Event-based Extraction of Navigation Features from Unsupervised Learning of Optic Flow Patterns - CNRS - Centre national de la recherche scientifique Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

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

Résumé

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.
Fichier principal
Vignette du fichier
108362.pdf (1.33 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03590636 , version 1 (28-02-2022)

Identifiants

Citer

Paul Fricker, Tushar Chauhan, Christophe Hurter, Benoit Cottereau. Event-based Extraction of Navigation Features from Unsupervised Learning of Optic Flow Patterns. 17th International Conference on Computer Vision Theory and Applications, Feb 2022, Vienne (Online Streaming ), France. pp.702-710, ⟨10.5220/0010836200003124⟩. ⟨hal-03590636⟩
220 Consultations
154 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More