Structure Line Pose Prediction for AR Devices
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems for determining the pose of a user's client device in augmented reality applications are computationally expensive and require significant data storage due to the use of complex machine-learning models for image matching.
Innovation Solution
The use of structure lines generated from captured images and a structure model to predict the pose of a client device, where structure lines delineate structures in the physical world and the structure model represents structures in the physical world within an area, applying an objective function to score the fit of the structure lines to the structure model.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If complex machine-learning models are used to match images for pose determination, then measurement precision is improved, but computational complexity and data storage requirements increase
Solution Approach 1:
The patent extracts only the essential structural information (lines representing building edges, corners, and geometric features) from complete images, rather than processing entire images through complex machine-learning models. This extraction of key structural elements reduces computational complexity while maintaining pose determination accuracy by focusing on the most discriminative features.
Solution Approach 2:
The patent creates simplified line-based representations (copies) of the physical environment's structural features and stores these in a virtual model. Instead of storing and processing complete images, the system uses these simplified line copies for matching, significantly reducing data storage requirements and computational complexity while preserving the essential geometric information needed for accurate pose determination.
2Measurement precision
If complete images are stored for matching, then measurement precision is improved, but data storage requirements increase
Solution Approach 1:
The patent extracts only the essential structural information (lines representing building edges, corners, and geometric features) from complete images, rather than processing entire images through complex machine-learning models. This extraction of key structural elements reduces computational complexity while maintaining pose determination accuracy by focusing on the most discriminative features.
Solution Approach 2:
The patent creates simplified line-based representations (copies) of the physical environment's structural features and stores these in a virtual model. Instead of storing and processing complete images, the system uses these simplified line copies for matching, significantly reducing data storage requirements and computational complexity while preserving the essential geometric information needed for accurate pose determination.
Data Source
AI summary
A client device, or an online system, uses structure lines that are generated based on an image to predict a pose of the client device. Structure lines are lines that delineate structures in the physical world depicted in the image. The client device also uses a structure model to predict its pose. A structure model is a model that represents structures in the physical world within an area. The client device predicts its pose based on the structure model and the structure lines by applying an objective function. The client device may then iteratively update the estimated pose and score the updated poses until the client device identifies an estimated pose at which the structure lines sufficiently fit the structure model.