Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
METHODS AND SYSTEMS FOR MULTIMODAL HAND STATE PREDICTION
Document Type and Number:
WIPO Patent Application WO/2023/178984
Kind Code:
A1
Abstract:
Methods and systems are described for generating hand state predictions. A hand state prediction system (200) includes a machine learning-based model, such as a neural network model, that is trained to convert inertial motion measurements and surface contact data into predictions of a corresponding hand gesture or gripping posture. For each window of data sampled, motion data (230) and contact data (250) are obtained, processed and fused to generate a fused prediction. The hand state prediction system (200) can operate in continuous mode to automatically detect a start and an end of a hand action, or a user can designate a start and an end of a hand action. The hand state predictions are generated by a multimodal classifier (360) by processing the fused prediction. Instructions represented by a hand action can be acted upon through a command action performed by a computing device or a computer application.

Inventors:
CODY ROYA (CA)
HUANG DA-YUAN (CA)
CAO XIANG (CA)
LI WEI (CA)
Application Number:
PCT/CN2022/123548
Publication Date:
September 28, 2023
Filing Date:
September 30, 2022
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
HUAWEI TECH CO LTD (CN)
International Classes:
G06F3/01
Foreign References:
US20220043517A12022-02-10
CN113849068A2021-12-28
CN106598243A2017-04-26
CN106575200A2017-04-19
CN112114665A2020-12-22
CN112492090A2021-03-12
CN113205074A2021-08-03
US20080211766A12008-09-04
KR20200005243A2020-01-15
Download PDF: