Surface-Feature Machine Vision for Consistent Indoor AR Localization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing techniques for determining the 3-D physical or geographic location and/or 6-D pose of a device indoors are inaccurate and require significant environmental setup or monitoring, such as GPS, WiFi routers, Bluetooth beacons, and fiducial markers, which are either unreliable or cumbersome.
Innovation Solution
A system and method for image-based localization using surface features from a previously scanned physical environment, allowing for the recognition and positioning of augmented reality features, enabling accurate localization and display of AR features without the need for absolute coordinates.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GPS or satellite signals are used for location determination, then outdoor location accuracy is adequate, but indoor location accuracy deteriorates due to signal blockage and reflections
Solution Approach 1:
The patent creates a digital copy of the physical environment through 3D scanning and computer vision techniques. The system captures images and generates three-dimensional representations of indoor spaces, storing them as virtual models. This digital twin allows the system to determine device location by comparing current camera views with the stored virtual model, achieving accurate indoor localization without relying on satellite signals that cannot penetrate buildings.
2Measurement precision
If WiFi routers or Bluetooth beacons are deployed for indoor location determination, then location precision improves beyond GPS, but environmental setup complexity and cost increase
Solution Approach 1:
The patent enables the environment to serve itself for localization purposes. Instead of requiring external infrastructure like WiFi routers or Bluetooth beacons, the system uses the existing visual features of the environment (walls, furniture, architectural elements) as natural landmarks. The 3D scanning process automatically captures and stores these features, and the computer vision algorithm uses them for triangulation and location determination, eliminating the need for additional environmental instrumentation.
3Measurement precision
If fiducial markers are placed in the environment for location determination, then location accuracy improves, but ease of operation deteriorates due to overhead effort and unsightly appearance
Solution Approach 1:
The patent replaces physical fiducial markers with a digital copy of the natural environment. The 3D scanning process creates a comprehensive virtual model that captures all visual features of the space. This digital representation serves as the reference framework for location determination, eliminating the need to physically place markers in the environment. The system achieves high accuracy by matching current views against the stored virtual model, maintaining precision while removing deployment overhead and aesthetic concerns.
4Measurement precision
If indoor surveillance cameras are deployed for location determination, then object location can be determined, but device complexity and operational overhead increase due to constant monitoring requirements
Solution Approach 1:
The patent transforms the continuous monitoring requirement into periodic, on-demand operation. Instead of deploying surveillance cameras that must constantly record and process video streams, the system captures images only when needed for localization. The computer vision algorithm processes these periodic images to determine device location, significantly reducing computational overhead and operational complexity while maintaining accurate location determination capability.
Data Source
AI summary
A system and method can support image based determination of mobile device location through recognition of surface features for a previously scanned physical environment. The system and method can also support authoring and positioning of augmented reality features in an authoring interface using the same images and positions of surface features that are to be used for subsequent mobile device localization. As a result, mobile devices leveraging those same images and positions of surface features for localization will be more likely to obtain a localization that is consistent with the positioning displayed in the authoring interface. Augmented reality features authored using the same scan of the environment can be reliably displayed to an end user of an augmented reality application in a position consistent with their authoring in a common coordinate system, even though the authoring may have been performed remotely, away from the actual situs of the physical environment.