Mainpage
  Stereovision
  Segmentation
  Publications
  Online-Processing

Links
Contact

Synchronization, Coherence-Detection and Three-Dimensional Vision

next up previous
Next: Introduction

Rolf D. Henkel
henkel@physik.uni-bremen.de
http://axon.physik.uni-bremen.de

University of Bremen
Institute for Theoretical Physics
D-28334 Bremen, Germany

Abstract:

A new functional role for spiking neurons is proposed, considered necessary to convert noisy sensory data into meaningful and stable perceptions. Percept creation and validation is performed by a dynamical process of coherence detection between neural signals. The crucial operational step of the network is the interaction of neural oscillators in the weak-coupling limit, which realizes coherence detection dynamically by selective synchronization of neural responses. A robust estimate of the incoming signals is transmitted as modulation frequency of the output current of the coherence-detecting layer, and a validation measure is given by the modulation depth of this current. As a real world example of these ideas, a neural network is presented solving the task of stereo vision with real image data. It combines operations of time-averaging, rate-coding neurons with integrate-and-fire-neurons, which calculate a disparity map of a scene by partially synchronizing their spike trains.

Keywords: Synchronization, Coherence, Neural Code, Neural Computations, Robust Estimators, Three-dimensional Vision, Integrate-And-Fire-Neurons.




next up previous
Next: Introduction

2000-11-20