AR Eyewear Scaling via Hand Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current augmented reality systems require calibration to determine the scale of a user's face, which is burdensome and inefficient, involving additional steps and resources, disrupting the user experience.
Innovation Solution
The system computes a true or real-world scale of a user's face by combining facial landmarks with a depth map, allowing for the adjustment and positioning of augmented reality elements like glasses or hats without calibration, using a true size estimation system that processes images in real-time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If calibration is used to determine face scale in AR systems, then measurement precision is improved, but device complexity and ease of operation deteriorate due to additional calibration steps
Solution Approach 1:
The system automatically determines face scale by detecting the user's hand and using it as a reference object, eliminating the need for manual calibration actions. The hand detection and automatic scaling computation occurs without user intervention, allowing the system to serve itself in determining accurate face dimensions.
Solution Approach 2:
The user's hand serves as an intermediary reference object to determine face scale. Instead of requiring direct calibration of the camera or face, the system uses the hand's known approximate size as a mediator to compute face dimensions, thereby achieving accurate measurement without complex calibration procedures.
2Measurement precision
If calibration procedures are implemented, then measurement precision is improved, but loss of time increases due to additional calibration steps
Solution Approach 1:
The system performs preliminary hand detection and uses it to establish the face scale reference frame before the actual AR rendering begins. By preparing the scaling computation in advance using hand detection, the system eliminates the need for time-consuming calibration procedures during the AR experience.
Solution Approach 2:
The system automatically computes face scale using hand detection without requiring user participation in calibration procedures. This self-service approach eliminates the time loss associated with manual calibration steps while maintaining measurement precision.
3Manufacturing precision
If calibration is required for AR face scaling, then manufacturing precision is improved, but device complexity increases due to additional system components
Solution Approach 1:
The system extracts the calibration function by removing the complex calibration procedure and replacing it with a simplified hand detection-based scaling approach. By taking out the calibration step, the system reduces device complexity while maintaining the precision needed for accurate AR element sizing.
Solution Approach 2:
The hand detection system serves as an intermediary that simplifies the scaling computation. Instead of requiring complex calibration algorithms and hardware, the system uses hand detection as a mediator to achieve accurate face scaling with reduced device complexity.
Data Source
AI summary
Methods and systems are disclosed for performing operations comprising: receiving, by one or more processors, an image that includes a depiction of a face of a user; computing a real-world scale of the face of the user based on a selected subset of landmarks of the face of the user; obtaining an augmented reality graphical element comprising augmented reality eyewear; scaling the augmented reality graphical element based on the computed real-world scale of the face; and positioning the scaled augmented reality graphical element within the image on the face of the user.