Event-based Extraction of Navigation Features from Unsupervised Learning of Optic Flow Patterns

Paul Fricker, Paul Fricker, Tushar Chauhan, Christophe Hurter, Benoit R. Cottereau

2022

Abstract

We developed a Spiking Neural Network composed of two layers that processes event-based data captured by a dynamic vision sensor during navigation conditions. The training of the network was performed using a biologically plausible and unsupervised learning rule, Spike-Timing-Dependent Plasticity. With such an approach, neurons in the network naturally become selective to different components of optic flow, and a simple classifier is able to predict self-motion properties from the neural population output spiking activity. Our network has a simple architecture and a restricted number of neurons. Therefore, it is easy to implement on a neuromorphic chip and could be used for embedded applications necessitating low energy consumption.

Paper Citation

in Harvard Style

Fricker P., Chauhan T., Hurter C. and Cottereau B. (2022). Event-based Extraction of Navigation Features from Unsupervised Learning of Optic Flow Patterns. In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 5: VISAPP; ISBN 978-989-758-555-5, SciTePress, pages 702-710. DOI: 10.5220/0010836200003124

in Bibtex Style

@conference{visapp22,
author={Paul Fricker and Tushar Chauhan and Christophe Hurter and Benoit R. Cottereau},
title={Event-based Extraction of Navigation Features from Unsupervised Learning of Optic Flow Patterns},
booktitle={Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 5: VISAPP},
year={2022},
pages={702-710},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010836200003124},
isbn={978-989-758-555-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2022) - Volume 5: VISAPP
TI - Event-based Extraction of Navigation Features from Unsupervised Learning of Optic Flow Patterns
SN - 978-989-758-555-5
AU - Fricker P.
AU - Chauhan T.
AU - Hurter C.
AU - Cottereau B.
PY - 2022
SP - 702
EP - 710
DO - 10.5220/0010836200003124
PB - SciTePress