✦ LIBER ✦
Robot vision with cellular neural networks: a practical implementation of new algorithms
✍ Scribed by Giovanni Egidio Pazienza; Xavier Ponce-García; Marco Balsi; Xavier Vilasís-Cardona
- Publisher
- John Wiley and Sons
- Year
- 2007
- Tongue
- English
- Weight
- 262 KB
- Volume
- 35
- Category
- Article
- ISSN
- 0098-9886
- DOI
- 10.1002/cta.395
No coin nor oath required. For personal study only.
✦ Synopsis
Abstract
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. Copyright © 2006 John Wiley & Sons, Ltd.