Stakes of Neuromorphic Foveation: a promising future for embedded event cameras - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2022

Stakes of Neuromorphic Foveation: a promising future for embedded event cameras

Résumé

Foveation can be defined as the organic action of directing the gaze towards a visual region of interest, to acquire relevant information selectively. With the recent advent of event cameras, we believe that taking advantage of this visual neuroscience mechanism would greatly improve the efficiency of event-data processing. Indeed, applying foveation to event data would allow to comprehend the visual scene while significantly reducing the amount of raw data to handle. In this respect, we demonstrate the stakes of neuromorphic foveation theoretically and empirically across several computer vision tasks, namely semantic segmentation and classification. We show that foveated event data has a significantly better trade-off between quantity and quality of the information conveyed than high or low resolution event data. Furthermore, this compromise extends even over fragmented datasets. Our code is publicly available online at: github.com/amygruel/FoveationStakes DVS/.
Fichier principal
Vignette du fichier
BiologicalCybernetics2022_preprint.pdf (955.34 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04209459 , version 1 (17-09-2023)

Identifiants

  • HAL Id : hal-04209459 , version 1

Citer

Amélie Gruel, Dalia Hareb, Antoine Grimaldi, Jean Martinet, Laurent Perrinet, et al.. Stakes of Neuromorphic Foveation: a promising future for embedded event cameras. 2022. ⟨hal-04209459⟩
19 Consultations
61 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More