Vehicle-mounted heart rate detection method and device, electronic equipment and storage medium

Abstract

Embodiments of the present application provide a vehicle-mounted heart rate detection method and device, electronic equipment and storage medium, the method comprising: acquiring a first signal collected by a first collection device at a first target area of a target human body and a second signal collected by a second collection device at a second target area of the target human body, performing principal component analysis on the first signal to obtain a first heartbeat interval of the target human body, performing correlation coefficient calculation on the second signal based on a correlation coefficient algorithm to obtain a second heartbeat interval of the target human body, and determining a comprehensive heartbeat interval of the target human body according to the first heartbeat interval and the second heartbeat interval. The above scheme solves the problem of poor stability and accuracy of the detected heart rate caused by incomplete contact or too short contact time, and realizes multi-angle signal collection by multiple collection devices, thereby improving the accuracy of heart rate detection.

Description

Technical Field

[0001] This application relates to the field of data processing technology, specifically to a vehicle-mounted heart rate detection method, device, electronic device, and storage medium. Background Technology

[0002] As cars become a common mode of transportation, real-time monitoring of drivers' physiological signals (such as heart rate) is essential for assessing fatigue and preventing illness. However, most existing physiological signal acquisition devices rely on wearable or short-term contact with a single sensor for heart rate detection. Incomplete or insufficient contact during acquisition leads to poor stability and accuracy of the collected signals. Therefore, achieving accurate heart rate detection is a pressing issue that needs to be addressed. Summary of the Invention

[0003] This application provides a vehicle-mounted heart rate detection method, device, electronic device, and storage medium. This aims to at least address the problems of poor heart rate stability and accuracy caused by incomplete contact or insufficient contact time in related technologies.

[0004] According to one embodiment of this application, a vehicle-mounted heart rate detection method is provided, comprising: acquiring a first signal acquired by a first acquisition device in a first target area of ​​a target human body and a second signal acquired by a second acquisition device in a second target area of ​​the target human body; performing principal component analysis on the first signal to obtain a first heartbeat interval of the target human body; calculating the correlation coefficient of the second signal based on a correlation coefficient algorithm to obtain a second heartbeat interval of the target human body; and determining a comprehensive heartbeat interval of the target human body based on the first heartbeat interval and the second heartbeat interval.

[0005] In one exemplary embodiment, the first acquisition device is an image acquisition device, the second acquisition device is a laser sensor, the first target area includes a forehead area, a nose and cheek area, and other areas of the face excluding the eyes and mouth, and the second target area includes a neck area. Acquiring a first signal acquired by the first acquisition device in the first target area of ​​the target human body includes: acquiring a first RGB image of the forehead area, a second RGB image of the nose and cheek area, and a third RGB image of the other areas; extracting a G-color signal from the first RGB image, the second RGB image, and the second RGB image; filtering the extracted G-color signal to obtain the first signal; acquiring a second signal acquired by the second acquisition device in the second target area of ​​the target human body includes: acquiring multiple laser point signals from the neck area; filtering the multiple laser point signals to obtain the second signal.

[0006] In an exemplary embodiment, performing principal component analysis on the first signal to obtain the first heartbeat interval of the target human body includes: performing principal component analysis on the first signal to extract principal component components therein, wherein the principal component components are the first signal whose quality meets a preset quality threshold; drawing a first heartbeat signal waveform based on the principal component components, and obtaining the first heartbeat interval based on the peaks and troughs of the first heartbeat signal waveform.

[0007] In an exemplary embodiment, calculating the correlation coefficient of the second signal based on a correlation coefficient algorithm to obtain the second heartbeat interval of the target human body includes: determining a reference signal from a plurality of second signals; calculating the correlation coefficients between other second signals among the plurality of second signals and the reference signal respectively; determining a second signal that meets a preset requirement based on the correlation coefficients; adding the second signals that meet the preset requirement to obtain a second heartbeat signal waveform; and obtaining the second heartbeat interval based on the peaks and troughs of the second heartbeat signal waveform.

[0008] In an exemplary embodiment, determining the comprehensive heartbeat interval of the target human body based on the first heartbeat interval and the second heartbeat interval includes: performing quality assessments on the first heartbeat interval and the second heartbeat interval respectively to obtain a first assessment result and a second assessment result; and combining the first assessment result and the second assessment result to obtain a heartbeat interval sequence of the comprehensive heartbeat interval.

[0009] In one exemplary embodiment, quality assessments are performed on the first heartbeat interval and the second heartbeat interval to obtain a first assessment result and a second assessment result, including: obtaining a first heartbeat interval sequence corresponding to the first heartbeat interval and a second heartbeat interval sequence corresponding to the second heartbeat interval; calculating the first heartbeat interval quality of the first heartbeat interval sequence and the second heartbeat interval quality of the second heartbeat interval sequence according to a preset heartbeat quality calculation formula, wherein the heartbeat quality calculation formula is as follows: QA represents the quality of the heartbeat interval, H avg H represents the average value of the skip interval sequence. i Let represent the i-th heartbeat interval in the heartbeat interval sequence, n represent the number of heartbeat intervals in the heartbeat interval sequence, and T represent the sampling frequency of the heartbeat interval sequence.

[0010] In an exemplary embodiment, combining the first evaluation result and the second evaluation result to obtain the comprehensive heartbeat interval sequence includes: determining weighting coefficients for the first heartbeat interval and the second heartbeat interval based on the quality of the first heartbeat interval and the quality of the second heartbeat interval, wherein the formula for determining the weighting coefficients is: if the quality of the heartbeat interval is greater than or equal to a preset heartbeat quality threshold, then λX =QA, if the heartbeat interval quality is less than the preset heartbeat quality threshold, then λ X =0, where λ X Let X be a weighting coefficient, X = 1 or 2, λ1 be the first weighting coefficient corresponding to the first heartbeat interval, and λ2 be the second weighting coefficient corresponding to the second heartbeat interval; multiply the first weighting coefficient and the first heartbeat interval sequence to obtain the first target heartbeat interval sequence; multiply the second weighting coefficient and the second heartbeat interval sequence to obtain the second target heartbeat interval sequence; combine the first target heartbeat sequence and the second target heartbeat sequence to obtain the comprehensive heartbeat interval heartbeat interval sequence.

[0011] According to one embodiment of this application, a vehicle-mounted heart rate detection device is provided, comprising: an acquisition module, configured to acquire a first signal acquired by a first acquisition device in a first target area of ​​a target human body and a second signal acquired by a second acquisition device in a second target area of ​​the target human body; a first determination module, configured to perform principal component analysis on the first signal to obtain a first heartbeat interval of the target human body; a second determination module, configured to calculate a correlation coefficient on the second signal based on a correlation coefficient algorithm to obtain a second heartbeat interval of the target human body; and a combination module, configured to determine a comprehensive heartbeat interval of the target human body based on the first heartbeat interval and the second heartbeat interval.

[0012] This application also provides an electronic device, including at least a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program in the memory.

[0013] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described method.

[0014] Through the above steps, a first signal collected by the first acquisition device in a first target area of ​​the target human body and a second signal collected by the second acquisition device in a second target area of ​​the target human body are obtained. Principal component analysis is performed on the first signal to obtain the first heartbeat interval of the target human body. Correlation coefficient is calculated on the second signal based on the correlation coefficient algorithm to obtain the second heartbeat interval of the target human body. The comprehensive heartbeat interval of the target human body is determined based on the first and second heartbeat intervals. This scheme solves the problem of poor heart rate stability and accuracy caused by incomplete contact or insufficient contact time, and realizes multi-angle signal acquisition through multiple acquisition devices, thus improving the accuracy of heart rate detection. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a schematic diagram of the hardware environment for an embodiment of the vehicle-mounted heart rate detection method of this application;

[0017] Figure 2 This is a flowchart of an embodiment of the vehicle-mounted heart rate detection method of this application;

[0018] Figure 3 This is a flowchart of a specific embodiment of the vehicle-mounted heart rate detection method of this application;

[0019] Figure 4 This is a schematic diagram of the structure of an on-board heart rate detection device according to an embodiment of this application. Detailed Implementation

[0020] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0021] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0022] According to one aspect of the embodiments of this application, an in-vehicle heart rate detection method is provided. This in-vehicle heart rate detection method can be executed in a terminal device or a similar computing device. Taking its execution on a terminal device as an example... Figure 1This is a hardware structure block diagram of a terminal device for an in-vehicle heart rate detection method according to an embodiment of the present invention. Figure 1 As shown, the terminal device may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor (MPU) or a programmable logic device (PLD)) and a memory 104 for storing data are also shown. In one exemplary embodiment, the terminal device may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the terminal device described above. For example, the terminal device may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 Equivalent functions or ratios shown Figure 1 The functions shown have more different configurations.

[0023] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the vehicle-mounted heart rate detection method in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thus implementing the aforementioned method. The memory 104 may include high-speed random access memory and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the terminal device via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0024] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the switching device. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module used for wireless communication with the Internet.

[0025] This embodiment provides a vehicle-mounted heart rate detection method, which can be applied to the aforementioned terminal device or configured in a server. Figure 2A flowchart of an embodiment of the vehicle-mounted heart rate detection method of this application is shown. Figure 2 As shown in the figure, this application provides an in-vehicle heart rate detection method, including:

[0026] S210, acquire the first signal acquired by the first acquisition device in the first target area of ​​the target human body and the second signal acquired by the second acquisition device in the second target area of ​​the target human body.

[0027] In the embodiments of this application, the first acquisition device is an image acquisition device, and the second acquisition device is a laser sensor.

[0028] The image acquisition device can be understood as an optical acquisition device, which includes, but is not limited to, cameras, 3D cameras, etc.

[0029] The first target area includes the forehead area, nose and cheek area, and other areas of the face that do not include the eyes and mouth. The second target area includes the neck area.

[0030] For example, a camera can capture signals from the forehead, nose and cheek areas, and other areas of the face that do not include the eyes and mouth of the target human body, and thus obtain signals from the forehead, nose and cheek areas, and other areas of the face captured by the camera; a laser sensor can capture signals from the neck area of ​​the target human body, and thus obtain signals from the neck area captured by the laser sensor.

[0031] S220, perform principal component analysis on the first signal to obtain the first heartbeat interval of the target human body.

[0032] In the embodiments of this application, when a first signal is acquired by the first acquisition device in a first target region of the target human body, principal component analysis is performed on the first signal to obtain the first heartbeat interval of the target human body. That is, principal component analysis is used to extract the main features in the first signal, thereby obtaining the first heartbeat interval of the target human body.

[0033] S230, the correlation coefficient of the second signal is calculated based on the correlation coefficient algorithm to obtain the second heartbeat interval of the target human body.

[0034] In the embodiments of this application, when the second signal collected by the second acquisition device in the second target area of ​​the target human body is obtained, the correlation coefficient algorithm is used to calculate the correlation coefficient of the second signal to obtain the second heartbeat interval of the target human body.

[0035] S240, determine the overall heart rate interval of the target human body based on the first heart rate interval and the second heart rate interval.

[0036] In the embodiments of this application, when a first heartbeat interval and a second heartbeat interval are obtained, the quality of the first heartbeat interval and the second heartbeat interval are evaluated respectively to obtain a first evaluation result and a second evaluation result; the first evaluation result and the second evaluation result are combined to obtain a heartbeat interval sequence with a comprehensive heartbeat interval. Specific implementation methods can be found in subsequent embodiments.

[0037] In the embodiments of this application, after obtaining the heart rate interval sequence of the comprehensive heart rate interval, the heart rate of the target human body can be determined. For example, the shorter the comprehensive heart rate interval sequence, the higher the heart rate; the longer the comprehensive heart rate interval sequence, the lower the heart rate.

[0038] According to the vehicle-mounted heart rate detection method of this application embodiment, a first signal collected by a first acquisition device in a first target area of ​​the target human body and a second signal collected by a second acquisition device in a second target area of ​​the target human body are acquired. Principal component analysis is performed on the first signal to obtain the first heartbeat interval of the target human body. The correlation coefficient is calculated on the second signal based on the correlation coefficient algorithm to obtain the second heartbeat interval of the target human body. The comprehensive heartbeat interval of the target human body is determined based on the first heartbeat interval and the second heartbeat interval. This method solves the problem of poor heart rate stability and accuracy caused by incomplete contact or insufficient contact time, and achieves multi-angle signal acquisition through multiple acquisition devices, thereby improving the accuracy of heart rate detection.

[0039] To facilitate understanding of this application by those skilled in the art, embodiments of this application also provide a specific embodiment of an in-vehicle heart rate detection method, such as... Figure 3 As shown, the vehicle-mounted heart rate detection method includes:

[0040] S310, acquire the first signal collected by the first acquisition device in the first target area of ​​the target human body.

[0041] For example, the first acquisition device is a camera, and the first target area includes the forehead area, the nose and cheek area, and other areas of the face that do not include the eyes and mouth.

[0042] In the embodiments of this application, a first RGB image of the forehead region of a face, a second RGB image of the nose and cheek region, and a third RGB image of other regions can be acquired by a camera. Then, the G color signal is extracted from the first RGB image, the second RGB image, and the second RGB image. The extracted G color signal is filtered to obtain the first signal.

[0043] The process involves converting the first RGB image to an HSV image, where an HSV image represents a combination of hue, saturation, and luminance, with luminance indicating the brightness of the image. Then, a luminance channel is extracted from the HSV image, representing the brightness information but not color information. Next, the luminance channel is converted to a grayscale image, which contains only one channel representing the luminance value of each pixel. Finally, the G color signal is extracted from the grayscale image. This process effectively extracts the G color signal from the first RGB image.

[0044] It should be noted that since G color is usually highly correlated with the luminance channel, grayscale images can be simply regarded as G color signals.

[0045] It should be noted that the specific implementation methods for extracting the G color signal from the second RGB image and the G color signal from the third RGB image can refer to the specific implementation methods for extracting the G color signal from the first RGB image. This application will not elaborate further on these methods here.

[0046] Filtering the extracted G-color signal can be understood as processing the extracted G-color signal to remove unwanted frequency components or noise, making the signal clearer and more reliable. The filtering bandwidth can be selected from 0.5-2Hz, based on a heart rate of 30-120 beats / minute.

[0047] S320, acquire the second signal collected by the second acquisition device in the second target area of ​​the target human body.

[0048] For example, the second acquisition device is a laser sensor, and the second target area includes the neck region.

[0049] In the embodiments of this application, multiple laser point signals from the neck region collected by a laser sensor can be acquired, and these signals can be filtered to obtain a second signal. For example, the laser sensor can acquire signals from nine laser points in the neck region. The filtering bandwidth can be selected from 0.5-2Hz, and the bandwidth selection is based on a heart rate of 30-120 beats / minute.

[0050] For example, mean filtering can be used to filter multiple laser point signals. For instance, averaging multiple laser point signals can effectively reduce noise in the signal.

[0051] For example, median filtering can be used to filter multiple laser point signals. This involves sorting the multiple laser point signals and taking the median value as the filtering result, which can remove outliers and impulse noise.

[0052] For example, a weighted moving average filtering method can be used to filter multiple laser point signals. This method involves weighting and summing the multiple laser point signals, adjusting the weights according to the importance of the signals, making it suitable for situations where the signals are more sensitive to dynamic changes.

[0053] S330 performs principal component analysis on the first signal to obtain the first heartbeat interval of the target human body.

[0054] In the embodiments of this application, principal component analysis is performed on the first signal to extract the principal component components, wherein the principal component components are the first signal whose quality meets a preset quality threshold; the waveform of the first heartbeat signal is plotted based on the principal component components, and the first heartbeat interval is obtained based on the peaks and troughs of the first heartbeat signal waveform.

[0055] For example, when performing principal component analysis on the first signal, the principal component analysis can be performed by calculating the covariance matrix of the first signal, then performing eigenvalue decomposition on the covariance matrix to obtain the first principal component components. Then, based on a preset quality threshold, the principal component components whose quality meets the preset quality threshold are selected from the first principal component components. The principal component components can then be used as the amplitude sequence of the signal, and the waveform of the first heartbeat signal can be plotted based on the time series. Finally, the first heartbeat interval can be obtained based on the peaks and troughs of the first heartbeat signal waveform, i.e., by detecting the positions of the peaks and troughs.

[0056] One approach is to use peak detection algorithms or other related signal processing methods to detect the positions of peaks and troughs, and then calculate the time interval between adjacent peaks and troughs to obtain the first heartbeat interval.

[0057] S340, based on the correlation coefficient algorithm, calculates the correlation coefficient of the second signal to obtain the second heartbeat interval of the target human body.

[0058] In the embodiments of this application, a reference signal can be determined from a plurality of second signals, and the correlation coefficients between other second signals and the reference signal can be calculated respectively; a second signal that meets the preset requirements can be determined according to the correlation coefficients; the second signals that meet the preset requirements can be added together to obtain a second heartbeat signal waveform, and a second heartbeat interval can be obtained based on the peaks and troughs of the second heartbeat signal waveform.

[0059] For example, a reference signal can be determined from multiple second signals. The reference signal can be any one of the multiple second signals. For instance, if there are nine second signals, and the reference signal is the first second signal, the correlation coefficients between the reference signal and the second, third, fourth, fifth, sixth, seventh, eighth, and ninth second signals can be calculated respectively. Then, it is determined whether the eight correlation coefficients corresponding to the first second signal meet a preset threshold. That is, if four or more correlation coefficients are greater than the preset threshold, the first second signal is retained.

[0060] Similarly, when the reference signal is determined to be the second second reference signal, the correlation coefficients of the reference signal and other second reference signals are calculated respectively. Then, it is determined whether the eight correlation coefficients corresponding to the second second reference signal meet the preset threshold. That is, if four or more of them are greater than the preset threshold, the second second reference signal is retained.

[0061] This allows us to determine the correlation coefficient of each second signal and judge the correlation coefficient of each second signal, thereby determining the second signal that meets the preset requirements. Then, the second signals that meet the preset requirements are summed to achieve the purpose of signal enhancement. The summed second signal represents the waveform of the second heartbeat signal collected by the laser sensor. By locating the peak value of the second heartbeat signal waveform, the interval between the peak values ​​is the second heartbeat interval of the target human body.

[0062] S350, the quality of the first heartbeat interval and the second heartbeat interval are evaluated respectively, and the first evaluation result and the second evaluation result are obtained.

[0063] In embodiments of this application, a first heartbeat interval sequence corresponding to a first heartbeat interval and a second heartbeat interval sequence corresponding to a second heartbeat interval are obtained; the first heartbeat interval quality of the first heartbeat interval sequence and the second heartbeat interval quality of the second heartbeat interval sequence are calculated according to a preset heartbeat quality calculation formula, wherein the heartbeat quality calculation formula is as follows: QA represents the quality of the heartbeat interval, H avg H represents the average value of the skip interval sequence. i Let represent the i-th heartbeat interval in the heartbeat interval sequence, n represent the number of heartbeat intervals in the heartbeat interval sequence, and T represent the sampling frequency of the heartbeat interval sequence.

[0064] The acquisition frequency of the heartbeat interval sequence can be understood as the acquisition interval of the heartbeat interval sequence or the sampling time period of the heartbeat interval sequence.

[0065] S360 combines the first and second assessment results to obtain a comprehensive heart rate interval sequence.

[0066] In the embodiments of this application, weighting coefficients for the first heartbeat interval and the second heartbeat interval are determined based on the first heartbeat interval quality and the second heartbeat interval quality. The formula for determining the weighting coefficients is: if the heartbeat quality is greater than or equal to a preset heartbeat quality threshold, λ... X =QA, if the heartbeat quality is less than the preset heartbeat quality threshold, λ X =0, where λ X Let X be the weighting coefficient, X = 1 or 2, λ1 be the first weighting coefficient corresponding to the first heartbeat interval, and λ2 be the second weighting coefficient corresponding to the second heartbeat interval. Multiply the first weighting coefficient and the first heartbeat interval sequence to obtain the first target heartbeat interval sequence. Multiply the second weighting coefficient and the second heartbeat interval sequence to obtain the second target heartbeat interval sequence. Combine the first target heartbeat sequence and the second target heartbeat sequence to obtain the comprehensive heartbeat interval sequence.

[0067] For example, the first heartbeat interval sequence is multiplied by the weights, i.e.

[0068]

[0069] The second heartbeat interval sequence is multiplied by the weights, i.e. The first target heartbeat sequence and the second target heartbeat sequence are then combined to obtain the comprehensive heartbeat interval sequence, i.e.

[0070]

[0071] In the embodiments of this application, after obtaining the heart rate interval sequence of the comprehensive heart rate interval, the heart rate of the target human body can be determined. For example, the shorter the comprehensive heart rate interval sequence, the higher the heart rate; the longer the comprehensive heart rate interval sequence, the lower the heart rate.

[0072] In another embodiment of this application, after obtaining the heart rate interval sequence of the comprehensive heart rate interval, each interval in the comprehensive heart rate interval sequence can be added together to obtain a sum. Then, the sum is divided by the length of the heart rate interval sequence to obtain the average heart rate interval. Finally, 60 is divided by the average heart rate interval to obtain the heart rate. Here, 60 represents per minute.

[0073] According to the vehicle-mounted heart rate detection method of the present application embodiment, the heart rate detection method realized by combining the first acquisition device and the second acquisition device solves the problem that a single camera needs to be in a position directly facing the user; and by performing quality assessment on the heartbeat interval, heartbeat intervals that do not meet the quality assessment coefficient are eliminated, so that the strategy of combining heartbeat intervals that meet the quality assessment coefficient and combining the heartbeat interval sequences corresponding to the first acquisition device and the second acquisition device is more accurate than the detection results of a single sensor, making the heartbeat interval data more valuable for medical and practical applications.

[0074] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of this application.

[0075] Figure 4 This is a structural block diagram of an on-board heart rate detection device according to an embodiment of this application; as shown below. Figure 4 As shown, it includes:

[0076] The acquisition module 410 is used to acquire a first signal acquired by the first acquisition device in a first target area of ​​the target human body and a second signal acquired by the second acquisition device in a second target area of ​​the target human body.

[0077] The first determining module 420 is used to perform principal component analysis on the first signal to obtain the first heartbeat interval of the target human body;

[0078] The second determining module 430 is used to calculate the correlation coefficient of the second signal based on the correlation coefficient algorithm to obtain the second heartbeat interval of the target human body.

[0079] The module 440 is used to determine the comprehensive heartbeat interval of the target human body based on the first heartbeat interval and the second heartbeat interval.

[0080] According to the vehicle-mounted heart rate detection device of this application embodiment, a first signal collected by a first acquisition device in a first target area of ​​the target human body and a second signal collected by a second acquisition device in a second target area of ​​the target human body are acquired. Principal component analysis is performed on the first signal to obtain the first heartbeat interval of the target human body. Correlation coefficient is calculated on the second signal based on a correlation coefficient algorithm to obtain the second heartbeat interval of the target human body. The comprehensive heartbeat interval of the target human body is determined based on the first heartbeat interval and the second heartbeat interval. This solution solves the problem of poor heart rate stability and accuracy caused by incomplete contact or insufficient contact time, and achieves multi-angle signal acquisition through multiple acquisition devices, thereby improving the accuracy of heart rate detection.

[0081] In one exemplary embodiment, the first acquisition device is an image acquisition device, the second acquisition device is a laser sensor, the first target area includes a forehead area, a nose and cheek area, and other areas of the face excluding the eyes and mouth, and the second target area includes a neck area. The acquisition module 410 is configured to acquire a first RGB image of the forehead area, a second RGB image of the nose and cheek area, and a third RGB image of the other areas; extract G-color signals from the first RGB image, the second RGB image, and the third RGB image; filter the extracted G-color signals to obtain the first signal; and the acquisition module 410 is further configured to acquire multiple laser point signals from the neck area; filter the multiple laser point signals to obtain the second signal.

[0082] In an exemplary embodiment, the first determining module 420 is configured to perform principal component analysis on the first signal, extract the principal component components therein, wherein the principal component components are the first signal whose quality meets a preset quality threshold; draw a first heartbeat signal waveform based on the principal component components, and obtain the first heartbeat interval based on the peaks and troughs of the first heartbeat signal waveform.

[0083] In an exemplary embodiment, the second determining module 430 is configured to determine a reference signal from a plurality of second signals, calculate the correlation coefficients between other second signals among the plurality of second signals and the reference signal respectively; determine a second signal that meets a preset requirement based on the correlation coefficients; add the second signals that meet the preset requirement together to obtain a second heartbeat signal waveform, and obtain the second heartbeat interval based on the peaks and troughs of the second heartbeat signal waveform.

[0084] In one exemplary embodiment, module 440 is used to perform quality assessments on the first heartbeat interval and the second heartbeat interval respectively, obtaining a first assessment result and a second assessment result; the first assessment result and the second assessment result are combined to obtain the heartbeat interval sequence of the comprehensive heartbeat interval. In one exemplary embodiment, module 440 is used to obtain the first heartbeat interval sequence corresponding to the first heartbeat interval and the second heartbeat interval sequence corresponding to the second heartbeat interval; calculate the first heartbeat interval quality of the first heartbeat interval sequence and the second heartbeat interval quality of the second heartbeat interval sequence according to a preset heartbeat quality calculation formula, wherein the heartbeat quality calculation formula is: QA represents the quality of the heartbeat interval, H avg H represents the average value of the skip interval sequence. i Let represent the i-th heartbeat interval in the heartbeat interval sequence, n represent the number of heartbeat intervals in the heartbeat interval sequence, and T represent the sampling frequency of the heartbeat interval sequence.

[0085] In an exemplary embodiment, module 440 is used to determine weighting coefficients for the first heartbeat interval and the second heartbeat interval based on the first heartbeat interval quality and the second heartbeat interval quality, wherein the formula for determining the weighting coefficients is: if the heartbeat interval quality is greater than or equal to a preset heartbeat quality threshold, then λ X =QA, if the heartbeat interval quality is less than the preset heartbeat quality threshold, then λ X =0, where λ X Let X be a weighting coefficient, X = 1 or 2, λ1 be the first weighting coefficient corresponding to the first heartbeat interval, and λ2 be the second weighting coefficient corresponding to the second heartbeat interval; multiply the first weighting coefficient and the first heartbeat interval sequence to obtain the first target heartbeat interval sequence; multiply the second weighting coefficient and the second heartbeat interval sequence to obtain the second target heartbeat interval sequence; combine the first target heartbeat sequence and the second target heartbeat sequence to obtain the comprehensive heartbeat interval heartbeat interval sequence.

[0086] Embodiments of this application also provide a storage medium including a stored program, wherein the program executes any of the methods described above when it is run.

[0087] Optionally, in this embodiment, the storage medium may be configured to store program code for performing the following steps:

[0088] S1, acquire a first signal acquired by the first acquisition device in the first target area of ​​the target human body and a second signal acquired by the second acquisition device in the second target area of ​​the target human body;

[0089] S2, perform principal component analysis on the first signal to obtain the first heartbeat interval of the target human body;

[0090] S3, calculate the correlation coefficient of the second signal based on the correlation coefficient algorithm to obtain the second heartbeat interval of the target human body;

[0091] S4, determine the comprehensive heartbeat interval of the target human body based on the first heartbeat interval and the second heartbeat interval.

[0092] Embodiments of this application also provide an electronic device, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to perform the steps in any of the above method embodiments.

[0093] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0094] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0095] S1, acquire a first signal acquired by the first acquisition device in the first target area of ​​the target human body and a second signal acquired by the second acquisition device in the second target area of ​​the target human body;

[0096] S2, perform principal component analysis on the first signal to obtain the first heartbeat interval of the target human body;

[0097] S3, calculate the correlation coefficient of the second signal based on the correlation coefficient algorithm to obtain the second heartbeat interval of the target human body;

[0098] S4, determine the comprehensive heartbeat interval of the target human body based on the first heartbeat interval and the second heartbeat interval.

[0099] Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0100] Optionally, specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.

[0101] Obviously, those skilled in the art should understand that the modules or steps of this application described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. Optionally, they can be implemented using computer-executable program code, thereby storing them in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those presented here, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, this application is not limited to any particular combination of hardware and software.

[0102] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A vehicle-mounted heart rate detection method, characterized in that, include: Acquire a first signal collected by a first acquisition device in a first target area of ​​a target human body and a second signal collected by a second acquisition device in a second target area of ​​the target human body; Principal component analysis is performed on the first signal to obtain the first heartbeat interval of the target human body; The second heartbeat interval of the target human body is obtained by calculating the correlation coefficient of the second signal based on the correlation coefficient algorithm. The overall heart rate interval of the target human body is determined based on the first heart rate interval and the second heart rate interval.

2. The vehicle-mounted heart rate detection method according to claim 1, characterized in that, The first acquisition device is an image acquisition device, and the second acquisition device is a laser sensor. The first target area includes the forehead area, the nose and cheek area, and other areas of the face excluding the eyes and mouth. The second target area includes the neck area. Acquiring the first signal acquired by the first acquisition device in the first target area of ​​the target human body includes: Acquire a first RGB image of the forehead region of the face, a second RGB image of the nose and cheek region, and a third RGB image of the other regions; Extract the G color signal from the first RGB image, the second RGB image, and the second RGB image; The extracted G-color signal is filtered to obtain the first signal; Acquiring a second signal collected by the second acquisition device in the second target region of the target human body includes: Acquire multiple laser point signals in the neck region; The multiple laser point signals are filtered to obtain the second signal.

3. The vehicle-mounted heart rate detection method according to claim 1, characterized in that, Principal component analysis is performed on the first signal to obtain the first heartbeat interval of the target human body, including: Principal component analysis is performed on the first signal to extract the principal component components, wherein the principal component components are the first signal whose quality meets a preset quality threshold. The first heartbeat signal waveform is plotted based on the principal component components. The first heartbeat interval is obtained based on the peaks and troughs of the first heartbeat signal waveform.

4. The vehicle-mounted heart rate detection method according to claim 1, characterized in that, The correlation coefficient of the second signal is calculated based on the correlation coefficient algorithm to obtain the second heartbeat interval of the target human body, including: A reference signal is determined from a plurality of second signals, and the correlation coefficients between the other second signals and the reference signal are calculated respectively. A second signal that meets the preset requirements is determined based on the correlation coefficient; The second signals that meet the preset requirements are added together to obtain the second heartbeat signal waveform, and the second heartbeat interval is obtained based on the peaks and troughs of the second heartbeat signal waveform.

5. The vehicle-mounted heart rate detection method according to claim 1, characterized in that, Determining the overall heart rate interval of the target human body based on the first heart rate interval and the second heart rate interval includes: The quality of the first heartbeat interval and the second heartbeat interval are evaluated respectively to obtain the first evaluation result and the second evaluation result; The heart rate interval sequence of the comprehensive heart rate interval is obtained by combining the first evaluation result and the second evaluation result.

6. The vehicle-mounted heart rate detection method according to claim 5, characterized in that, The quality of the first heartbeat interval and the second heartbeat interval are assessed separately to obtain a first assessment result and a second assessment result, including: Obtain the first heartbeat interval sequence corresponding to the first heartbeat interval and the second heartbeat interval sequence corresponding to the second heartbeat interval; The first heartbeat interval quality of the first heartbeat interval sequence and the second heartbeat interval quality of the second heartbeat interval sequence are calculated according to a preset heartbeat quality calculation formula. The formula for calculating heart rate quality is as follows: , Indicates the quality of the heartbeat interval. This represents the average value of the skip interval sequence. Let represent the i-th heartbeat interval in the heartbeat interval sequence, n represent the number of heartbeat intervals in the heartbeat interval sequence, and T represent the sampling frequency of the heartbeat interval sequence.

7. The vehicle-mounted heart rate detection method according to claim 6, characterized in that, The heart rate interval sequence, obtained by combining the first evaluation result and the second evaluation result, includes: The weighting coefficients for the first heartbeat interval and the second heartbeat interval are determined based on the quality of the first heartbeat interval and the quality of the second heartbeat interval. The formula for determining the weighting coefficients is as follows: if the quality of the heartbeat interval is greater than or equal to a preset heartbeat quality threshold, then... If the heartbeat interval quality is less than the preset heartbeat quality threshold, then ,in, The weighting coefficient, X = 1 or 2. The first weighting coefficient corresponds to the first heartbeat interval. This is the second weighting coefficient corresponding to the second heartbeat interval; Multiply the first weighting coefficient by the first heartbeat interval sequence to obtain the first target heartbeat interval sequence; Multiply the second weighting coefficient and the second heartbeat interval sequence to obtain the second target heartbeat interval sequence; The first target heartbeat sequence and the second target heartbeat sequence are combined to obtain the comprehensive heartbeat interval heartbeat interval heartbeat interval sequence.

8. A vehicle-mounted heart rate detection device, characterized in that, include: The acquisition module is used to acquire a first signal acquired by the first acquisition device in a first target area of ​​the target human body and a second signal acquired by the second acquisition device in a second target area of ​​the target human body; The first determining module is used to perform principal component analysis on the first signal to obtain the first heartbeat interval of the target human body; The second determining module is used to calculate the correlation coefficient of the second signal based on the correlation coefficient algorithm to obtain the second heartbeat interval of the target human body; The module is used to determine the overall heart rate interval of the target human body based on the first heart rate interval and the second heart rate interval.

9. An electronic device, characterized in that, It includes at least a memory and a processor, wherein the memory stores a computer program, and the processor, when executing the computer program in the memory, implements the steps of the method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable medium stores a computer program that, when executed by a processor, implements the steps of the method according to any one of claims 1-7.

Images