Processing

Please wait...

Settings

Settings

Goto Application

1. WO2022255641 - METHOD AND APPARATUS FOR ENHANCING HAND GESTURE AND VOICE COMMAND RECOGNITION PERFORMANCE, FOR INPUT INTERFACE OF AUGMENTED REALITY GLASS DEVICE

Publication Number WO/2022/255641
Publication Date 08.12.2022
International Application No. PCT/KR2022/005822
International Filing Date 24.04.2022
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
G02B 27/01 2006.1
GPHYSICS
02OPTICS
BOPTICAL ELEMENTS, SYSTEMS, OR APPARATUS
27Optical systems or apparatus not provided for by any of the groups G02B1/-G02B26/119
01Head-up displays
G06F 3/00 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
G06F 3/16 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
16Sound input; Sound output
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
G06T 19/00 2011.1
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
19Manipulating 3D models or images for computer graphics
CPC
G02B 27/01
GPHYSICS
02OPTICS
BOPTICAL ELEMENTS, SYSTEMS, OR APPARATUS
27Optical systems or apparatus not provided for by any of the groups G02B1/00 - G02B26/00, G02B30/00
01Head-up displays
G06F 3/00
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
G06F 3/01
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
G06F 3/16
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
16Sound input; Sound output
G06N 3/08
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
G06T 19/00
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
19Manipulating 3D models or images for computer graphics
Applicants
  • 주식회사 피앤씨솔루션 P&C SOLUTION [KR]/[KR]
Inventors
  • 최치원 CHOI, Chiwon
  • 김정환 KIM, Jeong Hwan
  • 이강휘 LEE, Kang Hwi
  • 백지엽 BACK, Jee Yeop
  • 조성동 JO, Seong Dong
  • 민경진 MIN, Kyoung Jin
Agents
  • 김건우 KIM, Keon Woo
Priority Data
10-2021-007307004.06.2021KR
Publication Language Korean (ko)
Filing Language Korean (KO)
Designated States
Title
(EN) METHOD AND APPARATUS FOR ENHANCING HAND GESTURE AND VOICE COMMAND RECOGNITION PERFORMANCE, FOR INPUT INTERFACE OF AUGMENTED REALITY GLASS DEVICE
(FR) PROCÉDÉ ET APPAREIL PERMETTANT D'AMÉLIORER LES PERFORMANCES DE RECONNAISSANCE DE MOUVEMENT DE LA MAIN ET DE COMMANDE VOCALE, DESTINÉS À UNE INTERFACE D'ENTRÉE D'UN DISPOSITIF DE VERRE À RÉALITÉ AUGMENTÉE
(KO) 증강현실 글라스 장치의 입력 인터페이스를 위한 손동작 및 음성명령어 인식 성능 향상 방법 및 장치
Abstract
(EN) According to a method and apparatus for enhancing a hand gesture and voice command recognition performance, for an input interface of an augmented reality glass device, which are proposed in the present invention, a hand gesture and a voice command are recognized by additionally training, using wearer data consisting of hand gesture image data and voice command signal data of a wearer wearing the augmented reality glass device, a pre-trained hand gesture recognition model and a pre-trained voice command recognition model and updating weights, and thus performances of the hand gesture and voice command recognition models can be increased according to a specific situation or specific wearer in the augmented reality glass device, and security of personal data can be reinforced since there is no need to transmit the wearer data to a server or the like.
(FR) Selon un procédé et un appareil permettant d'améliorer les performances de reconnaissance d'un mouvement de la main et de commande vocale, destinés à une interface d'entrée d'un dispositif de verre à réalité augmentée, qui sont proposés dans la présente invention, un mouvement de la main et une commande vocale sont reconnus par une formation supplémentaire, à l'aide de données d'un porteur constituées de données d'image de mouvement de main et de données de signal de commande vocale d'un porteur portant le dispositif de verre à réalité augmentée, un modèle de reconnaissance de mouvement de la main pré-formé et un modèle de reconnaissance de commande vocale pré-formé et des poids de mise à jour, et ainsi les performances du mouvement de la main et des modèles de reconnaissance de commande vocale peuvent être augmentés selon une situation spécifique ou un porteur spécifique dans le dispositif de verre à réalité augmentée, et la sécurité des données personnelles peut être renforcée étant donné qu'il n'est pas nécessaire de transmettre les données du porteur à un serveur ou similaire.
(KO) 본 발명에서 제안하고 있는 증강현실 글라스 장치의 입력 인터페이스를 위한 손동작 및 음성명령어 인식 성능 향상 방법 및 장치에 따르면, 증강현실 글라스 장치를 착용한 착용자의 손동작 영상 데이터 및 음성명령어 신호 데이터로 구성되는 착용자 데이터로, 사전 학습된 손동작 인식 모델 및 음성명령어 인식 모델을 추가 학습해 가중치를 업데이트하여 손동작 및 음성명령어 인식을 수행함으로써, 증강현실 글라스 장치 내에서 특정 상황 또는 특정 착용자에 맞추어 손동작 및 음성명령어 인식 모델의 성능을 높일 수 있고, 착용자 데이터를 서버 등에 송신할 필요가 없으므로 개인 데이터의 보안을 강화할 수 있다.
Related patent documents
Latest bibliographic data on file with the International Bureau