HMD Coordinate Registration Without Fiducial Markers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing mixed-reality technologies face challenges in efficiently and securely registering coordinate frames between head-mounted displays (HMDs) and other entities, such as 3D models or robots, due to the reliance on fiducial markers or keypoints that are time-consuming, prone to damage, and pose security risks.
Innovation Solution
A method using sensor data from HMDs to register coordinate frames by having users point at, gaze at, or touch real-world features with known 3D positions, computing correspondences, and applying geometric algorithms like Kabsch or Procrustes superimposition to determine registration information, minimizing human interaction and security risks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If fiducial markers or keypoints are used for coordinate frame registration, then registration accuracy can be achieved, but the process becomes time-consuming and prone to damage
Solution Approach 1:
The patent extracts the registration process from dependency on physical fiducial markers or pre-defined keypoints. Instead, it uses naturally occurring real-world features that the system automatically detects and tracks, eliminating the need to manually place or attach markers to the environment.
Solution Approach 2:
The system performs self-registration by automatically detecting real-world features through sensors and computing coordinate transformations without requiring manual marker placement or human intervention in the registration process, making the system self-sufficient.
2Measurement precision
If fiducial markers are used for registration, then coordinate alignment can be achieved, but security risks arise from marker placement and access
Solution Approach 1:
The patent removes the security vulnerability associated with fiducial markers by extracting the registration process from marker-based systems. It uses ambient real-world features that do not require physical attachment or secret placement, eliminating the security risks of marker management.
Solution Approach 2:
Instead of using permanent or semi-permanent fiducial markers that pose security risks, the system uses transient, naturally occurring real-world features that are freely available in the environment, requiring no security measures for their placement or protection.
3Reliability
If manual placement of fiducial markers is performed, then registration can be established, but device complexity and operational difficulty increase
Solution Approach 1:
The system automatically performs feature detection, tracking, and coordinate frame registration without requiring users to manually place markers or configure registration parameters. The HMD and computing device handle the entire process autonomously, greatly simplifying operation.
Solution Approach 2:
The patent replaces the mechanical process of manually placing physical fiducial markers with an automated computational system that detects and tracks real-world features using sensors and algorithms, eliminating the need for manual intervention.
4Reliability
If fiducial markers are used, then registration information can be obtained, but the system becomes vulnerable to marker damage or loss
Solution Approach 1:
The patent extracts the registration process from dependency on physical markers that can be damaged or lost. It uses immutable real-world features inherent in the environment, such as geometric shapes or natural landmarks, that cannot be damaged or misplaced.
Solution Approach 2:
The system compensates for potential feature occlusion or temporary unavailability by using multiple real-world features simultaneously for registration, ensuring that if one feature becomes unavailable, others can maintain the registration relationship.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method of registering a coordinate frame of a head mounted display (HMD) with a second coordinate frame comprises receiving sensor data depicting the wearer of the HMD pointing at, gazing at, or touching, a real world feature, where the 3D position of the real world feature in the second coordinate frame is known. The method computes a 3D position of the real world feature, in the coordinate frame of the HMD, from the sensor data. A correspondence is stored comprising: the 3D position of the real world feature in the coordinate frame of the HMD, and a 3D position of the real world feature in the second coordinate frame. The method repeats so that a second correspondence is stored. The method registers the coordinate frame of the HMD and the second coordinate frame by computing registration from the correspondences.