AR Tracking Using Precomputed 2D-3D Feature Database
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing augmented reality (AR) systems face challenges in accurately tracking the location of a user device relative to the environment, which affects the precise depiction of AR elements.
Innovation Solution
A method that captures data about an environment, generates a database of 2D features and associated 3D coordinates, and uses this database to determine the position and orientation of a device within the environment, allowing for the accurate display of AR elements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing AR tracking methods are used, then the system is simpler to implement, but the tracking accuracy and reliability deteriorate
Solution Approach 1:
The system performs preliminary photogrammetry to create a database of 2D features and 3D coordinates before AR tracking begins. This pre-established database enables accurate tracking by providing reference features for comparison, resolving the contradiction by preparing tracking data in advance rather than computing it in real-time during AR operation.
Solution Approach 2:
The patent introduces an intermediary database containing 2D features and 3D coordinates that mediates between the environment and the tracking system. This database acts as a reference layer that improves tracking accuracy without requiring direct complex computations between the camera and environment, thus enhancing precision while managing system complexity.
2Measurement precision
If photogrammetry is performed using multiple images, then the database accuracy improves, but the processing time increases
Solution Approach 1:
The photogrammetry process is executed as a preliminary action before AR tracking begins. By completing the computationally intensive multi-image processing in advance, the system creates an accurate database without impacting real-time tracking performance, thus resolving the time-accuracy tradeoff.
Solution Approach 2:
The system segments the tracking process into two distinct phases: an offline photogrammetry phase for database creation and an online tracking phase for real-time operation. This segmentation allows resource-intensive accuracy-improving operations to occur separately from time-sensitive tracking operations.
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
This approach enhances the accuracy, reliability, and speed of device tracking in AR applications, enabling more precise and effective AR implementations.
Implementation Method 1
a camera to capture data about the environment
Implementation Method 2
a three-dimensional scanner to capture data about the environment
Data Source
AI summary
Examples described herein provide a method that includes capturing data about an environment. The method further includes generating a database of two-dimensional (2D) features and associated three-dimensional (3D) coordinates based at least in part on the data about the environment. The method further includes determining a position (x, y, z) and an orientation (pitch, roll, yaw) of a device within the environment based at least in part on the database of 2D features and associated 3D coordinates. The method further includes causing the device to display, on a display of the device, an augmented reality element at a predetermined location based at least in part on the position and the orientation of the device.