VR scene automatic explanation method and system, and storage medium

A scene, automatic technology, applied in the field of virtual reality VR and artificial intelligence, can solve the problem of difficult voice playback sequence, increase communication costs, etc.

Inactive Publication Date: 2020-10-13
BEIJING CHUANSONG TECH
View PDF2 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] For example, for an existing VR scene of a model room in the field of home decoration, the traditional solution is that when customers experience the VR scene, the staff will give targeted explanations to the customer according to the screen information mapped on the screen. If 100 people are received a day, The staff need to explain 100 times, which greatly increases the communication cost. Another alternative is that the staff choose to record the explanation content in advance, and then control the playback of the corresponding recording when the user experiences VR. Considering that customers may not It will not be experienced in the order set, so it is difficult to control the order of voice playback

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • VR scene automatic explanation method and system, and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0038] The present invention implements a real-time VR intelligent commentary system, which uses computer vision technology to classify and recognize objects in real-time VR scene pictures, and then plays corresponding commentary recordings according to the recognition results. The system consists of three modules, and its general workflow is as follows: (1) VR picture extraction module. Use appropriate methods to capture VR images. For example, you can capture the rendered VR images through openVR SDK, openGL, DirectX rendering engine, etc., or you can use a video capture card to capture the images displayed by VR programs on the screen or glasses. (2) VR scene recognition module. Assuming that the number of scenes that need to be automatically explained in the VR scene is N, the scene content recognition module is trained by extracting and synthesizing the features of each target. During the operation of the system, the VR images captured in real time are input into the sce...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention relates to a VR scene automatic explanation method and system, and a storage medium. The method comprises the steps: obtaining the three-dimensional data of a target object in a to-be-explained VR scene and a corresponding category, and obtaining a scene content recognition module through training according to the target features of the three-dimensional data; obtaining a VR picturewatched by a user in real time, inputting the VR picture into the scene content identification module, judging whether the target object exists in the VR picture or not, if so, playing explanation content corresponding to the target object to the user according to the category of the target object, otherwise, continuing to obtain the VR picture being watched by the user in real time, inputting theVR picture into the scene content recognition module, and judging whether the target object exists in the VR picture or not. According to the invention, no requirement is required for manufacturing of an original VR scene, and VR picture extraction is carried out on the premise of not changing an original VR application. Scene classification is realized by means of feature recognition or machinelearning and the like.

Description

technical field [0001] The invention relates to the fields of virtual reality VR and artificial intelligence, and uses artificial intelligence to identify VR scene content, thereby providing personalized services, and particularly relates to a VR scene automatic interpretation method, system and storage medium. Background technique [0002] Self-service commentary systems are not uncommon in the market, and are widely used in large scenic spots or exhibition halls. This type of system usually obtains the coordinates of users through GPS positioning modules or radio frequency identification technology, and then plays pre-recorded voice content, such as patent 01274768.8 Disclosed is an electronic tour guide device, which realizes position positioning through radio or infrared coding. Patent 200310110653.7 uses GPS positioning technology to locate tourists, and then plays corresponding voice data. Most of these self-help commentary systems are based on the real natural world....

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G09F25/00G09F27/00G06N3/04G06N3/08
CPCG09F25/00G09F27/00G06N3/08G06N3/045
Inventor 邓涛周鹏冀德
Owner BEIJING CHUANSONG TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products