Visual-Orientation Fusion for 6-DoF Tracking in Featureless AR
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing augmented reality tracking systems struggle to accurately track moving objects in featureless environments, such as those with sparse or difficult-to-differentiate content, leading to improper motion tracking and display.
Innovation Solution
A computer-implemented method using one or more processing devices and memory instructions to obtain initial 3D positions and orientations of an electronic device from multiple tracking systems, generate queries based on detected movements, and combine updated positions and orientations to calculate a 6-DoF pose for accurate tracking and display.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single tracking system is used to track moving objects in augmented reality, then the system complexity is low, but the tracking accuracy and reliability deteriorate in featureless environments
Solution Approach 1:
The patent combines multiple tracking systems (first tracking system and second tracking system) into a unified tracking apparatus. The first tracking system provides initial 3D position data, while the second tracking system provides orientation data and updated position information. By merging their outputs, the system achieves reliable 6-DoF tracking in featureless environments where a single system would fail.
Solution Approach 2:
The tracking system uses a composite approach by integrating data from heterogeneous tracking sources. The system combines position data from visual tracking (first tracking system) with orientation and motion data from inertial sensors (second tracking system), creating a composite tracking solution that leverages the strengths of each individual system to overcome their respective weaknesses.
2Reliability
If multiple tracking systems are combined to improve tracking accuracy, then the tracking reliability improves, but the device complexity increases
Solution Approach 1:
The tracking apparatus is designed with multi-functionality to handle different tracking scenarios. The first tracking system can operate independently for position tracking, the second tracking system can operate independently for orientation tracking, and both can work together for comprehensive 6-DoF tracking. This universal design allows the system to adapt to various environment types (feature-rich or featureless) while maintaining manageable complexity through modular architecture.
3Measurement precision
If continuous tracking updates are performed to maintain accurate pose information, then the tracking precision improves, but the processing time and computational load increase
Solution Approach 1:
The system performs preliminary action by obtaining the initial 3D position from the first tracking system before motion occurs. When motion is detected by the second tracking system, the system only needs to calculate the updated pose by combining the pre-obtained initial position with the motion data, rather than performing complete tracking calculations from scratch. This reduces processing time while maintaining precision.
Solution Approach 2:
The system uses partial action by selectively updating only the necessary components of the pose information. The initial 3D position is obtained once, and then only the changes in position and orientation are calculated subsequent to motion detection. This partial updating approach reduces computational load compared to continuous full pose recalculation, while still maintaining accurate tracking.
Data Source
AI summary
Methods, systems, and computer program products are described for obtaining, from a first tracking system, an initial three-dimensional (3D) position of an electronic device in relation to image features captured by a camera of the electronic device and obtaining, from a second tracking system, an orientation associated with the electronic device. Responsive to detecting a movement of the electronic device, obtaining, from the second tracking system, an updated orientation associated with the detected movement of the electronic device, generating and providing a query to the first tracking system, the query corresponding to at least a portion of the image features and including the updated orientation and the initial 3D position of the electronic device, generating, for a sampled number of received position changes, an updated 3D position for the electronic device and generating a 6-DoF pose using the updated 3D positions and the updated orientation for the electronic device.