A Neural Field Model for Motion Estimation - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2011

A Neural Field Model for Motion Estimation

Abstract

We propose a bio-inspired approach to motion estimation based on recent neuroscience findings concerning the motion pathway. Our goal is to identify the key biological features in order to reach a good compromise between bio-inspiration and computational efficiency. Here we choose the neural field formalism which provides a sound mathematical framework to describe the model at a macroscopic scale. Within this framework we define the cortical activity as coupled integro-differential equations and we prove the well-posedness of the model. We show how our model performs on some classical computer vision videos, and we compare its behaviour against the visual system on a simple classical video used in psychophysics. As a whole, this article contributes to bring new ideas from computational neuroscience in the domain of computer vision, concerning modelling principles and mathematical formalism.

Dates and versions

hal-00845749 , version 1 (17-07-2013)

Identifiers

Cite

Emilien Tlapale, Pierre Kornprobst, Guillaume S. Masson, Olivier Faugeras. A Neural Field Model for Motion Estimation. Mathematical Image Processing, 2011, Orléans, France. pp.159-180, ⟨10.1007/978-3-642-19604-1_9⟩. ⟨hal-00845749⟩
184 View
0 Download

Altmetric

Share

Gmail Facebook X LinkedIn More