Non-contact respiratory rate detection method based on an infrared thermal imager

An infrared thermal imaging camera, non-contact technology, applied in the evaluation of respiratory organs, neural learning methods, instruments, etc., can solve the problems of automatic measurement of unfavorable respiratory rate, and achieve the effects of avoiding discomfort, improving accuracy, and high precision

Pending Publication Date: 2021-12-14
HEFEI UNIV OF TECH
View PDF0 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method has limitations in ROI tracking and requires manual selection of ROI, which is not conducive to automatic measurement of respiration rate.

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 respiratory rate detection method based on an infrared thermal imager
  • Non-contact respiratory rate detection method based on an infrared thermal imager
  • Non-contact respiratory rate detection method based on an infrared thermal imager

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0065] As mentioned earlier, combined figure 1 As shown, the present embodiment provides a non-contact respiratory rate detection method based on an infrared thermal imager, which specifically includes the following steps:

[0066] S1: The infrared thermal imager model used in this example is FLIR A40M, and the apparatus is schematically Figure 5 As shown, the infrared camera is placed on a flat table, and the thermal imager is connected to the computer. The subject faces the thermal imager, the camera is about 0.5m, and the sampling frequency of the thermal imager is set to 25fps. The resolution is 240 × 320. The image acquisition environment is a regular environment. It does not require special settings. The subject can be collected by the image according to its own comfortable posture, and the head can move according to normal conditions. A large amount of face infrared image is collected by the device as a training set.

[0067] S2: Use the Labelimg image tag software to mark ...

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 relates to the technical field of non-contact respiratory rate measurement, in particular to a non-contact respiratory rate detection method based on an infrared thermal imager, which comprises the following steps of: (1) acquiring an infrared image sequence of a human face at least comprising a nose area as a training set; (2) marking a nostril area in the face infrared image in the training set, and recording the nostril area as ROI; (3) performing model training on the marked parameters by using a deep learning YOLO V3 method; (4) acquiring a to-be-measured face infrared image sequence as a measurement set, detecting each frame of image in the measurement set by using the model obtained by training, outputting a positioned ROI coordinate, and calculating a temperature average value of a positioned ROI region of each frame of image to obtain a curve of temperature changing along with time; (5) filtering the curve by using a low-pass filter; and (6) calculating to obtain the respiratory rate. According to the invention, the thermal infrared imager is used as measuring equipment, the temperature value can be directly obtained, the precision is quite high, and the measuring accuracy is greatly improved.

Description

technical field [0001] The invention relates to the technical field of non-contact respiration rate measurement, in particular to a non-contact respiration rate detection method based on an infrared thermal imager. Background technique [0002] Among the various physiological indicators of the human body, the respiratory rate is one of the basic indicators for evaluating respiratory diseases and an important indicator for judging respiratory dysfunction. Medically, some diseases can cause breathing disorders, and these diseases can be detected by abnormal respiratory rate. RR (Respiration Rate) value is closely related to asthma, apnea, respiratory alkalosis and other diseases, and it can also be used to predict pneumonia or lower respiratory tract infection. RR value greater than 27bpm is also an important predictor of cardiac arrest. [0003] At present, the detection method of respiration rate is mainly a contact measurement method, such as using a temperature sensor to ...

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): G06T7/00G06K9/00G06K9/32G06K9/46G06K9/62G06N3/04G06N3/08A61B5/00A61B5/01A61B5/08
CPCG06T7/0012G06N3/08A61B5/0816A61B5/015A61B5/72G06T2207/10048G06T2207/20081G06T2207/20084G06T2207/30201G06T2207/30004G06N3/047G06N3/048G06N3/045G06F18/2415G06F18/241
Inventor 舒双宝梁华俊王子艺张宇张育中
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