Implicit Gaze Calibration Using Interpupillary Distance Estimation

Solution Overview

Problem

Existing head-up display systems face challenges in accurately estimating the optical axis and focal depth of the human eye due to deviations in the optical axis, limitations in head pose estimation, and inaccuracies in gaze and focal depth estimation, requiring cumbersome explicit calibration processes that disrupt user experience.

Innovation Solution

A system and method for implicit gaze and focus distance calibration using tracking cameras and processors to estimate uncalibrated gaze vectors and interpupillary distance without explicit user calibration, utilizing tracking parameters to determine calibrated gaze vectors based on predefined forward axes and focusing distances.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If explicit gaze calibration process is implemented, then measurement precision of gaze vectors is improved, but ease of operation deteriorates due to cumbersome calibration tasks

Engineering Contradiction:

Improvegaze estimation accuracyVSAvoiduser experience

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The system performs preliminary calibration actions by capturing images and determining tracking parameters during normal operation before explicit calibration is needed. The processor continuously captures images of the user's face and determines tracking parameters including head pose and eye positions, preparing calibration data in advance so that when calibration is needed, it can be performed implicitly without disrupting the user.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system performs self-calibration by automatically processing captured images to determine tracking parameters and estimate uncalibrated gaze vectors without requiring user intervention. The processor autonomously identifies eye features, calculates interpupillary distance, and generates calibration models based on captured data, eliminating the need for users to perform manual calibration tasks.

Inventive Principle:

Principle #25Self-service

2Reliability

If explicit gaze calibration process is required, then reliability of gaze estimation is improved, but loss of time increases due to calibration duration

Engineering Contradiction:

Improvegaze estimation reliabilityVSAvoidcalibration time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system maintains continuous calibration by constantly capturing images and updating tracking parameters during normal HUD operation. Instead of performing a discrete calibration session, the processor continuously monitors eye positions and head pose, accumulating calibration data over time so that reliable gaze estimation is maintained without interrupting the user's primary task.

Inventive Principle:

Principle #20Continuity of useful action

Solution Approach 2:

The system performs preliminary calibration actions by capturing images and determining tracking parameters during normal operation before explicit calibration is needed. The processor continuously captures images of the user's face and determines tracking parameters including head pose and eye positions, preparing calibration data in advance so that when calibration is needed, it can be performed implicitly without disrupting the user.

Inventive Principle:

Principle #10Preliminary action

3Device complexity

If generic calibration model from prerecorded databases is used, then device complexity is reduced, but measurement precision deteriorates due to lack of user-specific calibration

Engineering Contradiction:

Improvecalibration system complexityVSAvoidgaze estimation accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The system adapts calibration parameters to individual users by dynamically determining tracking parameters from captured images. The processor extracts user-specific features such as interpupillary distance, eye aspect ratios, and head pose characteristics, then uses these personalized parameters to generate accurate gaze estimates tailored to each user's anatomical and behavioral characteristics.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The system performs self-calibration by automatically processing captured images to determine tracking parameters and estimate uncalibrated gaze vectors without requiring user intervention. The processor autonomously identifies eye features, calculates interpupillary distance, and generates calibration models based on captured data, eliminating the need for users to perform manual calibration tasks.

Inventive Principle:

Principle #25Self-service

Data Source

PatentEP4659980A1Implicit gaze and focus distance calibration

Publication Date: 2025.12.10 DISTANCE TECHNOLOGIES OY

Figure 1~2
Figure 3~4A
Figure 4B~4C

AI summary

Images (300) of a user's face (302) are captured at a plurality of time instants. Tracking parameters are determined, tracking parameters comprising: a pose of the user's head (304, 410), positions of eyeballs (306a-b), and at least one of: relative positions of irises (310a-b) with respect to boundaries of the eyeballs, relative positions of irises with respect to corners, shapes of the user's eyes (308a-b, 404a-b). Uncalibrated gaze vectors (402a-b) of the user's eyes are estimated. A set of uncalibrated gaze vectors is generated. The uncalibrated gaze vectors of said set are stored along with corresponding time instants and tracking parameters. A first subset of uncalibrated gaze vectors whose direction matches with a predefined forward axis (408) of vision, is selected. For said uncalibrated gaze vectors, corresponding tracking parameters are fetched. A maximum distance between the irises is determined. The maximum distance is considered as an interpupillary distance (414).