TY - JOUR
T1 - Robot vision with cellular neural networks
T2 - A practical implementation of new algorithms
AU - Pazienza, Giovanni Egidio
AU - Ponce-García, Xavier
AU - Balsi, Marco
AU - Vilasís-Cardona, Xavier
PY - 2007/7
Y1 - 2007/7
N2 - 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.
AB - 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.
KW - Artificial vision
KW - Autonomous robot
KW - CNN
KW - Obstacle avoidance
KW - Tracking
UR - http://www.scopus.com/inward/record.url?scp=34547187567&partnerID=8YFLogxK
U2 - 10.1002/cta.395
DO - 10.1002/cta.395
M3 - Article
AN - SCOPUS:34547187567
SN - 0098-9886
VL - 35
SP - 449
EP - 462
JO - International Journal of Circuit Theory and Applications
JF - International Journal of Circuit Theory and Applications
IS - 4
ER -