Non-contact vital sign monitoring method and system based on thermal infrared imaging

Abstract

The application discloses a non-contact vital sign monitoring method and system based on thermal infrared imaging, relates to the field of infrared imaging technology, and is used for solving the problem of how to effectively utilize temperature data of thermal infrared imaging and analyze training effects of different sports projects on each part of the body; the application quantitatively analyzes temperature difference, variance and mean value through an entropy method, and systematically evaluates temperature changes of each part before and after sports. The method can not only reflect training intensity and effects of each part of the body, but also recommend more targeted sports projects for users through sorting results; the scheme analyzes the correlation between temperature data and training indexes, constructs an evaluation model of sports project recommendation, and can optimize training schemes according to the influence degree of different sports on each part. The scheme solves the problems of lack of pertinence and scientific basis in traditional sports recommendation.

Description

Technical Field

[0001] This invention relates to the field of infrared imaging technology, and more specifically, to a non-contact vital sign monitoring method and system based on thermal infrared imaging. Background Technology

[0002] In recent years, non-contact vital sign monitoring technology has received widespread attention in the fields of sports health, medical rehabilitation, and sports training. Traditional contact measurement methods, such as heart rate belts and thermometers, while accurately measuring vital sign parameters, have many shortcomings, such as poor comfort and susceptibility to sweat or slippage during exercise. Furthermore, contact devices require frequent calibration and maintenance, and in sports settings, their use may interfere with normal athletic performance.

[0003] Thermal infrared imaging, as a non-contact measurement method, captures thermal radiation from the human body surface to generate temperature distribution images, thereby extracting vital sign information. Due to its non-contact nature, high resolution, and high sensitivity, this technology is gradually becoming an emerging direction for vital sign monitoring and assessment. However, because thermal infrared imaging equipment is sensitive to ambient temperature, its practical applications are often affected by environmental factors such as direct sunlight and heat source interference, leading to inaccurate measurement results. Furthermore, effectively utilizing thermal infrared imaging temperature data to analyze the training effects of different sports on various body parts and optimizing exercise programs through scientific recommendation algorithms remains a technical challenge.

[0004] To address the above problems, this invention proposes a solution. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, embodiments of the present invention provide a non-contact vital sign monitoring method and system based on thermal infrared imaging to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] A non-contact vital sign monitoring method based on thermal infrared imaging includes the following steps:

[0008] Perform temperature calibration on the thermal infrared imaging equipment;

[0009] By utilizing temperature distribution information in thermal infrared images, temperature data of the user's body surface is extracted through image processing techniques.

[0010] The acquired temperature data is used to build a body temperature calibration model to calibrate the temperature data, and the impact of sports on training indicators of various parts of the body is calculated based on the entropy method.

[0011] Recommendations are made for sports that have a significant impact on training indicators.

[0012] In a preferred embodiment, the acquired temperature data is used to construct a body temperature calibration model to calibrate the temperature data, specifically including the following steps:

[0013] The initial temperature measured using an uncalibrated infrared thermometer is T. m The surface temperature of the part to be measured is T. 测 The ambient temperature is T temp The final calibration result is T. 实 ;

[0014] First, the temperature T was measured using an infrared thermometer. m The final calibration result is T. 实 There is a difference kb between them, which is the calibration value; that is: T 实 =T m +kb;

[0015] The difference b is the sum of multiple infrared thermometer temperature values ​​T. i Summing and averaging, then calculating the surface temperature T of the measured area. 测 It is obtained by subtracting the average; that is:

[0016] The coefficient k before b is used to calculate T using the covariance formula. m T temp The packaging temperature T of the infrared thermometer 封 Total error T m -T temp T m -T 封 Obtain, so that T 封 =0, that is

[0017] Finally, the formulas are integrated to obtain the body temperature calibration model, i.e.

[0018]

[0019] In a preferred embodiment, the method for extracting temperature data from the user's body surface is as follows:

[0020] The user's body is divided into multiple parts. Based on the proportions of the human body, the image of a standing person is simplified into a rectangle. Let the height of the person be h and the shoulder width be j. A rectangular coordinate system is established with the lower left corner of the rectangle as the origin.

[0021] Find the coordinates of each body part, where a = h / 9 and b = j / 3.

[0022] Let T be the minimum temperature difference of the i-th body part. iminThe maximum temperature difference is T imax The variance of the temperature difference is T. istd The average temperature difference is T iave The temperature difference is the difference in temperature measured at the same location before and after the movement.

[0023] The analysis method for temperature data is as follows:

[0024] (T) imax -T imin ), T istd T iave Perform mean normalization and multiply by 100; the new value is denoted as (T). imax -T imin ) new ,T istdnew ,T iavenew And sort them from largest to smallest, according to (T) imax -T imin ) new ,T istdnew ,T iavenew The magnitude of the numerical value determines the training effect of each part.

[0025] In a preferred embodiment, the method for evaluating the impact of a sport on training indicators of various body parts and the method for calculating the recommendation index of a sport for various body parts are as follows:

[0026] The dataset contains training metrics (T) for different body parts under each sport. imax -T imin ) new / T istdnew / T iavenew Each training metric needs to be input into the model multiple times; this solution requires inputting it three times.

[0027] Indicator selection: Given r training sessions, n sports events, and m body parts, then x θij Let θ be the training index value of the j-th body part of sport i under the θ-th training session;

[0028] To remove the influence of dimensionality, each indicator is standardized, x θ ' ij =x θij / x max ;

[0029] Determine the weights of the training metrics for the j-th body part:

[0030] Calculate the entropy value of the training metric for the j-th body part:

[0031] In the formula, ln is the natural logarithm, k≥0, k=ln(rn);

[0032] Calculate the variance coefficient g of the training index for the j-th body part. j :g j =1-e j ;

[0033] Calculate the weights of the training metrics for the j-th body part:

[0034] Calculate the degree of impact of each sport on different parts of the body:

[0035] Recommendation index ω for the i-th sport and the j-th body part ij The calculation formula for ω is as follows: ij =a 1 α ij +a 2 β ij +a 3 γ ij ;a 1 +a 2 +a 3 =1;

[0036] Where, α ij ,β ij and γ ij Let a1, a2, and a3 represent the influence of the i-th sport on the j-th body part on the training intensity, training effect, and training state, respectively.

[0037] In a preferred embodiment, the non-contact vital signs monitoring system based on thermal infrared imaging includes a body temperature calibration module, a thermal image processing module, an exercise recommendation module, and a data storage module, with signal connections between the modules;

[0038] The body temperature calibration module is used to acquire ambient temperature, ambient temperature data measured by an uncalibrated thermal infrared imaging device, user body temperature data, and body temperature data measured multiple times by the thermal infrared imaging device, and to perform temperature calibration.

[0039] The heatmap processing module is used to acquire user body surface data and perform data analysis;

[0040] The sports recommendation module is used to assess the impact of sports on training indicators of various parts of the body and to calculate the recommendation index.

[0041] The data storage module is used to store all data processed by the platform.

[0042] The technical effects and advantages of the non-contact vital sign monitoring method and system based on thermal infrared imaging of this invention are as follows:

[0043] This invention divides the human body into 24 parts using a human proportion-based partitioning model. Combining the pixel distribution and geometric features of infrared thermograms, it accurately extracts temperature data for each part, providing high-quality input for subsequent data analysis. Furthermore, it uses entropy analysis to quantify temperature difference, variance, and mean, systematically evaluating temperature changes in each part before and after exercise. This method not only reflects the training intensity and effect on body parts but also recommends more targeted exercise programs to users based on the ranking results. The solution constructs an evaluation model for exercise program recommendations by analyzing the correlation between temperature data and training indicators, optimizing training programs based on the degree of impact of different exercises on each body part. This solves the problem of traditional exercise recommendations lacking specificity and scientific basis. Attached Figure Description

[0044] Figure 1 This is a flowchart of the non-contact vital sign monitoring method based on thermal infrared imaging of the present invention. Detailed Implementation

[0045] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0046] A non-contact vital sign monitoring method based on thermal infrared imaging includes the following steps:

[0047] Install thermal infrared imaging equipment at appropriate locations before and after the user;

[0048] To reduce the influence of ambient temperature on body surface temperature measurement, the thermal infrared imaging equipment will be calibrated for temperature.

[0049] By utilizing temperature distribution information in thermal infrared images, image processing techniques are used to extract temperature data from the user's body surface.

[0050] The acquired temperature data will be analyzed to evaluate the training effect.

[0051] The entropy-based model assesses the impact of sports activities on training metrics for various body parts, with sports having a greater impact on these metrics receiving higher recommendation indexes. This allows for the recommendation of sports activities to users.

[0052] Furthermore, the method for installing thermal infrared imaging equipment is as follows:

[0053] Select two high-resolution, high-frame-rate, wide-temperature-range thermal infrared imagers with good stability and anti-interference capabilities, and place them at a distance d from the user, one in front and one behind. Ensure that the thermal infrared imagers can fully cover the user's activity area, while avoiding direct sunlight, heat source interference, and reflection effects.

[0054] The formula for calculating the distance d between a single thermal infrared imager and the user is as follows:

[0055] d = h / 2tan(θ / 2)

[0056] θ is the field of view of the thermal infrared imager. h is the user's height; if taken as 2m, the formula simplifies to...

[0057] d = 1 / tan(θ / 2)

[0058] Furthermore, the steps for temperature calibration of the thermal infrared imaging equipment are as follows:

[0059] The initial temperature measured using an uncalibrated infrared thermometer is T. m The surface temperature of the part to be measured is T. 测 The ambient temperature is T temp The final calibration result is T. 实 Literature confirms that the packaging temperature of the infrared thermometer has a negligible effect on the experiment.

[0060] First, the temperature T was measured using an infrared thermometer. m The final calibration result is T. 实 There is a difference of kb, which is the calibration value. That is:

[0061] T 实 =T m +kb

[0062] The difference b is the sum of multiple infrared thermometer temperature values ​​T. i Summing and averaging, then calculating the surface temperature T of the measured area. 测 It is obtained by subtracting the average. That is:

[0063]

[0064] The coefficient k before b can be calculated using the covariance formula for T. m T temp The packaging temperature T of the infrared thermometer 封 Total error T m -T temp T m -T 封 We obtain, without considering the packaging temperature, let T 封 =0, that is

[0065]

[0066] Finally, the formulas are integrated to obtain the body temperature calibration model, i.e.

[0067]

[0068] The corresponding hardware program design is as follows:

[0069] Prepare the drivers for the infrared thermometer, the ambient temperature measurement, and the LCD display, display, and button programs. First, activate the chip and peripheral drivers for the experimental equipment, entering a calibration waiting state. Second, display the ambient temperature in real time on the interface. When the infrared thermometer measures the temperature, record the measurement data into an array. Then, use a timer to measure once per second, displaying the measured temperature value on the LCD screen after each measurement. Perform 10 measurements in total. After 10 measurements, the real-time measured temperature value will be displayed in a designated area, but no record will be made. Finally, refresh the interface using the buttons to proceed to the next round of calibration temperature measurement. Program Flow Figure 1 As shown in the figure.

[0070] Furthermore, the method for extracting temperature data from the user's body surface is as follows:

[0071] The user's body is divided into 24 parts: 10 in the front (left chest, right chest, left abdomen, right abdomen, front left upper arm, front left forearm, front right upper arm, front right forearm, front left thigh, front right thigh) and 12 in the back (left back, right back, back left upper arm, back left forearm, back right upper arm, back right forearm, left hip, right hip, back left thigh, back right thigh, left calf, right calf).

[0072] Based on human proportions, we simplify the image of a standing person into a large rectangle. Let the person's height be h and shoulder width be j. Then the length of the rectangle is h and the width is j. Establish a rectangular coordinate system with the lower left corner of the rectangle as the origin (establish it once before and once after). Each body part is also considered as a small rectangle.

[0073] The coordinates of each body part can be calculated, where a = h / 9 and b = j / 3.

[0074] Predecessor:

[0075] Forward left upper arm: (0,7.5a), (0.5b,7.5a), (0,6a), (0.5b,6a)

[0076] Left chest: (0.5b, 7.5a), (1.5b, 7.5a), (0.5b, 6a), (1.5b, 6a)

[0077] Right chest: (1.5b, 7.5a), (2.5b, 7.5a), (1.5b, 6a), (2.5b, 6a)

[0078] Forearm right upper arm: (2.5b, 7.5a), (3b, 7.5a), (2.5b, 6a), (3b, 6a)

[0079] Left forearm: (0,6a), (0.5b,6a), (0,4.5a), (0.5b,4.5a)

[0080] Left abdomen: (0.5b,6a), (1.5b,6a), (0.5b,4.5a), (1.5b,4.5a)

[0081] Right ventral region: (1.5b, 6a), (2.5b, 6a), (1.5b, 4.5a), (2.5b, 4.5a)

[0082] Right forearm: (2.5b, 6a), (3b, 6a), (2.5b, 4.5a), (3b, 4.5a)

[0083] Front left thigh: (0.5b, 4.5a), (1.5b, 4.5a), (0.5b, 2.5a), (1.5b, 2.5a)

[0084] Right anterior thigh: (1.5b, 4.5a), (2.5b, 4.5a), (1.5b, 2.5a), (2.5b, 2.5a)

[0085] Back:

[0086] Left upper arm: (0,7.5a), (0.5b,7.5a), (0,6a), (0.5b,6a)

[0087] Left back: (0.5b,7.5a), (1.5b,7.5a), (0.5b,6a), (1.5b,6a)

[0088] Right back: (1.5b, 7.5a), (2.5b, 7.5a), (1.5b, 6a), (2.5b, 6a)

[0089] Right upper arm: (2.5b, 7.5a), (3b, 7.5a), (2.5b, 6a), (3b, 6a)

[0090] Left forearm: (0,6a), (0.5b,6a), (0,4.5a), (0.5b,4.5a)

[0091] Left buttock: (0.5b, 6a), (1.5b, 6a), (0.5b, 4.5a), (1.5b, 4.5a)

[0092] Right hip: (1.5b, 6a), (2.5b, 6a), (1.5b, 4.5a), (2.5b, 4.5a)

[0093] Right forearm: (2.5b, 6a), (3b, 6a), (2.5b, 4.5a), (3b, 4.5a)

[0094] Left posterior thigh: (0.5b, 4.5a), (1.5b, 4.5a), (0.5b, 2.5a), (1.5b, 2.5a)

[0095] Right thigh posterior: (1.5b, 4.5a), (2.5b, 4.5a), (1.5b, 2.5a), (2.5b, 2.5a)

[0096] Left lower leg: (0.5b, 2.5a), (1.5b, 2.5a), (0.5b, 0), (1.5b, 0)

[0097] Right lower leg: (1.5b, 2.5a), (2.5b, 2.5a), (1.5b, 0), (2.5b, 0)

[0098] Let T be the minimum temperature difference of the i-th body part. imin The maximum temperature difference is T imax The variance of the temperature difference is T. istd The average temperature difference is T iave The temperature difference is the difference in temperature measured at the same location before and after the movement.

[0099] Furthermore, the analysis methods for temperature data are as follows:

[0100] (T) imax -T imin ), T istd T iave Perform mean normalization and multiply by 100; the new value is denoted as (T). imax -T imin ) new ,T istdnew ,T iavenew Then sort them from largest to smallest. Mean normalization is a common method, which will not be elaborated here.

[0101] (T imax -T imin ) new The larger the value, the greater the temperature difference between the corresponding body part i before and after exercise, the faster the body part heats up, and the higher the training intensity.

[0102] T istdnew The smaller the value, the smaller the variance of the temperature difference of the corresponding body part i before and after exercise, the more uniform the temperature distribution of that body part, and the more stable the training effect.

[0103] T iavenew The larger the value, the greater the average temperature difference of the corresponding body part i before and after exercise, the better the overall temperature rise of that body part, and the better the training state.

[0104] Furthermore, the methods for assessing the impact of sports on training indicators of various body parts and the calculation methods for the recommended index of sports on various body parts are as follows:

[0105] For research on methods of evaluating exercise effectiveness, the entropy method in the objective weighting method is used to calculate the degree of influence of sports on training indicators of various parts of the body:

[0106] Information entropy measures the degree of disorder in a system, while information measures the degree of order. Their absolute values ​​are equal but their signs are opposite. The greater the variation in the value of an indicator, the lower the information entropy, the greater the amount of information provided by that indicator, and the greater its weight should be. Conversely, the smaller the variation in the value of an indicator, the higher the information entropy, the less information provided by that indicator, and the smaller its weight. Therefore, the weight of each indicator can be calculated using information entropy tools based on the degree of variation in its values.

[0107] The dataset contains training metrics (T) for different body parts under each sport. imax -T imin ) new / T istdnew / T iavenew Each training metric needs to be input into the model separately, and this solution requires inputting it three times.

[0108] 1. Indicator Selection: Given r training sessions, n sports events, and m body parts, in this scheme, m is chosen to be 24. Then x θij Let θ be the training index value for the j-th body part of sport i during the θ-th training session.

[0109] 2. To eliminate the influence of dimensionality, each indicator is standardized.

[0110] x′ θij =x θij / x max

[0111] 3. Determine the weights of the training metrics for the j-th body part:

[0112]

[0113] 4. Calculate the entropy value of the training metric for the j-th body part:

[0114]

[0115] In the formula, ln is the natural logarithm, k≥0, k=ln(rn).

[0116] 5. Calculate the variance coefficient g of the training index for the j-th body part. j :

[0117] g j =1-e j

[0118] 6. Calculate the weights of the training metrics for the j-th body part:

[0119]

[0120] 7. Calculate the degree of impact of each sport on different parts of the body:

[0121]

[0122] Recommendation index ω for the i-th sport and the j-th body part ij The calculation formula is as follows:

[0123] ω ij =a 1 α ij +a 2 β ij +a 3 γ ij

[0124] a1 + a2 + a3 = 1

[0125] Where, α ij ,β ij and γ ij Let a1, a2, and a3 represent the influence of the i-th sport on the j-th body part on the training intensity, training effect, and training state. These weights can be set by the user or selected from the system's default weights.

[0126] The following describes the calculation methods for the system's default training intensity, training effect, and training state weights:

[0127] Based on common sense, users of different body types will experience differences in training intensity, training effect, and training status. Anaerobic exercise and aerobic exercise will also differ in training intensity, training effect, and training status.

[0128] 1. Users with a BMI between [18.5 and 23.9] are classified as normal (nor), users with a BMI < 18.5 are classified as underweight (sho), and users with a BMI > 23.9 are classified as overweight (lar). BMI is calculated by dividing weight (kg) by the square of height (m). Exercise is divided into two main categories: aerobic exercise (ae) and anaerobic exercise (an).

[0129] 2. Collect user training data.

[0130] (1) Calculate the average value of all training intensity indicators for normal users, denoted as nor1; the average value of all training status indicators for normal users, denoted as nor2; the average value of all training effect indicators for normal users, denoted as nor3; and so on, calculate sho1, sho2, sho3, lar1, lar2, lar3.

[0131] (2) Calculate the average value of all training intensity indicators under aerobic exercise, and denot it as ae1; the average value of all training status indicators under aerobic exercise, and denot it as ae2; the average value of all training effect indicators under aerobic exercise, and denot it as ae3; and so on, calculate an1, an2, an3.

[0132] (3) For ease of understanding, it is recorded in the following table:

[0133] Training intensity Training effect Training status normal users <![CDATA[nor1]]> <![CDATA[nor2]]> <![CDATA[nor3]]> Slim users <![CDATA[sho1]]> <![CDATA[sho2]]> <![CDATA[sho3]]> Overweight users <![CDATA[lar1]]> <![CDATA[lar2]]> <![CDATA[lar3]]> Aerobic exercise <![CDATA[ae1]]> <![CDATA[ae2]]> <![CDATA[ae3]]> Anaerobic exercise <![CDATA[an1]]> <![CDATA[an2]]> <![CDATA[an3]]>

[0134] 3. The weights for training intensity, training effect, and training status of a normal user during aerobic exercise are calculated as follows:

[0135] a1=(nor1+ae1) / (nor1+ae1+nor2+ae2+nor3+ae3)

[0136] a2=(nor2+ae2) / (nor1+ae1+nor2+ae2+nor3+ae3)

[0137] a3=(nor3+ae3) / (nor1+ae1+nor2+ae2+nor3+ae3)

[0138] For a normal user undergoing anaerobic exercise, the weights for training intensity, training effect, and training state are as follows:

[0139] a1=(nor1+an1) / (nor1+an1+nor2+an2+nor3+an3)

[0140] a2=(nor2+an2) / (nor1+an1+nor2+an2+nor3+an3)

[0141] a3=(nor3+an3) / (nor1+an1+nor2+an2+nor3+an3)

[0142] For underweight users, the weights for training intensity, training effect, and training status during aerobic exercise are as follows:

[0143] a1=(sho1+ae1) / (sho1+ae1+sho2+ae2+sho3+ae3)

[0144] a2=(sho2+ae2) / (sho1+ae1+sho2+ae2+sho3+ae3)

[0145] a3=(sho3+ae3) / (sho1+ae1+sho2+ae2+sho3+ae3)

[0146] For underweight users, the weights for training intensity, training effect, and training status during anaerobic exercise are as follows:

[0147] a1=(sho1+an1) / (sho1+an1+sho2+an2+nor3+sho3)

[0148] a2=(sho2+an2) / (sho1+an1+sho2+an2+nor3+sho3)

[0149] a3=(sho3+an3) / (sho1+an1+sho2+an2+nor3+sho3)

[0150] For overweight users, the weights for training intensity, training effect, and training status during aerobic exercise are as follows:

[0151] a1=(l ar1+ae1) / (l ar1+ae1+l ar2+ae2+l ar3+ae3)

[0152] a2=(l ar2+ae2) / (l ar1+ae1+l ar2+ae2+l ar3+ae3)

[0153] a3=(l ar3+ae3) / (l ar1+ae1+l ar2+ae2+l ar3+ae3)

[0154] For overweight users, the weights for training intensity, training effect, and training status during anaerobic exercise are as follows:

[0155] a1=(l ar1+an1) / (l ar1+an1+l ar2+an2+l ar3+an3)

[0156] a2=(l ar2+an2) / (l ar1+an1+l ar2+an2+l ar3+an3)

[0157] a3=(l ar3+an3) / (l ar1+an1+l ar2+an2+l ar3+an3)

[0158] A non-contact vital sign monitoring method and system based on thermal infrared imaging includes a body temperature calibration module, a thermal image processing module, an exercise recommendation module, and a data storage module, with signal connections between the modules.

[0159] The body temperature calibration module is used to acquire ambient temperature data, ambient temperature data measured using an uncalibrated thermal infrared imaging device, user body temperature data, and body temperature data measured multiple times by the thermal infrared imaging device, and to perform temperature calibration.

[0160] The heatmap processing module is used to acquire user body surface data and perform data analysis.

[0161] The sports recommendation module is used to assess the impact of sports on training indicators of various parts of the body and to calculate the recommendation index.

[0162] The data storage module is used to store all data during the platform's processing. The above formulas are all dimensionless calculations, and the formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0163] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, in the form of a computer program product.

[0164] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and inventive constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0165] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0166] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0167] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A non-contact vital sign monitoring method based on thermal infrared imaging, characterized in that, The method comprises the following steps: Calibrating the temperature of the thermal infrared imaging device; Extracting the temperature data of the user's body surface by image processing technology using the temperature distribution information in the thermal infrared image; Calibrating the temperature data by constructing a body temperature calibration model, and calculating the influence degree of the sports project on the training indicators of each part of the body based on the entropy value method; Recommending the sports project with a large influence degree on the training indicators; The method for extracting the temperature data of the user's body surface is as follows: Divide the user's body into multiple parts, simplify the standing person image into a rectangle according to the human body proportion, and set the height of the person as h and the shoulder width as j, and establish a rectangular coordinate system with the left lower corner of the rectangle as the origin; Calculate the coordinates of each body part, wherein a = h / 9 and b = j / 3 Let the minimum temperature difference of the ith body part be , the maximum temperature difference be , the variance of the temperature difference be , and the mean of the temperature difference be ; the temperature difference is the difference between the temperatures measured at the same position before and after exercise. The analysis method for the temperature data is as follows: Will , , Mean value normalization and all multiplied by 100, the new value is And respectively from large to small order, according to The value size to determine the training effect of each part; The method for evaluating the influence of the sports project on the training indicators of each part of the body and the calculation method of the recommended index of the sports project on each part of the body are as follows: The data set is the training index of each part of the body under each sports project / / Each training index needs to be input into the model in batches, and the present scheme needs to be input 3 times respectively. Index selection: set r times of training, n sports events, m body parts, then is the jth body part of the i th sports event in the r th training training index value To remove the dimensional effect, each index is standardized, ; ; calculating an entropy value of the training indicator of the jth body part: ; ln is a natural logarithm, , ; calculating a coefficient of variability of the training indicator for the jth body part : ; calculating a weight of the training indicator of the jth body part: ; The degree of influence of each sports item on each part of the body is calculated: ; Recommendation index of the i-th sports event to the j-th body part The calculation formula is as follows ; ; wherein, , and is the influence degree of the i-th sports item on the j-th body part in the training intensity, the training effect, and the training state, is the weight of the training intensity, the training effect, and the training state; The training intensity is the temperature difference of the corresponding body part i before and after exercise, the training effect is the variance of the temperature difference of the corresponding body part i before and after exercise, and the training state is the mean value of the temperature difference of the corresponding body part i before and after exercise.

2. The non-contact vital sign monitoring method based on thermal infrared imaging of claim 1, wherein, Calibrating the temperature data by constructing a body temperature calibration model, specifically comprising the following steps: The initial temperature measured by the uncalibrated infrared thermometer is , the surface temperature of the part to be measured is , the ambient temperature is , and the final calibration result is ; First, the temperature measured by the infrared thermometer The final calibration result is There is a difference between , That is, the calibration value; that is: ; Difference is the temperature value of the infrared thermometer measured for several times Then the surface temperature of the part to be measured is subtracted from the average value; that is: ;​ coefficient using covariance formula respectively , total error of the package temperature with infrared thermometer , get, let i.e. ;​ Finally, the formula is integrated to obtain the body temperature calibration model, that is 。 3. A non-contact vital sign monitoring system based on thermal infrared imaging for realizing the non-contact vital sign monitoring method based on thermal infrared imaging according to any one of claims 1-2, characterized in that: It comprises a body temperature calibration module, a thermal map processing module, a sports project recommendation module and a data storage module, and the modules are signal connected; The body temperature calibration module is used to obtain the ambient temperature, the ambient temperature data measured by the uncalibrated thermal infrared imaging device, the body temperature data of the user, the body temperature data measured by the thermal infrared imaging device multiple times, and calibrate the temperature; The thermal map processing module is used to obtain the user's body surface data and perform data analysis; The sports project recommendation module is used to evaluate the influence degree of the sports project on the training indicators of each part of the body and calculate the recommended index; The data storage module is used to store all the data in the platform processing process.

Images