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

Body language-based emotion perception approach using deep learning and ukf

A deep learning and physical technology, applied in the field of emotional perception based on body language, to achieve less deceptive effects

Active Publication Date: 2022-04-22
SOUTH CHINA UNIV OF TECH
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But this approach is useless if people's emotions are not shown on their faces

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
  • Body language-based emotion perception approach using deep learning and ukf
  • Body language-based emotion perception approach using deep learning and ukf
  • Body language-based emotion perception approach using deep learning and ukf

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0103] Current methods of emotion perception include electrocardiogram (ECG), facial expression, voice, text and gestures for emotion perception. Electrocardiograms contain reliable emotional information. The electrocardiographic approach has been shown to be effective for emotion perception. However, this method requires special equipment and requires direct contact with the human body. Facial expressions are the more obvious features that convey emotion. Through facial expressions, emotions can be given generality. But this approach is useless if people's emotions are not shown on their faces. In the process of speaking, pitch and speed can also reflect the emotion of the speaker. This feature is also used for emotion perception. When people read, the text can also express the author's emotion, so the present invention is also one of the ways of emotion perception. Text is an effective way of conveying emotion in written communication, but people don't often use text f...

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 an emotion perception method based on body language using deep learning and UKF, comprising the following steps: using Kinect to monitor people entering the Kinect workspace, and then calculating the skeleton points of the people in real time; using unscented Kalman filter to estimate the skeleton Point position, calculate the measurement error due to tracking error and equipment noise; use convolutional neural network method for static body movements, and use two-way long-short-term memory conditional random domain analysis for dynamic body movements; after processing the movements, we can get The output items of the features are directly put into the softmax classifier for recognition, and eight emotions are recognized. Emotion perception based on body language has the following advantages: first, body language can be more easily captured by sensors; second, body language noise based on emotion perception is relatively small; third, body language is less deceptive; fourth, body movements The capture does not affect or interfere with the participant's movements.

Description

technical field [0001] The invention relates to the technical field of industrial robot teaching, in particular to an emotion perception method based on body language using deep learning and UKF. Background technique [0002] Today, robots are always used to replace humans to perform repetitive and dangerous tasks. With the further development of computer technology, emotion perception has become a new requirement for robots. Humans expect robots to be able to sense human emotions during interactions and respond accordingly. When people communicate with each other, they can understand each other's emotional state by observing details such as speech rate and facial expression. The development of sensor technology and deep learning algorithms has made emotion perception based on information fusion possible. [0003] Emotion sensing methods are: Emotion sensing electrocardiogram (ECG), facial expressions, voice, words and gestures. Electrocardiograms contain reliable emotio...

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): G06V40/10G06V40/20G06V10/764G06K9/62
CPCG06V40/10G06V40/20G06F18/2415
Inventor 杜广龙张爱玲张博刘彩冰张平
Owner SOUTH CHINA UNIV OF TECH
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