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

Intelligent forehead temperature measurement method based on Yolo neural network and application thereof

A neural network and neural network model technology, applied in the field of intelligent forehead temperature measurement based on Yolo neural network, can solve problems such as temperature interference, and achieve the effect of eliminating interference and solving speed problems

Pending Publication Date: 2020-12-01
SOUTH CHINA UNIV OF TECH
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In terms of intelligent temperature measurement, there are currently many intelligent temperature measurement cameras with face recognition. However, considering that some faces will be blocked under certain circumstances, such as: people wear masks when traveling, and the temperature measurement of the entire face area will be affected by the masks. The occlusion is subject to some interference

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
  • Intelligent forehead temperature measurement method based on Yolo neural network and application thereof
  • Intelligent forehead temperature measurement method based on Yolo neural network and application thereof
  • Intelligent forehead temperature measurement method based on Yolo neural network and application thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] Such as figure 1 As shown, the present embodiment provides a method of intelligent forehead temperature measurement based on Yolo neural network, comprising the following steps:

[0048] S1. Data preprocessing: collect face data sets, adjust the image format in batches, including face detection for large images with multiple faces, crop the face area to generate a single face image, and equidistant small images Padding, adjusted to the size of the input image of the Yolo neural network;

[0049] In this embodiment, the face data set can be collected by downloading a data set issued by a deep learning laboratory, such as the open source data set CelebA (Large-scale CelebFaces Attributes dataset), or crawling face data from the Internet using a crawler script. Then filter out the noise to form the original data set;

[0050] In this embodiment, the face detection module based on Opencv is used to detect the face, and the region containing the face is cut out, and all pi...

Embodiment 2

[0068] The present embodiment provides a kind of intelligent forehead temperature measuring device based on Yolo neural network, comprising: face data collection module, image preprocessing module, label file construction module, parameter setting module, neural network training module and forehead detection module;

[0069] In this embodiment, the face data collection module is used to collect the face data set,

[0070] In this embodiment, the image preprocessing module is used to perform face detection and crop the face area, intercept the image containing the forehead area, and adjust the image format in batches;

[0071] In this embodiment, the label file construction module is used to label the forehead area with label labeling software. The label content represents the coordinate position of the rectangle vertex of the forehead area, and exports the XML label file. The text conversion script generates Yolo according to the label of the XML label file. The label text fil...

Embodiment 3

[0076] Such as figure 2 As shown, the present embodiment provides a kind of intelligent forehead temperature measurement system based on Yolo neural network, is provided with the intelligent forehead temperature measurement device based on Yolo neural network of embodiment 2, also includes: temperature measurement camera, camera control module, communication module , forehead detection module, server and database;

[0077] The forehead detection module and database are deployed on the server, the camera and the camera control module form the front end, and the communication module communicates between the front end and the server. The main design operations of each module are as follows:

[0078] The forehead detection module uses the above-mentioned trained neural network model to realize the forehead detection algorithm, and can realize real-time positioning of the forehead area according to the picture data collected in real time by the camera;

[0079] Database: use the ...

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 intelligent forehead temperature measurement method based on a Yolo neural network and an application thereof. The method comprises the following steps of collecting a facedata set and carrying out image preprocessing; labeling the forehead area by using label labeling software, exporting an XML labeling file, and generating a label text file specified by the Yolo neural network according to the label of the XML labeling file; downloading a pre-trained weight of the Yolo neural network, converting a Yolo neural network model format, and setting model parameters; carrying out Yolo neural network training, storing network weights dynamically, and obtaining a forehead detection neural network model; and enabling the forehead detection neural network model to output the coordinate position of the pedestrian forehead, and positioning the temperature measurement acquisition range through the coordinate position of each pedestrian forehead so as to realize real-time temperature acquisition. According to the invention, real-time body temperature monitoring is carried out on pedestrians with face shielding behaviors in a specific detection range, so that the interference of face shielding is eliminated and the power consumption of the temperature measurement system is reduced.

Description

technical field [0001] The invention relates to the technical field of intelligent temperature measurement, in particular to an intelligent forehead temperature measurement method based on Yolo neural network and its application. Background technique [0002] With the rapid development of deep learning, face recognition technology has developed to a very mature stage. Since only relying on the features of facial features and facial contours can fully recognize the face, but there is no authoritative implementation plan for the recognition and analysis of the forehead. In terms of intelligent temperature measurement, there are currently many intelligent temperature measurement cameras with face recognition. However, considering that some faces will be blocked under certain circumstances, such as: people wear masks when traveling, and the temperature measurement of the entire face area will be affected by the masks. occlusion suffers from some interference. Contents of the ...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V40/161G06V40/168G06N3/045G06F18/2415
Inventor 唐杰宋弘健肖鸿昭帖千枫黄翊琳薛又天
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

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