一种MR设备动作识别的方法、装置、MR设备及存储介质

By using a combination of multiple image acquisition devices in an MR device, the problem of virtual scene feedback when the user's hand is not within the acquisition range was solved, enabling a wider range of user operations and higher recognition accuracy.

CN115599220BActive Publication Date: 2026-07-17BEIJING SWEET TECH CO LTD

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
BEIJING SWEET TECH CO LTD
Filing Date
2022-11-04
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

When recognizing user gestures, MR devices cannot perform effective analysis if the user's hand is not within the acquisition range, resulting in the virtual scene being unable to respond to the user's gesture operations.

Method used

By acquiring and analyzing images from the first image acquisition device, it is determined whether the hand is within the acquisition range. If not, images from the second image acquisition device are acquired and analyzed to determine the operation gesture, and the virtual scene is updated based on the gesture.

Benefits of technology

Even if the user's hands are not within the range of the first image acquisition device, they can still interact with the virtual scene, increasing the user's range of operation and improving the accuracy of gesture recognition.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115599220B_ABST
    Figure CN115599220B_ABST
Patent Text Reader

Abstract

本申请涉及一种MR设备动作识别的方法、装置、MR设备及存储介质,涉及混合现实领域,该方法包括获取当前第一图像采集装置采集的第一图像,对第一图像进行分析,判断第一图像内是否存在用户的手部图像,若否,则获取第二图像采集装置采集的第二图像,对第二图像进行分析,确定用户的操作手势,基于操作手势,对虚拟场景进行更新。本申请通过对多个图像采集装置进行控制,达到MR设备可识别范围扩大的效果。
Need to check novelty before this filing date? Find Prior Art