IR Camera Gaze Tracking for Robust Object-Distance Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing gaze tracking methods lack robustness and accuracy in predicting the distance of gazed objects, and they often require bulky hardware that is cumbersome to use.
Innovation Solution
A system using infrared (IR) cameras to predict the distance of gazed objects by pretraining a gaze predictor ML model, extracting features from pupillary information, and classifying objects into near, intermediate, and far classes, without additional hardware.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing gaze tracking methods are used to predict distance of gazed objects, then gaze direction can be identified, but robustness and accuracy of distance estimation deteriorates
Solution Approach 1:
The patent transforms the gaze tracking problem from 2D point prediction to 3D depth estimation by introducing distance as an additional parameter. The system uses pupillary distance measurements and geometric relationships to calculate actual distance, converting qualitative gaze direction into quantitative depth information with improved accuracy and robustness
Solution Approach 2:
The patent introduces intermediate computational steps including pupillary distance calculation, vergence angle determination, and geometric relationship analysis between eyes and objects. These intermediary measurements serve as mediators to derive accurate depth information that directly predicts gazed object distance
2Extent of automation
If heavy and bulky head mounted hardware is used for gaze tracking, then additional processing capability is gained, but ease of operation deteriorates due to cumbersome usage
Solution Approach 1:
The patent extracts the essential gaze tracking functionality from bulky head-mounted hardware and implements it through software-based processing of standard camera feeds. By taking out only the necessary computational elements (pupillary analysis, geometric calculations) and removing unnecessary hardware complexity, the system achieves adequate processing capability while dramatically improving ease of operation
Solution Approach 2:
The patent replaces mechanical head-mounted hardware with a software-based solution that processes images from existing cameras. By substituting physical hardware with computational algorithms for pupillary analysis and depth calculation, the system maintains processing capability while eliminating the bulk and discomfort of traditional head-mounted devices
Data Source
AI summary
This disclosure relates generally to method and system for predicting distance of gazed objects using IR camera. Eye tracking technology is widely used to study human behavior and patterns in eye movements. Existing gaze trackers focus on predicting gaze point and hardly analyzes distance of the gazed object from the gazer or directly classify region of focus. The method of the present disclosure predicts gazed objects distance using a pair of IR cameras placed on either side of a smart glass. The gaze predictor ML model predicts distance at least one gazed object positioned from eye of each subject during systematic execution of a set of tasks. From each pupillary information of each pupil a set of features are extracted which are utilized to classify the gazed object of the subject based on the distance into at least one of a near class, an intermediate class, and a far class.