Heart rate detection system and method

Abstract

The invention provides a heart rate detection system and a heart rate detection method, which can obtain biological information through irradiation of a plurality of near infrared rays, so that the biological information of an occupant can be stably obtained even in various environments such as daytime, night, sunset, sunrise, shadow, street lamps and the like. Furthermore, biological information based on hemoglobin absorption rates of different skin penetration depths is obtained by irradiating a plurality of near infrared rays, and the heart rate of an occupant is grasped based on a plurality of pieces of biological information, thereby minimizing noise and improving accuracy.

Description

Technical Field

[0001] The present invention relates to a heart rate detection system and method for detecting the heart rate of an occupant. Background Art

[0002] Generally, in order to sense the heart rate, a wearable device needs to be worn on the user's body to monitor the user's health indicators. In particular, a heart rate sensor can measure the user's heart rate and observe the disease prognosis in advance based on the user's heart rate.

[0003] Especially during the process of driving a vehicle, once the driver suffers from diseases such as cardiac arrest due to abnormal heart rate, a secondary accident may occur, leading to greater danger.

[0004] Therefore, a device for monitoring the driver's state is equipped in the vehicle. The monitoring device uses a camera to capture the driver's face, state, posture, etc., and analyzes them to confirm the driver's state.

[0005] However, there are limitations in confirming the driver's state based solely on the images captured by the camera. That is, when using the camera, only the driver's face, state, and posture can be grasped, and the heart rate cannot be directly confirmed.

[0006] On the other hand, as a method for measuring the driver's heart rate, there is a method using light, which is divided into a contact type and a non-contact type.

[0007] For the contact type, the driver needs to wear a wearable device in the vehicle, which causes the problem of inconvenient driving.

[0008] The non-contact type is to irradiate light of a specific wavelength band on the driver's skin and measure the driver's heart rate by sensing the amount of light transmitted and reflected.

[0009] However, according to the non-contact type, when using an RGB camera sensor to monitor the occupants in the vehicle, affected by the surrounding environment, there may be insufficient light or saturation, resulting in incorrect heart rate sensing.

[0010] In addition, when using a near-infrared camera sensor, the information for heart rate sensing is relatively insufficient, resulting in a decrease in accuracy.

[0011] The content described above as the background art is only used to enhance the understanding of the background of the present invention and should not be regarded as the prior art known to those skilled in the art of this technology.

[0012] [Prior Art Documents]

[0013] (Patent Document 1) KR 10-2436331B1 (August 22, 2022) Summary of the Invention

[0014] An object of the present invention is to provide a heart rate detection system and method that can stably acquire biometric information of an occupant even in various environments to accurately grasp the heart rate of the occupant.

[0015] The heart rate detection system of the present invention aimed at achieving the above object includes: a detection target area determination unit that checks the position of a subject to set a detection target area; a light information collection unit that obtains light information of each infrared wavelength band that changes over time using infrared rays of different wavelength bands in the detection target area; and a derivation unit that classifies a plurality of pieces of light information by frequency and filters out noise signals to derive heart rate information.

[0016] It is characterized in that the detection target area determination unit checks the facial position of the subject and sets the detection target area based on feature points derived by applying the face of the subject to a trained machine learning algorithm model.

[0017] It is characterized in that the detection target area determination unit is configured to: derive the detection target area based on a machine learning algorithm model trained according to the blood vessel distribution map in the face.

[0018] It is characterized in that the light information collection unit includes a plurality of irradiation devices and a detection unit, the irradiation devices irradiate infrared rays of different wavelength bands, and the detection unit obtains reflected light reflected by the infrared rays from the subject as light information.

[0019] It is characterized in that the plurality of irradiation devices respectively irradiate near-infrared rays of different wavelength bands.

[0020] It is characterized in that the plurality of irradiation devices are set to different wavelength bands in the range of 760 nm or more and less than 2,500 nm, and are classified into a shallower depth and a deeper depth for the subject.

[0021] It is characterized in that the plurality of irradiation devices are set by excluding the visible light wavelength band range in the solar spectrum.

[0022] It is characterized in that the plurality of irradiation devices of the light information collection unit operate with a plurality of lighting combinations that change over time by alternately turning on / off or simultaneously turning on.

[0023] It is characterized in that the light information collection unit excludes the control of simultaneous extinguishing of each irradiation device from the plurality of lighting combinations, and combines them in such a way that the lighting and extinguishing frequency of each irradiation device is minimized.

[0024] It is characterized in that the derivation unit obtains the brightness value of each lighting combination according to the light information obtained by the light information collection unit for each lighting combination, and derives heart rate information through a frequency classification and noise signal filtering process.

[0025] On the other hand, the heart rate detection method of the present invention includes: a detection target area determination step: checking the facial position of the subject and setting a detection target area in the face of the subject; a light information collection step: obtaining light information of each infrared band through an irradiation device that irradiates infrared rays of different bands; a derivation step: classifying the multiple light information by frequency, filtering out noise signals, and deriving heart rate information.

[0026] It is characterized in that the detection target area determination step sets the detection target area based on the feature points derived by applying the face of the subject to a trained machine learning algorithm model.

[0027] It is characterized in that the light information collection step operates with multiple lighting combinations that change over time by alternately turning on / off or simultaneously turning on multiple irradiation devices, thereby obtaining light information.

[0028] It is characterized in that the light information collection step excludes the control of simultaneous extinguishing of each irradiation device from the multiple lighting combinations, and combines them in such a way that the on / off frequency of each irradiation device is minimized.

[0029] It is characterized in that the derivation step obtains the brightness value of each lighting combination based on the light information obtained for each lighting combination, and derives heart rate information through a frequency classification and noise signal filtering process.

[0030] The heart rate detection system and method configured with the above structure obtain biological information by irradiating a variety of near-infrared rays, so that even in various environments such as daytime, night, sunset, sunrise, shadow, streetlights, etc., the biological information of the occupant can be stably obtained.

[0031] In addition, by irradiating a variety of near-infrared rays, biological information on the hemoglobin absorption rate based on different skin penetration depths is obtained, and the heart rate of the occupant is grasped based on the multiple biological information, thereby minimizing noise and improving accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 It is a structural diagram of the heart rate detection system of the present invention.

[0033] Figure 2 To show Figure 1 A diagram showing an example of the detection target area determination unit and the light information collection unit in the shown heart rate detection system.

[0034] Figure 3 A diagram showing the detection target area of the present invention.

[0035] Figure 4 A diagram showing an example of the solar spectrum.

[0036] Figure 5A diagram showing the lighting combination of the irradiation device according to an embodiment of the present invention.

[0037] Figure 6 A diagram showing the lighting combination of the irradiation device according to another embodiment of the present invention.

[0038] Figure 7 A diagram showing the change over time of the lighting combination of the irradiation device according to an embodiment of the present invention.

[0039] Figure 8 A diagram showing the classification of each channel in the lighting combination of the irradiation device according to an embodiment of the present invention.

[0040] Figure 9 A diagram showing the derivation of the brightness value of each channel according to an embodiment of the present invention.

[0041] Figure 10 A diagram showing the removal of the DC component of each channel according to an embodiment of the present invention.

[0042] Figure 11 A diagram showing the frequency distribution analysis and heart rate derivation of each channel according to an embodiment of the present invention.

[0043] Figure 12 A diagram showing the summarization of the results of each channel and the derivation of the heart rate according to an embodiment of the present invention.

[0044] Figure 13 A flowchart of the heart rate detection method according to the present invention.

[0045] Reference numerals

[0046] 10: Detection target area determination unit

[0047] 20: Optical information collection unit

[0048] 21: Irradiation device

[0049] 21a: First irradiation device

[0050] 21b: Second irradiation device

[0051] 22: Detection unit

[0052] 30: Derivation unit

[0053] P: Subject

[0054] S: Detection target area

[0055] S10: Detection target area determination step

[0056] S20: Optical information collection step

[0057] S30: Derivation step. Detailed implementation mode

[0058] Hereinafter, embodiments disclosed in this specification will be described in detail with reference to the accompanying drawings. It should be noted that when assigning reference numerals to the components in the respective drawings, for the same components, even if they are shown in different drawings, the same reference numerals are used as much as possible, and repeated descriptions thereof are omitted.

[0059] In this specification, the component suffixes "module" and "section" are only used for convenience in writing and do not have any meaning or function of mutual distinction in themselves.

[0060] When describing the embodiments disclosed in this specification, if it is determined that the specific description of a related well-known structure or function may impede the understanding of the embodiments of the present invention, the detailed description thereof is omitted. In addition, the drawings are only used as auxiliary tools to help understand the embodiments disclosed in this specification. The disclosed technical idea should not be limited to the forms shown in the drawings and should be understood to cover the technical idea of the present invention and all its variation embodiments, equivalent embodiments, and alternative embodiments within the technical scope.

[0061] Ordinal numbers such as "first" and "second" can be used to describe different components, but these terms are only used to distinguish each component and do not limit the components themselves.

[0062] When a component is described as "connected" or "continued" to another component, it should be understood that the component can be directly connected or continued to the other component, or can be indirectly connected through other components. On the contrary, when a component is described as "directly connected" or "directly continued" to another component, it should be understood that there is no intermediate component between the two.

[0063] Unless otherwise clearly stated in the context, the singular expression also includes the plural meaning.

[0064] In this specification, terms such as "including" or "having" should be understood to indicate the presence of the features, numbers, steps, actions, components, or combinations thereof described in this specification, but do not exclude the possibility of the presence or addition of other features, numbers, steps, actions, components, or combinations thereof.

[0065] The control unit (Controller) may include: a communication device for communicating with other controllers or sensors to implement its control function; a memory for storing an operating system, logical instructions, input / output information, etc.; and one or more processors that perform operations such as judgment, calculation, and decision-making required for control.

[0066] Hereinafter, a heart rate detection system and method according to a preferred embodiment of the present invention will be described with reference to the accompanying drawings.

[0067] The heart rate detection system of the present invention is asFigures 1 to 3 As shown in Figures 1 to 3 , it includes: a detection target area determination unit 10 that checks the position of the subject P to set a detection target area S; an optical information collection unit 20 that obtains optical information of each infrared wavelength band that changes over time using infrared rays of different wavelength bands in the detection target area S; and a derivation unit 30 that classifies a plurality of pieces of optical information by frequency and filters out noise signals to derive heart rate information.

[0068] The heart rate detection system includes a detection target area determination unit 10, an optical information collection unit 20, and a derivation unit 30. Among them, the detection target area determination unit 10 and the optical information collection unit 20 are responsible for collecting information for deriving the heart rate, and the derivation unit 30 aggregates the information collected by the detection target area determination unit 10 and the optical information collection unit 20 to derive heart rate information.

[0069] In the present invention, the subject P may be an occupant in a vehicle.

[0070] The detection target area determination unit 10 can check the facial position of the subject P and set the detection target area S based on feature points derived by applying the face of the subject P to a trained machine learning algorithm model.

[0071] The detection target area determination unit 10 may include a camera that can photograph the face of the subject P. The detection target area determination unit 10 may be located in front of the subject P inside the vehicle and configured to track the face of the subject P.

[0072] Refer to Figure 3 , the detection target area determination unit 10 checks the facial position of the subject P and applies the detected face to a trained machine learning algorithm model to set the detection target area S.

[0073] When checking the facial position of the subject P, the feature points can be based on the positions of the two eyes of the subject P. After removing noise including the eyes and eyebrows based on the feature points, the skin of the subject P can be set as the detection target area S.

[0074] Thus, the detection target area determination unit 10 can derive the detection target area S based on a machine learning algorithm model trained according to the blood vessel distribution map in the face.

[0075] That is, the detection target area S may be the skin of the face of the subject P where blood vessels are distributed, and the skin area of the subject P can be estimated only based on a trained machine learning algorithm model.

[0076] As described above, the detection target area determination unit 10 can photograph the face of the subject P, collect the facial information of the subject P as learning data based on the feature points, and use the collected learning data to generate an algorithm model through regression analysis or machine learning.

[0077] At this time, the regression analysis algorithm may include simple linear regression analysis, multiple linear regression analysis, logistic regression analysis, etc., and the machine learning algorithm may include artificial neural network, decision tree, genetic algorithm, random forest, and deep learning, etc.

[0078] In the present invention, the detection target area S is set according to the subject P through the trained machine learning algorithm.

[0079] As described above, the detection target area determination unit 10 photographs the face of the subject P, and sets the detection target area S according to the subject P through the trained machine learning algorithm model, so that the area where information for heart rate measurement can be collected can be defined in the face of the subject P, and further, when collecting heart rate information through the optical information collection unit 20, the noise can be minimized.

[0080] The optical information collection unit 20 obtains the optical information of each infrared ray band that changes with time by using infrared rays of different bands in the detection target area S set by the detection target area determination unit 10.

[0081] The optical information collection unit 20 can use an infrared sensor or an infrared sensor and an RGB sensor to obtain the optical information of the light reflected from the light irradiated on the subject P. That is, the optical information collection unit 20 can use multiple infrared sensors to obtain the optical information based on infrared rays of different bands, or combine an infrared sensor and an RGB sensor to obtain the optical information by using infrared rays of different bands and the colors of light of three bands.

[0082] In the present invention, infrared rays of different bands are used, and different bands of infrared rays are combined within a predetermined period over time, and the infrared rays are emitted in combination to obtain the optical information.

[0083] Specifically, the optical information collection unit 20 may include a plurality of irradiation devices 21 and a detection unit 22. The plurality of irradiation devices 21 irradiate infrared rays of different bands, and the detection unit 22 obtains the reflected light of the infrared rays reflected from the subject P as the optical information.

[0084] As described above, the optical information collection unit 20 is composed of a plurality of irradiation devices 21 and a detection unit 22. Each irradiation device 21 is configured to irradiate infrared rays of different bands, and the detection unit 22 is configured to detect the infrared rays irradiated by each irradiation device 21. Therefore, the detection unit 22 may be configured as a plurality, and each detection unit 22 may be set to detect infrared rays of different bands.

[0085] The plurality of irradiation devices 21 may be composed of light sources that respectively irradiate near-infrared rays of different wavelength bands.

[0086] As an embodiment, the irradiation device 21 is composed of a first irradiation device 21a and a second irradiation device 21b, and the first irradiation device 21a and the second irradiation device 21b may be configured to irradiate near-infrared rays of different wavelength bands.

[0087] That is, the first irradiation device 21a irradiates near-infrared rays of a first wavelength band, and the second irradiation device 21b irradiates near-infrared rays of a second wavelength band, where the first wavelength band and the second wavelength band may be determined by excluding the visible light wavelength band range from the solar spectrum.

[0088] Specifically, the plurality of irradiation devices 21 may be set to different wavelength bands within the range of more than 760 nm and less than 2,500 nm, and are divided into a shallower depth and a deeper depth for the subject P.

[0089] Refer to Figure 4 , in the solar spectrum, the range where the irradiance is lower than a certain threshold can be regarded as excluding the visible light wavelength band range. As an example, including 760 nm, 940 nm, 1,130 nm, the wavelength band can be determined within 760 nm to 2,500 nm. Therefore, the first wavelength band of the first irradiation device 21a and the second wavelength band of the second irradiation device 21b can be set to different wavelength bands within the range of 760 nm to 2,500 nm excluding the visible light wavelength band range.

[0090] For example, the first wavelength band of the first irradiation device 21a is a short wavelength with a shallower penetration depth and can be set to 760 nm. Compared with the short wavelength, the second wavelength band of the second irradiation device 21b is a long wavelength with a deeper penetration depth and can be set to 1,130 nm, which can penetrate deeper into the skin of the subject P.

[0091] Thus, the plurality of irradiation devices 21 can sense heart rate information based on the blood flow volume in blood vessels located in parts such as the dermis layer and subcutaneous tissue according to the skin depth of the subject P. Since the penetration depths of near-infrared rays of different wavelength bands into the skin are different, the accuracy of heart rate measurement can be improved by using the optical information confirmed through the plurality of irradiation devices 21.

[0092] Among them, the optical information collection unit 20 can operate with multiple lighting combinations that change over time by alternately turning on / off or simultaneously turning on the plurality of irradiation devices 21.

[0093] In addition, the optical information collection unit 20 excludes the control of simultaneously turning off each irradiation device 21 from the multiple lighting combinations, and can perform the combination in such a way that the lighting and extinguishing frequencies of each irradiation device 21 are minimized.

[0094] In the present invention, a plurality of irradiation devices 21 may be configured, such asFigure 5 As shown, when multiple irradiation devices 21 are composed of a first irradiation device 21a and a second irradiation device 21b, three lighting combinations may be included.

[0095] When three irradiation devices 21 are arranged, as Figure 6 shown, seven lighting combinations may be included. The number of irradiation devices 21 can be determined through preliminary experiments according to the influence of multiple optical information on the accuracy of heart rate judgment.

[0096] The above-mentioned irradiation devices 21 are arranged in multiple numbers and combined in such a way that the lighting and extinguishing frequencies of each irradiation device 21 are minimized, thereby reducing the generation of noise. That is, when applying N irradiation devices 21 with different wavelength bands, 2 N -1 lighting combinations may be included.

[0097] The lighting combinations of the optical information collection unit 20 can be repeated over time at a predetermined period. At this time, the period of the lighting combination can be set to at least twice per second based on the minimum target heart rate.

[0098] As an example, when the irradiation device 21 is composed of a first irradiation device 21a and a second irradiation device 21b, as Figure 7 shown, the lighting combinations of each irradiation device 21 can be repeated at a period of more than twice.

[0099] As described above, the irradiation device 21 can perform time-varying classification for each channel according to the alternating lighting / extinguishing or simultaneous lighting of the first irradiation device 21a and the second irradiation device 21b.

[0100] That is, as Figure 8 shown, when the first irradiation device 21a is lit and the second irradiation device 21b is extinguished (i.e., the first channel), since the near-infrared wavelength band characteristic of the first irradiation device 21a has a shallower penetration depth, the biological information corresponding to the hemoglobin absorption amount obtained through the first irradiation device 21a can be expressed as "a".

[0101] When the first irradiation device 21a and the second irradiation device 21b are lit simultaneously (i.e., the second channel), the biological information corresponding to the hemoglobin absorption amount obtained through the first irradiation device 21a with a shallower penetration depth in the near-infrared wavelength band and the second irradiation device 21b with a deeper penetration depth in the near-infrared wavelength band can be expressed as "a" and "b".

[0102] When the first irradiation device 21a is extinguished and the second irradiation device 21b is lit (i.e., the third channel), since the near-infrared wavelength band characteristic of the second irradiation device 21b has a deeper penetration depth, the biological information corresponding to the hemoglobin absorption amount obtained through the second irradiation device 21b can be expressed as "b".

[0103] Accordingly, the derivation unit 30 can obtain the brightness values of each lighting combination based on the optical information obtained by the optical information collection unit 20 according to the lighting combinations, and derive the heart rate information through frequency classification and noise signal filtering processes.

[0104] That is, the derivation unit 30 can obtain the optical information of multiple channels through each irradiation device 21 that makes up the optical information collection unit 20. In this way, the derivation unit 30 can obtain the brightness values that change over time for each channel, remove the DC components of each channel, and remove the noise signals to analyze the frequency, thereby deriving the heart rate information of the subject P.

[0105] For example, when the optical information collection unit 20 is composed of a first irradiation device 21a and a second irradiation device 21b, as Figure 9 shown, the brightness values of three channels can be derived. After that, as Figure 10 shown, the DC components are removed for the 3 channels to achieve normalization.

[0106] Then, as Figure 11 shown, the frequency distribution of each channel can be analyzed over time, and as Figure 12 shown, the analyzed results are summarized to derive the heart rate information of the subject P.

[0107] On the other hand, as Figure 13 shown, the heart rate detection method of the present invention may include: a detection target area determination step (S10): checking the facial position of the subject P and setting a detection target area S in the face of the subject P; an optical information collection step (S20): obtaining the optical information of each infrared band through an irradiation device 21 that irradiates infrared rays of different bands; and a derivation step (S30): classifying the multiple optical information by frequency, filtering the noise signals, and deriving the heart rate information.

[0108] Among them, the detection target area determination step (S10) can set the detection target area S based on the feature points derived by applying the face of the subject P to a trained machine learning algorithm model.

[0109] The face of the subject P can be confirmed through a camera, and the camera can be located in front of the subject P inside the vehicle and configured to track the face of the subject P.

[0110] In the detection target area determination step (S10), the facial position of the subject P is checked, and the checked face is applied to a trained machine learning algorithm model to set the detection target area S. When checking the facial position of the subject P, the feature points can be based on the positions of the two eyes of the subject P. After removing the noise including the eyes and eyebrows based on the feature points, the skin of the subject P is set as the detection target area S.

[0111] Accordingly, the detection target area determination unit 10 can derive the detection target area S based on a machine learning algorithm model trained according to the blood vessel distribution map in the face. That is, the detection target area S can be the skin of the subject P's face where blood vessels are distributed, and based on the trained machine learning algorithm model, only the skin area of the subject P can be speculated.

[0112] On the other hand, in the optical information collection step (S20), the plurality of irradiation devices 21 are alternately turned on / off or turned on simultaneously, and operated with a plurality of lighting combinations that change over time, thereby obtaining optical information.

[0113] In addition, in the optical information collection step (S20), the control in which each irradiation device 21 is turned off simultaneously can be excluded from the plurality of lighting combinations, and the combination can be made in such a way that the lighting and extinguishing frequency of each irradiation device 21 is minimized.

[0114] In the present invention, a plurality of irradiation devices 21 can be arranged. When the plurality of irradiation devices 21 are composed of a first irradiation device 21a and a second irradiation device 21b, three lighting combinations can be included.

[0115] The lighting combination of each irradiation device 21 can be repeated over time at a predetermined cycle. At this time, the cycle of the lighting combination can be set to at least twice per second based on the minimum target heart rate.

[0116] As an example, when the irradiation device 21 is composed of a first irradiation device 21a and a second irradiation device 21b, the lighting combination of each irradiation device 21 can be repeated at a cycle of more than twice. In this way, the lighting combination corresponding to the alternating on / off or simultaneous on of the first irradiation device 21a and the second irradiation device 21b can be classified over time for each channel.

[0117] On the other hand, in the derivation step (S30), based on the optical information obtained for each lighting combination, the brightness value of each lighting combination can be obtained, and the heart rate information can be derived through a frequency classification and noise signal filtering process.

[0118] In this way, in the derivation step (S30), through each irradiation device 21, the brightness value that changes over time can be obtained based on a plurality of channels, and the DC component of each channel can be removed, and the noise signal can be removed to analyze the frequency, thereby deriving the heart rate information of the subject P.

[0119] The heart rate detection system and method configured with the above-described structure obtain biological information by irradiating a plurality of near-infrared rays, so that the biological information of the occupant can be stably obtained even in various environments such as daytime, night, sunset, sunrise, shadow, and street lights.

[0120] In addition, by irradiating a variety of near-infrared rays, biometric information based on the absorption rate of hemoglobin with different skin penetration depths is obtained, and based on multiple biometric information, the heart rate of the occupant is grasped, thereby minimizing noise and improving accuracy.

[0121] Although the present invention has been illustrated and described in conjunction with specific embodiments, the present invention can be variously modified and changed without departing from the technical idea of the present invention provided by the claims, which will be obvious to those of ordinary skill in the art.

Claims

1. A heart rate detection system, comprising: A detection target area determination unit, which checks the position of the subject to set a detection target area; An optical information collection unit, which uses infrared rays of different bands in the detection target area to obtain optical information of each infrared band that changes over time; And An extraction unit, which classifies multiple optical information by frequency and filters out noise signals to extract heart rate information.

2. The heart rate detection system according to claim 1, wherein The detection target area determination unit checks the facial position of the subject and sets the detection target area based on feature points derived by applying the subject's face to a trained machine learning algorithm model.

3. The heart rate detection system according to claim 2, wherein The detection target area determination unit is configured to: extract the detection target area based on a machine learning algorithm model trained according to the blood vessel distribution map in the face.

4. The heart rate detection system according to claim 1, wherein The optical information collection unit includes multiple irradiation devices and a detection unit. The irradiation devices irradiate infrared rays of different bands, and the detection unit obtains the reflected light of the infrared rays reflected from the subject as optical information.

5. The heart rate detection system according to claim 4, wherein The multiple irradiation devices respectively irradiate near-infrared rays of different bands.

6. The heart rate detection system according to claim 5, wherein The multiple irradiation devices are set to different bands within the range of more than 760 nm and less than 2500 nm, and are divided into a shallower depth and a deeper depth for the subject.

7. The heart rate detection system according to claim 5, wherein The multiple irradiation devices are set by excluding the visible light band range in the solar spectrum.

8. The heart rate detection system according to claim 5, wherein The multiple irradiation devices of the optical information collection unit operate with multiple lighting combinations that change over time by alternately turning on / off or turning on simultaneously.

9. The heart rate detection system according to claim 8, wherein The optical information collection unit excludes the control of simultaneous extinction of each irradiation device from the multiple lighting combinations, and combines them in such a way that the lighting and extinction frequencies of each irradiation device are minimized.

10. The heart rate detection system according to claim 5, wherein The extraction unit obtains the brightness value of each lighting combination according to the optical information obtained by the optical information collection unit for each lighting combination, and extracts heart rate information through a frequency classification and noise signal filtering process.

11. A heart rate detection method, comprising: A detection target area determination step: checking the facial position of the subject photographed by a photographing device, and setting a detection target area in the subject's face; An optical information collection step: obtaining optical information of each infrared band through an irradiation device that irradiates infrared rays of different bands; An extraction step: classifying multiple optical information by frequency, filtering out noise signals, and extracting heart rate information.

12. The heart rate detection method according to claim 11, wherein The detection target area determination step sets a detection target area based on feature points derived by applying the face of the subject to a trained machine learning algorithm model.

13. The heart rate detection method according to claim 11, wherein The light information collection step operates with multiple lighting combinations that change over time by alternately turning on / off or simultaneously turning on multiple irradiation devices, thereby obtaining light information.

14. The heart rate detection method according to claim 13, wherein The light information collection step excludes the control of simultaneously turning off each irradiation device from the multiple lighting combinations, and combines them in such a way as to minimize the lighting and extinguishing frequency of each irradiation device.

15. The heart rate detection method according to claim 11, wherein The derivation step obtains the brightness value of each lighting combination based on the light information obtained for each lighting combination, and derives heart rate information through a frequency classification and noise signal filtering process.

Images