AR Object Tagging in Digital Twins for Easy Building Capture
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing building information models are limited in their extensibility and require onerous data entry processes, making it difficult for untrained users to capture comprehensive information about buildings for various applications.
Innovation Solution
An augmented reality method for scanning buildings into digital twins, enabling easy tagging and capturing information about real-world objects using a processor, camera, and depth sensor, allowing users to tag objects within the physical space and store their locations and labels in the digital twin.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If traditional building information models are used to capture building information, then the overall layout and standard information can be captured, but the process is onerous and difficult for untrained users
Solution Approach 1:
The patent uses augmented reality to create a digital twin (copy) of the physical building space. The system captures the physical environment through camera imaging and creates a virtual representation that can be annotated with building information, eliminating the need for manual data entry while preserving comprehensive building information.
Solution Approach 2:
The system enables untrained users to capture building information themselves through the augmented reality interface. Users can annotate objects and spaces directly in the AR view, and the system automatically processes and stores this information, making the user self-sufficient without requiring specialized training or complex tools.
2Loss of information
If manual data entry methods are used for building information, then comprehensive information can be captured, but the process is time-consuming and complex
Solution Approach 1:
The system creates a digital copy of the physical building environment using augmented reality and camera imaging. Objects in the physical space are automatically captured and represented in the digital twin, eliminating manual data entry while preserving complete object information including spatial relationships and attributes.
Solution Approach 2:
The system performs preliminary capture of building information through automated imaging and AR annotation during the scanning process. Object information is captured in advance through the digital twin creation process, eliminating the need for subsequent manual data entry and significantly reducing the time required to obtain complete building information.
3Adaptability or versatility
If existing building information models are used, then standard information can be captured, but the models are not extensible to other applications
Solution Approach 1:
The augmented reality digital twin system is designed to be universally applicable to multiple applications beyond traditional building information modeling. The same AR platform can capture and represent various types of information including object locations, tracking data, and guidance information, making the system extensible to diverse applications without requiring separate specialized systems.
Solution Approach 2:
The patent adds a new dimension to building information models by integrating augmented reality and spatial annotation capabilities. This transforms traditional 2D building information models into immersive 3D AR experiences with layered information, enabling extensibility to applications like object tracking and navigation without significantly increasing system complexity.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables untrained users to easily create and maintain comprehensive digital twins, facilitating downstream applications such as object location, tracking, and augmented reality guidance.
Implementation Method 1
determine a distance from a location of the camera to a location of the object
Data Source
AI summary
Various embodiments relate to a method, apparatus, and machine-readable storage medium including one or more of the following: receiving, from a user, a command to tag an object currently in view of a camera and located within a physical space; in response to the command, determining a distance from a location of the camera to a location of the object; determining the location of the object based on the determined distance; storing the location of the object and a label together as a tag in a digital twin representing the physical space; displaying a representation of the physical space; and displaying an indicator of the tag at a location in the representation of the physical space corresponding to the location of the object.