Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Real-time sight line inference method fusing head posture and eyeball tracking

A head posture and eye tracking technology, applied in the fields of computer vision and machine learning, can solve problems such as unnaturalness of people and difficulty in applying the interrogation process, and achieve the effect of low hardware resource requirements, high real-time performance, and good control of the error range.

Pending Publication Date: 2022-02-08
LIAONING UNIVERSITY
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the above-mentioned required hardware requirements are relatively high, and it is easy to put people in an unnatural state, and the traditional method of judging only using pupil coordinates is easily disturbed by changes in the posture of the human head, and it is difficult to apply to a wide range of interrogation processes

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
  • Real-time sight line inference method fusing head posture and eyeball tracking
  • Real-time sight line inference method fusing head posture and eyeball tracking
  • Real-time sight line inference method fusing head posture and eyeball tracking

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] The method of the present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments, so as to further understand the purpose, scheme and effect of the method of the present invention.

[0055] The method of the present invention is specifically divided into four major modules from the implementation process: 1) cascade detection, 2) eyeball direction estimation, 3) head posture estimation, 4) real-time line of sight direction estimation;

[0056] Among them, the method of the present invention mainly involves "direction inference", and mainly provides a method for inferring line of sight by combining various directions of eyeball movement with changes in head posture after realizing eyeball tracking;

[0057] Such as figure 1 As shown, it is the basic process of the implementation of the present invention. At the initial moment, it is necessary to face the camera, and the side view of the scene layout is as follow...

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 relates to a real-time sight line inference method fusing a head posture and eyeball tracking, and the method comprises the following steps: sequentially determining a face region, a head posture, an eyeball tracking point and a face reference point, obtaining an eyeball direction according to the distance proportion and angle change between an eyeball and the face reference point, correcting by combining with the change of the head posture, and deducing the sight line direction in the previous posture in real time. According to the method, the influence of human head movement and posture change on sight line direction inference is considered, the inference method is high in real-time performance, errors are easy to control, the embodiment is realized by using a machine learning algorithm, images are acquired by adopting a common visible light camera, the required hardware requirement is low, and the universality is good; in the inference process, people can be in a natural state.

Description

technical field [0001] The invention relates to a real-time line-of-sight inference method that combines head posture and eyeball direction tracking, and belongs to the fields of computer vision and machine learning. Background technique [0002] During interrogation, it is very important to grasp the psychological changes of the interrogated object. During the conversation, the changes in people's eyesight reflect part of their psychological activities, and the changes in the eyesight of the subject being interrogated are recorded and stored as quantitative data, which makes it possible to find the flaws of the subject being interrogated. However, it is too complicated to manually record these data, and how to use machines to naturally monitor the objects under investigation has become more critical. During the interrogation, by detecting the area of ​​the face, the direction of eye rotation is determined, and then the change of the gaze of the interrogated object is infer...

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 Applications(China)
IPC IPC(8): G06T7/246G06T7/73G06T7/11G06V40/70G06V40/18G06V40/10G06V10/25G06V10/77
CPCG06T7/246G06T7/73G06T7/11G06T2207/30041G06T2207/30241G06T2207/30201G06T2207/20132G06F18/2135G06F18/24317
Inventor 华春生潘英杰孟威
Owner LIAONING UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com