KR102399453B1 - Methods and apparatuses for estimating robust body temperature using bio-signal of skin image - Google Patents

Abstract

The present invention relates to a method and apparatus for measuring a robust body temperature using a biosignal of a skin image, and the method and apparatus for measuring a robust body temperature using a biosignal of a skin image according to an embodiment of the present invention include: estimating at least one bio-signal using a color signal, estimating at least one body temperature corresponding to each of the at least one bio-signal by applying the estimated at least one bio-signal to a regression analysis equation; estimating a skin temperature using color data of a skin region of interest, estimating a third body temperature by applying the estimated skin temperature to a regression analysis equation, and the estimated at least one body temperature and the estimated third body temperature estimating the robust body temperature by averaging the body temperatures, and estimating the improved body temperature by averaging the body temperatures calculated at a plurality of sites.

Description

Robust body temperature measurement method and device using biosignals of skin images

The present invention relates to a robust body temperature measurement method and apparatus using a biosignal of a skin image.

In order to keep body temperature constant at all times, the body continuously produces biological effects through the autonomic nervous system (sympathetic nerves, parasympathetic nerves), and the pulse and respiration frequency and rhythm are closely related to the function control of the autonomic nervous system (sympathetic nerves, parasympathetic nerves). related The rhythm of breathing is related to the rhythm of the pulse, the pulse increases during inhalation and slows down during exhalation. This connection between respiration and pulse is called Respiratory Sinus Arrhythmia (RSA). During exhalation, the pressure in the ribcage increases and the oxygen concentration in the blood decreases, thereby reducing the contraction of the heart in terms of energy efficiency. Respiration is controlled by the autonomic nervous system. In addition, since the autonomic nervous system (sympathetic nerve, parasympathetic nerve) can be controlled by the change in the frequency and rhythm of pulse wave and respiration, it is closely related to body temperature. However, in the prior art, it is difficult to find a case in which pulse and respiration signals are applied to the improvement of body temperature measurement technology.

The non-contact body temperature measurement technology using a thermal image measures the surface temperature including the skin temperature through the thermal image and displays it in color to measure the subject's body temperature (forehead or earlobe, etc.) in a non-contact manner. However, it has disadvantages in that expensive equipment is required to take a thermal image and it is greatly affected by external environmental factors (hot wind, cold wind, etc.).

A non-contact body temperature measurement technology using color data of a skin image estimates skin temperature using color data calculated from a skin image and measures body temperature using the estimated skin temperature. However, there were no cases of application of body temperature measurement technology that reflects changes in biosignals (pulse, respiration, etc.) using color data from skin images.

Therefore, in order to improve (improve) the non-contact body temperature measurement technology using color data, the bio-signals (pulse rate, respiration rate) and the skin temperature calculated from the skin image are used in a non-contact manner in the general camera, infrared camera, zoom camera, etc. owned by the user. There is a need for a method to measure body temperature using

Japanese Patent Laid-Open Patent JP2016-190022, 2016.11.10. open

Embodiments of the present invention are for measuring body temperature using a skin temperature and a biosignal (pulse rate, respiration rate) calculated using color data of a skin image captured by a smart device equipped with a camera possessed by a user, An object of the present invention is to provide a robust method and apparatus for measuring body temperature using biosignals of skin images. An embodiment of the present invention is to improve and compensate for the above-mentioned problems because the contact-type body temperature measuring equipment and the technology for measuring body temperature using the skin temperature calculated from color data of the skin image have the above problems. An embodiment of the present invention aims at a system for measuring body temperature by using a user's bio-signals (pulse rate, respiration rate) and skin temperature in a skin image taken through a smart device equipped with a camera.

However, the problem to be solved by the present invention is not limited thereto, and may be variously expanded in an environment within the scope not departing from the spirit and scope of the present invention.

According to an embodiment of the present invention, there is provided a body temperature measuring method performed by a body temperature measuring apparatus, the method comprising: estimating at least one bio-signal using color signals calculated from a plurality of skin regions of interest; estimating at least one body temperature corresponding to each of the at least one bio-signal by applying the estimated at least one bio-signal to a regression analysis equation; estimating a skin temperature using color data of the skin region of interest; estimating a third body temperature by applying the estimated skin temperature to a regression analysis equation; estimating a robust body temperature by averaging the at least one estimated body temperature and the estimated third body temperature; and estimating the improved body temperature by estimating the improved body temperature by averaging the body temperature calculated from the plurality of regions.

In the estimating of the skin temperature, the skin temperature may be estimated by applying the color data extracted from the skin ROI to a skin temperature regression analysis equation.

In the estimating of the skin temperature, the improved skin temperature may be estimated by applying the estimated skin temperature to an improved skin temperature regression analysis equation.

The at least one biosignal may include at least one of a pulse rate estimated from a pulse-related frequency band in the color signal of the skin region of interest and a respiration rate estimated from a respiration-related frequency band in the color signal of the skin region of interest. Signals may be included.

The estimating of the at least one body temperature may include estimating the first body temperature by applying the estimated pulse rate to a first body temperature regression analysis equation.

The first body temperature regression analysis equation may be calculated as a regression analysis equation by applying regression analysis to the estimated pulse rate and body temperature measured by a thermometer.

The estimating of the at least one body temperature may include estimating the improved first body temperature by applying the estimated first body temperature to a first improved body temperature regression analysis equation.

The first improved body temperature regression analysis equation may be calculated as an improved regression analysis equation by applying regression analysis to the estimated pulse rate and body temperature measured by the thermometer.

In the estimating of the at least one body temperature, the second body temperature may be estimated by applying the estimated respiration rate to a second body temperature regression analysis equation.

The second body temperature regression analysis equation may be calculated as a regression analysis equation by applying regression analysis to the estimated respiration rate and body temperature measured by a thermometer.

The estimating of the at least one body temperature may include estimating an improved second body temperature by applying the estimated second body temperature to a second improved body temperature regression analysis equation.

The second improved body temperature regression analysis equation may be calculated as an improved regression analysis equation by applying regression analysis to the estimated second body temperature and the body temperature measured by the thermometer.

The method may further include estimating at least one biosignal for each of a plurality of regions by using a color signal of each of the skin regions of interest in the plurality of regions, and estimating at least one body temperature for each of the plurality of regions. there is.

The method may further include estimating an improved body temperature by averaging at least one body temperature for each of the estimated plurality of regions and the estimated third body temperature.

On the other hand, according to another embodiment of the present invention, an image acquisition module for acquiring a skin image including a plurality of skin regions of interest; a memory storing one or more programs; and a processor executing the stored one or more programs, wherein the processor estimates at least one biosignal using the color signals calculated from the acquired skin regions of interest in the plurality of regions, and the estimated at least one Estimate at least one body temperature corresponding to each of the at least one bio-signal by applying the bio-signal to a regression analysis equation, estimate the skin temperature using the color data of the skin ROI, and regress the estimated skin temperature The third body temperature is estimated by applying the analysis formula, the robust body temperature is estimated by averaging the at least one estimated body temperature and the estimated third body temperature, and the body temperature is improved by averaging the body temperature calculated at the plurality of sites A robust body temperature measuring apparatus using a biosignal of a skin image for estimating the skin image may be provided.

The processor may estimate the skin temperature by applying the color data extracted from the skin ROI to a skin temperature regression analysis equation.

The processor may estimate the improved skin temperature by applying the estimated skin temperature to an improved skin temperature regression analysis equation.

At least one biosignal includes at least one of a pulse rate estimated from a pulse-related frequency band in the color signal of the skin region of interest and a respiration rate estimated from a respiration-related frequency band in the color signal of the skin region of interest. may be included.

The processor may estimate the first body temperature by applying the estimated pulse rate to a first body temperature regression analysis equation.

The first body temperature regression analysis equation may be calculated as a regression analysis equation by applying regression analysis to the estimated pulse rate and body temperature measured by a thermometer.

The processor may estimate the improved first body temperature by applying the estimated first body temperature to a first improved body temperature regression analysis equation.

The first improved body temperature regression analysis equation may be calculated as an improved regression analysis equation by applying regression analysis to the estimated pulse rate and body temperature measured by the thermometer.

The processor may estimate the second body temperature by applying the estimated respiration rate to a second body temperature regression analysis equation.

The second body temperature regression analysis equation may be calculated as a regression analysis equation by applying regression analysis to the estimated respiration rate and body temperature measured by a thermometer.

The processor may estimate the improved second body temperature by applying the estimated second body temperature to a second improved body temperature regression analysis equation.

The second improved body temperature regression analysis equation may be calculated as an improved regression analysis equation by applying regression analysis to the estimated second body temperature and the body temperature measured by the thermometer.

The processor may estimate at least one biosignal for each of the plurality of regions by using the color signal of each of the skin ROIs of the plurality of regions, and estimate at least one body temperature for each of the plurality of regions.

The processor may estimate the improved body temperature by averaging at least one body temperature of each of the estimated plurality of parts and the estimated third body temperature.

Meanwhile, according to another embodiment of the present invention, there is provided a non-transitory computer-readable storage medium for storing instructions that, when executed by a processor, cause the processor to execute a method, the method comprising: a plurality of regions of skin interest estimating at least one biosignal using the calculated color signal; estimating at least one body temperature corresponding to each of the at least one bio-signal by applying the estimated at least one bio-signal to a regression analysis equation; estimating a skin temperature using color data of the skin region of interest; estimating a third body temperature by applying the estimated skin temperature to a regression analysis equation; estimating a robust body temperature by averaging the at least one estimated body temperature and the estimated third body temperature; and estimating the improved body temperature by estimating the body temperature calculated at the plurality of sites by weighted average, a non-transitory computer-readable storage medium may be provided.

The disclosed technology may have the following effects. However, this does not mean that a specific embodiment should include all of the following effects or only the following effects, so the scope of the disclosed technology should not be understood as being limited thereby.

Embodiments of the present invention reflect both changes in biosignals (pulse rate, respiration rate) and skin temperature that are improved (improved) compared to the conventional non-contact skin image skin temperature-based body temperature measuring method for measuring body temperature and body temperature A signal-based non-contact body temperature measurement method and apparatus may be provided.

1 is a flowchart illustrating a robust body temperature measurement method using a biosignal of a skin image according to an embodiment of the present invention.
2 is a flowchart illustrating in detail a method for measuring a robust body temperature using a biosignal of a skin image according to an embodiment of the present invention.
3 to 5 are diagrams illustrating a method of estimating each body temperature in a robust body temperature measurement method using a biosignal of a skin image according to an embodiment of the present invention.
6 to 9 are diagrams conceptually illustrating biosignal measurement using a skin image according to an embodiment of the present invention.
10 is a flowchart illustrating a method of estimating a first body temperature using a pulse rate used in an embodiment of the present invention.
11 and 12 are diagrams showing examples of a method for calculating a first body temperature regression analysis equation and an example of a first body temperature regression analysis equation used in an embodiment of the present invention.
13 is a diagram illustrating a method of calculating a first improved body temperature regression analysis equation used in an embodiment of the present invention.
14 is a flowchart illustrating a method of estimating a second body temperature using a respiration rate according to an embodiment of the present invention.
15 and 16 are diagrams illustrating examples of a method for calculating a second body temperature regression analysis equation and a second body temperature regression analysis equation used in an embodiment of the present invention.
17 is a diagram illustrating a method of calculating a second improved body temperature regression analysis equation used in an embodiment of the present invention.
18 and 19 are flowcharts illustrating a method of estimating an improved body temperature by averaging the skin ROI of each of the plurality of regions and the body temperature estimated in each of the plurality of regions, which are used in an embodiment of the present invention.
20 is a block diagram for explaining the configuration of a robust body temperature measuring apparatus using a biosignal of a skin image according to an embodiment of the present invention.

Since the present invention can apply various transformations and can have various embodiments, specific embodiments are illustrated in the drawings and described in detail in the detailed description. However, this is not intended to limit the present invention to a specific embodiment, it can be understood to include all transformations, equivalents or substitutes included in the spirit and scope of the present invention. In describing the present invention, if it is determined that a detailed description of a related known technology may obscure the gist of the present invention, the detailed description thereof will be omitted.

Terms such as first, second, etc. may be used to describe various elements, but the elements are not limited by the terms. The terms are used only for the purpose of distinguishing one component from another.

The terms used in the present invention are only used to describe specific embodiments, and are not intended to limit the present invention. The terms used in the present invention have been selected as currently widely used general terms as possible while considering the functions in the present invention, but these may vary depending on the intention, precedent, or emergence of new technology of those of ordinary skill in the art. In addition, in a specific case, there is a term arbitrarily selected by the applicant, and in this case, the meaning will be described in detail in the description of the corresponding invention. Therefore, the term used in the present invention should be defined based on the meaning of the term and the overall content of the present invention, rather than the name of a simple term.

The singular expression includes the plural expression unless the context clearly dictates otherwise. In the present invention, terms such as "comprises" or "have" are intended to designate that the features, numbers, steps, operations, components, parts, or combinations thereof described in the specification exist, but one or more other features It should be understood that this does not preclude the existence or addition of numbers, steps, operations, components, parts, or combinations thereof.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings, and in the description with reference to the accompanying drawings, the same or corresponding components are given the same reference numerals, and the overlapping description thereof will be omitted. do.

In order to keep body temperature constant at all times, the body continuously produces biological effects through the autonomic nervous system (sympathetic nerves, parasympathetic nerves), and the pulse and respiration frequency and rhythm are closely related to the function control of the autonomic nervous system (sympathetic nerves, parasympathetic nerves). related The rhythm of breathing is related to the rhythm of the pulse, the pulse increases during inhalation and slows down during exhalation. This connection between respiration and pulse is called Respiratory Sinus Arrhythmia (RSA). During exhalation, the pressure in the ribcage increases and the oxygen concentration in the blood decreases, thereby reducing the contraction of the heart in terms of energy efficiency. Respiration is controlled by the autonomic nervous system. In addition, since the autonomic nervous system (sympathetic nerve, parasympathetic nerve) can be controlled by the change in the frequency and rhythm of pulse wave and respiration, it is closely related to body temperature. Therefore, we try to improve the temperature measurement technology by grafting pulse and respiration signals.

An embodiment of the present invention relates to a method and apparatus for robust body temperature measurement using biological signals (pulse rate, respiration rate) of skin images. In an embodiment of the present invention, a skin image (face, hand, etc.) is captured and a plurality of skin regions of interest (ROI) are detected. An embodiment of the present invention converts the RGB color system of the detected skin region of interest into the YCgCo color system to calculate the average value of Cg color data, and converts the average value of the Cg color data to the pulse and respiration-related frequency bands in BPF (Band Pass Filter) ), FFT (Fast Fourier Transform) is applied, and after selecting a frequency band of interest related to pulse and respiration, iFFT (Inverse Fast Fourier Transform) is applied to calculate a pulse wave signal and a respiration signal. Pulse RR interval and respiration PP interval average values are calculated by detecting the pulse and respiration peak positions from the pulse wave and respiration signals, and the pulse rate and respiration rate are estimated. The first body temperature may be estimated by applying the estimated pulse rate to the 'first body temperature regression analysis equation DB', and the first improved body temperature may be estimated by applying the estimated pulse rate to the 'first improved body temperature regression analysis equation DB'. The second body temperature may be estimated by applying the estimated respiration rate to the 'second body temperature regression analysis equation DB', and the second improved body temperature may be estimated by applying the estimated respiration rate to the 'second improved body temperature regression analysis equation DB'. In addition, the skin temperature calculated by applying the average value of the color data calculated in the skin region of interest to the 'skin temperature regression analysis formula DB' is applied to the 'third body temperature regression analysis formula DB' to estimate the third body temperature, and the 'third body temperature regression analysis formula DB' The third improved body temperature can be estimated by applying to the 'improved body temperature regression analysis equation DB'. A more improved body temperature can be estimated by averaging the body temperature calculated from multiple parts of the skin image. Strong body temperature can be estimated. Furthermore, the present invention can measure body temperature using various color systems of the skin region.

In order to achieve the above technical problem, an embodiment of the present invention includes the steps of measuring body temperature using a thermometer and calculating 'real body temperature DB', and using a smart device equipped with a camera to image skin (face, hand, etc.) Steps of photographing a skin region, detecting a skin region in the captured skin image, converting the RGB color system of the detected skin region into a specified color system, and converting the pulse and respiration-related frequency bands to the average value of the color data calculated from the skin image. Step of applying BPF (Band Pass Filter) and FFT (Fast Fourier Transform), after selecting a frequency band of interest related to pulse and respiration, applying iFFT (Inverse Fourier Transform) to calculate a pulse wave and respiration signal, the calculated pulse wave and respiration Detecting the peak point from the signal, calculating the average pulse RR interval and respiration PP interval, estimating the pulse rate and respiration rate, and estimating the first body temperature by applying the estimated pulse rate to the 'first body temperature regression equation DB' Step, estimating the second body temperature by applying the estimated respiration rate to the 'second body temperature regression analysis formula DB', applying the calculated color data average value to the 'skin temperature regression analysis formula DB' The step of estimating the third body temperature by applying the third body temperature regression analysis formula DB, and the first improvement improved by applying the calculated first body temperature, the second body temperature, and the third body temperature to the 'Improved body temperature regression analysis formula DB' measuring the measured body temperature, the second improved body temperature, and the third improved body temperature; and estimating the robust body temperature by applying a weighted average and bias value adjustment to the calculated first body temperature, second body temperature, and third body temperature.

1 is a flowchart illustrating a robust body temperature measurement method using a biosignal of a skin image according to an embodiment of the present invention.

In step S101, the body temperature measuring apparatus detects a skin ROI of a plurality of regions by taking a skin image.

In step S102, the body temperature measuring apparatus calculates a color signal from the detected skin regions of interest in a plurality of regions.

In step S103, the body temperature measuring apparatus estimates at least one biosignal using the color signal calculated in the skin ROI.

In step S104, the body temperature measuring apparatus estimates at least one body temperature corresponding to the at least one body signal by applying the estimated at least one bio-signal to the regression analysis equation.

In step S105, the body temperature measuring apparatus estimates the skin temperature by using the color data of the skin ROI.

In step S106, the body temperature measuring device estimates the third body temperature by applying the estimated skin temperature to the regression analysis equation.

In step S107, the body temperature measuring apparatus estimates the robust body temperature by averaging the at least one estimated body temperature and the estimated third body temperature.

In step S108 , the body temperature measuring device measures the improved (improved) body temperature by averaging the body temperatures calculated from a plurality of sites.

2 is a flowchart illustrating in detail a method for measuring a robust body temperature using a biosignal of a skin image according to an embodiment of the present invention.

In step S201, the body temperature measuring apparatus detects a skin ROI of a plurality of regions by taking a skin image.

In step S202, the body temperature measuring apparatus calculates color signals in the skin ROI in a plurality of regions.

In step S203, the body temperature measuring apparatus estimates a pulse rate from a pulse-related frequency band, and estimates an improved first body temperature by applying the estimated pulse rate to a regression analysis equation.

In step S204, the body temperature measuring apparatus estimates the respiration rate from the respiration-related frequency band, and estimates the improved second body temperature by applying the estimated respiration rate to the regression analysis equation.

In step S205, the body temperature measuring apparatus estimates the skin temperature by applying the color data to the skin temperature regression analysis equation, and estimates the improved third body temperature by applying the estimated skin temperature to the regression analysis equation.

In step S206 , the body temperature measuring apparatus estimates a robust body temperature by applying a weighted average and bias value adjustment to the improved first body temperature, second body temperature, and third body temperature.

In step S207, the body temperature measuring device measures the improved (improved) body temperature by averaging the body temperatures calculated from a plurality of sites.

3 to 5 are diagrams illustrating a method of estimating each body temperature in a robust body temperature measurement method using a biosignal of a skin image according to an embodiment of the present invention.

The body temperature measuring device, for example, takes a skin image (face, hand, etc.) using a camera of a smart device, and converts the RGB color system of the skin area designated as an example of various color systems to the YCgCo color system and extracts Cg Calculate the average value of color data.

A method of estimating the first body temperature related to the pulse will be described with reference to FIG. 3 .

In step S301, the body temperature measuring device takes a skin image and calculates a color signal from the detected skin ROI.

In step S302, the body temperature measuring apparatus applies a BPF (Band Pass Filter) and FFT (Fast Fourier Transform) as a pulse-related frequency band to the calculated Cg color signal.

In step S303, the body temperature measuring apparatus calculates a pulse wave signal by applying an Inverse Fast Fourier Transform (iFFT) after selecting a pulse-related frequency band of interest.

In steps S304 and S305, the body temperature measuring device detects the position of the pulse peak (Peak) from the pulse wave signal, and applies the average value of the pulse RR interval (peak-to-peak interval) calculated from the detected peak to [Equation 1] below Estimate your pulse rate.

The image Fps (Frame per second) refers to the number of images taken per second, and in the above formula, the number of frames per second of the detected skin image is indicated.

In step S306, the body temperature measuring apparatus estimates the first body temperature by applying the estimated pulse rate to the 'first body temperature regression analysis equation DB'.

In step S307 , the body temperature measuring apparatus may estimate the first improved body temperature by applying the estimated first body temperature to the 'first improved body temperature regression analysis equation DB'.

A method of estimating the second body temperature related to respiration will be described with reference to FIG. 4 .

In step S401, the body temperature measuring device takes a skin image and calculates a color signal from the detected skin ROI.

In step S402, the body temperature measuring apparatus applies a BPF (Band Pass Filter) and FFT (Fast Fourier Transform) to the calculated Cg color signal as a respiration-related frequency band.

In step S403, the body temperature measuring device calculates a respiration signal by applying an Inverse Fast Fourier Transform (iFFT) after selecting a respiration-related frequency band of interest.

In steps S404 and S405, the body temperature measuring device detects the position of the respiratory peak (Peak) from the respiratory signal, and applies the average value of the respiratory PP interval (peak-peak interval) calculated from the detected peak to [Equation 1] below Estimate the respiratory rate.

The image Fps (Frame per second) refers to the number of images taken per second, and in the above formula, the number of frames per second of the detected skin image is indicated.

In step S406, the body temperature measuring apparatus estimates the second body temperature by applying the estimated respiration rate to the 'second body temperature regression analysis equation DB'.

In step S407 , the body temperature measuring apparatus may estimate the second improved body temperature by applying the estimated second body temperature to the 'second improved body temperature regression analysis equation DB'.

A method of estimating the third body temperature related to the skin temperature will be described with reference to FIG. 5 .

In step S501, the body temperature measuring apparatus estimates the skin temperature by applying the average value of the color data calculated in the skin ROI to the 'skin temperature regression analysis formula DB'.

In step S502, the body temperature measuring apparatus estimates the improved skin temperature by applying the calculated skin temperature to the 'improved skin temperature regression analysis DB'.

In step S503, the body temperature measuring apparatus estimates the third body temperature by applying the improved skin temperature to the 'third body temperature regression analysis formula DB'.

In step S504 , the body temperature measuring apparatus may estimate the third improved body temperature by applying the estimated third body temperature to the 'third improved body temperature regression analysis equation DB'.

Meanwhile, the body temperature measuring apparatus estimates a further improved body temperature by averaging the weighted average of each of the first improved body temperature, the second improved body temperature, and the third improved body temperature calculated from a plurality of parts of the skin image, and the improved first body temperature; A robust body temperature is estimated by applying a weighted average and bias value adjustment to the second body temperature and the third body temperature.

6 to 9 are diagrams conceptually expressing body temperature measurement using a skin image according to an embodiment of the present invention.

As shown in FIGS. 6 and 7 , the body temperature measuring device detects a plurality of skin regions of interest (ROI ₁ , ROI ₂ ) from a skin image taken using a smart device equipped with a camera, and detects the RGB color system of the skin region. is converted to the YCgCo color system to calculate the average value of Cg color data.

8 and 9, the body temperature measuring apparatus applies BPF (Bans Pass Filter) and FFT (Fast Fourier Transform) to the calculated Cg color signal as a pulse and respiration-related frequency band, and applies a pulse-related frequency band (0.64). ~3.6 Hz) and respiration-related frequency bands (0.14~0.5Hz) apply iFFT (Inverse Fast Fourier Transform) to calculate a pulse wave signal and a respiration signal. The body temperature measuring device detects the positions of the pulse wave peak and respiration peak from the pulse wave and respiration signals calculated by applying iFFT, and the pulse RR interval (peak-peak interval) and respiration PP interval (Peak-Peak interval) calculated from each detected peak The pulse rate and respiration rate are estimated by applying the average value of the pulse RR interval calculated using the peak-peak interval) to the above [Equation 1] and the average value of each respiration PP interval to the above [Equation 2].

The body temperature measuring device can estimate the first body temperature by applying the estimated pulse rate to the 'first body temperature regression analysis equation DB', and estimate the first improved body temperature by applying the estimated pulse rate to the 'first improved body temperature regression analysis equation DB'. there is. The body temperature measuring device estimates the second body temperature by applying the estimated respiration rate to the 'second body temperature regression analysis formula DB'. The second improved body temperature can be estimated by applying to the 'second improved body temperature regression analysis equation DB'. In addition, the body temperature measuring device estimates the improved skin temperature by applying the average value of the color data calculated in the skin region of interest to the 'skin temperature regression analysis DB' and applying the calculated skin temperature to the 'improved skin temperature regression analysis DB'. In addition, it is possible to estimate the third body temperature by applying it to the '3rd body temperature regression analysis equation DB', and to estimate the third improved body temperature by applying it to the '3rd improved body temperature regression analysis equation DB'. The body temperature measuring device estimates a further improved body temperature by averaging the weighted average of each of the first improved body temperature, the second improved body temperature, and the third improved body temperature calculated from multiple regions (ROI ₁ , ROI ₂ ) of the skin image, and The robust body temperature is estimated by applying a weighted _average and bias value adjustment to the first body temperature, the _second body temperature, and the third body temperature. improved) temperature is measured.

10 is a flowchart illustrating a method of estimating a first body temperature using a pulse rate used in an embodiment of the present invention.

As shown in FIG. 10 , the body temperature measuring apparatus estimates body temperature by using a pulse rate calculated from a skin image captured using a smart device equipped with a camera.

In steps S601 and S602, the body temperature measuring apparatus captures a skin image, detects a plurality of skin ROIs, and calculates color signals from the plurality of skin ROIs.

In step S603, the body temperature measuring device applies a pulse-related frequency band BPF (Band Pass Filter) and FFT (Fast Fourier Transform) to the color signals calculated from multiple regions (ROI ₁ , ROI ₂ ) of the skin image, and applies a pulse-related frequency band A pulse wave signal is calculated by applying iFFT (Inverse Fast Fourier Transform) at (0.64 to 3.6 Hz), and a peak point is detected from the pulse wave signal.

In step S604, the body temperature measuring apparatus estimates the pulse rate by calculating the pulse RR interval (peak-to-peak interval) from the detected peak and using the average value of the pulse RR interval.

In step S605, the body temperature measuring apparatus estimates the first body temperature by applying the estimated pulse rate to the first body temperature regression analysis equation.

In step S606, the body temperature measuring apparatus estimates the first improved body temperature by applying the estimated first body temperature to the 'first improved body temperature regression analysis equation DB'.

In step S607, the body temperature measuring apparatus estimates a further improved body temperature by averaging the first improved body temperature calculated in each of the plurality of parts as a weighted average.

11 and 12 are diagrams showing examples of a method for calculating a first body temperature regression analysis equation and an example of a first body temperature regression analysis equation used in an embodiment of the present invention.

The body temperature measuring device calculates the first body temperature regression analysis equation (linear or curve) and stores it in the 'first body temperature regression analysis equation DB'.

In step S701, the body temperature measuring apparatus captures a skin image, detects a plurality of skin ROIs, and calculates a color signal from the plurality of skin ROIs.

In step S702, the body temperature measuring device applies BPF (Band Pass Filter) and FFT (Fast Fourier Transform) to the color signal as a pulse-related frequency band, and iFFT (Inverse Fast Fourier Transform) to a pulse-related frequency band (0.64 to 3.6 Hz) to calculate a pulse wave signal and detect a peak point from the pulse wave signal.

In step S703, the body temperature measuring apparatus estimates the pulse rate by calculating the pulse RR interval (peak-to-peak interval) from the detected peak and using the average value of the pulse RR interval.

In step S704, the body temperature measuring apparatus stores the estimated pulse rate in the 'pulse rate DB of the skin image'.

Meanwhile, in step S705, the body temperature measuring device stores the body temperature measured using the electronic thermometer in the 'body temperature DB'.

And in step S706, the body temperature measuring device applies regression analysis to the pulse rate DB and the body temperature DB of the skin image to calculate a regression analysis equation (linear or curve) and stores it in the 'first body temperature regression analysis equation DB'. As an example, FIG. 12 shows an example of a regression analysis equation that is a result of a regression analysis between a pulse rate and body temperature.

13 is a diagram illustrating a method of calculating a first improved body temperature regression analysis equation used in an embodiment of the present invention.

13 , the body temperature measuring apparatus calculates a first improved body temperature regression analysis equation (linear or curve) and stores it in the 'first improved body temperature regression analysis equation DB'.

In steps S801 and S802, the body temperature measuring apparatus captures a skin image, detects a region of interest in a plurality of skin regions, and calculates a color signal in a plurality of regions (ROI ₁ , ROI ₂ ) of the skin image.

In step S803, the body temperature measuring device applies a pulse-related frequency band BPF (Band Pass Filter) and FFT (Fast Fourier Transform) to the color signal, and performs an iFFT (Inverse Fast Fourier Transform) with a pulse-related frequency band (0.64 to 3.6 Hz). It is applied to calculate a pulse wave signal and detects a peak point from the pulse wave signal.

In step S804, the body temperature measuring apparatus estimates the pulse rate by calculating the pulse RR interval (peak-to-peak interval) from the detected peak and using the average value of the pulse RR interval.

In step S805, the body temperature measuring apparatus calculates the first body temperature by applying the estimated pulse rate to the 'first body temperature regression analysis equation DB'.

In step S806, the body temperature measuring apparatus estimates the improved first body temperature by averaging the first body temperatures calculated in each of the plurality of regions (ROI ₁ , ROI ₂ ), and sets the estimated first body temperature as 'estimated body temperature of the skin image. It is stored in 'DB'.

Meanwhile, in step S807, the body temperature measuring apparatus stores the body temperature measured using the electronic thermometer in the 'body temperature DB'.

And in step S808, the body temperature measuring device applies regression analysis to the body temperature DB and body temperature DB estimated from the skin image, calculates a regression analysis equation (linear or curve), and stores it in the 'first improved body temperature regression analysis equation DB' .

14 is a flowchart illustrating a method of estimating a second body temperature using a respiration rate according to an embodiment of the present invention.

As shown in FIG. 14 , the body temperature measuring device estimates body temperature by using the respiration rate calculated from the skin image taken using a smart device equipped with a camera.

In steps S901 and S902, the body temperature measuring apparatus captures a skin image, detects a skin region of interest in multiple regions, and calculates color signals in multiple regions (ROI ₁ , ROI ₂ ) of the skin image.

In step S903, the body temperature measuring device applies BPF (Band Pass Filter) and FFT (Fast Fourier Transform) to the color signal as a respiration-related frequency band, and iFFT (Inverse Fast Fourier Transform) to a pulse-related frequency band (0.14-0.5 Hz) to calculate the respiration signal and detect the peak point from the respiration signal.

In step S904, the body temperature measuring device estimates the respiratory rate using the calculation of the respiratory PP interval (peak-peak interval) from the detected peak and the average value of the respiration PP interval.

In step S905, the body temperature measuring apparatus estimates the second body temperature by applying the estimated respiration rate to the second body temperature regression analysis equation.

In step S906, the body temperature measuring apparatus estimates the second improved body temperature by applying the estimated second body temperature to the 'second improved body temperature regression analysis equation DB'.

In step S907 , the body temperature measuring apparatus estimates a further improved body temperature by averaging the second improved body temperature calculated in each of the plurality of regions.

15 and 16 are diagrams illustrating examples of a method for calculating a second body temperature regression analysis equation and a second body temperature regression analysis equation used in an embodiment of the present invention.

The body temperature measuring device calculates the second body temperature regression analysis equation (linear or curve) and stores it in the 'second body temperature regression analysis equation DB'.

In steps S1001 and S1002, the body temperature measuring apparatus captures a skin image, detects a region of interest in a plurality of skin regions, and calculates a color signal in a plurality of regions (ROI ₁ , ROI ₂ ) of the skin image.

In step S1003, the body temperature measuring device applies BPF (Band Pass Filter) and FFT (Fast Fourier Transform) to the color signal as a respiration-related frequency band, and iFFT (Inverse Fast Fourier Transform) to a pulse-related frequency band (0.14-0.5 Hz) to calculate the respiration signal and detect the peak point from the respiration signal.

In step S1004, the body temperature measuring device calculates the respiratory PP interval (peak-to-peak interval) from the detected peak and estimates the respiration rate using the average value of the respiration PP interval, and stores the estimated respiration rate in the 'respiration rate DB of the skin image'. Save.

Meanwhile, in step S1005, the body temperature measuring device stores the body temperature measured using the electronic thermometer in the 'body temperature DB'.

And in step S1006, the body temperature measuring device applies regression analysis to the respiratory rate DB and body temperature DB of the skin image to calculate a regression analysis equation (linear or curve) and stores it in the 'second body temperature regression analysis equation DB'. As an example, FIG. 16 shows an example of a regression analysis equation that is a result of a regression analysis between respiration rate and body temperature.

17 is a diagram illustrating a method of calculating a second improved body temperature regression analysis equation used in an embodiment of the present invention.

17 , the body temperature measuring apparatus calculates a second improved body temperature regression analysis equation (linear or curve) and stores it in the 'second improved body temperature regression analysis equation DB'.

In steps S1101 and S1102, the body temperature measuring apparatus captures a skin image, detects a skin region of interest in multiple regions, and calculates color signals in multiple regions (ROI ₁ , ROI ₂ ) of the skin image.

In step S1103, the body temperature measuring device applies a respiration-related frequency band BPF (Band Pass Filter) and FFT (Fast Fourier Transform) to the color signal and iFFT (Inverse Fast Fourier Transform) with a pulse-related frequency band (0.14-0.5 Hz) It is applied to calculate the respiration signal and detects the peak point from the respiration signal.

In step S1104, the body temperature measuring device estimates the respiration rate using the calculation of the respiratory PP interval (peak-peak interval) from the detected peak and the average value of the respiration PP interval.

In step S1105, the body temperature measuring device calculates the second body temperature by applying the estimated respiration rate to the 'second body temperature regression analysis formula DB'.

In step S1106, the body temperature measuring apparatus estimates the improved second body temperature by averaging the second body temperature calculated in each of the plurality of regions (ROI ₁ , ROI ₂ ), and sets the estimated second body temperature as 'estimated body temperature of the skin image. It is stored in 'DB'.

Meanwhile, in step S1107, the body temperature measuring device stores the body temperature measured using the electronic thermometer in the 'body temperature DB'.

And in step S1108, the body temperature measuring device applies regression analysis to the body temperature DB and body temperature DB estimated from the skin image to calculate a regression analysis equation (linear or curve) and stores it in the 'second improved body temperature regression analysis equation DB' .

On the other hand, as an example of the regression analysis equation, a straight line obtained by representing a set of points on a scatter diagram with a straight line represents the relationship between two variables. A regression line equation can be derived using the 'respiration rate DB' and 'the body temperature DB measured using an electronic thermometer'. The body temperature measuring apparatus may derive a regression straight line equation using the DB of each of the estimated first body temperature, the second body temperature, and the third body temperature, and the body temperature DB measured using the electronic thermometer. The regression linear equation is as follows [Equation 3].

When y is the estimated body temperature, x represents the pulse rate or respiration rate estimated from the skin image.

When y is the improved body temperature, x represents the body temperature estimated from the skin image. In the result obtained by applying the actual data, the constant a and b values may change depending on the data used.

On the other hand, as another example of the regression analysis equation, a curve obtained by representing a set of points on a scatter diagram as a curve represents the relationship between two variables, and in the present invention, 'pulse rate and respiration rate DB estimated from skin images' A regression curve equation can be derived using the DB and 'body temperature DB measured using an electronic thermometer' ' can be used to derive the regression curve equation. The regression curve equation is as follows [Equation 4].

When y is the estimated body temperature, x represents the pulse rate or respiration rate estimated from the skin image.

When y is the improved body temperature, x represents the body temperature estimated from the skin image. In the result obtained by applying the actual data, the constants a, b, and c values may change depending on the data used.

18 and 19 are flowcharts illustrating a method of estimating an improved body temperature by averaging the skin ROI of each of the plurality of regions and the body temperature estimated in each of the plurality of regions, which are used in an embodiment of the present invention.

As shown in FIG. 18 , in step S1201, the body temperature measuring device takes a skin image (eg, face, hand, etc.) using a smart device equipped with a camera, and a plurality of skin regions of interest ( For example, left cheeks (ROI ₁ , ROI ₂ ) and right cheeks (ROI ₃ , ROI ₄ ) are detected, and a color signal is calculated in a plurality of skin regions of interest.

In steps S1202 and S1208, the body temperature measuring apparatus converts the color system of the detected skin region of interest and applies a band pass filter (BPF) and a fast Fourier transform (FFT) as a pulse and respiration-related frequency band to the calculated color signal.

In steps S1203 and S1209, the body temperature measuring apparatus selects a pulse- and respiration-related frequency band of interest and applies Inverse Fast Fourier Transform (iFFT) to calculate a pulse wave signal and a respiration signal.

In steps S1204 and S1210, the body temperature measuring device detects a pulse and a respiratory peak position from the calculated pulse wave and respiration signal.

In steps S1205 and S1211, the body temperature measuring device calculates the average value of the pulse RR interval and the respiration PP interval from the detected peak, and estimates the pulse rate and respiration rate.

In steps S1206 and S1207, the body temperature measuring device estimates the first body temperature by applying the estimated pulse rate to the 'first body temperature regression analysis equation DB', and applies the estimated pulse rate to the 'first improved body temperature regression analysis equation DB' to make the first improvement body temperature can be estimated.

And in steps S1212 and S1213, the body temperature measuring device estimates the second body temperature by applying the estimated respiration rate to the 'second body temperature regression equation DB'. The second improved body temperature can be estimated by applying to the 'second improved body temperature regression analysis formula DB'.

In step S1214, the body temperature measuring apparatus estimates a further improved body temperature by averaging each of the first improved body temperature and the second improved body temperature calculated from a plurality of parts of the skin image.

20 is a block diagram for explaining the configuration of a robust body temperature measuring apparatus using a biosignal of a skin image according to an embodiment of the present invention.

As shown in FIG. 20 , the body temperature measuring apparatus 100 according to an embodiment of the present invention includes an image acquisition module 110 , a memory 120 , and a processor 130 . However, not all illustrated components are essential components. The body temperature measuring apparatus 100 may be implemented by more components than the illustrated components, or the body temperature measuring apparatus 100 may be implemented by fewer components.

Hereinafter, a detailed configuration and operation of each component of the body temperature measuring apparatus 100 of FIG. 20 will be described.

The image acquisition module 110 acquires a skin image photographed through a mounted camera. The skin image includes a plurality of skin regions of interest.

The memory 120 stores one or more programs. The memory 120 includes the first body temperature regression analysis equation DB, the first improved body temperature regression analysis equation DB, the second body temperature regression analysis equation DB, the second improved body temperature regression analysis equation DB, the skin temperature regression analysis equation DB, the improved Includes skin temperature regression analysis equation DB, third body temperature regression analysis equation DB, third improved body temperature regression analysis equation DB, skin image pulse rate DB, body temperature DB, body temperature estimated from skin image DB, and skin image respiration rate DB do.

The processor 130 executes one or more programs stored in the memory 120 . The processor 130 estimates at least one bio-signal by using the color signal calculated from the skin ROI of a plurality of regions obtained by the image acquisition module 110, and applies the estimated at least one bio-signal to a regression analysis equation. estimating at least one body temperature corresponding to at least one biosignal, estimating the skin temperature using the color data of the skin region of interest, and estimating the third body temperature by applying the estimated skin temperature to a regression analysis equation, , a robust body temperature is estimated by weighted averaging the at least one estimated body temperature and the estimated third body temperature, and an improved body temperature is estimated by averaging body temperatures calculated at a plurality of sites.

According to embodiments, the processor 130 may estimate the skin temperature by applying the color data extracted from the skin ROI to a skin temperature regression analysis equation.

According to embodiments, the processor 130 may estimate the improved skin temperature by applying the estimated skin temperature to the improved skin temperature regression analysis equation.

According to embodiments, the at least one biosignal may include at least one of a pulse rate estimated from a pulse-related frequency band in the color signal of the skin region of interest and a respiration rate estimated from a breathing-related frequency band in the color signal of the skin region of interest. One biosignal may be included.

According to embodiments, the processor 130 may estimate the first body temperature by applying the estimated pulse rate to the first body temperature regression analysis equation.

The first body temperature regression analysis equation may be calculated as a regression analysis equation by applying regression analysis to the estimated pulse rate and body temperature measured by the thermometer.

According to embodiments, the processor 130 may estimate the improved first body temperature by applying the estimated first body temperature to the first improved body temperature regression analysis equation.

The first improved body temperature regression analysis equation may be calculated as an improved regression analysis equation by applying regression analysis to the estimated pulse rate and body temperature measured by the thermometer.

According to embodiments, the processor 130 may estimate the second body temperature by applying the estimated respiration rate to the second body temperature regression analysis equation.

According to embodiments, the second body temperature regression analysis equation may be calculated as a regression analysis equation by applying regression analysis to the estimated respiration rate and the body temperature measured by the thermometer.

According to embodiments, the processor 130 may estimate the improved second body temperature by applying the estimated second body temperature to the second improved body temperature regression analysis equation.

According to embodiments, the second improved body temperature regression analysis equation may be calculated as an improved regression analysis equation by applying regression analysis to the estimated second body temperature and the body temperature measured by the thermometer.

According to embodiments, the processor 130 may estimate at least one biosignal for each of a plurality of regions by using a color signal of each of the regions of interest in the skin of a plurality of regions, and estimate at least one body temperature for each of the plurality of regions. can

According to embodiments, the processor 130 may estimate the improved body temperature by averaging at least one body temperature of each of the estimated plurality of parts and the estimated third body temperature.

Meanwhile, the contents and results of a body temperature measurement experiment using a biosignal of a skin image will be described.

In order to check the performance of the body temperature measurement method using the biosignals of the skin image, a smart device camera and thermometer were used.

A face image was taken using the camera of a smart device, and body temperature was measured at the same time. In an embodiment of the present invention, the average value of Cg color data extracted by converting the RGB color system to the YCgCo color system is used as one example of the color systems.

Using a smart device equipped with a camera, a skin image (face, hand, etc.) is taken, and multiple skin regions of interest (left cheek (ROI ₁ , ROI ₂ ), right cheek (ROI ₃ , ROI ₄ )) are detected. .

The body temperature measuring device captures a skin image (face, hand, etc.) and detects a region of interest (ROI) of a plurality of skin regions. The body temperature measuring device converts the color system of the detected skin region of interest and applies BPF (Band Pass Filter) and FFT (Fast Fourier Transform) to the average value of the calculated color data as a frequency band related to pulse and respiration and frequency of interest related to pulse and respiration. By selecting a band and applying iFFT (Inverse Fast Fourier Transform), a pulse wave signal and a respiration signal are calculated. The body temperature measuring device calculates the average value of the pulse RR interval and respiration PP interval by detecting the pulse and respiration peak positions from the pulse wave and respiration signals, and estimates the pulse rate and respiration rate. The body temperature measuring device can estimate the first body temperature by applying the estimated pulse rate to the 'first body temperature regression analysis equation DB', and estimate the first improved body temperature by applying the estimated pulse rate to the 'first improved body temperature regression analysis equation DB'. there is. And the body temperature measuring device estimates the second body temperature by applying the estimated respiration rate to the 'second body temperature regression analysis formula DB'. The second improved body temperature can be estimated by applying to the 'second improved body temperature regression analysis equation DB'. In addition, the body temperature measuring device estimates the skin temperature by applying the average value of the color data calculated in the skin region of interest to the 'skin temperature regression analysis DB' and calculates the estimated skin temperature by applying the estimated skin temperature to the 'improved skin temperature regression analysis DB'. The third body temperature is estimated by applying the improved skin temperature to the third body temperature regression analysis equation DB. In addition, the body temperature measuring device may estimate the third improved body temperature by applying the 'third improved body temperature regression analysis formula DB'. The body temperature measuring apparatus may estimate a further improved body temperature by averaging each of the first improved body temperature, the second improved body temperature, and the third improved body temperature calculated from a plurality of parts of the skin image. The body temperature estimated by applying a weighted average and bias value adjustment to the first improved body temperature, the second improved body temperature, and the third improved body temperature was compared with the body temperature measured using the electronic thermometer and the error rate.

Face imaging and body temperature measurement were performed simultaneously for 1 minute per experiment, and the accuracy of body temperature measurement was calculated by performing a total of 25 experiments (5 times each for 5 subjects).

The body temperature measurement error rate using the skin temperature is shown in [Table 1] below.

The body temperature measurement error rate using biosignals is shown in [Table 2] below.

The weighted average body temperature measurement error rate of skin temperature and biosignals is shown in [Table 3] below.

In one embodiment of the present invention, in measuring body temperature using bio-signals (pulse rate, respiration rate) of skin images (face, hands, etc.), skin images are taken from a smart device owned by the user without a separate hardware module. and extracts a biosignal using the average value of the color data calculated in the region of interest, and the body temperature can be measured using this.

This may be used to provide a quick and convenient body temperature measurement system for general users. In addition, the body temperature can be measured by reducing the measurement time compared to the conventional method.

On the other hand, a non-transitory computer-readable storage medium for storing instructions that, when executed by a processor, cause the processor to execute a method, the method comprising: at least using a color signal calculated in a plurality of skin regions of interest estimating one biosignal; estimating at least one body temperature corresponding to each of the at least one bio-signal by applying the estimated at least one bio-signal to a regression analysis equation; estimating a skin temperature using color data of the skin region of interest; estimating a third body temperature by applying the estimated skin temperature to a regression analysis equation; estimating a robust body temperature by averaging the at least one estimated body temperature and the estimated third body temperature; and estimating the improved body temperature by estimating the body temperature calculated at the plurality of sites by weighted average, a non-transitory computer-readable storage medium may be provided.

Meanwhile, according to an embodiment of the present invention, the various embodiments described above are implemented as software including instructions stored in a machine-readable storage media readable by a machine (eg, a computer). can be The device is a device capable of calling a stored command from a storage medium and operating according to the called command, and may include an electronic device (eg, the electronic device A) according to the disclosed embodiments. When the instruction is executed by the processor, the processor may perform a function corresponding to the instruction by using other components directly or under the control of the processor. Instructions may include code generated or executed by a compiler or interpreter. The device-readable storage medium may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' means that the storage medium does not include a signal and is tangible, and does not distinguish that data is semi-permanently or temporarily stored in the storage medium.

In addition, according to an embodiment of the present invention, the methods according to the various embodiments described above may be provided by being included in a computer program product. Computer program products may be traded between sellers and buyers as commodities. The computer program product may be distributed in the form of a machine-readable storage medium (eg, compact disc read only memory (CD-ROM)) or online through an application store (eg, Play Store™). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily generated in a storage medium such as a memory of a server of a manufacturer, a server of an application store, or a relay server.

In addition, according to an embodiment of the present invention, the various embodiments described above are stored in a recording medium readable by a computer or a similar device using software, hardware, or a combination thereof. can be implemented in In some cases, the embodiments described herein may be implemented by the processor itself. According to the software implementation, embodiments such as the procedures and functions described in this specification may be implemented as separate software modules. Each of the software modules may perform one or more functions and operations described herein.

Meanwhile, computer instructions for performing the processing operation of the device according to the above-described various embodiments may be stored in a non-transitory computer-readable medium. The computer instructions stored in the non-transitory computer-readable medium, when executed by the processor of the specific device, cause the specific device to perform the processing operation in the device according to the various embodiments described above. The non-transitory computer-readable medium refers to a medium that stores data semi-permanently, not a medium that stores data for a short moment, such as a register, cache, memory, etc., and can be read by a device. Specific examples of the non-transitory computer-readable medium may include a CD, DVD, hard disk, Blu-ray disk, USB, memory card, ROM, and the like.

In addition, each of the components (eg, a module or a program) according to the above-described various embodiments may be composed of a single or a plurality of entities, and some sub-components of the above-described corresponding sub-components may be omitted, or other Sub-components may be further included in various embodiments. Alternatively or additionally, some components (eg, a module or a program) may be integrated into a single entity to perform the same or similar functions performed by each corresponding component prior to integration. According to various embodiments, operations performed by a module, program, or other component are executed sequentially, parallel, iteratively, or heuristically, or at least some operations are executed in a different order, are omitted, or other operations are added. can be

In the above, preferred embodiments of the present invention have been illustrated and described, but the present invention is not limited to the specific embodiments described above, and is commonly used in the technical field pertaining to the present disclosure without departing from the gist of the present invention as claimed in the claims. Various modifications are possible by those having the knowledge of, of course, and these modifications should not be individually understood from the technical spirit or prospect of the present invention.

100: body temperature measuring device
110: image acquisition module
120: memory
130: processor

Claims (29)

A method for measuring body temperature performed by a body temperature measuring device, the method comprising:
acquiring a skin image including a plurality of skin regions of interest;
estimating at least one biosignal using the color signal calculated for the skin ROI of the plurality of regions;
estimating at least one body temperature corresponding to each of the at least one bio-signal by applying the estimated at least one bio-signal to a regression analysis equation;
estimating a skin temperature using color data of the skin region of interest;
estimating a third body temperature by applying the estimated skin temperature to a regression analysis equation;
estimating a robust body temperature by averaging the at least one estimated body temperature and the estimated third body temperature; and estimating the improved body temperature by estimating the improved body temperature by averaging the body temperature calculated in the plurality of regions. According to claim 1,
The step of estimating the skin temperature,
A robust body temperature measurement method using a biosignal of a skin image, wherein the skin temperature is estimated by applying the color data extracted from the skin region of interest to a skin temperature regression analysis equation. 3. The method of claim 2,
The step of estimating the skin temperature,
A robust body temperature measurement method using a biosignal of a skin image, wherein the improved skin temperature is estimated by applying the estimated skin temperature to an improved skin temperature regression analysis equation. According to claim 1,
The at least one biosignal is
At least one biosignal of a pulse rate estimated from a pulse-related frequency band in the color signal of the skin region of interest and a respiration rate estimated from a breathing-related frequency band in the color signal of the skin region of interest is included. A robust body temperature measurement method using biosignals. 5. The method of claim 4,
The step of estimating the at least one body temperature comprises:
A robust body temperature measurement method using a biosignal of a skin image, wherein the first body temperature is estimated by applying the estimated pulse rate to the first body temperature regression analysis equation. 6. The method of claim 5,
The first body temperature regression analysis equation,
A robust body temperature measurement method using a biosignal of a skin image, which is calculated by a regression analysis equation by applying regression analysis to the estimated pulse rate and body temperature measured by a thermometer. 6. The method of claim 5,
The step of estimating the at least one body temperature comprises:
A robust body temperature measurement method using a biosignal of a skin image, wherein the improved first body temperature is estimated by applying the estimated first body temperature to a first improved body temperature regression analysis equation. 8. The method of claim 7,
The first improved body temperature regression analysis equation,
A robust body temperature measurement method using a biosignal of a skin image, which is calculated by an improved regression analysis formula by applying regression analysis to the estimated pulse rate and body temperature measured by a thermometer. 5. The method of claim 4,
The step of estimating the at least one body temperature comprises:
A robust body temperature measuring method using a biosignal of a skin image, wherein the second body temperature is estimated by applying the estimated respiration rate to a second body temperature regression analysis equation. 10. The method of claim 9,
The second body temperature regression analysis equation,
A robust body temperature measurement method using a biosignal of a skin image, which is calculated by a regression analysis equation by applying regression analysis to the estimated respiration rate and body temperature measured by a thermometer. 10. The method of claim 9,
The step of estimating the at least one body temperature comprises:
A robust body temperature measurement method using a biosignal of a skin image, wherein an improved second body temperature is estimated by applying the estimated second body temperature to a second improved body temperature regression analysis equation. 12. The method of claim 11,
The second improved body temperature regression analysis equation,
A robust body temperature measurement method using a biosignal of a skin image, which is calculated by an improved regression analysis formula by applying regression analysis to the estimated second body temperature and body temperature measured by a thermometer. According to claim 1,
The method of claim 1 , further comprising: estimating at least one biosignal for each of a plurality of regions using a color signal of each of the regions of interest in the skin of the plurality of regions, and estimating at least one body temperature for each of the plurality of regions A robust method of measuring body temperature using signals. 14. The method of claim 13,
The method of claim 1, further comprising the step of estimating an improved body temperature by averaging at least one body temperature for each of the estimated plurality of regions and the estimated third body temperature. an image acquisition module for acquiring a skin image including a plurality of skin regions of interest;
a memory storing one or more programs; and
a processor executing the stored one or more programs;
The processor estimates at least one biosignal using the color signal calculated from the acquired skin region of interest of the plurality of regions,
applying the estimated at least one bio-signal to a regression analysis equation to estimate at least one body temperature corresponding to the at least one bio-signal,
estimating the skin temperature using the color data of the skin region of interest;
Estimate the third body temperature by applying the estimated skin temperature to the regression analysis equation,
estimating a robust body temperature by averaging the estimated at least one body temperature and the estimated third body temperature;
A robust body temperature measuring apparatus using a biosignal of a skin image, estimating an improved body temperature by averaging the body temperature calculated from the plurality of parts. 16. The method of claim 15,
The processor is
A robust body temperature measuring apparatus using a biosignal of a skin image, which estimates skin temperature by applying color data extracted from the skin region of interest to a skin temperature regression analysis equation. 17. The method of claim 16,
The processor is
A robust body temperature measuring apparatus using a biosignal of a skin image, which estimates an improved skin temperature by applying the estimated skin temperature to an improved skin temperature regression analysis equation. 16. The method of claim 15,
The at least one biosignal is
At least one biosignal of a pulse rate estimated from a pulse-related frequency band in the color signal of the skin region of interest and a respiration rate estimated from a breathing-related frequency band in the color signal of the skin region of interest is included. A robust body temperature measuring device using biosignals. 19. The method of claim 18,
The processor is
A robust body temperature measuring apparatus using a biosignal of a skin image, estimating a first body temperature by applying the estimated pulse rate to a first body temperature regression analysis equation. 20. The method of claim 19,
The first body temperature regression analysis equation,
A robust body temperature measuring apparatus using a biosignal of a skin image, which is calculated by a regression analysis equation by applying regression analysis to the estimated pulse rate and body temperature measured by a thermometer. 20. The method of claim 19,
The processor is
A robust body temperature measuring apparatus using a biosignal of a skin image to estimate an improved first body temperature by applying the estimated first body temperature to a first improved body temperature regression analysis equation. 22. The method of claim 21,
The first improved body temperature regression analysis equation,
A robust body temperature measuring apparatus using a biosignal of a skin image, which is calculated by an improved regression analysis formula by applying regression analysis to the estimated pulse rate and body temperature measured by a thermometer. 19. The method of claim 18,
The processor is
A robust body temperature measuring apparatus using a biosignal of a skin image, estimating a second body temperature by applying the estimated respiration rate to a second body temperature regression analysis equation. 24. The method of claim 23,
The second body temperature regression analysis equation,
A robust body temperature measuring device using a biosignal of a skin image, which is calculated by a regression analysis formula by applying regression analysis to the estimated respiration rate and body temperature measured by a thermometer. 24. The method of claim 23,
The processor is
A robust body temperature measuring apparatus using a biosignal of a skin image, estimating an improved second body temperature by applying the estimated second body temperature to a second improved body temperature regression analysis equation. 26. The method of claim 25,
The second improved body temperature regression analysis equation,
A robust body temperature measuring apparatus using a biosignal of a skin image, which is calculated by an improved regression analysis formula by applying regression analysis to the estimated second body temperature and body temperature measured by a thermometer. 16. The method of claim 15,
The processor is
Robust body temperature using bio-signals from skin images, estimating at least one bio-signal for each of a plurality of regions using color signals of respective regions of interest in the skin, and estimating at least one body temperature for each of the plurality of regions measuring device. 28. The method of claim 27,
The processor is
A robust body temperature measuring apparatus using a biosignal of a skin image for estimating an improved body temperature by averaging the weighted average of at least one body temperature for each of the estimated plurality of parts and the estimated third body temperature. A non-transitory computer-readable storage medium for storing instructions that, when executed by a processor, cause the processor to execute a method, the method comprising:
acquiring a skin image including a plurality of skin regions of interest;
estimating at least one biosignal using the color signal calculated for the skin ROI of the plurality of regions;
estimating at least one body temperature corresponding to each of the at least one bio-signal by applying the estimated at least one bio-signal to a regression analysis equation;
estimating a skin temperature using color data of the skin region of interest;
estimating a third body temperature by applying the estimated skin temperature to a regression analysis equation;
estimating a robust body temperature by averaging the at least one estimated body temperature and the estimated third body temperature; and
A non-transitory computer-readable storage medium comprising the step of estimating an improved body temperature by averaging the body temperature calculated at the plurality of sites.

Images