A Gaze Estimation Method Based on Human Eye Features

A line-of-sight estimation and human-eye technology, applied in the field of line-of-sight estimation, can solve problems such as poor applicability and inapplicability, and achieve the effect of good applicability

Active Publication Date: 2018-11-20
ZHEJIANG UNIV OF TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In order to overcome the shortcomings of the existing sight line estimation methods that cannot be applied to occasions where the human head rotates and have poor applicability, the present invention provides a human eye feature-based visual inspection method that is effectively applicable to the occasion where the human head rotates and has good applicability. line of sight estimation method

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A Gaze Estimation Method Based on Human Eye Features
  • A Gaze Estimation Method Based on Human Eye Features
  • A Gaze Estimation Method Based on Human Eye Features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The present invention will be further described below in conjunction with the accompanying drawings.

[0029] refer to figure 1 , a line of sight estimation method based on human eye features, comprising the following steps:

[0030] 1) First define the characteristics of the human eye, as shown in formula (1):

[0031]

[0032] where e i Represents the human eye feature vector of the i-th image, y lj Indicates the coordinates of the jth feature point of the left eye, y rj Indicates the coordinates of the jth feature point of the right eye, p l represents the center of the iris of the left eye, p r Represents the iris center of the right eye, the feature vector {e i}∈R m , that is, it has m=12-dimensional space.

[0033] 2) After defining the characteristics of the human eye, the following model (2) is used to estimate the gaze direction as follows:

[0034]

[0035] Among them, {e i} represents the features of the training set, {θ i} represents the ang...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

A line of sight estimation method based on human eye features, comprising the following steps: 1) first defining the features of the human eyes; 2) after defining the features of the human eyes, using the model (2) to estimate the line of sight direction, an adaptive regression method based on features, The Euclidean distance between the estimated feature Ew and the real feature is limited by ε, and the line of sight estimation is realized by minimizing ||w||1 to determine the line of sight parameter. The invention provides a line-of-sight estimation method based on human eye characteristics, which is effectively applicable to the occasion where the head of the human body rotates and has good applicability.

Description

technical field [0001] The invention relates to the field of line of sight detection, in particular to a line of sight estimation method. Background technique [0002] At present, the methods of gaze estimation can be mainly divided into three categories: electromagnetic coil method, electrooculogram method and image-based method. Although the electromagnetic coil method has high precision, it will be in direct contact with the eyeball, causing discomfort; the cost of the electrooculogram method is low, but it needs to use a sensor with high sensitivity, and the detection results are easily affected by human metabolic activities and external conditions. Environmental impact; image-based methods are divided into contact and non-contact methods. Among them, the contact method requires additional wearing equipment, which causes great interference to the experiment. The non-contact method has the advantages of low interference, low cost, and convenient operation. It is the curre...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V40/18G06F18/214
Inventor 张剑华陈胜勇蔡海斌刘洪海
Owner ZHEJIANG UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap