AR Eyewear Ego Motion Alignment Without Markers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing augmented reality (AR) technologies face challenges in enabling collaborative and shared AR experiences between multiple users without the need for a common scene or image content, which often require significant computational resources and memory, and do not allow for real-time alignment and modification of virtual 3D content.
Innovation Solution
The use of six degrees of freedom (6DOF) tracker trajectories and visual inertial odometry (VIO) pose trackers for ego motion alignment between eyewear devices, allowing users to share common 3D content without aligning to a marker, and enabling local odometry systems to reduce computational burden and memory usage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional AR alignment methods using common scene or image content are used, then virtual objects can be aligned in the environment, but computational resources and memory consumption increase significantly
Solution Approach 1:
The patent divides the alignment problem into two independent parts: each device independently tracks its own ego motion using local odometry, rather than all devices jointly processing global scene data. This segmentation reduces computational burden while maintaining alignment precision through separate trajectory generation and subsequent transformation application.
Solution Approach 2:
The patent extracts and removes the requirement for global scene understanding and common image content from the alignment process. By using only local ego motion trajectories and device-to-device transformations, the system eliminates the need for computationally intensive global mapping and scene reconstruction while preserving alignment capability.
2Measurement precision
If global mapping pipeline is used for AR alignment, then accurate positioning is achieved, but memory usage and computational burden increase
Solution Approach 1:
The patent segments the positioning system into independent local odometry modules running on each device, eliminating the need for a centralized global mapping pipeline. Each device maintains its own trajectory independently, reducing system complexity while achieving positioning accuracy through relative transformation calculations.
Solution Approach 2:
Each AR device performs self-service positioning by running its own local odometry system to generate ego motion trajectories independently. This eliminates the need for complex inter-device coordination and global mapping infrastructure, reducing system complexity while maintaining positioning accuracy through autonomous trajectory generation.
3Measurement precision
If markers are used for device alignment, then alignment between devices is achieved, but the system requires additional physical infrastructure and reduces flexibility
Solution Approach 1:
The patent removes the dependency on physical markers and pre-configured alignment infrastructure from the system. By using markerless visual inertial odometry and device-to-device tracking, the system achieves alignment accuracy without requiring additional physical infrastructure, thereby enhancing environmental adaptability and flexibility.
Solution Approach 2:
The patent creates a universal alignment system that works across diverse environments without requiring environment-specific setup or markers. The visual inertial odometry and ego motion tracking approach provides multi-functional capability to align devices in any setting, greatly enhancing environmental adaptability while maintaining alignment accuracy.
Data Source
AI summary
Eyewear providing an interactive augmented reality experience between two eyewear devices by using alignment between respective 6DOF trajectories, also referred to herein as ego motion alignment. An eyewear device of user A and an eyewear device of user B track the eyewear device of the other user, or an object of the other user, such as on the user's face, to provide the collaborative AR experience. This enables sharing common three-dimensional content between multiple eyewear users without using or aligning the eyewear devices to common image content such as a marker, which is a more lightweight solution with reduced computational burden on a processor. An inertial measurement unit may also be used to align the eyewear devices.