AR Edge Alignment Using Camera-Based Surface Plane Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing augmented reality (AR) devices face challenges in accurately aligning virtual content with real-world objects due to computational limitations and the need for specialized depth sensors, which are not feasible in compact AR devices.
Innovation Solution
Utilizing commonly available optical sensors, such as color cameras, for stereo vision to determine surface planes and edges of real-world objects, allowing for efficient alignment of virtual content with respect to these edges.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If depth sensors such as LIDAR sensors are used to estimate surface characteristics, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent uses optical sensor data (camera images) to create a computational model that replicates the depth measurement capability of specialized depth sensors. By processing 2D image data through algorithms that analyze perspective, scale, and visual cues, the system generates accurate depth estimates without requiring physical depth sensing hardware, thus copying the functional capability of LIDAR through software-based computational photography
Solution Approach 2:
The patent replaces the mechanical/optical LIDAR sensing system with a computational image processing system. Instead of using active light emission and time-of-flight measurement mechanisms, the system substitutes these with passive optical capture followed by computational analysis of image characteristics, thereby eliminating the need for specialized depth sensors while maintaining measurement capability
2Measurement precision
If specialized depth sensors are used, then measurement precision is improved, but ease of manufacture worsens
Solution Approach 1:
The patent makes the optical sensor serve multiple functions: it captures both 2D image data for visual recognition and sufficient 3D depth information for spatial understanding and virtual content placement. This multi-functionality eliminates the need for separate specialized depth sensors, simplifying device manufacturing while maintaining measurement precision through computational methods that extract depth from the universal optical sensor data
3Device complexity
If computational methods are used to estimate surface characteristics, then device complexity is reduced, but measurement precision may worsen
Solution Approach 1:
The patent transforms 2D image data into 3D spatial understanding by analyzing multiple dimensions within the image data, including perspective projection relationships, object scale variations, and geometric constraints. This dimensional transformation allows the computational method to extract accurate depth information from 2D optical sensor data, maintaining measurement precision while avoiding the need for specialized 3D sensing hardware
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
Enhances the perceived realism and usability of virtual content by ensuring it is accurately positioned and oriented relative to real-world edges, reducing computational overhead and sensor specialization requirements.
Implementation Method 1
a color camera image of the environment in front of an AR device is used to determine the distance
Data Source
AI summary
A system is disclosed, including a processor and a memory. The memory stores instructions that, when executed by the processor, configure the system to perform operations. Surface plane information is obtained, defining a surface plane passing through a surface location and oriented according to a surface normal. An edge is detected in an image. Virtual content is presented, having a virtual position based on an orientation of the edge and the surface plane information.