Advanced non-contact blood pressure measurement system combined with computer-vision-based subject age measurement algorithm, and method of using same
Patent Information
- Application Number
- PCT/KR2026/001203
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2025-03-17
- Filing Date
- 2026-01-20
- Publication Date
- 2026-09-24
Smart Images
Figure KR2026001203_24092026_PF_FP_ABST
Abstract
Description
Advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm and method of using the same
[0001] The present invention relates to an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm and a method of using the same. More specifically, the invention relates to an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm and a method of using the same, which enables advanced non-contact blood pressure measurement through the estimation of a subject's age based on computer vision and the measurement of machine learning-blood pressure (ML-BP) and face-blood pressure (Face-BP).
[0002] The content described in this section merely provides background information regarding an embodiment of the present invention and does not constitute prior art.
[0003]
[0004] Generally, blood pressure refers to the pressure exerted on the walls of blood vessels by blood pumped from the heart as it flows through them, and it is used as a measure to assess an individual's health status. Blood pressure can be measured using direct / indirect methods, invasive / non-invasive methods, and restrictive / unrestrictive methods. Among these, the most commonly used is the non-invasive and restrictive indirect method.
[0005]
[0006] Indirect methods of blood pressure measurement involve wrapping a cuff around the blood spot and inflating it with air to measure the pressure at which blood flow in the brachial or radial artery stops. In other words, conventional blood pressure monitors utilize either the oscillometric method, which analyzes the Korotkoff sound by applying pressure with a cuff to block a blood vessel and then gradually reducing the pressure, or a method that directly measures the pressure on the blood vessel wall using a pressure sensor. In the case of air-pressure blood pressure monitors, users often experience discomfort due to the compression of the upper arm, and since the analysis is performed by gradually reducing the applied pressure, it has the disadvantage that measuring blood pressure in real time is nearly impossible.
[0007]
[0008] Furthermore, the method of directly measuring pressure on blood vessel walls using pressure sensors is an invasive procedure involving a catheter, which causes discomfort to the user; additionally, in the case of pressure sensors attached to the skin, there was a problem where noise was generated due to user movement, making measurement difficult.
[0009]
[0010] Meanwhile, recent technology utilizes a method that infers proximal blood pressure by measuring the amount of light transmitted using the blood flow generated from the heart via photoplethysmography. Although this method enables continuous real-time measurement, it has the disadvantage of large errors depending on the algorithm and the need to input physical variation information (height, weight, age, arm length, etc.) as correction values during measurement. Furthermore, there was a problem in that the measurement values were generally affected by the measurement location and method, resulting in large errors. Korean Patent Publication No. 10-2023-0112835 is disclosed as a prior art document.
[0011]
[0012] The aforementioned background technology is technical information that the inventor possessed for the derivation of the present invention or acquired during the process of deriving the present invention, and it cannot be considered as publicly known technology disclosed to the general public prior to the filing of the present invention.
[0013] The present invention is proposed to solve the aforementioned problems of previously proposed methods, and aims to provide an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm and a method of using the same, which enables advanced non-contact blood pressure measurement through computer vision-based estimation of the subject's age and measurement of machine learning-blood pressure (ML-BP) and face-blood pressure (Face-BP), by comprising: a data collection unit that collects a video of a subject for non-contact blood pressure measurement and BMI based on the subject's height and weight; a face blood pressure measurement unit that measures face-blood pressure (Face-BP) using a face image included in the subject's video among the data collected through the data collection unit; a machine learning blood pressure measurement unit that predicts age based on the face image included in the video of the data collected through the data collection unit and measures machine learning-blood pressure (ML-BP) using BMI based on the subject's height and weight; and a blood pressure prediction output unit that outputs one of the blood pressures measured by the face blood pressure measurement unit and the machine learning blood pressure measurement unit as the final predicted blood pressure.
[0014]
[0015] In addition, another objective of the present invention is to provide an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm and a method of using the same, which enables advanced non-contact blood pressure measurement through the estimation of a subject's age based on computer vision and the measurement of machine learning-blood pressure (ML-BP) and face-blood pressure (Face-BP), thereby enabling more precise and accurate non-contact blood pressure measurement management by measuring face-blood pressure using a face image and treadmill-blood pressure using BMI, estimated age, and heart rate, and outputting a single blood pressure as a result through preset conditions for each measured blood pressure.
[0016]
[0017] However, the technical problem that the present invention aims to solve is not limited to the technical problem described above, and other technical problems may exist.
[0018] An advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm according to the features of the present invention for achieving the above-mentioned purpose is,
[0019] As an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm,
[0020] A data collection unit that collects a video of a subject for non-contact blood pressure measurement, and BMI through the subject's height and weight;
[0021] A face blood pressure measuring unit that measures face-blood pressure (Face-BP) using a face image included in a video of a subject among the data collected through the above data collection unit;
[0022] A machine learning blood pressure measurement unit that measures machine learning-blood pressure (ML-BP) using BMI based on the subject's height and weight, and predicts age through facial images included in the video of data collected through the above data collection unit; and
[0023] The configuration is characterized by including a blood pressure prediction output unit that outputs one of the measured blood pressures of the face blood pressure measuring unit and the machine learning blood pressure measuring unit as the final predicted blood pressure.
[0024]
[0025] Preferably, the data collection unit is,
[0026] It can be configured to include a camera module for capturing video of a subject for non-contact blood pressure measurement.
[0027]
[0028] Preferably, the data collection unit is,
[0029] It can be configured to include an input module for collecting BMI through the subject's height and weight for non-contact blood pressure measurement.
[0030]
[0031] Preferably, the face blood pressure measuring unit is,
[0032] Face-blood pressure (Face-BP) is measured using a face image included in a video of a subject among the data collected through the above-mentioned data collection unit, and blood pressure (BP) and heart rate can be measured through the processes of face detection, Region of Interest detection, signal processing, and filtering of the subject included in the captured video.
[0033]
[0034] More preferably, the face blood pressure measuring unit is,
[0035] The blood pressure (BP) measured through the processes of face detection, Region of Interest detection, signal processing, and filtering of the subject included in the captured video can be used as the face-blood pressure (Face-BP) transmitted to the blood pressure prediction output unit.
[0036]
[0037] More preferably, the face blood pressure measuring unit is,
[0038] The heart rate measured through the face detection, Region Of Interest detection, signal processing, and filtering processes of the subject included in the captured video can be transmitted and used as a condition input value for generating machine learning-blood pressure (ML-BP) of the machine learning blood pressure measurement unit (130).
[0039]
[0040] More preferably, the machine learning blood pressure measuring unit is,
[0041] Age is predicted using face images included in the video of the data collected through the above data collection unit, and machine learning-blood pressure (ML-BP) is measured using BMI based on the subject's height and weight, wherein age prediction can be performed through face detection, face cropping, feature extraction, and age prediction processes included in the video via an age measurement algorithm.
[0042]
[0043] Even more preferably, the machine learning blood pressure measuring unit is,
[0044] As condition input values for measuring machine learning-blood pressure (ML-BP), BMI consisting of the subject's height and weight, age predicted based on computer vision, and heart rate received from the face blood pressure measuring unit (120) can be used.
[0045]
[0046] A method of using an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm according to the features of the present invention for achieving the above-mentioned purpose is,
[0047] As a method of using an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm,
[0048] (1) A step in which a data collection unit collects a video of a subject for non-contact blood pressure measurement, and BMI through the subject's height and weight;
[0049] (2) A step in which a face blood pressure measuring unit measures face-blood pressure (Face-BP) using a face image included in the subject's video among the data collected through the data collection unit;
[0050] (3) A machine learning blood pressure measurement unit that measures machine learning-blood pressure (ML-BP) using age prediction through a face image included in a video of data collected through the data collection unit and BMI through the subject's height and weight; and
[0051] (4) The blood pressure prediction output unit is characterized by the step of outputting one of the measured blood pressures of the face blood pressure measuring unit and the machine learning blood pressure measuring unit as the final predicted blood pressure.
[0052]
[0053] Preferably, the data collection unit is,
[0054] It can be configured to include a camera module for capturing video of a subject for non-contact blood pressure measurement.
[0055]
[0056] Preferably, the data collection unit is,
[0057] It can be configured to include an input module for collecting BMI through the subject's height and weight for non-contact blood pressure measurement.
[0058]
[0059] Preferably, the face blood pressure measuring unit is,
[0060] Face-blood pressure (Face-BP) is measured using a face image included in a video of a subject among the data collected through the above-mentioned data collection unit, and blood pressure (BP) and heart rate can be measured through the processes of face detection, Region of Interest detection, signal processing, and filtering of the subject included in the captured video.
[0061]
[0062] More preferably, the face blood pressure measuring unit is,
[0063] The blood pressure (BP) measured through the processes of face detection, Region of Interest detection, signal processing, and filtering of the subject included in the captured video can be used as the face-blood pressure (Face-BP) transmitted to the blood pressure prediction output unit.
[0064]
[0065] More preferably, the face blood pressure measuring unit is,
[0066] The heart rate measured through the face detection, Region Of Interest detection, signal processing, and filtering processes of the subject included in the captured video can be transmitted and used as a condition input value for generating machine learning-blood pressure (ML-BP) of the machine learning blood pressure measurement unit (130).
[0067]
[0068] More preferably, the machine learning blood pressure measuring unit is,
[0069] Age is predicted using face images included in the video of the data collected through the above data collection unit, and machine learning-blood pressure (ML-BP) is measured using BMI based on the subject's height and weight, wherein age prediction can be performed through face detection, face cropping, feature extraction, and age prediction processes included in the video via an age measurement algorithm.
[0070]
[0071] Even more preferably, the machine learning blood pressure measuring unit is,
[0072] As condition input values for measuring machine learning-blood pressure (ML-BP), BMI consisting of the subject's height and weight, age predicted based on computer vision, and heart rate received from the face blood pressure measuring unit (120) can be used.
[0073] According to the advanced non-contact blood pressure measurement system and method of use combined with a computer vision-based subject age measurement algorithm proposed in the present invention, the system comprises: a data collection unit that collects a video of a subject for non-contact blood pressure measurement and BMI based on the subject's height and weight; a face blood pressure measurement unit that measures face-blood pressure (Face-BP) using a face image included in the subject's video among the data collected through the data collection unit; a machine learning blood pressure measurement unit that predicts age using a face image included in the video of the data collected through the data collection unit and measures machine learning-blood pressure (ML-BP) using BMI based on the subject's height and weight; and a blood pressure prediction output unit that outputs one of the blood pressures measured by the face blood pressure measurement unit and the machine learning blood pressure measurement unit as the final predicted blood pressure. By configuring the system to include these components, it is possible to enable advanced non-contact blood pressure measurement through computer vision-based estimation of the subject's age and measurement of machine learning-blood pressure (ML-BP) and face-blood pressure (Face-BP).
[0074]
[0075] In addition, according to the advanced non-contact blood pressure measurement system and method of use combined with the computer vision-based subject age measurement algorithm of the present invention, advanced non-contact blood pressure measurement is made possible through the estimation of a subject's age based on computer vision and the measurement of machine learning-blood pressure (ML-BP) and face-blood pressure (Face-BP). This enables face-blood pressure using a face image and treadmill-blood pressure using BMI, estimated age, and heart rate, and allows for more precise and accurate non-contact blood pressure measurement management by outputting a single blood pressure result through preset conditions for each measured blood pressure.
[0076]
[0077] Furthermore, the various and beneficial advantages and effects of the present invention are not limited to those described above and may be more easily understood in the process of explaining specific embodiments of the present invention.
[0078] FIG. 1 is a diagram illustrating the configuration of an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm according to an embodiment of the present invention in functional blocks.
[0079] FIG. 2 is a diagram illustrating an example of the implementation of an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm according to an embodiment of the present invention.
[0080] FIG. 3 is a diagram illustrating the configuration of a face-blood pressure output of an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm according to an embodiment of the present invention.
[0081] FIG. 4 is a diagram illustrating another configuration of the face-blood pressure output of an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm according to an embodiment of the present invention.
[0082] FIG. 5 is a diagram illustrating the configuration of the ML-BP output of an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm according to an embodiment of the present invention.
[0083] FIG. 6 is a diagram illustrating the functional importance for predicting hypertension risk in an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm according to an embodiment of the present invention.
[0084] FIG. 7 is a diagram illustrating the relationship between blood pressure and body mass index to be applied to an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm according to an embodiment of the present invention.
[0085] FIG. 8 is a graph showing the prevalence of hypertension in American adults classified by age and gender to be applied to an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm according to an embodiment of the present invention.
[0086] FIG. 9 is a diagram illustrating the age prediction processing process of an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm according to an embodiment of the present invention.
[0087] FIG. 10 is a diagram illustrating the age estimation configuration of a captured video of an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm according to an embodiment of the present invention.
[0088] FIG. 11 is a diagram illustrating the subject age estimation processing of an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm according to an embodiment of the present invention.
[0089] FIG. 12 is a diagram illustrating the subject age estimation processing of an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm according to an embodiment of the present invention.
[0090] FIG. 13 is a diagram illustrating an implementation configuration in which a computer vision-based age measurement algorithm is applied to an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm according to an embodiment of the present invention.
[0091] FIG. 14 is a diagram illustrating the flow of a method for using an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm according to an embodiment of the present invention.
[0092] <Explanation of Symbols>
[0093] 100: An advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm according to an embodiment of the present invention
[0094] 110: Data Collection Unit
[0095] 120: Face blood pressure measurement unit
[0096] 130: Machine learning blood pressure measurement unit
[0097] 140: Blood pressure prediction output section
[0098] S110: A step in which the data collection unit collects a video of the subject for non-contact blood pressure measurement, and BMI through the subject's height and weight.
[0099] S120: A step in which the face blood pressure measuring unit measures face-blood pressure (Face-BP) using a face image included in the subject's video among the data collected through the data collection unit.
[0100] S130: A step in which a machine learning blood pressure measurement unit measures machine learning-blood pressure (ML-BP) using age prediction based on a face image included in a video of data collected through a data collection unit, and BMI based on the subject's height and weight.
[0101] S140: A step in which the blood pressure prediction output unit outputs either of the measured blood pressures of the face blood pressure measurement unit and the machine learning blood pressure measurement unit as the final predicted blood pressure.
[0102] Embodiments of the present invention are described below with reference to the attached drawings so that those skilled in the art can easily implement the invention. However, the present invention may be embodied in various different forms and is not limited to the embodiments described herein. Furthermore, in order to clearly explain the present invention in the drawings, parts unrelated to the explanation have been omitted, and similar parts throughout the specification are denoted by similar reference numerals.
[0103]
[0104] Throughout the specification, when a part is described as being "connected" to another part, this includes not only cases where they are "directly connected" but also cases where they are "indirectly connected" with other elements interposed between them. Furthermore, when a part is described as "including" a component, this means that, unless specifically stated otherwise, it does not exclude other components but rather allows for the inclusion of additional components; it should be understood that this does not preclude the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.
[0105]
[0106] The following examples are detailed descriptions to aid in understanding the present invention and are not intended to limit the scope of the present invention. Accordingly, inventions within the same scope that perform the same function as the present invention will also fall within the scope of the present invention.
[0107]
[0108] In addition, each component, process, procedure, or method included in each embodiment of the present invention may be shared within a scope that is not technically contradictory to one another.
[0109]
[0110] FIG. 1 is a diagram illustrating the configuration of an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm according to an embodiment of the present invention in functional blocks; FIG. 2 is a diagram illustrating an example of the implementation of an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm according to an embodiment of the present invention; FIG. 3 is a diagram illustrating the configuration of the face-blood pressure output of an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm according to an embodiment of the present invention; FIG. 4 is a diagram illustrating another configuration of the face-blood pressure output of an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm according to an embodiment of the present invention; and FIG. 5 is a diagram illustrating the configuration of the ML-BP output of an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm according to an embodiment of the present invention. As illustrated in FIGS. 1 to 5, an advanced non-contact blood pressure measurement system (100) combined with a computer vision-based subject age measurement algorithm according to an embodiment of the present invention may be configured to include a data collection unit (110) that collects a video of a subject for non-contact blood pressure measurement and BMI through the subject's height and weight, a face blood pressure measurement unit (120) that measures face-blood pressure (Face-BP) using a face image included in the subject's video among the data collected through the data collection unit (110), a machine learning blood pressure measurement unit (130) that predicts age through a face image included in the video of the data collected through the data collection unit (110) and measures machine learning-blood pressure (ML-BP) using BMI through the subject's height and weight, and a blood pressure prediction output unit (140) that outputs one of the blood pressures measured by the face blood pressure measurement unit (120) and the machine learning blood pressure measurement unit (130) as the final predicted blood pressure.Hereinafter, with reference to the attached drawings, the specific configuration of an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm according to an embodiment of the present invention will be described in detail.
[0111]
[0112] FIG. 6 is a diagram illustrating the functional importance for predicting hypertension risk in an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm according to an embodiment of the present invention; FIG. 7 is a diagram illustrating the relationship between blood pressure and body mass index to be applied to an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm according to an embodiment of the present invention; FIG. 8 is a diagram illustrating a graph classifying the prevalence of hypertension in U.S. adults by age and gender to be applied to an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm according to an embodiment of the present invention; FIG. 9 is a diagram illustrating the age prediction processing process of an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm according to an embodiment of the present invention; FIG. 10 is a diagram illustrating the age estimation configuration of a captured video in an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm according to an embodiment of the present invention; and FIG. 11 is a computer vision-based subject age according to an embodiment of the present invention FIG. 12 is a diagram illustrating the processing of subject age estimation in an advanced non-contact blood pressure measurement system combined with a measurement algorithm according to an embodiment of the present invention, FIG. 13 is a diagram illustrating the implementation configuration in which the computer vision age measurement algorithm is applied in an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm according to an embodiment of the present invention.
[0113]
[0114] The data collection unit (110) is configured to collect a video of a subject for non-contact blood pressure measurement and BMI based on the subject's height and weight. This data collection unit (110) may be configured to include a camera module for capturing a video of a subject for non-contact blood pressure measurement. Here, the camera module captures a face image of the subject for non-contact blood pressure measurement, and the captured face image may be provided to a face blood pressure measurement unit (120) and a machine learning blood pressure measurement unit (130), which will be described later. At this time, the captured face image provided to the blood pressure measurement unit (120) is used for face-blood pressure measurement, and the captured face image provided to the machine learning blood pressure measurement unit (130) may be used as data for age estimation.
[0115]
[0116] Additionally, the data collection unit (110) may be configured to include an input module for collecting BMI through the height and weight of a subject for non-contact blood pressure measurement. This input module may be configured so that the user directly inputs the height and weight, or so that the height and weight are automatically input through a body mass measuring device.
[0117]
[0118] The face blood pressure measuring unit (120) is configured to measure face-blood pressure (Face-BP) using a face image included in a video of a subject among the data collected through the data collection unit (110). This face blood pressure measuring unit (120) measures face-blood pressure (Face-BP) using a face image included in a video of a subject among the data collected through the data collection unit (110), and as illustrated in FIG. 13, it can measure blood pressure (BP) and heart rate through the processes of face detection, Region of Interest detection, signal processing, and filtering of the subject's face included in the captured video. Here, the face blood pressure measuring unit (120) can be implemented as a computer vision-based algorithm that measures face-blood pressure (Face-BP) through the processing of the subject's face image included in the captured video.
[0119]
[0120] Additionally, the face blood pressure measurement unit (120) can use the blood pressure (BP) measured through the processes of face detection, Region of Interest detection, signal processing, and filtering of the subject included in the captured video as the face-blood pressure (Face-BP) transmitted to the blood pressure prediction output unit (140). Additionally, the heart rate measured through the processes of face detection, Region of Interest detection, signal processing, and filtering of the subject included in the captured video by the face blood pressure measurement unit (120) can be transmitted and used as a condition input value for generating machine learning-blood pressure (ML-BP) of the machine learning blood pressure measurement unit (130).
[0121]
[0122] The machine learning blood pressure measurement unit (130) is configured to predict age using face images included in the video of data collected through the data collection unit (110) and to measure machine learning-blood pressure (ML-BP) using BMI based on the subject's height and weight. This machine learning blood pressure measurement unit (130) measures age using face images included in the video of data collected through the data collection unit (110) and to measure machine learning-blood pressure (ML-BP) using BMI based on the subject's height and weight, wherein age prediction can be performed through face detection, face cropping, feature extraction, and age prediction processes included in the video via an age measurement algorithm. Here, the machine learning blood pressure measurement unit (130) can be implemented as a computer vision-based algorithm capable of estimating age through the processing of the subject's face images included in the captured video.
[0123]
[0124] Additionally, the machine learning blood pressure measurement unit (130) may use the BMI consisting of the subject's height and weight, the age predicted based on computer vision, and the heart rate received from the face blood pressure measurement unit (120) as condition input values for measuring machine learning-blood pressure (ML-BP).
[0125]
[0126] The blood pressure prediction output unit (140) is configured to output one of the respective blood pressures measured by the face blood pressure measurement unit (120) and the machine learning blood pressure measurement unit (130) as the final predicted blood pressure. This blood pressure prediction output unit (140) receives and outputs the face-blood pressure (Face BP) of the face blood pressure measurement unit (120) and the machine learning-blood pressure (ML-BP) of the machine learning blood pressure measurement unit (130), and can output one of the respective face-blood pressure (Face BP) and machine learning-blood pressure (ML-BP) as the final predicted blood pressure value according to a preset condition. That is, it can function to select ML-BP and Face-BP according to a preset condition and output them as a result.
[0127]
[0128] Thus, an advanced non-contact blood pressure measurement system (100) combined with a computer vision-based subject age measurement algorithm comprises: a data collection unit (110) for collecting a video of a subject for non-contact blood pressure measurement and BMI based on the subject's height and weight; a face blood pressure measurement unit (120) for measuring face-blood pressure (Face-BP) using a face image included in the subject's video among the data collected through the data collection unit (110); a machine learning blood pressure measurement unit (130) for predicting age through a face image included in the video of the data collected through the data collection unit (110) and measuring machine learning-blood pressure (ML-BP) using BMI based on the subject's height and weight; and a blood pressure prediction output unit (140) for outputting one of the blood pressures measured by the face blood pressure measurement unit (120) and the machine learning blood pressure measurement unit (130) as the final predicted blood pressure. The system measures face-blood pressure (Face BP) and treadmill-blood pressure (ML-BP) in a non-contact manner, and the measured By selecting either Face Blood Pressure (Face BP) or Roller Machine Blood Pressure (ML-BP) according to preset conditions and outputting it as the final blood pressure, it is possible to enable advanced non-contact blood pressure measurement.
[0129]
[0130] FIG. 14 is a diagram illustrating the flow of a method for using an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm according to an embodiment of the present invention. As illustrated in FIG. 14, a method of using an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm according to an embodiment of the present invention may be implemented by including the following steps: a data collection unit collecting a video of a subject for non-contact blood pressure measurement and BMI through the subject's height and weight (S110); a face blood pressure measurement unit measuring face-blood pressure (Face-BP) using a face image included in the subject's video among the data collected through the data collection unit (S120); a machine learning blood pressure measurement unit measuring age prediction through the face image included in the video of the data collected through the data collection unit and machine learning-blood pressure (ML-BP) using BMI through the subject's height and weight (S130); and a blood pressure prediction output unit outputting one of the blood pressures measured by the face blood pressure measurement unit and the machine learning blood pressure measurement unit as the final predicted blood pressure (S140).
[0131]
[0132] In step S110, the data collection unit (110) collects a video of the subject for non-contact blood pressure measurement and BMI based on the subject's height and weight. The data collection unit (110) in step S110 may be configured to include a camera module for capturing a video of the subject for non-contact blood pressure measurement. Here, the camera module captures a face image of the subject for non-contact blood pressure measurement, and the captured face image may be provided to a face blood pressure measurement unit (120) and a machine learning blood pressure measurement unit (130), which will be described later. At this time, the captured face image provided to the blood pressure measurement unit (120) is used for face-blood pressure measurement, and the captured face image provided to the machine learning blood pressure measurement unit (130) may be used as data for age estimation.
[0133]
[0134] Additionally, the data collection unit (110) may be configured to include an input module for collecting BMI through the height and weight of a subject for non-contact blood pressure measurement. This input module may be configured so that the user directly inputs the height and weight, or so that the height and weight are automatically input through a body mass measuring device.
[0135]
[0136] In step S120, the face blood pressure measuring unit (120) measures face-blood pressure (Face-BP) using a face image included in the subject's video among the data collected through the data collection unit (110). In step S120, the face blood pressure measuring unit (120) measures face-blood pressure (Face-BP) using a face image included in the subject's video among the data collected through the data collection unit (110), and as illustrated in FIG. 13, can measure blood pressure (BP) and heart rate through the processes of face detection, Region of Interest detection, signal processing, and filtering of the subject's face included in the captured video. Here, the face blood pressure measuring unit (120) can be implemented as a computer vision-based algorithm that measures face-blood pressure (Face-BP) through the processing of the subject's face image included in the captured video.
[0137]
[0138] Additionally, the face blood pressure measurement unit (120) can use the blood pressure (BP) measured through the processes of face detection, Region of Interest detection, signal processing, and filtering of the subject included in the captured video as the face-blood pressure (Face-BP) transmitted to the blood pressure prediction output unit (140). Additionally, the heart rate measured through the processes of face detection, Region of Interest detection, signal processing, and filtering of the subject included in the captured video by the face blood pressure measurement unit (120) can be transmitted and used as a condition input value for generating machine learning-blood pressure (ML-BP) of the machine learning blood pressure measurement unit (130).
[0139]
[0140] In step S130, the machine learning blood pressure measurement unit (130) measures machine learning-blood pressure (ML-BP) using BMI derived from the subject's height and weight and age prediction through face images included in the video of data collected through the data collection unit (110). In step S130, the machine learning blood pressure measurement unit (130) measures machine learning-blood pressure (ML-BP) using BMI derived from the subject's height and weight and age prediction through face images included in the video of data collected through the data collection unit (110), and age prediction can be performed through face detection, face cropping, feature extraction, and age prediction processes included in the video via an age measurement algorithm. Here, the machine learning blood pressure measurement unit (130) can be implemented as a computer vision-based algorithm capable of estimating age through the processing of the subject's face images included in the captured video.
[0141]
[0142] Additionally, the machine learning blood pressure measurement unit (130) may use the BMI consisting of the subject's height and weight, the age predicted based on computer vision, and the heart rate received from the face blood pressure measurement unit (120) as condition input values for measuring machine learning-blood pressure (ML-BP).
[0143]
[0144] In step S140, the blood pressure prediction output unit (140) outputs one of the respective blood pressures measured by the face blood pressure measurement unit (120) and the machine learning blood pressure measurement unit (130) as the final predicted blood pressure. In this step S140, the blood pressure prediction output unit (140) receives and outputs the face-blood pressure (Face BP) of the face blood pressure measurement unit (120) and the machine learning-blood pressure (ML-BP) of the machine learning blood pressure measurement unit (130), and can output one of the respective face-blood pressure (Face BP) and machine learning-blood pressure (ML-BP) as the final predicted blood pressure value according to a preset condition. That is, it can function to select ML-BP and Face-BP according to a preset condition and output them as a result.
[0145]
[0146] As described above, an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm according to an embodiment of the present invention and a method for using the same comprises: a data collection unit that collects a video of a subject for non-contact blood pressure measurement and BMI based on the subject's height and weight; a face blood pressure measurement unit that measures face-blood pressure (Face-BP) using a face image included in the subject's video among the data collected through the data collection unit; a machine learning blood pressure measurement unit that predicts age using a face image included in the video of the data collected through the data collection unit and measures machine learning-blood pressure (ML-BP) using BMI based on the subject's height and weight; and a blood pressure prediction output unit that outputs one of the blood pressures measured by the face blood pressure measurement unit and the machine learning blood pressure measurement unit as the final predicted blood pressure. By comprising these components, it is possible to enable advanced non-contact blood pressure measurement through the estimation of the subject's age based on computer vision and the measurement of machine learning-blood pressure (ML-BP) and face-blood pressure (Face-BP). In particular, the system enables the estimation of the subject's age based on computer vision and By enabling advanced non-contact blood pressure measurement through machine learning-blood pressure (ML-BP) and face-blood pressure (Face-BP) measurements, it is possible to measure face-blood pressure using face images and treadmill-blood pressure using BMI, estimated age, and heart rate, and to output a single blood pressure result based on preset conditions for each measured blood pressure, thereby enabling more precise and accurate non-contact blood pressure measurement management.
[0147]
[0148] The foregoing description of the present invention is for illustrative purposes only, and those skilled in the art will understand that other specific forms can be easily modified without altering the technical spirit or essential features of the present invention. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive. For example, each component described as a single unit may be implemented in a distributed manner, and components described as distributed may likewise be implemented in a combined form.
[0149]
[0150] The scope of the present invention is defined by the claims set forth below rather than by the detailed description above, and all modifications or variations derived from the meaning and scope of the claims and equivalent concepts thereof should be interpreted as being included within the scope of the present invention.
Claims
1. An advanced non-contact blood pressure measurement system (100) combined with a computer vision-based subject age measurement algorithm, A data collection unit (110) for collecting a video of a subject for non-contact blood pressure measurement and BMI through the subject's height and weight; A face blood pressure measuring unit (120) that measures face-blood pressure (Face-BP) using a face image included in a video of a subject among the data collected through the above data collection unit (110); A machine learning blood pressure measurement unit (130) that measures machine learning-blood pressure (ML-BP) using BMI based on the subject's height and weight, and predicts age through a face image included in the video of the data collected through the data collection unit (110); and An advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm, characterized by including a blood pressure prediction output unit (140) that outputs one of the measured blood pressures of the face blood pressure measurement unit (120) and the machine learning blood pressure measurement unit (130) as the final predicted blood pressure.
2. In paragraph 1, the data collection unit (110) is, An advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm, characterized by being configured to include a camera module for capturing video of a subject for non-contact blood pressure measurement.
3. In paragraph 1, the data collection unit (110) is, An advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm, characterized by being configured to include an input module for collecting BMI through the subject's height and weight for non-contact blood pressure measurement.
4. In any one of paragraphs 1 to 3, the face blood pressure measuring unit (120) is, An advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm, characterized by measuring face-blood pressure (Face-BP) using a face image included in a video of a subject among the data collected through the above data collection unit (110), and measuring blood pressure (BP) and heart rate through the processes of face detection, Region Of Interest detection, signal processing, and filtering of the subject included in the captured video.
5. In paragraph 4, the face blood pressure measuring unit (120) is, An advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm, characterized in that the blood pressure (BP) measured through the processes of face detection, Region Of Interest detection, signal processing, and filtering of a subject included in a captured video is used as the face-blood pressure (Face-BP) transmitted to the blood pressure prediction output unit (140).
6. In paragraph 4, the face blood pressure measuring unit (120) is, An advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm, characterized in that the heart rate measured through the processes of face detection, Region Of Interest detection, signal processing, and filtering of the subject included in the captured video is transmitted and used as a conditional input value for generating machine learning-blood pressure (ML-BP) of the machine learning blood pressure measurement unit (130).
7. In paragraph 4, the machine learning blood pressure measuring unit (130) is, An advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm, characterized in that age is predicted through a face image included in a video of data collected through the above data collection unit (110), and machine learning-blood pressure (ML-BP) is measured using BMI based on the subject's height and weight, wherein age prediction is performed through face detection, face cropping, feature extraction, and age prediction processes included in the video via an age measurement algorithm.
8. In paragraph 7, the machine learning blood pressure measuring unit (130) is, An advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm, characterized by using a BMI consisting of the subject's height and weight, a computer vision-based predicted age, and a heart rate received from a face blood pressure measurement unit (120) as condition input values for measuring machine learning-blood pressure (ML-BP).
9. A method of using an advanced non-contact blood pressure measurement system (100) combined with a computer vision-based subject age measurement algorithm, (1) A data collection unit (110) collects a video of a subject for non-contact blood pressure measurement, and BMI through the subject's height and weight; (2) A step in which the face blood pressure measuring unit (120) measures face-blood pressure (Face-BP) using a face image included in the subject's video among the data collected through the data collection unit (110); (3) A machine learning blood pressure measurement unit (130) measures machine learning-blood pressure (ML-BP) using age prediction through a face image included in a video of data collected through the data collection unit (110) and BMI through the subject's height and weight; and (4) A method of using an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm, characterized in that the blood pressure prediction output unit (140) outputs one of the measured blood pressures of the face blood pressure measurement unit (120) and the machine learning blood pressure measurement unit (130) as the final predicted blood pressure.
10. In paragraph 9, the data collection unit (110) is, A method of using an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm, characterized by being configured to include a camera module for capturing a video of a subject for non-contact blood pressure measurement.
11. In paragraph 9, the data collection unit (110) is, A method of using an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm, characterized by being configured to include an input module for collecting BMI through the subject's height and weight for non-contact blood pressure measurement.
12. In any one of claims 9 to 11, the face blood pressure measuring unit (120) is, A method of using an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm, characterized by measuring face-blood pressure (Face-BP) using a face image included in a video of a subject among the data collected through the above data collection unit (110), and measuring blood pressure (BP) and heart rate through the processes of face detection, Region Of Interest detection, signal processing, and filtering of the subject included in the captured video.
13. In paragraph 12, the face blood pressure measuring unit (120) is, A method of using an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm, characterized in that the blood pressure (BP) measured through the processes of face detection, Region Of Interest detection, signal processing, and filtering of a subject included in a captured video is used as the face-blood pressure (Face-BP) transmitted to the blood pressure prediction output unit (140).
14. In paragraph 12, the face blood pressure measuring unit (120) is, A method of using an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm, characterized in that the heart rate measured through the processes of face detection, Region Of Interest detection, signal processing, and filtering of a subject included in a captured video is transmitted and used as a conditional input value for generating machine learning-blood pressure (ML-BP) of the machine learning blood pressure measurement unit (130).
15. In paragraph 12, the machine learning blood pressure measuring unit (130) is, A method of using an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm, wherein age is predicted through a face image included in a video of data collected through the above data collection unit (110), and machine learning-blood pressure (ML-BP) is measured using BMI based on the subject's height and weight, wherein the age prediction is characterized by performing face detection, face cropping, feature extraction, and age prediction processes included in the video through an age measurement algorithm.
16. In item 15, the machine learning blood pressure measuring unit (130) is, A method of using an advanced non-contact blood pressure measurement system combined with a computer vision-based subject age measurement algorithm, characterized by using a BMI consisting of the subject's height and weight, a computer vision-based predicted age, and a heart rate received from a face blood pressure measurement unit (120) as conditional input values for measuring machine learning-blood pressure (ML-BP).