Supercharge Your Innovation With Domain-Expert AI Agents!

Scene graph optimization method based on relationship constraints in virtual reality and augmented reality scenes

A technology of virtual reality and augmented reality, applied in the field of scene map optimization based on relationship constraints, can solve the problems of limited scene map expression ability and poor practicability, and achieve the effects of good practicability, quality improvement and optimization effectiveness

Active Publication Date: 2020-05-08
SUN YAT SEN UNIV
View PDF9 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, there is currently no good technical solution that can generate high-quality scene graphs, specifically:
[0006] (1) The existing scene graph generation methods only use image information, resulting in the generated scene graph containing many conflicting object relationship groups, which is not practical
[0007] (2) The object relation group of the scene graph itself implies relational constraints, which can help improve the quality of the scene graph, but the existing methods do not fully consider and utilize these relational constraints, which limit the expressive ability of the scene graph

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
  • Scene graph optimization method based on relationship constraints in virtual reality and augmented reality scenes
  • Scene graph optimization method based on relationship constraints in virtual reality and augmented reality scenes
  • Scene graph optimization method based on relationship constraints in virtual reality and augmented reality scenes

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] In order to make the objectives, technical solutions and advantages of the present invention more clear and complete, the present invention will be further described below in conjunction with the accompanying drawings and examples, but the embodiments of the present invention are not limited thereto. In addition, it should be noted that, for ease of description, only parts relevant to the present application are shown in the drawings. For those of ordinary skill in the art, it is understandable that certain known structures and their descriptions may be omitted in the drawings.

[0024] The invention provides a scene map optimization method based on relationship constraints in virtual reality and augmented reality scenes. In this embodiment, all images of the scene graph sample dataset are denoted as Imgs, the set of scene graphs is denoted as G, the set of object categories is denoted as C, the set of relational categories is denoted as R, and the scene graph of image ...

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 discloses a scene graph optimization method based on relation constraints in virtual reality and augmented reality scenes, and relates to the field of scene graphs. The method comprisesthe following steps: inputting a scene atlas sample data set which comprises image information and object relation group information; extracting relationship constraints by utilizing the object relationship group, wherein the relationship constraints comprise 1-m relationship constraints, m-1 relationship constraints and 1-1 relationship constraints; training a scene graph generation model based on the relationship constraints; detecting an object contained in the virtual reality and augmented reality scene graph by using a target detection model; generating an initial scene graph of the virtual reality and augmented reality scene graph by using a trained scene graph generation model based on the detected object; and further optimizing the initial scene graph by using the relationship constraints, and removing the object relationship group violating the relationship constraints to obtain a final scene graph. According to the invention, for the images captured in virtual reality and augmented reality scenes, the scene graph generated based on the relation constraint optimization model is proposed for the first time, and the quality of the scene graph is effectively improved.

Description

technical field [0001] The present invention relates to the field of artificial intelligence, and more specifically, to a scene map optimization method based on relationship constraints in virtual reality and augmented reality scenes. Background technique [0002] Both virtual reality technology and augmented reality technology are representatives of contemporary digital technology. Virtual reality can generate an interactive three-dimensional environment for users through the comprehensive use of computer graphics systems and various control devices. Augmented reality augments reality by superimposing computer-generated virtual objects, scenes or information onto real ones. In order to make the scenes under virtual reality and augmented reality better perceived by humans, it is necessary for the system to understand the scene, and building a scene map is a key step in understanding the scene. [0003] A scene graph is an abstract, structured representation of the scene de...

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): G06F16/532
CPCG06F16/532
Inventor 万海王宝亿曾娟欧佳玲
Owner SUN YAT SEN UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More