Floor Detection in VR Devices Using Stereo Image Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current mechanisms for detecting the real-world floor in AR and VR devices often result in inaccurate identification, leading to less immersive experiences, inefficient use of computing resources, and user frustration, as they rely on approximations or user input that can be erroneous.
Innovation Solution
A method and system using stereo images to automatically detect the 3D plane corresponding to the floor, perpendicular to the gravity vector, by evaluating candidate planes through texture-mapped projections and image similarity scoring, reducing the need for user input and improving accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If current floor detection mechanisms are used (asking user to hold device toward computer or manually input height), then the device can be operated, but the floor detection accuracy deteriorates leading to incorrect virtual floor placement
Solution Approach 1:
The system performs self-measurement by automatically detecting the floor plane using the camera and processing images to determine the floor's position and orientation in 3D space, eliminating the need for user input about height or manual device positioning
Solution Approach 2:
The patent replaces manual mechanical measurement methods (holding device at specific angles, user input) with an automated vision-based system that uses image processing and plane detection algorithms to automatically determine floor characteristics
2Measurement precision
If floor detection is repeated due to inaccurate identification, then detection accuracy can be improved, but computing resource usage increases
Solution Approach 1:
The system uses feedback from image analysis and plane detection to automatically verify floor detection accuracy, reducing the need for repeated detection procedures and associated computing resource consumption
Solution Approach 2:
The system performs preliminary filtering and processing of candidate planes to identify the most likely floor plane early in the detection process, reducing computational overhead by eliminating the need for multiple full detection cycles
Data Source
Figure 1A
Figure 1B
Figure 1C
AI summary
A first image and a second image of a scene are obtained for use in detecting the location of the floor in the scene. A first of the images is mapped onto a candidate plane that is perpendicular to a gravity vector, thereby creating a texture-mapped plane. The texture-mapped plane is projected into the geometry of the camera utilized to take the second image to create an artificial first image. A comparison is then performed between the first image and the artificial first image to generate a similarity score. Multiple candidate planes are processed in this manner for the first and second images, and the candidate plane generating the highest associated similarity score is chosen as the floor. This process can be repeated for multiple sets of stereo images.