Head Movement Electronic Apparatus Gaze Tracking

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing eye-tracking and head movement tracking technologies for electronic device operation are limited by the need for additional infrared emitters and sensors, and accuracy is compromised by factors like small eye size or obstructions such as glasses or virtual reality wear.

Innovation Solution

An electronic device utilizing a typical camera to capture head images, perform face recognition, and detect facial landmarks to estimate the user's gaze position on a screen, eliminating the need for infrared emitters and sensors, and improving accuracy through calibration and distance adjustments.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If infrared emitters and sensors are used for eyeball tracking, then tracking capability is achieved, but device complexity and cost increase

Engineering Contradiction:
Improveeyeball tracking capabilityVSAvoidhardware requirements
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent extracts the essential tracking function from the complex infrared system and implements it using only a standard camera. By removing the infrared emitter and sensor components, the system achieves eyeball tracking capability while significantly reducing device complexity and hardware requirements.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

Instead of using specialized infrared sensing, the patent uses a standard camera to capture images that contain sufficient information for eyeball tracking. The camera creates a visual copy of the scene that can be processed to extract gaze information, eliminating the need for dedicated infrared hardware.

Inventive Principle:
Principle #26Copying

2Ease of operation

If nose movement is used to control cursor, then operation alternative is provided, but detection accuracy is insufficient

Engineering Contradiction:
Improvealternative control methodVSAvoidface or nose detection accuracy
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The patent segments the face detection task into multiple facial landmark points (eyes, nose, mouth, contours). By detecting and tracking these segmented features rather than treating the face as a single object, the system achieves higher precision in determining head movement and gaze direction while maintaining ease of operation.

Inventive Principle:
Principle #1Segmentation

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Enables intuitive and accurate control of electronic devices using head movements without additional hardware, enhancing usability in various environments, including those with virtual reality wear.

Implementation Method 1

The basic principle of the eyeball tracking technology is to use infrared light beam to irradiate the user's eyeballs, and then a sensor captures the light reflected from different parts such as the pupil, the iris, and the cornea

Methodology Applied
Scientific EffectLight reflection: Reflection

Data Source

PatentEP3608755B1Electronic apparatus operated by head movement and operation method thereof
Publication Date: 2022.04.20 ACER INC
  • EP3608755B1 patent drawingFigure 1
  • EP3608755B1 patent drawingFigure 2A~2B
  • EP3608755B1 patent drawingFigure 3~4

AI summary

An electronic apparatus including an image capturing device, a storage device and a processor and an operation method thereof are provided. The image capturing device captures an image for a user, and the storage device records a plurality of modules. The processor is coupled to the image capturing device and the storage device and is configured to: configure the image capturing device to capture a head image of a user; perform a face recognition operation to obtain a face region; detect a plurality of facial landmarks within the face region; estimate a head posture angle of the user according to the facial landmarks; calculate a gaze position where the user gazes on the screen according to the head posture angle, a plurality of rotation reference angle, and a plurality of predetermined calibration positions; and configure the screen to display a corresponding visual effect according to the gaze position.