In the field of robotics real-time image processing can provide the information necessary for mobile robots to execute a task in indoor environment. In this paper the application of a simple CNN-based system to translation and scale-invariant object recognition in the artificial vision structure of a mobile robot is proposed. The suggested bio-inspired vision system is mainly constituted by an encoder and a cellular associative memory. Bipolar images constitute the input to the cellular associative memory, which performs the recognizing stage of the bio-inspired vision system. The capability of the proposed system to detect and recognize scaled and translated targets is investigated on suitable test situations.
|Autori interni:||CARNIMEO, Leonarda|
|Titolo:||A CNN-based Vision System for Pattern Recognition in Mobile Robots|
|Titolo del libro:||Circuit paradigm in the 21st Century : ECCTD '01, proceedings of the 15th European Conference on Circuit Theory and Design, Helsinki University of Technology, Finland, 28th-31st August 2001. Vol. 1|
|Data di pubblicazione:||2001|
|Appare nelle tipologie:||2.1 Contributo in volume (Capitolo o Saggio)|