Processing

Please wait...

Settings

Settings

Goto Application

1. WO2021002733 - DEVICE AND METHOD FOR RECOGNIZING GESTURE IN AIR

Publication Number WO/2021/002733
Publication Date 07.01.2021
International Application No. PCT/KR2020/008800
International Filing Date 06.07.2020
IPC
G01S 7/41 2006.01
GPHYSICS
01MEASURING; TESTING
SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
7Details of systems according to groups G01S13/, G01S15/, G01S17/127
02of systems according to group G01S13/58
41using analysis of echo signal for target characterisation; Target signature; Target cross-section
G06K 9/00 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
G01S 7/28 2006.01
GPHYSICS
01MEASURING; TESTING
SRADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
7Details of systems according to groups G01S13/, G01S15/, G01S17/127
02of systems according to group G01S13/58
28Details of pulse systems
G06N 3/02 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
Applicants
  • 한양대학교 산학협력단 INDUSTRY-UNIVERSITY COOPERATION FOUNDATION HANYANG UNIVERSITY [KR]/[KR]
Inventors
  • 조성호 CHO, Sung Ho
  • 칸파임 KHAN, Faheem
  • 콴수안준 QUAN, Xuanjun
Agents
  • 민영준 MIN, Young Joon
Priority Data
10-2019-008066204.07.2019KR
Publication Language Korean (KO)
Filing Language Korean (KO)
Designated States
Title
(EN) DEVICE AND METHOD FOR RECOGNIZING GESTURE IN AIR
(FR) DISPOSITIF ET PROCÉDÉ POUR RECONNAÎTRE UN GESTE DANS L'AIR
(KO) 공중 제스쳐 인식 장치 및 방법
Abstract
(EN)
The present invention may provide a device and method for recognizing a gesture in the air, which converts a three-dimensional gesture generated in the air into a two-dimensional image, and determines the gesture by using an artificial neural network which has learned a pattern estimation method in advance, thereby being capable of accurately and robustly recognizing the gesture in the air despite changes in an angle, a distance, and a hand shape, and which recognizes the gesture in a user-independent manner, thereby being capable of recognizing the gesture in the air regardless of a type of gesture which may differ according to users.
(FR)
La présente invention peut fournir un dispositif et un procédé pour reconnaître un geste dans l'air, qui convertit un geste tridimensionnel généré dans l'air en une image bidimensionnelle, et détermine le geste en utilisant un réseau neuronal artificiel qui a appris un procédé d'estimation de motif à l'avance, ce qui permet de reconnaître précisément et de manière robuste le geste dans l'air malgré les changements d'angle, de distance et de forme de main, et qui reconnaît le geste de manière indépendante de l'utilisateur, ce qui permet de reconnaître le geste dans l'air indépendamment d'un type de geste qui peut différer selon les utilisateurs.
(KO)
본 발명은 공중에서 발생된 3차원 제스쳐를 2차원의 이미지로 변환하고, 패턴 추정 방식이 미리 학습된 인공 신경망을 이용하여 제스처를 판별함으로써, 각도, 거리, 손 모양의 변화에 강건하게 공중 제스쳐를 정확하게 인식할 수 있으며, 사용자 독립적으로 제스쳐를 인식하여 사용자별로 상이할 수 있는 제스쳐 형태에 무관하게 공중 제스쳐를 인식할 수 있는 공중 제스쳐 인식 장치 및 방법을 제공할 수 있다.
Latest bibliographic data on file with the International Bureau