Adaptive Motion Pooling and Diffusion for Optical Flow Computation

Abstract : We propose to extend a state of the art bio-inspired model for optic flow computation through adaptive processing by focusing on the role of local context indicative of the local velocity estimates reliability. We set a network structure representative of cortical areas V1, V2 and MT, and incorporate three functional principles observed in primate visual system: contrast adaptation, adaptive afferent pooling and MT diffusion that are adaptive dependent upon the 2D image structure (Adaptive Motion Pooling and Diffusion, AMPD). We assess the AMPD performance on Middlebury optical flow estimation dataset, showing that the proposed AMPD model performs better than the baseline one and its overall performance is comparable with many computer vision methods.
Type de document :
Communication dans un congrès
WBICV 2017 : First International Workshop on Brain-Inspired Computer Vision, Sep 2017, Catania, Sicily, Italy. 〈http://wbicv2017.ai.edu.mt〉
Liste complète des métadonnées

Littérature citée [20 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01589983
Contributeur : Pierre Kornprobst <>
Soumis le : mardi 19 septembre 2017 - 11:52:23
Dernière modification le : jeudi 11 janvier 2018 - 16:35:51

Fichier

paper_wbicv.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01589983, version 1

Collections

Citation

N Kartheek Medathati, Manuela Chessa, Guillaume Masson, Pierre Kornprobst, Fabio Solari. Adaptive Motion Pooling and Diffusion for Optical Flow Computation. WBICV 2017 : First International Workshop on Brain-Inspired Computer Vision, Sep 2017, Catania, Sicily, Italy. 〈http://wbicv2017.ai.edu.mt〉. 〈hal-01589983〉

Partager

Métriques

Consultations de la notice

69

Téléchargements de fichiers

30