Skip to Main content Skip to Navigation
New interface
Reports (Research report)

Bio-inspired motion estimation – From modelling to evaluation, can biology be a source of inspiration?

Émilien Tlapale 1, * Pierre Kornprobst 1 Guillaume S. Masson 2 Olivier Faugeras 1 Jan D. Bouecke 3 Heiko Neumann 3 
* Corresponding author
CRISAM - Inria Sophia Antipolis - Méditerranée , INRIA Rocquencourt, ENS-PSL - École normale supérieure - Paris, UNS - Université Nice Sophia Antipolis (1965 - 2019), CNRS - Centre National de la Recherche Scientifique : UMR8548
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. Following this idea, we propose a new benchmark to evaluate models against visual system performance. Baseline results are provided for both bio-inspired and computer vision models. Results confirm the good performance of recent computer vision approaches even on such synthetic stimuli, and also show that taking biology into account in models can improve performance. As a whole, this article affords a considerable insight into how biology can bring new ideas in computer vision at different levels: modelling principles, mathematical formalism and evaluation methodology. Perspectives around this work are promising and cover the addition of delays to constrain propagation as well as the extension of our benchmark to better characterise the visual system performance.
Document type :
Reports (Research report)
Complete list of metadata

Cited literature [79 references]  Display  Hide  Download
Contributor : Émilien Tlapale Connect in order to contact the contributor
Submitted on : Monday, November 8, 2010 - 1:07:34 PM
Last modification on : Wednesday, October 26, 2022 - 8:16:33 AM
Long-term archiving on: : Thursday, March 30, 2017 - 2:40:20 AM


Files produced by the author(s)


  • HAL Id : inria-00532894, version 2


Émilien Tlapale, Pierre Kornprobst, Guillaume S. Masson, Olivier Faugeras, Jan D. Bouecke, et al.. Bio-inspired motion estimation – From modelling to evaluation, can biology be a source of inspiration?. [Research Report] RR-7447, INRIA. 2010. ⟨inria-00532894v2⟩



Record views


Files downloads