaction and Computing, Lido Venice, Italy, 29 Oct 2017.

[img]
Preview
Text
148802.pdf - Accepted Version

1MB

Publisher's URL: http://www.eyewear-computing.org/EPIC_ICCV17/Short_Papers/EPIC17_id21.pdf

Abstract

We presented the concept of of a software retina, capable of significant visual data reduction in combination with scale and rotation invariance, for applications in egocentric and robot vision at the first EPIC workshop in Amsterdam [9]. Our method is based on the mammalian retino-cortical transform: a mapping between a pseudo-randomly tessellated retina model (used to sample an input image) and a CNN. The aim of this first pilot study is to demonstrate a functional retina-integrated CNN implementation and this produced the following results: a network using the full retino-cortical transform yielded an F1 score of 0.80 on a test set during a 4-way classification task, while an identical network not using the proposed method yielded an F1 score of 0.86 on the same task. On a 40K node retina the method reduced the visual data bye×7, the input data to the CNN by 40% and the number of CNN training epochs by 36%. These results demonstrate the viability of our method and hint at the potential of exploiting functional traits of natural vision systems in CNNs. In addition, to the above study, we present further recent developments in porting the retina to an Apple iPhone, an implementation in CUDA C for NVIDIA GPU platforms and extensions of the retina model we have adopted.

Item Type:Conference or Workshop Item
Keywords:Data efficient deep learning, computer vision, biologically motivated vision, retina, foveated vision.
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Siebert, Dr Jan
Authors: Ozimek, P., Balog, L., Wong, R., Esparon, T., and Siebert, J. P.
College/School:College of Science and Engineering > School of Computing Science
Research Group:Computer Vision for Autonomous Systems within IDA
Copyright Holders:Copyright © 2017 The Authors
First Published:First published in International Conference on Computer Vision 2017, ICCV 2017, Second International Workshop on Egocentric Perception, Interaction and Computing
Publisher Policy:Reproduced in accordance with the publisher copyright policy
Related URLs:

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