Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020140798 - GESTURE RECOGNITION METHOD, DEVICE, ELECTRONIC APPARATUS, AND STORAGE MEDIUM

Publication Number WO/2020/140798
Publication Date 09.07.2020
International Application No. PCT/CN2019/128029
International Filing Date 24.12.2019
IPC
G06K 9/62 2006.1
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
62Methods or arrangements for recognition using electronic means
CPC
G06F 3/017
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
017Gesture based interaction, e.g. based on a set of recognized hand gestures
G06K 9/00
GPHYSICS
06COMPUTING; CALCULATING; 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
G06K 9/00201
GPHYSICS
06COMPUTING; CALCULATING; 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
00201Recognising three-dimensional objects, e.g. using range or tactile information
G06K 9/00355
GPHYSICS
06COMPUTING; CALCULATING; 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
00335Recognising movements or behaviour, e.g. recognition of gestures, dynamic facial expressions; Lip-reading
00355Recognition of hand or arm movements, e.g. recognition of deaf sign language
G06K 9/00375
GPHYSICS
06COMPUTING; CALCULATING; 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
00362Recognising human body or animal bodies, e.g. vehicle occupant, pedestrian; Recognising body parts, e.g. hand
00375Recognition of hand or arm, e.g. static hand biometric or posture recognition
G06K 9/62
GPHYSICS
06COMPUTING; CALCULATING; 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
62Methods or arrangements for recognition using electronic means
Applicants
  • 北京达佳互联信息技术有限公司 BEIJING DAJIA INTERNET INFORMATION TECHNOLOGY CO., LTD. [CN]/[CN]
Inventors
  • 刘裕峰 LIU, Yufeng
  • 郑文 ZHENG, Wen
Agents
  • 北京同达信恒知识产权代理有限公司 TDIP & PARTNERS
Priority Data
201910009529.204.01.2019CN
Publication Language Chinese (ZH)
Filing Language Chinese (ZH)
Designated States
Title
(EN) GESTURE RECOGNITION METHOD, DEVICE, ELECTRONIC APPARATUS, AND STORAGE MEDIUM
(FR) PROCÉDÉ DE RECONNAISSANCE DE GESTE, DISPOSITIF, APPAREIL ÉLECTRONIQUE ET SUPPORT D'INFORMATIONS
(ZH) 手势识别方法、装置、电子设备及存储介质
Abstract
(EN)
A gesture recognition method, a device, an electronic apparatus, and a storage medium. The gesture recognition method comprises: acquiring a hand image (S101); adopting a feature mapping model, and extracting a first standard feature of a hand, the feature mapping model being obtained from pre-training with respect to second standard features of hands in synthesized image samples and real image samples (S102); processing the first standard feature, and obtaining three-dimensional coordinates of multiple key points of the hand (S103); and determining a hand gesture according to the three-dimensional coordinates of each of the key points (S104). In the method, common hand features are adopted from synthesized images and real images to perform model training, thereby eliminating differences between synthesized images and real images in terms of standard features, and accordingly improving the accuracy of hand gesture recognition in weak supervision scenarios. The method does not require synthesized image samples and real image samples to have an entirely consistent gesture, thereby relaxing requirements on training data sets. The method is further applicable to gesture recognition using color images and thus has a wider range of applications.
(FR)
L'invention concerne un procédé de reconnaissance de geste, un dispositif, un appareil électronique et un support d'informations. Le procédé de reconnaissance de geste consiste à : acquérir une image de main (S101) ; adopter un modèle de mappage de caractéristiques, et extraire une première caractéristique standard d'une main, le modèle de mappage de caractéristiques étant obtenu à partir d'un pré-apprentissage par rapport à des secondes caractéristiques standard de mains contenues dans des échantillons d'images synthétisées et dans des échantillons d'images réelles (S102) ; traiter la première caractéristique standard, et obtenir des coordonnées tridimensionnelles de multiples points clés de la main (S103) ; et déterminer un geste de la main conformément aux coordonnées tridimensionnelles de chacun des points clés (S104). Selon le procédé, des caractéristiques de main communes sont adoptées à partir d'images synthétisées et d'images réelles pour effectuer un apprentissage de modèle, ce qui permet d'éliminer des différences entre des images synthétisées et des images réelles en termes de caractéristiques standard, et d'améliorer ainsi la précision de la reconnaissance de geste de la main dans des scénarios de supervision faible. Le procédé ne nécessite pas d'échantillon d'image synthétisée ni d'échantillon d'image réelle pour obtenir un geste entièrement cohérent, ce qui permet d'amoindrir des exigences concernant des ensembles de données d'apprentissage. Le procédé est en outre applicable à la reconnaissance de geste à l'aide d'images couleurs et offre ainsi une plus large gamme d'applications.
(ZH)
一种手势识别方法、装置、电子设备及存储介质,其中手势识别方法包括:获取手部图像(S101);采用特征映射模型,提取手部的第一标准特征;特征映射模型是根据合成图像样本和真实图像样本中手部的第二标准特征预先训练得到的(S102);对第一标准特征进行处理,获得手部多个关键点的三维坐标(S103);根据各关键点的三维坐标,确定手部的姿势(S104)。该方法由于采用合成图像与真实图像中手部的共同特征进行模型训练,在标准特征层面消除了合成图像与真实图像之间的差异,从而可以提升弱监督情形下手势识别的准确率;并且该方法不需要手势完全一致的合成图像样本与真实图像样本,放宽了对训练数据集的要求;该方法还适用于彩色图像的手势识别,应用面更广泛。
Latest bibliographic data on file with the International Bureau