3D Gaze Tracker Using Time-of-Flight Camera for Head-Free Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional gaze tracking systems require head stabilization and are limited in their field of view, restricting freedom of motion and accuracy in determining gaze direction and point of regard, especially for applications like virtual or augmented reality.
Innovation Solution
A 3D gaze tracker system using a combination of a time-of-flight 3D camera and a picture camera to acquire range and contrast images, allowing for the determination of gaze vectors and point of regard without headgear, with a field of view extending to large distances, enabling freedom of head motion and accurate tracking.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If head stabilization is used in conventional gaze tracking systems, then measurement precision of gaze direction is improved, but freedom of motion and ease of operation deteriorate
Solution Approach 1:
The system transitions from static head stabilization to dynamic head-free tracking by using multiple cameras to capture eye movements and head pose simultaneously, allowing the gaze tracking to adapt dynamically to head movements without requiring the user to maintain a fixed head position
Solution Approach 2:
The system introduces an intermediary computational model that combines eye movement data from multiple cameras with head pose information to calculate gaze direction in 3D space, serving as a mediator between raw camera data and accurate gaze measurement without requiring head stabilization
2Adaptability or versatility
If field of view is limited in conventional systems, then device complexity is reduced, but adaptability to different viewing distances and angles deteriorates
Solution Approach 1:
The system divides the field of view into multiple segments by using multiple cameras positioned at different locations, each capturing a specific portion of the scene, and then combines these segmented views through computational processing to reconstruct the complete 3D gaze trajectory
Solution Approach 2:
The system transitions from 2D image analysis to 3D spatial reasoning by using multiple camera views to determine the three-dimensional position and orientation of the gaze vector, enabling accurate tracking across a wider field of view and at various distances
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 accurate and unencumbered tracking of gaze vectors and point of regard over a wide field of view, allowing for seamless interaction with computers and virtual/augmented reality environments without the need for head stabilization, improving user experience and application flexibility.
Implementation Method 1
A 3D camera, referred to as a time of flight (TOF) 3D camera, images a person with light pulses to provide a set of three-dimensional (3D) spatial coordinates for a set of features of the person
Implementation Method 2
First, second, third, and fourth Purkinje reflections refer respectively to reflections from the front surface of the cornea, from the back surface of the cornea, the front surface of the lens and the back surface of the lens
Data Source
AI summary
An apparatus for interfacing a person with a computer, the apparatus comprising a gaze tracker having a 3D camera and a picture camera that image the person and a controller that processes images acquired by the cameras to determine a gaze direction and point of regard of the person.