Gaze intention recognition method and system based on historical visual behaviors

A visual behavior and recognition method technology, applied in the field of intent recognition, can solve the problem of not considering the impact, etc., to achieve the effect of improving accuracy, high classification accuracy, and improving accuracy

Active Publication Date: 2021-05-28
SHANDONG UNIV
View PDF5 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In these studies, gaze information provided auxiliary information for identifying intentions, but existing work did not consider the impact of historical gaze information on current intentions

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
  • Gaze intention recognition method and system based on historical visual behaviors
  • Gaze intention recognition method and system based on historical visual behaviors
  • Gaze intention recognition method and system based on historical visual behaviors

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0044] In the technical solution disclosed in one or more embodiments, a method for gazing intention recognition based on historical visual behavior, the method first extracts eye movement features, including, gazing duration, gazing times, gazing interval and gazing speed; then using The SVM classifier divides the gaze behavior into intentional gaze and unintentional gaze according to the eye movement characteristics; finally, the Naive Bayesian method is used to infer the person's intention according to the historical gaze objects.

[0045] like figure 1 The frame diagram of the fixation intention recognition method based on historical visual behavior is shown. The framework is mainly composed of three parts: first, use Tobii eye tracker 5 to extract eye movement features, namely fixation duration, fixation times, fixation interval and fixation speed; Then, use the support vector machine SVM classifier to divide the gaze behavior into intentional gaze and unintentional gaze ...

Embodiment 2

[0096] The present embodiment provides a system for gazing intention recognition based on historical visual behavior, including:

[0097] The data acquisition module is used to acquire the user's historical visual behavior;

[0098] The eye movement feature extraction module is used to extract the user's eye movement features for each object based on historical visual behavior;

[0099] The SVM classification module is used to input the user's eye movement characteristics to the SVM classifier for each object, and judges whether the user is watching the object with intention, and if so, adds the object to the historical attention object sequence with intention;

[0100] The Naive Bayesian classification module is used to input the intentional historical gaze object sequence to the Naive Bayesian classifier to determine the user's intention.

[0101] The eye movement characteristics include fixation duration, fixation times, fixation interval and fixation speed.

Embodiment 3

[0103] This embodiment provides a computer-readable storage medium, in which a plurality of instructions are stored, and the instructions are suitable for being loaded by a processor of a terminal device and executing the above-mentioned gaze intent recognition method based on historical visual behavior.

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 provides a gaze intention recognition method and system based on historical visual behaviors. The method comprises the following steps: firstly, extracting eye movement characteristics of a user for each object based on historical visual behaviors, including fixation duration, fixation frequency, fixation interval and fixation speed; then inputting eye movement features of the user to each object to an SVM classifier, judging whether the user intentionally watches the object, and if so, adding the object into an intentionally historical watched object sequence; and finally, inputting a historical staring object sequence with intentions to a naive Bayes classifier, and determining the intentions of the user. Compared with a method based on a single object, the gaze intention recognition method based on the historical visual behaviors has the advantage that the intention recognition accuracy is remarkably improved.

Description

technical field [0001] The invention belongs to the field of intent recognition, and in particular relates to a gaze intent recognition method and system based on historical visual behavior. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] With the development of population aging, the demand for daily life assistance for the elderly has increased significantly. Assistive robots have been increasingly accepted by society to care for the elderly and disabled. Assistive robots can recognize people's daily needs, and perform auxiliary actions by perceiving and processing demand information. The advent of assistive robots offers the potential to improve the quality of life and personal independence of older adults. In order to increase the acceptance of assistive robots by the elderly, robots need to be able to communicate naturally and smoot...

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
IPC IPC(8): G06K9/00G06K9/62
CPCG06V40/20G06F18/2411
Inventor 马昕聂玉洁宋锐荣学文李贻斌
Owner SHANDONG UNIV
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