Robot vision with cellular neural networks: A practical implementation of new algorithms

Giovanni Egidio Pazienza, Xavier Ponce-García, Marco Balsi, Xavier Vilasís-Cardona

Producció científica: Article en revista indexadaArticleAvaluat per experts

18 Cites (Scopus)

Resum

Cellular neural networks (CNNs) are well suited for image processing due to the possibility of a parallel computation. In this paper, we present two algorithms for tracking and obstacle avoidance using CNNs. Furthermore, we show the implementation of an autonomous robot guided using only real-time visual feedback; the image processing is performed entirely by a CNN system embedded in a digital signal processor (DSP). We successfully tested the two algorithms on this robot.

Idioma originalAnglès
Pàgines (de-a)449-462
Nombre de pàgines14
RevistaInternational Journal of Circuit Theory and Applications
Volum35
Número4
DOIs
Estat de la publicacióPublicada - de jul. 2007

Fingerprint

Navegar pels temes de recerca de 'Robot vision with cellular neural networks: A practical implementation of new algorithms'. Junts formen un fingerprint únic.

Com citar-ho