AR Scene Matching via Multi-Coordinate System Segmentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current augmented and mixed reality technologies lack high-precision methods for matching and positioning remote scenes, resulting in inaccurate alignment between virtual and real scenes.

Innovation Solution

Establishing multiple coordinate systems, including a global coordinate system, camera coordinate system, and environmental coordinate system, with physical and virtual marks to determine precise position relationships, and using correction methods like reverse-fitting adjustment, multi-mark-points matching, and multiple-users-assisted deployment to achieve accurate alignment.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If local matching and positioning using landmarks or specific patterns and textures is used, then the method is simple to implement, but the positioning accuracy is limited to meter level

Engineering Contradiction:
Improvepositioning accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent divides the positioning system into multiple independent modules: global coordinate system establishment, camera coordinate system establishment, environmental coordinate system establishment, and mark point matching modules. Each module handles a specific aspect of positioning, allowing the system to achieve high precision through coordinated operation of segmented functions rather than a monolithic complex system.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces mark points as intermediary elements that connect different coordinate systems. These mark points serve as mediators between the global coordinate system, camera coordinate system, and environmental coordinate system, enabling precise positioning through their known positions in multiple frames of reference without requiring direct complex measurements between all systems.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Manufacturing precision

If remote scene matching is performed without high-precision methods, then the implementation is straightforward, but the virtual and real scenes cannot be accurately aligned

Engineering Contradiction:
Improvescene matching precisionVSAvoidcoordinate system management complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The patent merges multiple coordinate systems (global, camera, environmental) into a unified positioning framework. By combining these coordinate systems and establishing their relative transformations through mark points, the system achieves precise scene matching while managing complexity through integration rather than isolation of individual systems.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent performs preliminary actions by pre-establishing the global coordinate system and pre-positioning mark points in the environment before the actual positioning operation. This preliminary setup includes determining the positions of mark points in the global coordinate system and preparing the coordinate transformation parameters, which enables high-precision matching during execution without requiring complex real-time calculations.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS11288877B2Method for matching a virtual scene of a remote scene with a real scene for augmented reality and mixed reality
Publication Date: 2022.03.29 CHINA ELECTRONIC TECH GRP CORP NO 38 RES INST
  • US11288877B2 patent drawing
  • US11288877B2 patent drawing
  • US11288877B2 patent drawing

AI summary

Provided is a method for matching a virtual scene of a remote scene with a real scene for augmented reality and mixed reality. Multiple coordinate systems are established and a position relationship between the multiple coordinate systems is determined. A position of a point cloud scene in the near-side environmental space and the position of the near-side virtual scene are determined in the near-side environmental space through real marks, so as to realize the high-precision matching and positioning for augmented reality and mixed reality. Based on the position of objects marked in the real space, the method realizes adaptive and accurate positioning of the virtual objects in the augmented reality and mixed reality by overcoming spatial barriers. The scene in the virtual space is accurately superimposed into the near-side environmental space.