AR Orientation Accuracy via Inertial Sensor Merging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Augmented reality systems face issues with inconsistent location and orientation estimates, leading to undesired effects like jitter and incorrect placement of augmented objects, due to noise in existing algorithms and high resource consumption.
Innovation Solution
Incorporating inertial sensors, such as accelerometers and gyroscopes, to provide accurate orientation estimates by merging their measurements with pose estimates from augmented reality algorithms, reducing algorithm complexity and latency, and enabling faster tracking of regions of interest.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If augmented reality algorithms process real time images to determine location and orientation, then location and orientation estimates can be obtained, but the results are inconsistent and produce jitter and incorrect placement
Solution Approach 1:
The patent combines data from inertial sensors (accelerometer and gyroscope) with pose estimates from augmented reality algorithms to determine device orientation. This merging of multiple data sources compensates for the weaknesses of each individual method, producing more consistent and accurate orientation estimates that reduce jitter and incorrect placement of augmented objects.
Solution Approach 2:
The inertial sensors act as an intermediary between the camera-based augmented reality algorithms and the final pose determination. The sensors provide continuous orientation data that bridges gaps between processed frames and smooths transitions, ensuring consistent rendering without the jitter caused by algorithmic inconsistencies alone.
2Measurement precision
If augmented reality algorithms process all frames at full frame rate, then accuracy may be improved, but computational complexity and resource consumption increase
Solution Approach 1:
The system performs preliminary action by using inertial sensors to predict device orientation between processed frames. This allows the augmented reality algorithms to operate at lower frame rates while maintaining smooth, accurate rendering through interpolation, reducing computational complexity without sacrificing visual quality or accuracy.
Solution Approach 2:
The patent implements a dynamic system where inertial sensor data continuously updates the device orientation estimate between algorithm processing cycles. This dynamic approach allows the system to adapt to rapid movements while maintaining accuracy, reducing the need for high-frequency full algorithm execution and thereby lowering overall computational complexity.
3Measurement precision
If augmented reality algorithms process images to track features, then pose estimates can be obtained, but latency increases when processing cannot keep up with frame rate
Solution Approach 1:
Inertial sensors serve as an intermediary that provides continuous orientation data independent of algorithm processing speed. This allows the system to maintain accurate, low-latency pose estimates even when the augmented reality algorithms cannot process frames at full rate, as the sensor data fills temporal gaps without requiring additional processing time.
Solution Approach 2:
The inertial sensors perform preliminary measurement of device orientation continuously, so when augmented reality algorithms complete processing, the most recent sensor data is already available to immediately update the pose estimate. This preliminary action eliminates waiting time and reduces latency without compromising accuracy.
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 and stability of augmented reality systems by providing higher accuracy orientation estimates and reducing the complexity and resource consumption of the algorithms, resulting in smoother and more precise placement of augmented objects.
Implementation Method 1
Inertial sensors (e.g., accelerometers and gyroscopes) may be used to determine device orientation
Implementation Method 2
Inertial sensors (e.g., accelerometers and gyroscopes) may be used to determine device orientation
Data Source
AI summary
Example embodiments of the present disclosure provide techniques for receiving measurements from one or more inertial sensors (i.e. accelerometer and angular rate gyros) attached to a device with a camera or other environment capture capability. In one embodiment, the inertial measurements may be combined with pose estimates obtained from computer vision algorithms executing with real time camera images. Using such inertial measurements, a system may more quickly and efficiently obtain higher accuracy orientation estimates of the device with respect to an object known to be stationary in the environment.