CORSO DI LAUREA MAGISTRALE IN BIOINGEGNERIA

Scheda di Offerta Tesi

Titolo (provvisorio): A neuromorphic neural network for robot vision

Relatore/i: Sabatini Silvio P., Michael Spratling (King's College London) E-mail:
Indirizzo: Via Opera Pia 13 (III piano) Tel.: (+39) 010353 - 2092
Descrizione

Motivazione e campo di applicazione
Developing biologically-inspired algorithms for visual perception to either model the biological visual system or to develop methods for computer vision or robot control.

Obiettivi generali e principali attività
The thesis will concern, in general, bio-inspired computational algorithms for visual perception. In particular, the algorithms will be based on neural network models inspired by theories of cortical visual information processing. It will be particularly concerned with developing a system for analysing stereo visual information, with the aim of either stereo disparity estimation, or the control of eye/camera movements. The performance of the developed algorithm will be quanitatively assessed to validate the approach.

Obiettivi di apprendimento (strumenti tecnici e analitici, metodologie sperimentali)
To gain practical experience in developing and using neural network models, to gain MATLAB programming experience, experience applying benchmark assessment methods and of performing quantitative analysis of results, experience using a robot simulator (such as the iCub simulator).

Luogo/i in cui si svolgerà il lavoro: Department of Informatics, King's College London and DIBRIS, University of Genoa

Informazioni aggiuntive

Abilità e capacità richieste: (MATLAB) programming skills

Numero massimo di studenti: 1

Supporto finanziario/borse di studio: ERASMUS+ placement

Sei qui: Home Proposte Tesi Magistrale