Neuromorphic foveation applied to semantic segmentation
Résumé
Foveation can be defined as the organic action of directing the gaze towards a visual region of interest, to selectively acquire relevant information. 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 present in this work the evolution of the performance of semantic segmentation with respect to the amount of event data used, to demonstrate the stakes of foveation.
Origine | Fichiers produits par l'(les) auteur(s) |
---|