Kiosk Eye Tracking With Touch-Based Real-Time Calibration

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional kiosks require a separate and cumbersome calibration process for eye tracking and calibration functions, leading to inefficiencies, reduced accuracy due to fixed calibration values, and limited accessibility for users of varying ages and skill levels.

Innovation Solution

A kiosk system that performs real-time eye tracking and calibration using machine learning models to collect user data during interaction, adjusting screen coordinates based on touch selections, and providing a customized interface.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a separate calibration process is performed for eye tracking in conventional kiosks, then eye tracking function can be provided, but the process becomes complicated and time-consuming for users

Engineering Contradiction:

Improveeye tracking accuracyVSAvoidcalibration process complexity

Core Design Contradiction:

ReliabilityVSEase of operation

Solution Approach 1:

The system automatically performs calibration by observing the user's natural eye movements and touch interactions with the interface, eliminating the need for users to manually complete calibration tasks. The kiosk serves itself by collecting calibration data from user behavior without requiring separate calibration actions from the user.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system collects calibration data during the user's first interaction with the kiosk before the user completes their required task. By performing calibration preliminarily during natural usage, the system avoids adding separate calibration steps after the user has already engaged with the interface.

Inventive Principle:

Principle #10Preliminary action

2Ease of operation

If fixed calibration values are used in conventional kiosks, then calibration process can be simplified, but tracking accuracy cannot be customized for different users

Engineering Contradiction:

Improvecalibration process simplicityVSAvoideye tracking accuracy

Core Design Contradiction:

Ease of operationVSMeasurement precision

Solution Approach 1:

The system transitions from static fixed calibration values to dynamic adaptive calibration. The calibration parameters are continuously adjusted based on real-time observation of each user's eye movements and interaction patterns, allowing the system to adapt to individual user characteristics while maintaining operational simplicity.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes calibration parameters based on observed user behavior and physical characteristics. By monitoring eye movement patterns, touch positions, and interaction duration, the system dynamically adjusts calibration parameters to optimize tracking accuracy for each specific user without requiring manual calibration input.

Inventive Principle:

Principle #35Parameter changes

3Measurement precision

If a separate calibration process is required for each user, then individual calibration can be performed, but accessibility is reduced for users of varying ages and skill levels

Engineering Contradiction:

Improveuser-specific calibration accuracyVSAvoidaccessibility for diverse users

Core Design Contradiction:

Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The system automatically adapts to each user without requiring them to understand or perform calibration procedures. Users of any age or skill level can simply interact with the kiosk as needed, and the system self-calibrates by observing their natural eye movements and touch interactions, making the technology accessible to all users regardless of their technical knowledge.

Inventive Principle:

Principle #25Self-service

4Productivity

If conventional eye tracking and calibration functions are implemented, then basic functionality is provided, but user experience is lowered due to incorrect settings and unnecessary waiting time

Engineering Contradiction:

Improvekiosk operation efficiencyVSAvoidcalibration waiting time

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The system performs calibration observations during the user's initial interaction with the interface, before the user completes their required task. This preliminary calibration occurs naturally as the user navigates menus or selects options, eliminating the need for separate calibration time and allowing the user to complete their transaction without waiting.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS12578792B1Method and apparatus for real-time eye tracking of kiosk userand by performing inference on calibration model

Publication Date: 2026.03.17 KOREA ELECTRONICS TECH INST

AI summary

Proposed are a method and apparatus including real-time eye tracking and calibration functions in a kiosk including a display. The method may include collecting first data related to a user's appearance based on image data on the user acquired from a camera of the kiosk, and generating first screen coordinates of the display corresponding to the user's eyes based on the first data and performing eye tracking on the user. The method may also include collecting second data including second screen coordinates for a corresponding touch point detected when the user touches and selects a menu displayed on the display and training a calibration machine learning model using the collected second data, and performing inference on the calibration model using the first screen coordinates according to the eye tracking performed at a time other than the touch selection time point to perform calibration on the eye tracking.