Six-degree-of-freedom face tracking method and device of non-contact physiological detection robot

A non-contact, physiological detection technology, applied in the field of visual servoing, can solve the problems of low operation efficiency and poor tracking effect of dynamic face tracking, and achieve the effect of simplifying the processing process and ensuring the tracking effect.

Active Publication Date: 2021-08-24
HEFEI UNIV OF TECH
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Benefits of technology

In this technology described by the current method for acquiring accurate 360° body pose data from an object's surface it involves converting its shape into scale based on how well they are at rest or moving around inside them. By calculating these bounds, we get the best possible viewing angle that allows us to see what objects appear when looking through their appearance. Additionally, there may be other features like muscle activity (such as swallowing), heartbility, blood flow etc., which help improve the accuracy of recognition over time. These technical improvements allow robots to perform various tasks such as interacting with patients during physical therapy sessions without touching themselves.

Problems solved by technology

The technical problem addressed by this patented technology relates to improving the accuracy and responsiveness of detecting people who may move around without being detected during physical examination procedures due to their lack of mobility. Current solutions involve fixed sensors that require trained staff members to operate them regularly over time.

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
  • Six-degree-of-freedom face tracking method and device of non-contact physiological detection robot
  • Six-degree-of-freedom face tracking method and device of non-contact physiological detection robot
  • Six-degree-of-freedom face tracking method and device of non-contact physiological detection robot

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0106] Such as figure 1 As shown, the present invention provides a 6-DOF human face tracking method of a non-contact physiological detection robot, the method comprising:

[0107] Fix the camera at the end of the robot;

[0108] Real-time facial feature point detection and tracking based on the face image collected by the camera, and the camera coordinate system O 3 The face pose information under p face ;

[0109] The face pose information p face Transformed into a face in the base coordinate system O 1 The lower pose T b ;

[0110] Based on the face in the base coordinate system O 1 The lower pose T b Calculate the optimal target pose T at the end of the robot t ;

[0111] Based on the face in the base coordinate system O 1 The lower pose T b and the optimal target pose T at the end of the robot t Perform proportional control to get the desired pose p target ;

[0112] Based on the desired pose p target Find the inverse kinematics solution to get the target join

Embodiment 2

[0206] A 6-degree-of-freedom face tracking device for a non-contact physiological detection robot, the device includes: a 6-degree-of-freedom robot, a camera fixed at the end of the robot, and a computer for acquiring face images collected by the camera and controlling the robot ;

[0207] The computers include:

[0208] The face pose information acquisition module is used for real-time facial feature point detection and tracking based on the face image collected by the camera, and obtains the camera coordinate system O 3 The face pose information under p face ;

[0209] Coordinate transformation module, used to convert face pose information p face Transformed into a face in the base coordinate system O 1 The lower pose T b ;

[0210] The optimal target pose generation module at the end of the robot is used to base the face on the base coordinate system O 1 The lower pose T b Calculate the optimal target pose T at the end of the robot t ;

[0211] Scale control module,

Embodiment 3

[0215] A computer-readable storage medium, which stores a computer program for 6-DOF face tracking of a non-contact physiological detection robot, wherein the computer program causes the computer to perform the following steps:

[0216] Real-time facial feature point detection and tracking based on the face image collected by the camera, and the camera coordinate system O 3 The face pose information under p face ;

[0217] The face pose information p face Transformed into a face in the base coordinate system O 1 The lower pose T b ;

[0218] Based on the face in the base coordinate system O 1 The lower pose T b Calculate the optimal target pose T at the end of the robot t ;

[0219] Based on the face in the base coordinate system O 1 The lower pose T b and the optimal target pose T at the end of the robot t Perform proportional control to get the desired pose p target ;

[0220] Based on the desired pose p target Find the inverse kinematics solution to get the targe

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 six-degree-of-freedom face tracking method and device of a non-contact physiological detection robot, and relates to the technical field of visual servo. According to the method, after the face pose information is received, the face pose information is converted to a base coordinate system according to the tail end pose of the robot, the optimal target pose of the tail end of the robot is obtained according to constraints, and then the error between the current face information and the ideal face pose is calculated. And then the expected pose of the camera is obtained by using a proportional controller, and an inverse kinematics solution is solved. And finally, the robot is controlled to move to the target posture. And the process is repeated every time a group of face information is received. Therefore, six-degree-of-freedom control and position-based visual servo are adopted, the tracking effect can be guaranteed, the processing process can be simplified, face image acquisition can be completed by actively cooperating with a patient, and a non-contact physiological detection task can be completed.

Description

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

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
Owner HEFEI UNIV OF 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