3D Venue Reference Point Detection for Accurate AR Registration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing augmented reality systems struggle to accurately provide individualized content to viewers at sporting events, as they often rely on ad-hoc solutions that fail to account for non-2-D shapes, changing lighting conditions, and distinctive features, leading to inaccurate positioning and orientation of virtual graphics.
Innovation Solution
A system that detects specific features like ridge lines and edges of man-made structures, using iterative techniques to establish a robust correspondence between the viewer's frame of reference and the real-world coordinate system, employing multiple feature types and surveying techniques to create a spatially-organized database for precise registration.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If ad-hoc solutions are used for AR content delivery, then implementation is simpler, but positioning and orientation accuracy deteriorates
Solution Approach 1:
The system performs preliminary surveying of the venue to create a spatially-organized database of 3D reference points with known coordinates before the event. This pre-established reference framework enables accurate real-time positioning without complex ad-hoc solutions during the event itself.
Solution Approach 2:
The system transitions from 2D image processing to 3D spatial coordinate matching by detecting specific geometric features (ridge lines, edges) and establishing correspondence between camera coordinates and real-world coordinates through iterative techniques. This parameter transformation enables precise positioning despite changing lighting conditions.
2Measurement precision
If multiple feature types and surveying techniques are employed, then positioning accuracy is improved, but system complexity increases
Solution Approach 1:
The system segments the venue into multiple identifiable features (ridge lines, edges, corners) and processes each feature type separately through specialized detection algorithms. This segmentation allows accurate positioning by combining results from multiple feature detections rather than relying on a single complex system.
Solution Approach 2:
The patent introduces an intermediary spatially-organized database that stores 3D reference points with known coordinates. This database acts as a mediator between the camera's frame of reference and the real-world coordinate system, enabling accurate positioning without direct complex transformations.
3Measurement precision
If iterative techniques are used to establish correspondence between frames, then registration accuracy is improved, but processing time increases
Solution Approach 1:
The system performs preliminary detection of specific features (ridge lines, edges) and establishes the spatial correspondence database before real-time AR delivery. This pre-computation reduces the burden on real-time processing while maintaining high registration accuracy.
Solution Approach 2:
The patent applies iterative techniques locally to specific geometric features (ridge lines, edges, corners) rather than processing the entire image globally. This localized approach maintains registration accuracy while reducing overall processing time by focusing computational effort on critical feature points.
Data Source
AI summary
Augmented reality systems provide graphics over views from a mobile device for both in-venue and remote viewing of a sporting or other event. A server system can provide a transformation between the coordinate system of a mobile device (smart phone, tablet computer, head mounted display) and a real world coordinate system. Requested graphics for the event are displayed over a view of an event.