Non-contact emotional recognition method based on dual-mode sensor

A non-contact emotion recognition technology, applied in the field of emotion recognition, can solve the problems of increasing measurement error and discomfort of subjects, and achieve the effects of reducing measurement error, wide applicability, and improving accuracy

Active Publication Date: 2019-09-06
NANJING UNIV OF SCI & TECH
View PDF10 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Existing studies on emotion recognition use physiological signals in a contact way, which will have a certain i

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
  • Non-contact emotional recognition method based on dual-mode sensor
  • Non-contact emotional recognition method based on dual-mode sensor
  • Non-contact emotional recognition method based on dual-mode sensor

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0131] The present invention is based on the non-contact emotion recognition method of bimodal sensor, comprises the following contents:

[0132] 1. Obtain the vital sign signal from the radar signal through the arctangent demodulation algorithm, and then extract the respiratory signal through a 0.15Hz-0.7Hz band-pass filter, and extract the heartbeat signal through a 0.8Hz-4Hz band-pass filter, and the breathing signal signal and heartbeat signal respectively Figure 5 , Image 6 shown.

[0133] 2. Obtain the face area through the Adaboost algorithm, and extract the heartbeat signal and optical flow signal from it, specifically:

[0134] 2-1. Through the Adaboost algorithm, the normalization technology based on the local histogram is introduced to improve the image contrast, and the Harr feature is selected as the detection feature to extract the face area such as Figure 7 shown;

[0135] 2-2. In the RGB three channels, the gray level average of the pixels in the face ar...

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 non-contact emotional recognition method based on a dual-mode sensor, wherein the non-contact emotional recognition method comprises the following steps: obtaining vital signsignals from echo signals collected by radar sensors, and extracting breathing signals and heartbeat signals from the signals; selecting a human face region from video images collected by video sensors, and obtaining the heartbeat signals and optical flow vector signals according to the human face region; for the heartbeat signals, carrying out heartbeat optimization treatment based on a light intensity method; based on the optical flow vector signals, carrying out body motion optimization treatment on the breathing signals obtained by the radar sensors; for the optimized heartbeat and breathing signals, carrying out characteristic extraction; carrying out characteristic selection on heartbeat characteristics and breathing characteristics, and establishing an emotion recognition model according to the screened characteristics; and according to the emotion recognition model, recognizing the emotion to be recognized. The non-contact measurement not only cannot introduce discomfort, butalso can reduce measurement error, and has the advantages of high recognition accuracy, good robustness and wider applicability.

Description

technical field [0001] The invention belongs to the field of emotion recognition, in particular to a non-contact emotion recognition method based on a dual-mode sensor. Background technique [0002] Emotion is a kind of psychological state that people face in the face of objective things. Different emotional states will have different effects on people's memory, learning and other behaviors. With the improvement of people's quality of life, the health awareness of the whole people has generally increased, and emotional health has become an issue of increasing concern to the public. Bad emotional states will affect the quality of personal life. Especially for some special groups, such as drivers, pilots, soldiers, doctors, etc., the emotional health of such groups may even affect public safety and social stability. Emotions play a very important role in people's daily life, and it is particularly important to identify and study emotions. [0003] Common emotion recognition ...

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): A61B5/16A61B5/0205A61B5/11
CPCA61B5/165A61B5/0205A61B5/11A61B5/7235
Inventor 洪弘肖雅萌顾陈孙理李彧晟朱晓华张宏宇
Owner NANJING UNIV OF SCI & 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