Simulated prosthetic vision: The benefits from computer-based object recognition and localization - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Artificial Organs Année : 2015

Simulated prosthetic vision: The benefits from computer-based object recognition and localization

Résumé

Clinical trials with blind patients implanted with a visual neuroprosthesis showed that even the simplest tasks were difficult to perform with the limited vision restored with current implants. Simulated prosthetic vision (SPV) is a powerful tool to investigate the putative functions of the upcoming generations of visual neuroprostheses. Recent studies based on SPV showed that several generations of implants will be required before usable vision is restored. However, none of these studies relied on advanced image processing. High-level image processing could significantly reduce the amount of information required to perform visual tasks and help restore visuomotor behaviors, even with current low-resolution implants. In this study, we simulated a prosthetic vision device based on object localization in the scene. We evaluated the usability of this device for object recognition, localization, and reaching. We showed that a very low number of electrodes (e.g., nine) are sufficient to restore visually guided reaching movements with fair timing (10 s) and high accuracy. In addition, performance, both in terms of accuracy and speed, was comparable with 9 and 100 electrodes. Extraction of high level information (object recognition and localization) from video images could drastically enhance the usability of current visual neuroprosthesis. We suggest that this method—that is, localization of targets of interest in the scene—may restore various visuomotor behaviors. This method could prove functional on current low-resolution implants. The main limitation resides in the reliability of the vision algorithms, which are improving rapidly.
Fichier principal
Vignette du fichier
mace_15215.pdf (409.74 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01387831 , version 1 (26-10-2016)

Identifiants

Citer

Marc J.-M. Macé, Valérian Guivarch, Grégoire Denis, Christophe Jouffrais. Simulated prosthetic vision: The benefits from computer-based object recognition and localization. Artificial Organs, 2015, 39 (7), pp.E102-E113. ⟨10.1111/aor.12476⟩. ⟨hal-01387831⟩
85 Consultations
183 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More