Heart Rate and Respiration Monitoring Method Based on Millimeter-Wave Radar

Abstract

The present invention relates to the technical field of information processing, and in particular to a heart rate and respiration monitoring method based on a millimeter-wave radar. The method includes determining whether the driver is speaking; acquiring a first reflected wave signal; analyzing the first reflected wave signal; determining whether monitoring is abnormal; determining a second heart rate and a second respiration rate; determining whether the driver is abnormal; and correcting a standard distance range. By combining head image recognition and mouth feature analysis, the present invention ensures that heart rate and respiration monitoring is only performed in a target stationary state, significantly improving the efficiency of heart rate and respiration monitoring. By dynamically adjusting the duration of the transmitted wave and the monitoring strategy according to the actual distance between the driver and the transmitter, it effectively adapts to changes in the target position, avoids monitoring errors, and improves the accuracy and effectiveness of monitoring. When a wrong judgment occurs, the standard distance range is automatically corrected according to the feedback, continuously optimizing the monitoring parameters, improving the monitoring accuracy, and providing a more reliable guarantee for driving safety.

Description

Technical Field

[0001] The present invention relates to the technical field of information processing, and particularly to a heart rate and respiration monitoring method based on a millimeter-wave radar. Background Art

[0002] With the rapid development of modern transportation, the number of motor vehicles continues to grow. Road traffic accidents are still one of the important factors seriously endangering human life safety. As one of the main causes of traffic accidents, fatigue driving has become a major concern in the global traffic safety field. Statistical data shows that traffic accidents caused by fatigue driving account for as high as 20%-30%, and the severity of the accidents is often relatively high. Especially for long-distance transportation, truck drivers, and night drivers, due to maintaining a high degree of concentration for a long time, they are more likely to have the risk of fatigue driving.

[0003] In recent years, millimeter-wave radar technology has shown great potential in the field of non-contact physiological monitoring. Compared with traditional sensors, millimeter-wave radar has the advantages of strong penetration, good anti-interference ability, and no radiation, and can accurately capture the minute movements of the human body, providing a new technical path for fatigue driving monitoring.

[0004] The patent document with the publication number CN114366054A discloses a driver heart rate and respiration frequency detection system based on a non-contact lidar, including an in-vehicle lidar monitoring device, an in-vehicle warning device, an in-vehicle monitoring device, and an Internet monitoring system; the lidar can non-contact collect the driver's heart rate and respiration frequency in real time; the heart rate and respiration frequency processing and control device judges whether the received value is within the normal threshold range; if not, a prompt message is sent to the vehicle through the in-vehicle warning device, and at the same time, a warning light flashes; the Internet monitoring system can remotely view the real-time video of the driver, and through the big data analysis of the Internet monitoring system, monitor the driver's historical heart rate data and alarm data, and can statistically analyze the number of heart rate and respiration frequency alarms.

[0005] It can be seen that there are the following problems: In the prior art, the respiration monitoring of the driver may be inefficient and inaccurate due to the driver's own factors. Summary of the Invention

[0006] Therefore, the present invention provides a heart rate and respiration monitoring method based on a millimeter-wave radar to determine whether to monitor according to the driver's situation and determine the monitoring standard to overcome the problems of low monitoring efficiency and accuracy in the prior art.

[0007] To achieve the above object, the present invention provides a heart rate and respiration monitoring method based on a millimeter-wave radar, including:

[0008] Obtain the head image of the driver, obtain the mouth features of the driver based on the head image, and determine whether the driver is speaking based on the mouth features;

[0009] When it is determined that the driver is not speaking, use a millimeter-wave radar to periodically emit an emission wave with a first duration to the driver;

[0010] Receive the first reflected wave signal reflected after the emission wave irradiates the driver;

[0011] Analyze the first reflected wave signal to obtain a first heart rate and a first breathing rate;

[0012] Compare the first heart rate and the first breathing rate with the corresponding standard heart rate range and standard breathing rate range to determine whether the monitoring is abnormal;

[0013] When it is determined that the monitoring is abnormal, obtain the standard distance between the driver and the transmitter to determine the standard distance range, monitor the interval distance between the driver and the transmitter, determine the second duration based on the interval distance, the first duration and the standard distance range, and emit an emission wave with a second duration to the driver, and determine a second heart rate and a second breathing rate according to the second reflected wave signal;

[0014] Compare the second heart rate and the second breathing rate with the corresponding standard heart rate range and standard breathing rate range to determine whether the driver is abnormal, and give an early warning when it is determined that the driver is abnormal;

[0015] Receive the feedback after the early warning. If the feedback is that the early warning is incorrect, correct the standard distance range to obtain the corrected distance range.

[0016] Further, the comparing the first heart rate and the first breathing rate with the corresponding standard heart rate range and standard breathing rate range to determine whether the monitoring is abnormal includes:

[0017] If the first heart rate is within the standard heart rate range and the first breathing rate is within the standard breathing rate range, it is determined that the monitoring is normal;

[0018] If the first heart rate is not within the standard heart rate range or the first breathing rate is not within the standard breathing rate range, it is determined that the monitoring is abnormal when either condition is met.

[0019] Further, the obtaining the standard distance between the driver and the transmitter to determine the standard distance range includes:

[0020] Determine the standard distance between the driver and the transmitter within a preset time when the driver is speaking;

[0021] Determine the standard distance range based on the standard distance.

[0022] Further, the determining the standard distance range based on the standard distance includes:

[0023] Perform statistical analysis on each of the standard distances to obtain the average value and standard deviation of the standard distance;

[0024] Calculate the difference and sum value between the average value and the standard deviation to determine the standard distance range.

[0025] Further, the determining the second duration based on the interval distance, the first duration, and the standard distance range includes:

[0026] Compare the interval distance with the standard distance range. During the time period when the monitoring duration reaches the first duration, when the interval distance is not within the standard distance range, stop transmitting to the driver, and the second duration is the time from the start of the transmitted wave to the stop;

[0027] During the time period when the monitoring duration reaches the first duration, if the interval distance is within the standard distance range, then the second duration is the first duration.

[0028] Further, the modifying the standard distance range to obtain a modified distance range includes:

[0029] Determine the difference values between the standard distances, compare the difference values with a preset standard difference value, and perform corresponding standard distance screening based on the comparison result;

[0030] If there is no abnormal difference value greater than the standard difference value among the difference values, the standard distance screening is to remove the suspicious distance corresponding to the largest difference value among the difference values;

[0031] If there is an abnormal difference value greater than the standard difference value among the difference values, the standard distance screening is to remove each abnormal distance corresponding to the abnormal difference value;

[0032] Obtain the modified average value and modified standard deviation of each screened distance after the standard distance screening;

[0033] Calculate the difference and sum value between the modified average value and the modified standard deviation to determine the modified distance range.

[0034] Further, the determining the second heart rate and the second breathing rate based on the second reflected wave signal includes:

[0035] Perform Fourier transform on the second reflected wave signal to obtain a second frequency domain signal;

[0036] Analyze the second frequency domain signal to determine the second heart rate and the second respiratory rate.

[0037] Further, the comparing the second heart rate, the second respiratory rate with the corresponding standard heart rate range and standard respiratory rate range to determine whether the driver is abnormal includes:

[0038] If the second heart rate is within the standard heart rate range and the second respiratory rate is within the standard respiratory rate range, it is determined that the driver is normal;

[0039] If either the second heart rate is not within the standard heart rate range or the second respiratory rate is not within the standard respiratory rate range, it is determined that the driver is abnormal.

[0040] Further, the determining whether the driver is speaking based on the mouth feature includes:

[0041] Determine the change factor of the mouth feature within a preset time;

[0042] Compare the change factor with a standard change threshold to obtain a comparison result;

[0043] Determine whether the driver is speaking based on the comparison result, where

[0044] If the change factor is less than the standard change threshold, it is determined that the driver is not speaking;

[0045] If the change factor is greater than or equal to the standard change threshold, it is determined that the driver is speaking.

[0046] Further, the analyzing the first reflected wave signal to obtain the first heart rate and the first respiratory rate includes:

[0047] Perform a Fourier transform on the first reflected wave signal to obtain a first frequency domain signal;

[0048] Analyze the first frequency domain signal to determine the first heart rate and the first respiratory rate.

[0049] Compared with the prior art, the beneficial effects of the present invention are as follows: By combining head image recognition and mouth feature analysis, it is ensured that heart rate and respiration monitoring is only carried out in the target stationary state, significantly improving the efficiency of heart rate and respiration monitoring. By dynamically adjusting the duration of the transmitted wave and the monitoring strategy according to the actual distance between the driver and the transmitter, it effectively adapts to changes in the target position, avoids monitoring errors caused by target movement, and improves the accuracy and effectiveness of monitoring. By adopting multiple frequency comparison and continuous monitoring strategies, abnormal states can be further verified and confirmed, significantly reducing the false alarm rate. When a wrong judgment occurs, the standard distance range can be automatically corrected according to the feedback, continuously optimizing the monitoring parameters, improving the monitoring accuracy, and providing a more reliable guarantee for driving safety.

[0050] Furthermore, by precisely setting the standard heart rate frequency range and the standard respiration frequency range and establishing a dual judgment standard, the accuracy and sensitivity of heart rate and respiration abnormality detection can be significantly improved, timely capturing potential physiological risks that the driver may have, and contributing to preventing fatigue driving and ensuring driving safety.

[0051] Furthermore, by collecting multiple distance data during the driver's speech, a more accurate and stable standard distance can be obtained, effectively reducing measurement errors and improving the reliability of distance measurement. Collecting the distance during the driver's speech can determine the accurate distance between the driver and the radar in the awake state, making the standard distance range more representative and providing a more accurate reference benchmark for subsequent heart rate and respiration monitoring.

[0052] Furthermore, through statistical analysis of the standard distance, the standard distance range between the driver and the millimeter-wave radar transmitter can be accurately determined. By statistically analyzing multiple collected standard distance data, calculating their average value and standard deviation, the interference of individual abnormal data is effectively eliminated, calculating the difference and sum value of the average value and the standard deviation, and obtaining an accurate distance range, which can better adapt to different driving environments and driver body characteristics, and improve the accuracy and applicability of heart rate and respiration monitoring.

[0053] Furthermore, by dynamically monitoring the real-time distance between the driver and the transmitter and comparing it with the pre-determined standard distance range in real time, the monitoring duration of the transmitted wave can be effectively adjusted. When the interval distance exceeds the standard distance range, the system immediately stops transmitting. This can not only improve the monitoring accuracy but also significantly reduce the emission of ineffective radar waves, reducing energy consumption. At the same time, when the interval distance remains within the standard range, the original monitoring duration is maintained to ensure the continuity and stability of monitoring, making the monitoring process more accurate, efficient, and energy-saving.

[0054] Furthermore, by analyzing the difference values of the standard distance and filtering out outliers, the noise data and extreme outliers during the monitoring process can be effectively removed, significantly improving the accuracy and reliability of distance measurement. By adopting a dynamic threshold and an adaptive screening mechanism, the distance range can be adjusted in real time according to the actual monitoring environment and data distribution, and the actual distance range between the driver and the device can be determined more accurately.

[0055] Furthermore, by performing a Fourier transform on the second reflected wave signal to obtain the second frequency domain signal and further analyzing the frequency domain signal to determine the second heart rate and the second breathing rate, the time domain signal is converted into the frequency domain signal, and the physiological characteristic signal is accurately extracted through spectrum analysis, providing more reliable technical support for real-time monitoring of the driver's health status and improving the detection accuracy of the heart rate and breathing rate.

[0056] Furthermore, by simultaneously detecting the heart rate and the breathing rate and strictly comparing them with the preset standard frequency range, the timely discovery and warning of the driver's potential abnormal state can be achieved, significantly improving the accuracy and reliability of the driver's physiological state monitoring.

[0057] Furthermore, by accurately capturing and analyzing the dynamic changes of the mouth features, the speaking state of the driver can be efficiently and accurately identified. By calculating the change factor of the mouth features within a preset time and comparing it with the preset standard change threshold, the real-time monitoring of the driver's language behavior can be achieved, providing support for subsequent heart rate and breathing monitoring and improving the monitoring accuracy.

[0058] Furthermore, by performing a Fourier transform on the first reflected wave signal and analyzing the frequency domain signal, the accurate extraction ability of the heart rate and breathing rate can be significantly improved. The Fourier transform can convert the time domain signal into the frequency domain signal, effectively extracting the heart rate and breathing rate, and enabling the continuous and stable monitoring of the driver's physiological state without affecting the driver's normal activities. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] Figure 1 is a flowchart of the heart rate and breathing monitoring method based on a millimeter wave radar according to an embodiment of the present invention;

[0060] Figure 2 is a flowchart of determining the standard distance range according to an embodiment of the present invention;

[0061] Figure 3 is a determination logic diagram of determining the corrected distance range according to an embodiment of the present invention;

[0062] Figure 4 is a flowchart of determining whether the driver is speaking according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0063] To make the objectives and advantages of the present invention more clear and understandable, the present invention will be further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0064] The preferred embodiments of the present invention will be described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present invention and do not limit the protection scope of the present invention.

[0065] It should be noted that in the description of the present invention, the terms indicating directions or positional relationships such as "upper", "lower", "left", "right", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings. This is only for convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention.

[0066] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installation", "connection", and "connection" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two elements. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific situations.

[0067] Please refer to Figure 1 Figure 1

[0068]

[0069] Specifically, the method for monitoring heart rate and respiration based on a millimeter-wave radar provided by the embodiments of the present invention includes:

[0069] Obtain the head image of the driver, obtain the mouth features of the driver based on the head image, and determine whether the driver is speaking based on the mouth features;

[0070] When it is determined that the driver is not speaking, use the millimeter-wave radar to periodically emit an emission wave with a first duration to the driver;

[0071] Receive the first reflected wave signal reflected after the emission wave irradiates the driver;

[0072] Analyze the first reflected wave signal to obtain a first heart rate and a first respiration rate;

[0073] Compare the first heart rate and the first respiration rate with the corresponding standard heart rate range and standard respiration rate range to determine whether the monitoring is abnormal;

[0074] When determining abnormal monitoring, obtain the standard distance between the driver and the transmitter to determine the standard distance range, monitor the interval distance between the driver and the transmitter, determine the second duration based on the interval distance, the first duration, and the standard distance range, and emit an emission wave with a duration of the second duration to the driver, and determine the second heart rate and the second respiratory rate according to the second reflected wave signal;

[0075] Compare the second heart rate and the second respiratory rate with the corresponding standard heart rate range and standard respiratory rate range to determine whether the driver is abnormal, and give an early warning when it is determined that the driver is abnormal;

[0076] Receive the feedback after the early warning. If the feedback is that the early warning is incorrect, correct the standard distance range to obtain the corrected distance range.

[0077] The standard heart rate range is the heart rate range of the driver in a waking state, generally set to 60 - 100 beats per minute. In this embodiment, the standard heart rate range is 70 - 90 beats per minute. The standard respiratory rate range is the respiratory rate range of the driver in a waking state, generally set to 12 - 20 breaths per minute. In this embodiment, the standard respiratory rate range is 14 - 18 breaths per minute. The feedback is the voice feedback, action feedback, etc. received from the driver after giving an early warning to the driver, as long as it can represent whether the driver approves of the early warning. The mouth feature is the distance between the upper and lower lips of the driver.

[0078] Specifically, it is determined whether the driver is speaking based on the mouth features recognized in the obtained head image. When it is determined that the driver is speaking, it is determined not to perform heart rate and respiration monitoring on the driver. When it is determined that the driver is not speaking, a transmission wave with a first duration is periodically transmitted to perform heart rate and respiration monitoring on the driver. The respiration rate and heart rate obtained from the monitoring are used to timely determine whether the driver is fatigued. During the periodic monitoring process, if monitoring anomalies are detected, the driver is immediately re-monitored to verify whether the driver is driving while fatigued, or whether the monitoring is affected by the driver's own movement resulting in monitoring anomalies. A standard distance range between the driver and the transmitter is determined based on the respective standard distances between the driver and the transmitter when the driver is awake and speaking. During the immediate monitoring and verification of the driver, the interval distance between the driver and the transmission wave is monitored. If, within the period when the transmission wave continues to be transmitted for the first duration, it is detected that the interval distance between the driver and the transmission wave exceeds the standard distance range, the irradiation is immediately stopped. If, within the period when the transmission wave continues to be transmitted for the first duration, the interval distance does not exceed the standard distance range, the irradiation is stopped when the second duration is reached. Based on the second reflected wave signal emitted from the driver's body within the second duration from the start of irradiation to the stop of irradiation, it is determined whether the driver is abnormal. When the driver is determined to be abnormal, a warning is given to the driver, and after the warning, the feedback given by the driver is received. If the feedback indicates a warning error, it means that the determination of the standard distance range between the driver and the transmitter is incorrect, and the driver's own movement still affects the heart rate and respiration monitoring, resulting in incorrect monitoring. Therefore, the standard distance range is corrected to obtain a corrected distance range, and then the heart rate and respiration are monitored and abnormal conditions are determined.

[0079] Specifically, by combining head image recognition and mouth feature analysis, it is ensured that heart rate and respiration monitoring are only performed in the target stationary state, significantly improving the efficiency of heart rate and respiration monitoring. By dynamically adjusting the duration of the transmission wave and the monitoring strategy according to the actual interval distance between the driver and the transmitter, it effectively adapts to changes in the target position, avoids monitoring errors caused by target movement, and improves the accuracy and effectiveness of monitoring. By adopting a multi-frequency comparison and continuous monitoring strategy, abnormal states can be further verified and confirmed, significantly reducing the false alarm rate. When a wrong judgment occurs, the standard distance range can be automatically corrected according to the feedback, continuously optimizing the monitoring parameters, improving the monitoring accuracy, and providing a more reliable guarantee for driving safety.

[0080] Specifically, the comparison of the first heart rate and the first respiration rate with the corresponding standard heart rate range and standard respiration rate range to determine whether there is a monitoring anomaly includes:

[0081] If the first heart rate is within the standard heart rate range and the first respiratory rate is within the standard respiratory rate range, it is determined that the monitoring is normal;

[0082] If either the first heart rate is not within the standard heart rate range or the first respiratory rate is not within the standard respiratory rate range, it is determined that the monitoring is abnormal.

[0083] In a specific implementation process, the standard heart rate range is 70 - 90 beats per minute, the standard respiratory rate range is 14 - 18 breaths per minute. The monitored first heart rate is 100 beats per minute, and the monitored first respiratory rate is 22 breaths per minute. Then, the first heart rate is not within the standard heart rate range, and the first respiratory rate is not within the standard respiratory rate range, so it is determined that the monitoring is abnormal.

[0084] Specifically, by precisely setting the standard heart rate range and the standard respiratory rate range and establishing a dual judgment standard, the accuracy and sensitivity of heart rate and respiratory abnormality detection can be significantly improved, potential physiological risks that the driver may have can be captured in a timely manner, which helps prevent fatigue driving and ensure driving safety.

[0085] Please continue to refer to Figure 2 , as Figure 2 shown, which is a flowchart for determining the standard distance range in an embodiment of the present invention;

[0086] Specifically, the obtaining of the standard distance between the driver and the transmitter to determine the standard distance range includes:

[0087] Determining the standard distance between the driver and the transmitter within a preset time when the driver is speaking;

[0088] Determining the standard distance range based on the standard distance.

[0089] Specifically, determining the standard distance between the driver and the transmitter due to respiratory changes within a certain preset time when the driver is awake and speaking, and determining the standard distance range between the driver and the transmitter according to the obtained standard distances.

[0090] Specifically, by collecting multiple distance data during the driver's speech, more accurate and stable standard distances can be obtained, effectively reducing measurement errors and improving the reliability of distance measurement. Collecting distances when the driver is speaking can determine the accurate distance between the driver and the radar in a waking state, making the standard distance range more representative and providing a more accurate reference benchmark for subsequent heart rate and respiratory monitoring.

[0091] Specifically, the determining of the standard distance range based on the standard distance includes:

[0092] Perform statistical analysis on each of the said standard distances to obtain the mean value and standard deviation of the standard distances;

[0093] Calculate the difference and sum of the mean value and the standard deviation to determine the standard distance range.

[0094] In the specific implementation process, the standard distances obtained within a preset time period of 5 seconds are 0.50m, 0.51m, 0.505m, 0.501m, 0.507m, and 0.49m respectively. The calculated mean value of the standard distances is 0.5019m, and the standard deviation is 0.0087m. Then the difference between the mean value and the standard deviation is 0.4932m, and the sum of the mean value and the standard deviation is 0.5106m. Therefore, the standard distance range is 0.4932m - 0.5106m.

[0095] Specifically, by performing statistical analysis on the standard distances, the standard distance range between the driver and the millimeter-wave radar transmitter can be accurately determined. By performing statistical analysis on multiple collected standard distance data, calculating their mean value and standard deviation, the interference of individual abnormal data is effectively eliminated. Calculating the difference and sum of the mean value and the standard deviation to obtain an accurate distance range can better adapt to different driving environments and driver body characteristics, and improve the accuracy and applicability of heart rate and respiration monitoring.

[0096] Specifically, determining the second duration based on the interval distance, the first duration, and the standard distance range includes:

[0097] Compare the interval distance with the standard distance range. During the time period when the monitoring duration reaches the first duration, when the interval distance is not within the standard distance range, stop transmitting to the driver, and the second duration is the time from the emission of the emission wave to the stop;

[0098] During the time period when the monitoring duration reaches the first duration, if the interval distance is within the standard distance range, then the second duration is the first duration.

[0099] Specifically, during the process when the irradiation time of the emission wave reaches the first duration, if it is detected that the interval distance between the driver and the transmitter exceeds the standard distance range at a certain moment, stop the transmitter from emitting the emission wave to the driver. If the interval distance is within the standard distance range during the process when the emission time reaches the first duration, then stop the transmitter from emitting the emission wave to the driver when the first duration is reached.

[0100] Specifically, by dynamically monitoring the real-time interval distance between the driver and the transmitter and comparing it with a pre-determined standard distance range in real time, the monitoring duration of the transmitted wave can be effectively adjusted. When the interval distance exceeds the standard distance range, the system immediately stops transmitting. This can not only improve the accuracy of monitoring, but also significantly reduce the emission of ineffective radar waves, reduce energy consumption. At the same time, when the interval distance remains within the standard range, the original monitoring duration is maintained to ensure the continuity and stability of monitoring, making the monitoring process more accurate, efficient and energy-saving.

[0101] Please continue to refer to Figure 3 , such as Figure 3 shown, which is the decision logic diagram for determining the corrected distance range in the embodiment of the present invention;

[0102] Specifically, the method of correcting the standard distance range to obtain the corrected distance range includes:

[0103] Determine the difference values between the standard distances, compare the difference values with a preset standard difference value, and perform corresponding standard distance screening based on the comparison results;

[0104] If there is no abnormal difference value greater than the standard difference value among the difference values, the standard distance screening is to remove the suspicious distance corresponding to the largest difference value among the difference values;

[0105] If there is an abnormal difference value greater than the standard difference value among the difference values, the standard distance screening is to remove each abnormal distance corresponding to the abnormal difference value;

[0106] Obtain the corrected average value and corrected standard deviation of each screened distance after standard distance screening;

[0107] Calculate the difference value and sum value of the corrected average value and corrected standard deviation to determine the corrected distance range.

[0108] Specifically, the standard difference value is the difference between the standard distances caused by normal breathing between the driver and the transmitter, generally set between 0.006m - 0.01m. In this embodiment, the standard difference value is 0.08m. The two standard distances for calculating the abnormal difference degree are the abnormal distances corresponding to the abnormal difference value, and the two standard distances for calculating the largest difference value are used as the suspicious distances corresponding to the largest difference value.

[0109] In the specific implementation process, the preset standard difference value is 0.008m. The standard distances obtained within a preset time period of 5 seconds are 0.50m, 0.51m, 0.505m, 0.501m, 0.507m, and 0.49m respectively. The difference values between the standard distances are calculated as 0.01m, 0.005m, 0.004m, 0.006m, and 0.017m. Among them, both 0.01m and 0.017m are greater than the standard difference value of 0.008m. Therefore, 0.01m and 0.017m are both abnormal difference values. The suspicious distances corresponding to the abnormal difference values of 0.01m and 0.017m, namely 0.50m, 0.51m, 0.507m, and 0.49m, are removed. The corrected average value of the filtered distances of 0.505m and 0.501m after removing the suspicious distances is 0.503m, and the corrected standard deviation is 0.002m. Then, the difference between the corrected average value and the corrected standard deviation is 0.501m, the sum value is 0.505m, and the corrected distance range is 0.501m - 0.505m.

[0110] Specifically, by performing difference value analysis and outlier screening on the standard distances, noise data and extreme outliers in the monitoring process can be effectively removed, significantly improving the accuracy and reliability of distance measurement. By adopting a dynamic threshold and an adaptive screening mechanism, the distance range can be adjusted in real time according to the actual monitoring environment and data distribution, and the actual distance range between the driver and the device can be determined more accurately.

[0111] Specifically, the determining the second heart rate and the second respiratory rate according to the second reflected wave signal includes:

[0112] Performing a Fourier transform on the second reflected wave signal to obtain a second frequency domain signal;

[0113] Analyzing the second frequency domain signal to determine the second heart rate and the second respiratory rate.

[0114] Specifically, converting the second reflected wave signal into a frequency domain signal, determining the heart rate characteristic peak and the respiratory rate characteristic peak in the frequency domain signal, and determining the frequencies corresponding to the peaks, which are the second heart rate and the second respiratory rate.

[0115] Specifically, obtaining a second frequency domain signal by performing a Fourier transform on the second reflected wave signal, and further analyzing the frequency domain signal to determine the second heart rate and the second respiratory rate. Converting the time domain signal into a frequency domain signal, and accurately extracting the physiological characteristic signal through spectrum analysis, which provides more reliable technical support for real-time monitoring of the driver's health status and improves the detection accuracy of the heart rate and the respiratory rate.

[0116] Specifically, the comparison of the second heart rate and the second respiratory rate with the corresponding standard heart rate range and standard respiratory rate range to determine whether the driver is abnormal includes:

[0117] If the second heart rate is within the standard heart rate range and the second respiratory rate is within the standard respiratory rate range, it is determined that the driver is normal;

[0118] If either the second heart rate is not within the standard heart rate range or the second respiratory rate is not within the standard respiratory rate range, it is determined that the driver is abnormal.

[0119] In a specific implementation process, the standard heart rate range is 70 - 90 beats per minute, and the standard respiratory rate range is 14 - 18 breaths per minute. If the obtained second heart rate is 95 beats per minute and the second respiratory rate is 20 breaths per minute, then the second heart rate is not within the standard heart rate range and the second respiratory rate is not within the standard respiratory rate range, and it is determined that the driver is abnormal.

[0120] Specifically, by simultaneously detecting the heart rate and the respiratory rate and strictly comparing them with the preset standard frequency range, it is possible to achieve the timely discovery and warning of the driver's potential abnormal state, significantly improving the accuracy and reliability of the driver's physiological state monitoring.

[0121] Please continue to refer to Figure 4 , as Figure 4 shown, which is the flowchart for determining whether the driver is speaking in an embodiment of the present invention;

[0122] Specifically, the determination of whether the driver is speaking based on the mouth feature includes:

[0123] Determine the change factor of the mouth feature within a preset time;

[0124] Compare the change factor with the standard change threshold to obtain a comparison result;

[0125] Determine whether the driver is speaking based on the comparison result, where

[0126] If the change factor is less than the standard change threshold, it is determined that the driver is not speaking;

[0127] If the change factor is greater than or equal to the standard change threshold, it is determined that the driver is speaking.

[0128] Specifically, the change factor is the number of changes of the mouth feature within a preset time, and the standard change threshold is the minimum number of changes of the mouth feature within the preset time for determining that the driver is speaking.

[0129] In the specific implementation process, the standard change threshold is 3 times, and the mouth features within a preset time of 5 seconds are 10mm, 3mm, 8mm, 2mm, 9mm, 2mm. Then the change factor is 5 times. Since the change factor is greater than the standard change threshold, it is determined that the driver is speaking.

[0130] Specifically, by accurately capturing and analyzing the dynamic changes of the mouth features, the speaking state of the driver can be efficiently and accurately identified. By calculating the change factor of the mouth features within the preset time and comparing it with the preset standard change threshold, real-time monitoring of the driver's language behavior can be achieved, providing support for subsequent heart rate and respiration monitoring and improving the accuracy of monitoring.

[0131] Specifically, the analysis of the first reflected wave signal to obtain the first heart rate and the first respiration rate includes:

[0132] Performing a Fourier transform on the first reflected wave signal to obtain a first frequency domain signal;

[0133] Analyzing the first frequency domain signal to determine the first heart rate and the first respiration rate.

[0134] Specifically, converting the first reflected wave signal into a frequency domain signal, determining the characteristic peaks of the heart rate and the respiration rate in the frequency domain signal, and determining the frequencies corresponding to each peak, which are the first heart rate and the first respiration rate.

[0135] Specifically, by performing a Fourier transform on the first reflected wave signal and analyzing the frequency domain signal, the ability to accurately extract the heart rate and respiration rate can be significantly improved. The Fourier transform can convert the time domain signal into a frequency domain signal, effectively extracting the heart rate and respiration rate, and can continuously and stably monitor the physiological state of the driver without affecting the normal activities of the driver.

[0136] So far, the technical solution of the present invention has been described in combination with the preferred embodiments shown in the drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0137] The above are only the preferred embodiments of the present invention and are not used to limit the present invention; for those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A heart rate and respiration monitoring method based on millimeter-wave radar, characterized in that, Including: Obtain the head image of the driver, obtain the mouth feature of the driver based on the head image, and determine whether the driver is speaking based on the mouth feature; When it is determined that the driver is not speaking, use a millimeter-wave radar to periodically transmit a transmission wave with a first duration to the driver; Receive a first reflected wave signal reflected after the transmission wave irradiates the driver; Analyze the first reflected wave signal to obtain a first heart rate and a first breathing rate; Compare the first heart rate and the first breathing rate with the corresponding standard heart rate range and standard breathing rate range to determine whether the monitoring is abnormal; When it is determined that the monitoring is abnormal, obtain the standard distance between the driver and the transmitter to determine the standard distance range, monitor the interval distance between the driver and the transmitter, determine a second duration based on the interval distance, the first duration, and the standard distance range, and transmit a transmission wave with a second duration to the driver, and determine a second heart rate and a second breathing rate according to the second reflected wave signal; Compare the second heart rate and the second breathing rate with the corresponding standard heart rate range and standard breathing rate range to determine whether the driver is abnormal, and give an alarm when it is determined that the driver is abnormal; Receive the feedback after the alarm. If the feedback is an alarm error, correct the standard distance range to obtain a corrected distance range; The determining the second duration based on the interval distance, the first duration, and the standard distance range includes: Compare the interval distance with the standard distance range. When the monitoring duration reaches the first duration, stop transmitting to the driver when the interval distance is not within the standard distance range, and the second duration is the time from the transmission of the transmission wave to the stop; When the monitoring duration reaches the first duration, if the interval distance is within the standard distance range, the second duration is the first duration; The correcting the standard distance range to obtain a corrected distance range includes: Determine the difference value between the standard distances, compare the difference value with a preset standard difference value, and perform corresponding standard distance screening based on the comparison result; If there is no abnormal difference value greater than the standard difference value among the difference values, the standard distance screening is to remove the suspicious distance corresponding to the largest difference value among the difference values; If there is an abnormal difference value greater than the standard difference value among the difference values, the standard distance screening is to remove each abnormal distance corresponding to the abnormal difference value; Obtain the corrected average value and corrected standard deviation of each screened distance after the standard distance screening; Calculate the difference value and sum value of the corrected average value and the corrected standard deviation to determine the corrected distance range.

2. The heart rate and respiration monitoring method based on millimeter wave radar according to claim 1, characterized in that, The comparing the first heart rate and the first breathing rate with the corresponding standard heart rate range and standard breathing rate range to determine whether the monitoring is abnormal includes: If the first heart rate is within the standard heart rate range and the first breathing rate is within the standard breathing rate range, it is determined that the monitoring is normal; If the first heart rate is not within the standard heart rate range and the first breathing rate is not within the standard breathing rate range, it is determined that the monitoring is abnormal when either one is satisfied.

3. The heart rate and respiration monitoring method based on millimeter-wave radar according to claim 2, wherein, The obtaining of the standard distance between the driver and the transmitter to determine the standard distance range includes: Determining the standard distance between the driver and the transmitter within a preset time when the driver is speaking; Determining the standard distance range based on the standard distance.

4. The heart rate and respiration monitoring method based on millimeter wave radar according to claim 3, wherein The determining of the standard distance range based on the standard distance includes: Performing statistical analysis on each of the standard distances to obtain the average value and standard deviation of the standard distance; Calculating the difference and sum of the average value and the standard deviation to determine the standard distance range.

5. The heart rate and respiration monitoring method based on millimeter-wave radar according to claim 1, characterized in that The determining of the second heart rate and the second breathing rate according to the second reflected wave signal includes: Performing Fourier transform on the second reflected wave signal to obtain a second frequency domain signal; Analyzing the second frequency domain signal to determine the second heart rate and the second breathing rate.

6. The heart rate and respiration monitoring method based on millimeter-wave radar according to claim 5, characterized in that The comparing of the second heart rate, the second breathing rate with the corresponding standard heart rate range and standard breathing rate range to determine whether the driver is abnormal includes: If the second heart rate is within the standard heart rate range and the second breathing rate is within the standard breathing rate range, it is determined that the driver is normal; If either the second heart rate is not within the standard heart rate range or the second breathing rate is not within the standard breathing rate range, it is determined that the driver is abnormal.

7. The heart rate and respiration monitoring method based on millimeter wave radar according to claim 6, characterized in that, The determining of whether the driver is speaking based on the mouth feature includes: Determining the change factor of the mouth feature within a preset time; Comparing the change factor with a standard change threshold to obtain a comparison result; Determining whether the driver is speaking based on the comparison result, where If the change factor is less than the standard change threshold, it is determined that the driver is not speaking; If the change factor is greater than or equal to the standard change threshold, it is determined that the driver is speaking.

8. The heart rate and respiration monitoring method based on millimeter-wave radar according to claim 7, wherein The analyzing of the first reflected wave signal to obtain the first heart rate and the first breathing rate includes: Performing Fourier transform on the first reflected wave signal to obtain a first frequency domain signal; Analyzing the first frequency domain signal to determine the first heart rate and the first breathing rate.

Images