Continuous Surface And Depth Estimation Using Windowed Stereo Vision
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current techniques for determining depth and surface normal in augmented reality (AR) devices are computationally expensive and require special hardware like depth sensors, which consume additional power, making them unsuitable for small, user-friendly AR devices.
Innovation Solution
A continuous surface and depth estimation system using stereo vision within a predetermined window, limiting its application to a sub-portion of captured images, and employing methods like RANSAC and ray casting to estimate depth and surface normal, reducing computational requirements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If depth sensors and special hardware are used to determine depth and surface normal, then measurement precision is improved, but use of energy and device complexity increase
Solution Approach 1:
The patent replaces specialized depth sensing hardware with a computational approach using standard camera images. By applying continuous surface and depth estimation algorithms to regular 2D images, the system achieves depth information extraction without requiring additional power-consuming depth sensors or special hardware components.
Solution Approach 2:
The patent creates a virtual depth map by processing standard 2D images through computational algorithms. Instead of directly capturing depth information with specialized sensors, the system generates a computational copy of depth data from regular image inputs, eliminating the need for additional hardware while maintaining measurement capability.
2Measurement precision
If depth sensors and special hardware are used to determine depth and surface normal, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent enables standard cameras to perform multiple functions - both 2D image capture and 3D depth estimation - through computational processing. This universal approach allows a single hardware component to serve dual purposes, eliminating the need for specialized depth sensors and reducing overall device complexity while maintaining measurement precision.
Solution Approach 2:
The patent substitutes specialized depth sensing hardware with computational image processing algorithms. By replacing physical depth sensors with software-based continuous surface and depth estimation methods, the system reduces hardware complexity while achieving comparable or superior measurement accuracy through algorithmic processing.
3Measurement precision
If continuous depth estimation is performed on entire captured images, then measurement precision is improved, but productivity decreases due to computational cost
Solution Approach 1:
The patent divides the image processing task into segments by applying continuous surface and depth estimation algorithms only to selected regions of interest rather than processing entire images. This segmentation approach maintains measurement precision in critical areas while significantly reducing overall computational load, enabling higher frame rates and improved productivity.
Solution Approach 2:
The patent applies depth estimation processing selectively to portions of images that contain relevant objects or regions of interest, rather than processing every pixel in the entire image. This partial action approach achieves sufficient measurement precision for AR applications while reducing computational complexity and increasing processing speed for real-time performance.
Data Source
AI summary
Disclosed are systems, methods, and non-transitory computer-readable media for continuous surface and depth estimation. A continuous surface and depth estimation system determines the depth and surface normal of physical objects by using stereo vision limited within a predetermined window.