A Fixation Estimation Method Based on Correlation Entropy

A fixation point and correlation entropy technology, applied in the field of fixation point estimation based on correlation entropy, can solve the problems of fixation point estimation influence and low resolution, and achieve the effect of low hardware requirements, strong anti-interference ability, and enhanced locality.

Active Publication Date: 2019-01-29
陕西百乘网络科技有限公司
View PDF10 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The applicability of gaze point estimation in different environments also faces challenges, such as low camera resolution, or environments with noise interference, which have a great impact on gaze point estimation

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 Fixation Estimation Method Based on Correlation Entropy
  • A Fixation Estimation Method Based on Correlation Entropy
  • A Fixation Estimation Method Based on Correlation Entropy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The present invention is described in further detail below in conjunction with accompanying drawing:

[0048] The flow chart of the concrete implementation of the present invention is as figure 1 As shown, the steps involved are as follows:

[0049] Step 1, face image acquisition;

[0050] Step 2, human eye image sub-pixel extraction;

[0051] Step 3: Dimensionality reduction of human eye image features;

[0052] Step 4, gaze point position estimation;

[0053] The concrete implementation steps of described step 1 are:

[0054] Use the Adaboost algorithm to locate the face of the collected image, and then extract the face image, which is the step of extracting the human eye image later.

[0055] The specific implementation steps of step 2:

[0056] After the face image is extracted through step 1, the initial vertex coordinates (x 0 ,y 0 ), assuming that the position information after the alignment operation is (x, y), the transformation function between the two...

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

The invention discloses a fixation point estimation method based on correlation entropy, which comprises the following steps: 1. Face image acquisition; 2. Human eye image sub-pixel extraction; 3. Human eye image feature dimensionality reduction; 4. Gaze point position estimation ; The method of the present invention can accurately estimate the gaze point under different environmental conditions.

Description

technical field [0001] The invention relates to the gaze point estimation field of human-computer interaction, in particular to a gaze point estimation method based on correlation entropy. Background technique [0002] In recent years, the technical sophistication and applicability of eye gaze tracking has attracted great interest from the commercial sector. Eye gaze tracking is used in a wide variety of disciplines, including cognitive science, psychology (particularly psycholinguistics, the paradigm of the visual world), human-computer interaction (HCI), market research, and medical research (neurodiagnostics). Specific applications include tracking eye movements in verbal reading, musical reading, human activity recognition, advertising design, and motion design. Therefore, the study of gaze tracking has always attracted the interest of researchers. [0003] The gaze point estimation accuracy is usually affected by the extracted human eye image, and the superpixel-level...

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): G06K9/00
CPCG06V40/165G06V40/171G06V40/193
Inventor 张雪涛李中常王飞陈霸东王颖姜沛林郑南宁
Owner 陕西百乘网络科技有限公司
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