What can we expect from a V1-MT feedforward architecture for optical flow estimation?

Abstract : Motion estimation has been studied extensively in neuroscience in the last two decades. Even though there has been some early interaction between the biological and computer vision communities at a modelling level, comparatively little work has been done on the examination or extension of the biological models in terms of their engineering efficacy on modern optical flow estimation datasets. An essential contribution of this paper is to show how a neural model can be enriched to deal with real sequences. We start from a classical V1-MT feedforward architecture. We model V1 cells by motion energy (based on spatio-temporal filtering), and MT pattern cells (by pooling V1 cell responses). The efficacy of this architecture and its inherent limitations in the case of real videos are not known. To answer this question, we propose a velocity space sampling of MT neurons (using a decoding scheme to obtain the local velocity from their activity) coupled with a multi-scale approach. After this, we explore the performance of our model on the Middlebury dataset. To the best of our knowledge, this is the only neural model in this dataset. The results are promising and suggest several possible improvements, in particular to better deal with discontinuities. Overall, this work provides a baseline for future developments of bio-inspired scalable computer vision algorithms and the code is publicly available to encourage research in this direction. & 2015 Published by Elsevier B.V.
Type de document :
Article dans une revue
Signal Processing: Image Communication, Elsevier, 2015, 〈10.1016/j.image.2015.04.006〉
Liste complète des métadonnées

Littérature citée [26 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01215519
Contributeur : Pierre Kornprobst <>
Soumis le : mardi 20 octobre 2015 - 14:28:02
Dernière modification le : jeudi 3 mai 2018 - 13:32:58
Document(s) archivé(s) le : vendredi 28 avril 2017 - 05:52:21

Fichier

2015-solari-image-communicatio...
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Fabio Solari, Manuela Chessa, N. V. Kartheek Medathati, Pierre Kornprobst. What can we expect from a V1-MT feedforward architecture for optical flow estimation?. Signal Processing: Image Communication, Elsevier, 2015, 〈10.1016/j.image.2015.04.006〉. 〈hal-01215519〉

Partager

Métriques

Consultations de la notice

285

Téléchargements de fichiers

137