Plane Identification Using Vanishing Points in AR
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing artificial reality systems face challenges in identifying plane surfaces within images to effectively blend virtual objects with the real world, often requiring stereo and depth computations or Simultaneous Localization And Mapping (SLAM) techniques, which are resource-intensive and complex.
Innovation Solution
A computing device identifies planes in a single image using detected straight-line segments and vanishing points, allowing for the placement of virtual objects on identified planar regions without the need for multiple cameras or extensive depth calculations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If stereo and depth computations or SLAM techniques are used to identify planes, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent extracts only the essential geometric features (straight-line segments and vanishing points) needed for plane identification, discarding the complex stereo and depth computation processes. By taking out only the necessary computational elements, the system achieves plane identification without requiring full stereo vision or SLAM implementations, thus reducing device complexity while maintaining measurement precision.
Solution Approach 2:
The patent uses vanishing points as a simplified copy or representation of three-dimensional spatial relationships. Instead of computing full depth information from multiple cameras, the system creates a two-dimensional projection copy of spatial geometry through vanishing points, which preserves enough information for plane identification while avoiding the complexity of three-dimensional reconstruction.
2Measurement precision
If stereo computations are used to identify planes, then measurement precision is improved, but use of energy increases
Solution Approach 1:
The patent extracts only the essential geometric features (straight-line segments and vanishing points) needed for plane identification, discarding the complex stereo and depth computation processes. By taking out only the necessary computational elements, the system achieves plane identification without requiring full stereo vision or SLAM implementations, thus reducing device complexity while maintaining measurement precision.
3Measurement precision
If multiple cameras are used for plane identification, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent makes a single camera perform the work that would traditionally require multiple cameras by extracting vanishing points from two-dimensional image data. The single camera system achieves multi-functionality by simultaneously capturing images and deriving three-dimensional geometric information through vanishing point analysis, eliminating the need for multiple cameras while maintaining plane identification capability.
Solution Approach 2:
The patent uses vanishing points as a simplified copy or representation of three-dimensional spatial relationships. Instead of computing full depth information from multiple cameras, the system creates a two-dimensional projection copy of spatial geometry through vanishing points, which preserves enough information for plane identification while avoiding the complexity of three-dimensional reconstruction.
Data Source
AI summary
In one embodiment, a method includes accessing an image of a physical world scene, detecting a number of straight-line segments in the accessed image, identifying a first vanishing point and a second vanishing point in the image, where each vanishing point corresponds to a sub-set of the number of straight-line segments, and where the first vanishing point and the second vanishing point are orthogonal, identifying a planar region in the accessed image represented by one or more straight-line segments associated with the first vanishing point and one or more straight-line segments associated with the second vanishing point, transforming a virtual object associated with the planar region based on one or more properties associated with the planar region, and displaying the transformed virtual object over the image.