Processing

Please wait...

Settings

Settings

Goto Application

1. WO2022003013 - EYE TRACKING DEVICE, EYE TRACKING METHOD, AND COMPUTER-READABLE MEDIUM

Publication Number WO/2022/003013
Publication Date 06.01.2022
International Application No. PCT/EP2021/067972
International Filing Date 30.06.2021
IPC
G06F 3/01 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
FELECTRIC DIGITAL DATA PROCESSING
3Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
01Input arrangements or combined input and output arrangements for interaction between user and computer
G06N 3/04 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architecture, e.g. interconnection topology
G06N 3/08 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
CPC
G06F 3/013
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
3Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
01Input arrangements or combined input and output arrangements for interaction between user and computer
011Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
013Eye tracking input arrangements
G06N 3/0445
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
0445Feedback networks, e.g. hopfield nets, associative networks
G06N 3/0454
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
0454using a combination of multiple neural nets
G06N 3/084
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
084Back-propagation
Applicants
  • INIVATION AG [CH]/[CH]
Inventors
  • DEBRUNNER, Thomas
  • GIRAUD, Pierre
  • LI, Chenghan
  • ENG, Kynan
Agents
  • ADARES PATENT- UND RECHTSANWÄLTE REININGER & PARTNER GMBB
Priority Data
20184020.403.07.2020EP
Publication Language English (en)
Filing Language English (EN)
Designated States
Title
(EN) EYE TRACKING DEVICE, EYE TRACKING METHOD, AND COMPUTER-READABLE MEDIUM
(FR) DISPOSITIF DE SUIVI OCULAIRE, PROCÉDÉ DE SUIVI OCULAIRE ET SUPPORT LISIBLE PAR ORDINATEUR
Abstract
(EN) The invention relates to an eye tracking device, an eye tracking method, and a computer-readable medium. The eye tracking device comprises an event-based optical sensor (1 ), which is configured to receive radiation (12) reflected off an eye (2) of a user and produce a signal stream (3) of events (31 ), each event (31 ) corresponding to detection of a temporal change in the received radiation at one or more pixels of said optical sensor (1 ), and a controller (4), which is connected to said optical sensor (1 ) and configured to: a) receive the signal stream (3) of events (31 ) from said optical sensor (1 ), b) generate an inference frame (61 ) based on at least a portion of said stream (3) of events (31 ), c) utilize said inference frame (61 ) as input to a machine learning module (6) and operate said machine learning module (6) to obtain output data, and e) extract from said output data information related to said eye (2) of said user, wherein said controller (4) is configured to generate said inference frame (61 ) utilizing a first artificial neural network (5).
(FR) La présente invention concerne un dispositif de suivi oculaire, un procédé de communication sans fil et un support lisible par ordinateur. Le dispositif de suivi oculaire comprend un capteur optique basé sur un événement (1 ), qui est conçu pour recevoir un rayonnement (12) réfléchi par un œil (2) d'un utilisateur et produire un flux de signaux (3) d'événements (31), chaque événement (31 ) correspondant à la détection d'un changement temporel dans le rayonnement reçu au niveau d'un ou de plusieurs pixels dudit capteur optique (1), et un dispositif de commande (4), qui est relié audit capteur optique (1) et configuré pour : a) recevoir le flux de signaux (3) d'événements (31) à partir dudit capteur optique (1), b) générer une trame d'inférence (61) sur la base d'au moins une partie dudit flux (3) d'événements (31), c) utiliser ladite trame d'inférence (61) en tant qu'entrée à un module d'apprentissage machine (6) et faire fonctionner ledit module d'apprentissage machine (6) pour obtenir des données de sortie, et e) extraire desdites données de sortie des informations relatives audit œil (2) dudit utilisateur, ledit dispositif de commande (4) étant configuré pour générer ladite trame d'inférence (61) à l'aide d'un premier réseau neuronal artificiel (5).
Related patent documents
Latest bibliographic data on file with the International Bureau