CN117158939A - Non-contact type respiratory heart rate monitoring method and system - Google Patents
Non-contact type respiratory heart rate monitoring method and system Download PDFInfo
- Publication number
- CN117158939A CN117158939A CN202310582920.8A CN202310582920A CN117158939A CN 117158939 A CN117158939 A CN 117158939A CN 202310582920 A CN202310582920 A CN 202310582920A CN 117158939 A CN117158939 A CN 117158939A
- Authority
- CN
- China
- Prior art keywords
- data
- heart rate
- respiratory
- millimeter wave
- wave radar
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 65
- 238000000034 method Methods 0.000 title claims abstract description 52
- 230000000241 respiratory effect Effects 0.000 title claims abstract description 52
- 238000001514 detection method Methods 0.000 claims abstract description 48
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 22
- 238000012545 processing Methods 0.000 claims abstract description 20
- 230000036391 respiratory frequency Effects 0.000 claims abstract description 20
- 238000007781 pre-processing Methods 0.000 claims abstract description 14
- 230000009466 transformation Effects 0.000 claims abstract description 13
- 230000008859 change Effects 0.000 claims abstract description 11
- 230000036387 respiratory rate Effects 0.000 claims description 30
- 238000001228 spectrum Methods 0.000 claims description 23
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 7
- 238000013528 artificial neural network Methods 0.000 claims description 5
- 230000003595 spectral effect Effects 0.000 claims description 5
- 230000002547 anomalous effect Effects 0.000 claims description 2
- 230000008569 process Effects 0.000 abstract description 6
- 238000013136 deep learning model Methods 0.000 abstract description 4
- 210000000115 thoracic cavity Anatomy 0.000 abstract description 2
- 210000000038 chest Anatomy 0.000 description 20
- 230000029058 respiratory gaseous exchange Effects 0.000 description 12
- 238000004891 communication Methods 0.000 description 8
- 230000002159 abnormal effect Effects 0.000 description 6
- 238000006073 displacement reaction Methods 0.000 description 5
- 230000036541 health Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 239000002184 metal Substances 0.000 description 3
- 238000002203 pretreatment Methods 0.000 description 3
- 230000003187 abdominal effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 208000015181 infectious disease Diseases 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000002555 auscultation Methods 0.000 description 1
- 230000035565 breathing frequency Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 206010040872 skin infection Diseases 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Landscapes
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The application relates to the technical field of intelligent monitoring, and provides a non-contact type respiratory heart rate monitoring method, which is characterized in that a camera is used for identifying the position of a human body through steps S1 to S4, the direction of a millimeter wave radar is automatically adjusted, so that the respiratory heart rate can be measured, the position change of a chest cavity and a vibration signal are perceived through the millimeter wave radar, the obtained first detection data are stored, the preprocessing methods such as continuous wavelet transformation are adopted, so that interference is overcome, the signal quality is improved, and the preprocessed data are input into a deep convolutional neural network model for classification processing, so that the data output of respiratory frequency and heart rate are obtained. The application also discloses a system, which utilizes the camera and the millimeter wave radar non-contact sensor to process signals through a deep learning model, so that the long-time and continuous monitoring of the respiratory heart rate of the human body is realized, and meanwhile, the inconvenience and the interference of the traditional contact type monitoring equipment are avoided.
Description
Technical Field
The application relates to the technical field of intelligent monitoring, in particular to a non-contact type respiratory heart rate monitoring method and system.
Background
Non-contact respiratory heart rate monitoring is used as a monitoring method without using conventional contact equipment. It may detect human motion and physiological signals, such as respiration and heartbeat, etc., by using cameras, microwave radar or other sensors. The monitoring method can be used in the fields of medical care, sports training and the like, and can also be applied to scenes such as intelligent home and automobile driver monitoring.
CN110464564B discloses an intelligent bed board system based on automatic detection and remote analysis, comprising: the device comprises a non-contact monitoring bed board, a communication unit, a power module and a monitoring platform; the power supply module is used for supplying power to the noncontact monitoring bed board and the communication unit; the non-contact monitoring bed board is used for collecting the breathing frequency, heart rate and weight data of the user; transmitting the acquired respiratory rate, heart rate and weight data to a communication unit; the communication unit is used for sending the received respiratory rate, heart rate and weight data to the monitoring platform through a network; the monitoring platform is used for displaying the received respiratory rate, heart rate and weight data, analyzing and judging the physical sign state of the user according to the respiratory rate, heart rate and weight data, evaluating the sleep state of the user, and displaying the result obtained by evaluation and judgment; the noncontact monitoring bed board comprises a bed board body, a weight acquisition module and a respiratory heart rate detection module; the bed board body is of a double-layer structure, and the weight acquisition module and the respiratory heart rate detection module are arranged between the bed boards of the double-layer structure; the weight acquisition module comprises a plurality of non-contact pressure sensors which are arranged between the bed board bodies with the double-layer structure at equal intervals and are used for acquiring the weight of a user; the respiratory rate detection module is used for collecting respiratory rate and rate signals of a user and transmitting the collected respiratory rate and rate signals to the communication unit; the bed board body also comprises a rectangular bed board body, and the rectangular bed board body is used for fixing the bed board body with a double-layer structure; the inner side surface of the rectangular bed frame is fixedly provided with a metal plate extending inwards, the metal plate is positioned between the bed plate bodies with the double-layer structure, and the metal plate is used for fixing the weight acquisition module; the waterproof explosion-proof box body is used for placing the non-contact type respiratory heart rate sensor and the power module, a plurality of cross beams are arranged between two long sides of the rectangular bedstead, and the cross beams are perpendicular to the two long sides of the rectangular bedstead; the monitoring platform comprises a display module, a state analysis module, a setting module, a sleep state evaluation module, a controller, an alarm module and the like.
CN116033868A discloses a non-contact health monitoring device comprising: a housing; a radar sensor comprising a plurality of antennas, wherein the radar sensor is housed by the housing; and a processing system including one or more processors, the processing system in communication with the radar sensor, the processing system housed by the housing, wherein the processing system is configured to: receiving a radar data stream from the radar sensor for each of the plurality of antennas, thereby receiving a plurality of radar data streams; performing a beam steering process that creates a plurality of target space region radar data streams from the received plurality of radar data streams; determining a respiratory displacement of the user for each target spatial region radar data stream of the plurality of target spatial region radar data streams; analyzing the respiratory displacement of the user for each target spatial region radar data stream of the plurality of target spatial region radar data streams; and analyzing the respiratory displacement of the user in relation to time based on the radar data streams for each of the plurality of target spatial region radar data streams, outputting a screening result; wherein a first target spatial region radar stream of the target spatial region radar streams corresponds to a chest region of the user; wherein a second target spatial region radar stream of the target spatial region radar streams corresponds to an abdominal region of the user; wherein the analyzing comprises detecting a phase difference between the respiratory displacement of the abdominal region and the respiratory displacement of the chest region sufficient to indicate an abnormal respiratory condition; and wherein the output screening result includes information indicative of the detected abnormal respiratory condition.
CN115460980a discloses a non-contact respiration monitoring method based on doppler radar, comprising the following steps: s1, transmitting periodic linear frequency modulation continuous wave pulses to a region where a monitored object is located, and acquiring corresponding echo signals by using an antenna array; s2, preprocessing radar echo signals by adopting a frequency mixing and FFT mode; s3, extracting the position of the thoracic cage of the monitored object from the radar echo signal, wherein the position comprises distance and direction angle parameters relative to an antenna array; s4, extracting motion information of the position of the thoracic cage of the monitored object from the radar echo signal by adopting a phase correlation method; s5, extracting a respiratory waveform component from the motion information of the chest of the monitored subject by adopting an improved CEEMD algorithm; s6, obtaining a corresponding frequency spectrum by utilizing the extracted respiration waveform of the monitored object, and obtaining the respiration frequency of the monitored object based on the frequency spectrum estimation.
Because in the health monitoring process, the traditional health monitoring mode usually adopts a contact mode to collect respiration and heart rate data, such as wearing a heart rate monitor or artificial auscultation. This approach is often uncomfortable and may even cause problems with skin infections.
Disclosure of Invention
Long-term practice shows that the traditional contact type heart rate and respiratory signal monitoring equipment needs to attach a sensor to the surface of a human body, and a user can feel uncomfortable even contact infection due to direct contact; because heart rate and breathing monitoring need long-time data, traditional contact heart rate and breathing signal monitoring equipment can only gather data in the short time, can't satisfy long-time monitoring's demand, often causes the travelling comfort not high, carries inconvenient, receives technical problem such as external interference is big.
In view of the above, the present application provides a non-contact respiratory heart rate monitoring method, the non-contact respiratory heart rate monitoring method comprising,
step S1, recognizing the position of a human body in a measuring range by a camera for recognizing the face image of the human body, and locking the position of a camera holder; according to the position of the locking cradle head, automatically adjusting the millimeter wave radar capable of measuring the respiratory heart rate to the chest position of the human body;
step S2, sensing chest position change and vibration signals through millimeter wave radar, and acquiring a time point t 1 To time point t 2 Is a first detection data of (a); wherein the first detection data comprises respiratory rate data and heart rate signal data;
step S3, storing the obtained first detection data, and preprocessing the data by adopting continuous wavelet transformation;
and S4, inputting the preprocessed data into a deep convolutional neural network model for classification processing, and obtaining the respiratory rate and the heart rate.
Preferably, in step S2, in the first detection data, a phase difference calculation is performed by acquiring a phase of the millimeter wave radar reflected millimeter wave and a phase of the transmitted millimeter wave, so as to obtain second detection data.
Preferably, in step S2, the second detection data is separated into respiratory rate data and heart rate signal data by a band-pass filter.
Preferably, the separated respiratory frequency data and heart rate signal data are respectively subjected to spectrum estimation to obtain the respiratory frequency spectrum data and the heart rate signal spectrum data.
Preferably, the preprocessed data is input into a trained deep convolutional neural network model, so that abnormal data is identified.
A system for a non-contact respiratory heart rate monitoring method as described above, the system comprising,
the detection unit comprises a camera, a cradle head, a millimeter wave radar and a control module, wherein the camera is fixedly arranged on the cradle head, and the cradle head comprises an electric cradle head; the millimeter wave radar is used for detecting the position of a human body entering the measuring range through the camera and adjusting the orientation of the millimeter wave radar to the position of the chest of the human body;
the camera is used for recognizing the face image of the person and recognizing the position of the person entering the measuring range;
the control module acquires a human body position signal identified by the camera, sends a first control signal to the cradle head and locks the position of the cradle head of the camera; the control module sends a second control signal to the millimeter wave radar according to the position of the locking holder;
the millimeter wave radar is used for automatically adjusting and measuring the respiratory heart rate, acquiring a second control signal of the control module and facing to the chest position of the human body; thereby transmitting and receiving the reflected millimeter wave;
the sensing unit is used for sensing the chest position change and the vibration signal through the millimeter wave radar and acquiring a time point t 1 To time point t 2 Is a first detection data of (a); wherein the first detection data comprises respiratory rate data and heart rate signal data;
a preprocessing unit for storing the obtained first detection data and preprocessing the data by adopting continuous wavelet transformation;
the recognition unit is used for inputting the preprocessed data into the deep convolutional neural network model for classification processing to obtain the respiratory rate and the heart rate.
Preferably, the sensing unit further comprises a calculating module, and the calculating unit is used for obtaining the phase difference calculation between the millimeter wave radar reflected millimeter wave phase and the millimeter wave transmitted phase in the first detection data to obtain second detection data;
the calculation module further comprises a band-pass filter sub-module and a spectrum sub-module, and the band-pass filter sub-module separates the second detection data into respiratory frequency data and heart rate signal data through a band-pass filter;
the spectrum submodule is used for obtaining the frequency spectrum data of the respiratory frequency and the frequency spectrum data of the heart rate signal by spectrum estimation respectively from the separated respiratory frequency data and the heart rate signal data.
Preferably, the identifying unit includes a neural network module, and the neural network module is used for inputting the preprocessed data into the trained deep convolutional neural network model, so as to identify the abnormal data.
The application also discloses an electronic device, which comprises a memory and a processor: the memory is used for storing a computer program; the processor is configured to implement a non-contact respiratory heart rate monitoring method as described above when executing the computer program.
The application also discloses a machine-readable storage medium having stored thereon instructions for causing a machine to perform the non-contact respiratory heart rate monitoring method of the application as described above.
Compared with the prior art, the non-contact type respiratory heart rate monitoring method provided by the application has the advantages that the position of a human body is identified by using the camera through the steps S1 to S4, the direction of the millimeter wave radar is automatically adjusted, so that the respiratory heart rate can be measured, the chest position change and the vibration signal are perceived by the millimeter wave radar, the obtained first detection data are stored, the preprocessing methods such as continuous wavelet transformation are adopted to overcome interference and improve the signal quality, and the preprocessed data are input into the deep convolutional neural network model for classification processing, so that the data output of the respiratory frequency and the heart rate are obtained. The application also discloses a system, which utilizes the camera and the millimeter wave radar non-contact sensor to process signals through a deep learning model, so that the long-time and continuous monitoring of the respiratory heart rate of the human body is realized, and meanwhile, the inconvenience and the interference of the traditional contact type monitoring equipment are avoided. The non-contact type sensor such as the camera and the millimeter wave radar is adopted, the sensor is not required to be directly attached to the surface of a human body, and interference and uncomfortable feeling possibly caused by the traditional contact type monitoring equipment are avoided. The real-time and continuous monitoring of respiration and heart rate is realized through the millimeter wave radar, and the method has higher accuracy and stability; by adopting pretreatment methods such as continuous wavelet transformation, the interference can be effectively removed, and the signal quality can be improved. And (5) carrying out classification processing by adopting a deep convolutional neural network model to obtain data output such as respiratory rate, heart rate and the like. The method has good adaptability and prediction accuracy.
Additional features and advantages of the application will be set forth in the detailed description which follows.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application, illustrate and explain the application and are not to be construed as limiting the application. In the drawings:
FIG. 1 is a flow chart of a non-contact respiratory rate monitoring method according to an embodiment of the present application;
FIG. 2 is a schematic diagram of a non-contact respiratory heart rate monitoring system according to one embodiment of the present application;
fig. 3 is a data flow diagram of a non-contact respiratory heart rate monitoring method according to an embodiment of the present application.
Detailed Description
The following describes specific embodiments of the present application in detail with reference to the drawings. It should be understood that the detailed description and specific examples, while indicating and illustrating the application, are not intended to limit the application.
In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, shall fall within the scope of the present application.
It should be noted that the terms "first," "second," "third," "fourth," and the like in the description and claims of the present application and in the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the application herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
In the prior art, the traditional contact type heart rate and respiratory signal monitoring equipment needs to attach a sensor to the surface of a human body, and a user can feel uncomfortable even contact infection due to direct contact; long time data is required for heart rate and respiration monitoring; traditional contact heart rate and respiratory signal monitoring facilities can only gather data in the short time, can't satisfy long-time monitoring's demand, often cause the travelling comfort not high, carry inconvenient, receive technical problem such as external interference is big. As shown in fig. 1, the present application provides a non-contact respiratory heart rate monitoring method comprising,
step S1, recognizing the position of a human body in a measuring range by a camera for recognizing the face image of the human body, and locking the position of a camera holder; according to the position of the locking cradle head, automatically adjusting the millimeter wave radar capable of measuring the respiratory heart rate to the chest position of the human body;
step S2, sensing chest position change and vibration signals through millimeter wave radar, and acquiring a time point t 1 To time point t 2 Is a first detection data of (a); wherein the first detection data comprises respiratory rate data and heart rate signal data;
step S3, storing the obtained first detection data, and preprocessing the data by adopting continuous wavelet transformation;
and S4, inputting the preprocessed data into a deep convolutional neural network model for classification processing, and obtaining the respiratory rate and the heart rate.
According to the non-contact type respiratory heart rate monitoring method provided by the application, the position of a human body is identified by using the camera through the steps S1 to S4, the direction of the millimeter wave radar is automatically adjusted, so that the respiratory heart rate can be measured, the position change and the vibration signal of the thoracic cavity are perceived by the millimeter wave radar, the obtained first detection data are stored, the preprocessing methods such as continuous wavelet transformation and the like are adopted to overcome the interference and improve the signal quality, and the preprocessed data are input into the deep convolutional neural network model for classification processing, so that the data output of the respiratory frequency and the heart rate are obtained. The method utilizes the camera and the millimeter wave radar non-contact sensor to process signals through the deep learning model, so that the long-time and continuous monitoring of the respiratory rate of the human body is realized, and meanwhile, the inconvenience and the interference of the traditional contact type monitoring equipment are avoided. The non-contact type sensor such as the camera and the millimeter wave radar is adopted, the sensor is not required to be directly attached to the surface of a human body, and interference and uncomfortable feeling possibly caused by the traditional contact type monitoring equipment are avoided. The real-time and continuous monitoring of respiration and heart rate is realized through the millimeter wave radar, and the method has higher accuracy and stability; by adopting pretreatment methods such as continuous wavelet transformation, the interference can be effectively removed, and the signal quality can be improved. And (5) carrying out classification processing by adopting a deep convolutional neural network model to obtain data output such as respiratory rate, heart rate and the like. The method has good adaptability and prediction accuracy.
In order to better monitor the respiration and the heart rate in real time and continuously for a long time and improve the anti-interference performance, in the more preferable case of the application, in step S2, in the first detection data, the phase difference calculation is performed by acquiring the phase of the millimeter wave radar reflected millimeter wave and the phase of the transmitted millimeter wave, so as to obtain second detection data. The millimeter wave radar transmits millimeter waves to the chest of the human body, and the phase of the reflected millimeter waves changes from the chest position change and the vibration signal. By performing fast time-dimensional processing (Range-FFT) on the millimeter wave radar reflected millimeter wave and transmitted millimeter wave as shown in fig. 3, phase information is then extracted from the signal, and then the phase is spread. After the phase difference calculation is carried out on the millimeter wave radar reflected millimeter wave phase and the phase of the transmitted millimeter wave, the band-pass filter separation can be carried out.
In order to separate the respiratory rate data and the heart rate signal data from the raw signal better and faster, in a more preferred aspect of the application, in step S2 the second detection data is separated into respiratory rate data and heart rate signal data by a band pass filter. For example, a 0.1-0.5Hz band pass filter can separate the respiratory signal, while a heart rate signal is separated from a 0.8-4Hz band pass filter. In order to better identify the respiratory signal and the heart rate signal, the respiratory frequency data and the heart rate signal data are separated, and the respiratory frequency spectrum data and the heart rate signal spectrum data are obtained through spectrum estimation respectively.
In order to improve the adaptability and the prediction precision of the monitoring, a deep convolutional neural network model is adopted for classification processing. In a more preferred aspect of the application, the preprocessed data is input into a trained deep convolutional neural network model, thereby identifying anomalous data. The spectral data of the respiratory frequency and the spectral data of the heart rate signal are used as the input of the deep convolutional neural network model. The deep convolutional neural network model includes ResNet, denseNet, seNet, among other things. And outputting data of abnormal respiratory frequency and heart rate signals for identifying and predicting the health state of the detected human body.
The present application also provides a system for a non-contact respiratory heart rate monitoring method as described above, as shown in fig. 2, the system comprising,
the detection unit comprises a camera, a cradle head, a millimeter wave radar and a control module, wherein the camera is fixedly arranged on the cradle head, and the cradle head comprises an electric cradle head; the millimeter wave radar is used for detecting the position of a human body entering the measuring range through the camera and adjusting the orientation of the millimeter wave radar to the position of the chest of the human body;
the camera is used for recognizing the face image of the person and recognizing the position of the person entering the measuring range;
the control module acquires a human body position signal identified by the camera, sends a first control signal to the cradle head and locks the position of the cradle head of the camera; the control module sends a second control signal to the millimeter wave radar according to the position of the locking holder;
the millimeter wave radar is used for automatically adjusting and measuring the respiratory heart rate, acquiring a second control signal of the control module and facing to the chest position of the human body; thereby transmitting and receiving the reflected millimeter wave;
the sensing unit is used for sensing the chest position change and the vibration signal through the millimeter wave radar and acquiring a time point t 1 To time point t 2 Is a first detection data of (a); wherein the first detection data comprises respiratory rate data and heart rate signal data;
a preprocessing unit for storing the obtained first detection data and preprocessing the data by adopting continuous wavelet transformation;
the recognition unit is used for inputting the preprocessed data into the deep convolutional neural network model for classification processing to obtain the respiratory rate and the heart rate.
The system of the non-contact type respiratory heart rate monitoring method provided by the application comprises the detection unit, wherein the detection unit comprises a camera, a cradle head, a millimeter wave radar and a control module, the position of a human body entering a measurement range is identified through the camera, and the millimeter wave radar is adjusted to the chest position, so that the automatic measurement of the respiratory heart rate is realized. The sensing unit senses the chest position change and the vibration signal by utilizing the millimeter wave radar to acquire the respiratory frequency and heart rate data. The preprocessing unit adopts methods such as continuous wavelet transformation to remove interference and improve signal quality, and the recognition unit carries out classification processing through a deep convolutional neural network model to obtain accurate respiratory frequency and heart rate data output. The camera and millimeter wave radar non-contact sensor are utilized, signals are processed through the deep learning model, long-time and continuous monitoring of the respiratory rate of a human body is achieved, and meanwhile inconvenience and interference of traditional contact type monitoring equipment are avoided. The non-contact type sensor such as the camera and the millimeter wave radar is adopted, the sensor is not required to be directly attached to the surface of a human body, and interference and uncomfortable feeling possibly caused by the traditional contact type monitoring equipment are avoided. The real-time and continuous monitoring of respiration and heart rate is realized through the millimeter wave radar, and the method has higher accuracy and stability; by adopting pretreatment methods such as continuous wavelet transformation, the interference can be effectively removed, and the signal quality can be improved. And (5) carrying out classification processing by adopting a deep convolutional neural network model to obtain data output such as respiratory rate, heart rate and the like. The method has good adaptability and prediction accuracy.
In order to better preprocess the original signal, under the more preferable condition of the application, the sensing unit further comprises a calculation module, and the calculation unit is used for obtaining the phase difference calculation between the millimeter wave radar reflected millimeter wave phase and the millimeter wave transmitted phase in the first detection data to obtain second detection data;
the calculation module further comprises a band-pass filter sub-module and a spectrum sub-module, and the band-pass filter sub-module separates the second detection data into respiratory frequency data and heart rate signal data through a band-pass filter;
the spectrum submodule is used for obtaining the frequency spectrum data of the respiratory frequency and the frequency spectrum data of the heart rate signal by spectrum estimation respectively from the separated respiratory frequency data and the heart rate signal data.
In order to improve the adaptability and the prediction precision of the monitoring, in a more preferable case of the application, the identification unit comprises a neural network module, and the neural network module is used for inputting the preprocessed data into a trained deep convolutional neural network model so as to identify abnormal data.
Further, the present application also provides an electronic device, including a memory and a processor: the memory is used for storing a computer program; the processor is configured to implement a non-contact respiratory heart rate monitoring method as described above when executing the computer program.
Further, the application also provides a computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements the above-mentioned non-contact respiratory heart rate monitoring method.
It should be noted that, for simplicity of description, the foregoing method embodiments are all described as a series of acts, but it should be understood by those skilled in the art that the present application is not limited by the order of acts described, as some steps may be performed in other orders or concurrently in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required for the present application.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, such as the division of the units, merely a logical function division, and there may be additional manners of dividing the actual implementation, such as multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, or may be in electrical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be embodied essentially or in part or all of the technical solution contributing to the prior art or in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a mobile terminal, a server or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The above description is only of the preferred embodiments of the present application and is not intended to limit the present application, but various modifications and variations can be made to the present application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.
Claims (10)
1. A non-contact respiratory heart rate monitoring method is characterized in that the non-contact respiratory heart rate monitoring method comprises the following steps of,
step S1, recognizing the position of a human body in a measuring range by a camera for recognizing the face image of the human body, and locking the position of a camera holder; according to the position of the locking cradle head, automatically adjusting the millimeter wave radar capable of measuring the respiratory heart rate to the chest position of the human body;
step S2, sensing chest position change and vibration signals through millimeter wave radar, and acquiring a time point t 1 To time point t 2 Is a first detection data of (a); wherein the first detection data comprises respiratory rate data and heart rate signal data;
step S3, storing the obtained first detection data, and preprocessing the data by adopting continuous wavelet transformation;
and S4, inputting the preprocessed data into a deep convolutional neural network model for classification processing, and obtaining the respiratory rate and the heart rate.
2. The method according to claim 1, wherein in step S2, in the first detection data, a phase difference calculation is performed between a millimeter wave radar reflected millimeter wave phase and a millimeter wave transmitted phase, so as to obtain second detection data.
3. The method according to claim 2, wherein in step S2, the second detection data is separated into respiratory rate data and heart rate signal data by a band-pass filter.
4. A method according to claim 3, wherein the separated respiratory rate data and heart rate signal data are respectively subjected to spectral estimation to obtain respiratory rate spectral data and heart rate signal spectral data.
5. The method of claim 1-4, wherein the pre-processed data is input into a trained deep convolutional neural network model to identify outlier data.
6. A system for a non-contact respiratory heart rate monitoring method as claimed in any one of claims 1-5, wherein the system comprises,
the detection unit comprises a camera, a cradle head, a millimeter wave radar and a control module, wherein the camera is fixedly arranged on the cradle head, and the cradle head comprises an electric cradle head; the millimeter wave radar is used for detecting the position of a human body entering the measuring range through the camera and adjusting the orientation of the millimeter wave radar to the position of the chest of the human body;
the camera is used for recognizing the face image of the person and recognizing the position of the person entering the measuring range;
the control module acquires a human body position signal identified by the camera, sends a first control signal to the cradle head and locks the position of the cradle head of the camera; the control module sends a second control signal to the millimeter wave radar according to the position of the locking holder;
the millimeter wave radar is used for automatically adjusting and measuring the respiratory heart rate, acquiring a second control signal of the control module and facing to the chest position of the human body; thereby transmitting and receiving the reflected millimeter wave;
the sensing unit is used for sensing the chest position change and the vibration signal through the millimeter wave radar and acquiring a time point t 1 To time point t 2 Is a first detection data of (a); wherein the first detection data includes a callFrequency data and heart rate signal data;
a preprocessing unit for storing the obtained first detection data and preprocessing the data by adopting continuous wavelet transformation;
the recognition unit is used for inputting the preprocessed data into the deep convolutional neural network model for classification processing to obtain the respiratory rate and the heart rate.
7. The system according to claim 6, wherein the sensing unit further comprises a calculating module, and the calculating unit is configured to obtain, in the first detection data, a phase difference calculation between a millimeter wave radar reflected millimeter wave phase and a millimeter wave transmitted phase, so as to obtain second detection data;
the calculation module further comprises a band-pass filter sub-module and a spectrum sub-module, and the band-pass filter sub-module separates the second detection data into respiratory frequency data and heart rate signal data through a band-pass filter;
the spectrum submodule is used for obtaining the frequency spectrum data of the respiratory frequency and the frequency spectrum data of the heart rate signal by spectrum estimation respectively from the separated respiratory frequency data and the heart rate signal data.
8. The system according to any of claims 6-7, wherein the identification unit comprises a neural network module for inputting the preprocessed data into the trained deep convolutional neural network model, thereby identifying anomalous data.
9. An electronic device comprising a memory and a processor: the memory is used for storing a computer program; the processor for implementing a non-contact respiratory heart rate monitoring method according to any of claims 1-5 when executing a computer program.
10. A machine-readable storage medium having stored thereon instructions for causing a machine to perform the non-contact respiratory heart rate monitoring method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310582920.8A CN117158939A (en) | 2023-05-23 | 2023-05-23 | Non-contact type respiratory heart rate monitoring method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310582920.8A CN117158939A (en) | 2023-05-23 | 2023-05-23 | Non-contact type respiratory heart rate monitoring method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117158939A true CN117158939A (en) | 2023-12-05 |
Family
ID=88940144
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310582920.8A Pending CN117158939A (en) | 2023-05-23 | 2023-05-23 | Non-contact type respiratory heart rate monitoring method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117158939A (en) |
-
2023
- 2023-05-23 CN CN202310582920.8A patent/CN117158939A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9788762B2 (en) | Motion monitor | |
| Yamamoto et al. | ECG signal reconstruction via Doppler sensor by hybrid deep learning model with CNN and LSTM | |
| Yang et al. | Multi-breath: Separate respiration monitoring for multiple persons with UWB radar | |
| US9265448B2 (en) | System and method for detecting the walk of a person | |
| CN112998701A (en) | Vital sign detection and identity recognition system and method based on millimeter wave radar | |
| CN111568437B (en) | Non-contact type bed leaving real-time monitoring method | |
| CN106236049A (en) | Blood pressure measuring method based on video image | |
| RU2691006C2 (en) | Device and method for determining chest and abdominal breathing signals from image data | |
| CN112806975A (en) | Sleep monitoring device, method and medium based on millimeter wave radar | |
| EP4029439A1 (en) | Method for monitoring a recumbent patient to obtain information on a body position of the patient | |
| CN112674738A (en) | Method and device for detecting respiration heartbeat signal | |
| Liu et al. | Human biometric signals monitoring based on wifi channel state information using deep learning | |
| Toda et al. | ECG signal reconstruction using FMCW radar and convolutional neural network | |
| JP7001244B1 (en) | Non-contact biological signal detector | |
| CN109239707A (en) | Behavior state detection device and method | |
| US20210045697A1 (en) | Method and system for pairing physiological signal | |
| CN111839520A (en) | Human respiration monitoring method and device based on CSI signal power response autocorrelation | |
| CN113729677B (en) | Intelligent vital sign monitoring method | |
| Oguntala et al. | Design framework for unobtrusive patient location recognition using passive RFID and particle filtering | |
| CN117158939A (en) | Non-contact type respiratory heart rate monitoring method and system | |
| Toda et al. | ECG signal reconstruction using FMCW radar and a convolutional neural network for contactless vital-sign sensing | |
| CN117218793A (en) | High-accuracy household type fall alarm intelligent robot | |
| CN116602640A (en) | Millimeter wave radar heart rate detection method based on adaptive clutter filtering | |
| Rong et al. | Non-contact cardiac parameters estimation using radar acoustics for healthcare iot | |
| Marty et al. | Investigation of mmwave radar technology for non-contact vital sign monitoring |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |