AR Coordinate Registration via Precomputed Survey Matrices
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies struggle to provide personalized and accurate augmented reality (AR) experiences for event viewers, both at the venue and remotely, due to challenges in tracking moving cameras and relating image coordinates to real-world coordinates.
Innovation Solution
The system employs a novel technique for registering mobile device images with real-world coordinates by detecting specific features such as ridge lines and edges, using GPS, compass, and gravitometer data for initial positioning, and optimizing feature matching through iterative refinement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If broadcasters insert graphics into broadcast images or provide alternate views, then the viewing experience is optimized for general audiences, but the content does not correspond to individual viewers' preferences or viewpoints
Solution Approach 1:
The system performs preliminary registration of camera coordinates with real-world coordinates before the event occurs. Survey images are captured and processed in advance to establish coordinate transformations, so that when live viewing occurs, the AR content can be quickly aligned without complex real-time computation
Solution Approach 2:
The system introduces an intermediary coordinate transformation layer that maps between camera image coordinates and real-world coordinates. This intermediary mathematical model (involving rotation matrices and translation vectors) acts as a bridge, allowing AR content to be accurately positioned without direct complex tracking during the event
2Measurement precision
If AR content is provided to viewers at the venue, then personalized viewing experience is enabled, but the content may not be available or accurate without precise coordinate registration
Solution Approach 1:
Coordinate registration is performed in advance using survey images captured before the event. The system pre-computes transformation matrices that map camera coordinates to real-world coordinates, eliminating the need for complex real-time measurement and tracking during the actual event
Solution Approach 2:
The system uses detected features (ridge lines, edges, corners) from survey images to compute coordinate transformations, and then uses this transformation feedback to accurately position AR content. The process iteratively refines the coordinate mapping based on feature matching quality
3Manufacturing precision
If feature matching is performed without iterative optimization, then processing is faster, but alignment precision is insufficient for accurate AR placement
Solution Approach 1:
Iterative feature matching and coordinate registration are performed in advance during the survey phase, before the actual event. This preliminary processing allows sufficient time for multiple iterations to achieve high precision, while the results are then reused during the event without requiring real-time iterative computation
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 (mobile 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. In a tabletop presentation, video of the event can be displayed with augmented reality graphics overlays at a remote location.