Interpupillary Distance Estimation Using Aligned Depth and Pupil Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing interpupillary distance estimation methods based on range imaging techniques are limited by the high cost of depth cameras, precision dependence on depth sensor accuracy, and environmental conditions, leading to inaccurate measurements.
Innovation Solution
An interpupillary distance estimation method using a depth camera to capture depth images, align 2D maps with 2D images, locate pupil markers, calculate initial and second estimates, and apply trigonometric calculations with anthropometric data to determine a final estimate, while filtering unreliable images to enhance accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If expensive depth cameras are used to capture depth images, then measurement precision is improved, but device cost increases
Solution Approach 1:
The patent uses a standard camera to capture images and creates a depth map through image processing algorithms rather than using expensive depth cameras. The depth information is derived by analyzing facial features and geometric relationships in the captured images, effectively copying the depth measurement function through software processing instead of hardware
Solution Approach 2:
The patent replaces the mechanical depth sensing hardware with an optical imaging system combined with computational algorithms. Instead of using structured light or time-of-flight sensors, the system uses standard camera optics and processes the captured images through algorithms that simulate depth perception by analyzing facial geometry and feature relationships
2Measurement precision
If multiple refinement steps are applied to locate pupil positions, then measurement precision is improved, but processing complexity and time increase
Solution Approach 1:
The patent performs preliminary detection of facial features and geometric relationships in the captured images before final pupil position determination. By pre-processing the image to identify key facial landmarks and establish geometric constraints, the system reduces the complexity of subsequent refinement steps and can achieve accurate pupil localization more efficiently
Solution Approach 2:
The patent implements an iterative refinement process where the system continuously adjusts and improves pupil position estimates based on feedback from the captured images and geometric constraints. The algorithm refines the initial detection by analyzing the consistency of facial features and adjusting the pupil positions accordingly, achieving higher precision through systematic feedback loops
3Adaptability or versatility
If depth images are captured under various environmental conditions, then adaptability is improved, but measurement reliability decreases due to processing difficulties
Solution Approach 1:
The patent adjusts processing parameters and algorithmic approaches based on environmental conditions detected in the captured images. The system analyzes lighting conditions, image quality metrics, and geometric consistency to dynamically modify processing thresholds and refinement steps, maintaining reliable measurements across varying environmental conditions by adapting parameters to match the capture context
Data Source
AI summary
A system performs an interpupillary distance estimation method, which includes capturing a plurality of depth images of a user's face where each depth image comprises a 2D image and a 2D map of data representative of the distances of each pixel from an observation point. For each of the captured depth images, the system processes the captured depth image by correcting the alignment between the 2D map of data and the 2D image, locates two first marker points corresponding to the pupils on the 2D image, and obtains the spatial coordinates in metric units of the first marker points from the 2D data map. The system further determines an initial estimate of the interpupillary distance by calculating the distance between the first marker points, determines a second estimate of the interpupillary distance, and calculates the final estimate of the interpupillary distance based on the first estimates or the second estimates.