Saliency extraction with a distributed spiking neural network

Abstract : We present a distributed spiking neuron network (SNN) for handling low-level visual perception in order to extract salient locations in robot camera images. We describe a new method which reduce the computional load of the whole system, stemming from our choices of architecture. We also describe a modeling of post-synaptic potential, which allows to quickly compute the contribution of a sum of incoming spikes to a neuron's membrane potential. The interests of this saliency extraction method, which differs from classical image processing, are also exposed.
Complete list of metadatas

Cited literature [13 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00023820
Contributor : Sylvain Chevallier <>
Submitted on : Monday, April 12, 2010 - 5:57:29 PM
Last modification on : Saturday, May 4, 2019 - 1:20:01 AM
Long-term archiving on : Thursday, September 23, 2010 - 12:49:49 PM

File

ESANN-06_v2.pdf
Publisher files allowed on an open archive

Identifiers

  • HAL Id : hal-00023820, version 2

Citation

Sylvain Chevallier, Philippe Tarroux, Hélène Paugam-Moisy. Saliency extraction with a distributed spiking neural network. European Symposium on Artificial Neural Networks, Apr 2006, Bruges, Belgium. pp.209-214. ⟨hal-00023820v2⟩

Share

Metrics

Record views

233

Files downloads

110