CN115530787A

CN115530787A - Vehicle signal processing method and device and vehicle

Info

Publication number: CN115530787A
Application number: CN202211255454.4A
Authority: CN
Inventors: 毕圆浩; 丁逢; 张栋; 姜长坤; 陈鹤文; 张昀琪
Original assignee: FAW Group Corp
Current assignee: FAW Group Corp
Priority date: 2022-10-13
Filing date: 2022-10-13
Publication date: 2022-12-30
Anticipated expiration: 2042-10-13
Also published as: CN115530787B

Abstract

The invention discloses a signal processing method and device for a vehicle and the vehicle. Wherein, the method comprises the following steps: acquiring an original physiological signal of a physiological object in a vehicle; carrying out noise reduction processing on the original physiological signal to obtain a target physiological signal; determining heartbeat interval time of the physiological object based on the target physiological signal and a reference physiological signal, wherein the reference physiological signal is a physiological signal of a plurality of physiological object samples collected in an original time period, and the heartbeat interval time is used for representing the time of two adjacent heartbeat intervals of the physiological object. The invention solves the technical problem of low accuracy of acquiring the physiological signals of the physiological objects in the vehicle.

Description

Vehicle signal processing method and device and vehicle

Technical Field

The invention relates to the field of vehicles, in particular to a signal processing method and device of a vehicle and the vehicle.

Background

As vehicles become daily transportation tools, people use vehicles more and more frequently and more time. The frequency of traffic accidents caused by fatigue driving or sudden illness of drivers is higher and higher, and real-time monitoring of physiological parameters (such as heart rate and respiratory rate) of drivers is necessary.

In the related art, the physiological signal of the physiological object is mainly acquired by wearing the physiological signal acquisition device, but in the acquisition process, the acquired physiological signal is easy to be unstable due to the influence of the acquisition environment and the contact area of the physiological signal acquisition device, so that the technical problem of low accuracy in acquiring the physiological signal of the physiological object in the vehicle occurs.

In view of the technical problems in the related art, no effective solution has been proposed at present.

Disclosure of Invention

The embodiment of the invention provides a vehicle signal processing method and device and a vehicle, and at least solves the technical problem of low accuracy of acquisition of physiological signals of physiological objects in the vehicle.

According to an aspect of an embodiment of the present invention, there is provided a signal processing method of a vehicle. The method can comprise the following steps: acquiring an original physiological signal of a physiological object in a vehicle; carrying out noise reduction processing on the original physiological signal to obtain a target physiological signal; determining heartbeat interval time of the physiological object based on the target physiological signal and a reference physiological signal, wherein the reference physiological signal is a physiological signal of a plurality of physiological object samples collected in an original time period, and the heartbeat interval time is used for representing the time of two adjacent heartbeat intervals of the physiological object.

Optionally, determining a heartbeat interval time of the physiological subject based on the target physiological signal and the reference physiological signal comprises: generating a rising edge template based on a rising edge signal of the reference physiological signal and generating a falling edge template based on a falling edge signal of the reference physiological signal; determining a rising edge physiological signal based on the target physiological signal and a rising edge template, and determining a falling edge physiological signal based on the target physiological signal and the falling edge template, wherein the rising edge physiological signal is a signal obtained after signal enhancement is carried out on the rising edge signal of the target physiological signal, and the falling edge physiological signal is a signal obtained after signal enhancement is carried out on the falling edge signal of the target physiological signal; based on the rising edge physiological signal and the falling edge physiological signal, a heartbeat interval time of the physiological object is determined.

Optionally, determining a rising edge physiological signal based on the target physiological signal and the rising edge template comprises: performing autocorrelation calculation on a rising edge signal of the target physiological signal and a rising edge template to obtain a first calculation result, and performing convolution calculation on the rising edge signal of the target physiological signal and the rising edge template to obtain a second calculation result; and normalizing the sum of the first calculation result and the second calculation result to obtain the physiological signal of the rising edge.

Optionally, determining a falling edge physiological signal based on the target physiological signal and the falling edge template, comprising: performing autocorrelation calculation on the target physiological signal and the falling edge template to obtain a third calculation result, and performing convolution calculation on the falling edge signal of the target physiological signal and the falling edge template to obtain a fourth calculation result; and normalizing the sum of the third calculation result and the fourth calculation result to obtain the falling edge physiological signal.

Optionally, determining a heartbeat interval time of the physiological object based on the rising edge physiological signal and the falling edge physiological signal comprises: determining a set of rising edge heartbeat intervals of the physiological subject based on the rising edge physiological signal and a set of falling edge heartbeat intervals of the physiological subject based on the falling edge physiological signal; merging the rising edge heartbeat interval set and the falling edge heartbeat interval set to obtain a target heartbeat interval set of the physiological object; an average of a plurality of elements in the target set of heartbeat intervals is determined as the heartbeat interval time.

Optionally, determining a set of rising edge heartbeat intervals of the physiological object based on the rising edge physiological signal comprises: extracting a time value corresponding to each wave peak value in a plurality of wave peak values which are larger than a first threshold value on a oscillogram of the rising edge physiological signal to obtain a plurality of first time values; calculating the difference value of every two adjacent first time values in the plurality of first time values to obtain a plurality of first time difference values; a set of the plurality of first time difference values is determined as a set of rising edge heartbeat intervals.

Optionally, determining a set of falling edge heartbeat intervals of the physiological subject based on the falling edge physiological signal comprises: extracting a time value corresponding to each of a plurality of wave valley values of which the oscillogram of the falling edge physiological signal is smaller than a second threshold value to obtain a plurality of second time values; calculating the difference value of every two adjacent second time values in the plurality of second time values to obtain a plurality of second time difference values; a set of the plurality of second time difference values is determined as a set of falling edge heartbeat intervals.

Optionally, the performing noise reduction processing on the original physiological signal to obtain a target physiological signal includes: determining a maximum wave peak value in a plurality of wave peak values on a waveform diagram of the original physiological signal, and determining a third time value corresponding to the maximum wave peak value; and extracting a signal corresponding to the time range of the third time value from the target threshold value on the oscillogram, and performing correlation operation on the extracted signal and the original physiological signal to obtain a target physiological signal.

According to another aspect of the embodiments of the present invention, there is also provided a signal processing apparatus of a vehicle, which may include: an acquisition unit for acquiring an original physiological signal of a physiological object in a vehicle; the noise reduction processing unit is used for carrying out noise reduction processing on the original physiological signal to obtain a target physiological signal; the determining unit is used for determining the heartbeat interval time of the physiological object based on the target physiological signal and the reference physiological signal, wherein the reference physiological signal is the physiological signal of a plurality of physiological object samples collected in the historical time period, and the heartbeat interval time is used for representing the time of two adjacent heartbeat intervals of the physiological object.

According to another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium. The computer-readable storage medium includes a stored program, wherein the apparatus in which the computer-readable storage medium is located is controlled to execute the signal processing method of the vehicle of the embodiment of the present invention when the program runs.

According to another aspect of the embodiments of the present invention, there is also provided a processor. The processor is used for running a program, wherein the program is run to execute the signal processing method of the vehicle of the embodiment of the invention.

According to another aspect of the embodiment of the invention, a vehicle is also provided. The vehicle is used for executing the signal processing method of the vehicle of the embodiment of the invention.

In an embodiment of the invention, an original physiological signal of a physiological object in a vehicle is acquired; carrying out noise reduction processing on the original physiological signal to obtain a target physiological signal; based on the target physiological signal and the reference physiological signal, a heartbeat interval time of the physiological subject is determined. That is to say, in the embodiment of the present invention, the original physiological signals of the physiological objects in the vehicle are collected, then the collected original physiological signals are subjected to noise reduction processing to obtain the target physiological signals, and finally the target physiological signals are processed according to the physiological signal samples of the plurality of physiological objects collected in the historical time period, so as to achieve the purposes of performing signal enhancement on the target physiological signals and determining the heartbeat intervals of the physiological objects, thereby solving the technical problem of low collection accuracy of the physiological signals of the physiological objects in the vehicle, and achieving the technical effect of improving the collection accuracy of the physiological signals of the physiological objects in the vehicle.

Drawings

The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:

FIG. 1 is a flow chart of a method of signal processing for a vehicle according to an embodiment of the present invention;

FIG. 2 is a schematic diagram of a multi-sensor combined heart rate detection system according to an embodiment of the present invention;

fig. 3 is a flowchart of a heartbeat signal processing method of an onboard seat belt according to an embodiment of the present invention;

fig. 4 is a schematic diagram of a signal processing apparatus of a vehicle according to an embodiment of the present invention.

Detailed Description

In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

Example 1

In accordance with an embodiment of the present invention, there is provided an embodiment of a signal processing method for a vehicle, it is noted that the steps illustrated in the flowchart of the drawings may be performed in a computer system such as a set of computer executable instructions and that, although a logical order is illustrated in the flowchart, in some cases, the steps illustrated or described may be performed in an order different than that herein.

Fig. 1 is a flowchart of a signal processing method of a vehicle according to an embodiment of the present invention, which may include the steps of, as shown in fig. 1:

step S102, acquiring an original physiological signal of a physiological object in a vehicle.

In the technical solution provided by step S102 of the present invention, an original physiological signal of a physiological object in a vehicle may be obtained, where the physiological object may include all people in the vehicle, such as a driver and a passenger, and the original physiological signal may be a signal obtained by preprocessing an acquired physiological signal, such as acquiring and preprocessing a heartbeat signal, so as to obtain an original heartbeat signal.

Optionally, the acquired physiological signals may be acquired by a sensor deployed on the vehicle, where the sensor may be a three-axis acceleration sensor, the physiological signals in three directions may be acquired by three single axes, and the deployment position of the sensor may be a safety belt of the vehicle, which is merely for illustration and is not limited specifically.

Optionally, the preprocessing the acquired physiological signal to obtain an original physiological signal includes: the physiological signals of a physiological object in a target time period can be collected through a sensor, the variance of the collected physiological signals is calculated, then the calculated variance is compared with a variance threshold, if the variance exceeds the variance threshold, the collected physiological signals can be indicated as noise generated by body movement, if the variance does not exceed the threshold, the physiological signals can be further filtered, and the filtered physiological signals are subjected to principal component analysis to extract the physiological signals which can represent heartbeat most, namely the original physiological signals, wherein the variance threshold can be a value calibrated in advance or determined through experiments, and specific values of the variance threshold and a determination method are not limited specifically.

Optionally, since the normal heart rate of the human body is considered to be 60 to 100 times/min, the physiological signals can be filtered by using 0.5 to 2HZ band-pass filtering, so as to achieve the technical effect of removing the limit drift of the physiological signals in each direction acquired by the sensor.

Optionally, the preprocessed original physiological signal is converted into a frequency domain, and displayed through a frequency spectrum, a frequency corresponding to a maximum peak value on the frequency domain spectrum is a heart rate, and 60/heart rate is a representative value of a heartbeat interval of the time signal, wherein the frequency domain can be used for describing a coordinate system of the physiological signal in terms of frequency, an abscissa is frequency, and an ordinate is amplitude.

And step S104, performing noise reduction processing on the original physiological signal to obtain a target physiological signal.

In the technical solution provided by step S104 of the present invention, a heartbeat position in the original physiological signal can be determined through a maximum peak value on a frequency spectrum of the original physiological signal, a frequency corresponding to the heartbeat position is determined, a representative value of a heartbeat interval of the original physiological signal is obtained by calculation based on 60/frequency, and the original physiological signal is subjected to noise reduction processing through the calculated representative value of the heartbeat interval to obtain the target physiological signal.

Optionally, performing noise reduction processing on the original physiological signal through the calculated representative value of the heartbeat interval, and reaching the target physiological signal may include: and intercepting the physiological signals before and after the heartbeat position by taking half of the representative value of the heartbeat interval as the length, and performing related operation on the intercepted physiological signals and the original physiological signals to obtain target physiological signals, thereby achieving the technical effects of reducing noise and reducing abnormal heartbeat intervals.

Step S106, determining the heartbeat interval time of the physiological object based on the target physiological signal and the reference physiological signal.

In the technical solution provided in step S106 of the present invention, a rising edge template and a falling edge template may be generated based on the target physiological signal, the rising edge and the falling edge of the target physiological signal are respectively processed through the rising edge template and the falling edge template to obtain a rising edge heartbeat interval sequence and a falling edge heartbeat interval sequence, and the rising edge heartbeat interval sequence and the falling edge heartbeat interval sequence are summed and averaged to obtain a more accurate heartbeat interval time of the physiological object, where the reference physiological signal may be physiological signals of a plurality of physiological object samples collected in a historical time period, for example, physiological signals of a plurality of users detected in advance, and the heartbeat interval time may be used to represent a time between two adjacent heartbeats of the physiological object.

Optionally, processing the rising edge signal of the target physiological signal through the rising edge template to obtain a rising edge heartbeat interval sequence includes: the method comprises the steps of carrying out autocorrelation calculation and convolution calculation on a rising edge template and a target physiological signal, then adding the physiological signals after the autocorrelation calculation and the convolution calculation and then normalizing, finally determining a plurality of wave peak values of the normalized physiological signal, determining the positions of the wave peak values exceeding a threshold value as heartbeat positions, determining the difference value of two adjacent heartbeat positions as a heartbeat interval, and calculating the difference value of all two adjacent heartbeat positions to obtain a plurality of heartbeat intervals, namely a rising edge heartbeat interval sequence.

Optionally, the processing the falling edge signal of the target physiological signal by the falling edge template to obtain the falling edge heartbeat interval sequence includes: the method comprises the steps of carrying out autocorrelation calculation and convolution calculation on a falling edge template and a target physiological signal, then adding the physiological signals after the autocorrelation calculation and the convolution calculation and then normalizing, finally determining a plurality of wave trough values of the normalized physiological signal, determining the position of the wave trough value lower than a threshold value as a heartbeat position, determining the difference value of two adjacent heartbeat positions as a heartbeat interval, and calculating the difference value of all two adjacent heartbeat positions to obtain a plurality of heartbeat intervals, namely a falling edge heartbeat interval sequence.

Optionally, the rising edge template and the falling edge template are respectively subjected to autocorrelation calculation and convolution calculation with the target physiological signal, and then the physiological signals after the autocorrelation calculation and the convolution calculation are added and then subjected to normalization processing, so that the technical effect of performing signal enhancement on the target physiological signal can be achieved.

The above-described method of this embodiment is further described below.

As an alternative embodiment, the step S106 of determining the heartbeat interval time of the physiological object based on the target physiological signal and the reference physiological signal includes: generating a rising edge template based on a rising edge signal of the reference physiological signal and generating a falling edge template based on a falling edge signal of the reference physiological signal; determining a rising edge physiological signal based on the target physiological signal and the rising edge template, and determining a falling edge physiological signal based on the target physiological signal and the falling edge template; based on the rising edge physiological signal and the falling edge physiological signal, a heartbeat interval time of the physiological object is determined.

In this embodiment, a rising edge and a falling edge may be cut from a waveform diagram of a reference physiological signal, the physiological signal corresponding to the rising edge is a rising edge signal, the physiological signal corresponding to the falling edge is a falling edge signal, a rising edge template may be generated based on the rising edge signal, a falling edge template may be generated based on the falling edge signal, then the rising edge physiological signal may be determined based on the target physiological signal and the rising edge template, the falling edge physiological signal may be determined based on the target physiological signal and the falling edge template, and the heartbeat interval time of the physiological object may be determined based on the rising edge physiological signal and the falling edge physiological signal, wherein the rising edge may be used to characterize a portion of the rising trend of the waveform in the waveform diagram, the falling edge physiological signal may be a signal after signal enhancement is performed on the rising edge portion of the target physiological signal, and the falling edge physiological signal may be a signal after signal enhancement is performed on the falling edge portion of the target physiological signal.

As an alternative embodiment, the step S106 of determining the rising edge physiological signal based on the target physiological signal and the rising edge template includes: performing autocorrelation calculation on a rising edge signal of the target physiological signal and a rising edge template to obtain a first calculation result, and performing convolution calculation on the rising edge signal of the target physiological signal and the rising edge template to obtain a second calculation result; and normalizing the sum of the first calculation result and the second calculation result to obtain the physiological signal of the rising edge.

In this embodiment, according to the oscillogram of the target physiological signal, the specific position of the rising edge of the target physiological signal can be determined, the rising edge is intercepted, then the autocorrelation calculation and the convolution calculation can be performed on the rising edge of the target physiological signal and the rising edge template of the reference physiological signal to obtain two calculation results, and the sum of the two calculation results is normalized to obtain the rising edge physiological signal.

Optionally, according to the waveform diagram of the reference physiological signal, specific positions of a rising edge and a falling edge may be determined, the rising edge and the falling edge are intercepted, the rising edge is used as a rising edge template, the falling edge is used as a falling edge template, then the rising edge and the falling edge of the waveform in the waveform diagram of the target physiological signal are intercepted, correlation operation is performed on the rising edge and the rising edge template of the target physiological signal, so as to obtain a signal-enhanced rising edge physiological signal, correlation operation is performed on the falling edge and the falling edge template of the target physiological signal, so as to obtain a signal-enhanced falling edge physiological signal, and the heartbeat interval time of the physiological subject may be determined based on the peak value of the rising edge physiological signal waveform diagram and the valley value of the falling edge physiological signal waveform diagram.

As an alternative embodiment, the step S106 of determining the falling edge physiological signal based on the target physiological signal and the falling edge template includes: performing autocorrelation calculation on a falling edge signal of the target physiological signal and a falling edge template to obtain a third calculation result, and performing convolution calculation on the falling edge signal of the target physiological signal and the falling edge template to obtain a fourth calculation result; and normalizing the sum of the third calculation result and the fourth calculation result to obtain the falling edge physiological signal.

In this embodiment, according to the oscillogram of the target physiological signal, the specific position of the falling edge of the target physiological signal can be determined, the falling edge is intercepted, then the autocorrelation calculation and the convolution calculation can be performed on the falling edge of the target physiological signal and the falling edge template of the reference physiological signal to obtain two calculation results, and the sum of the two calculation results is normalized to obtain the falling edge physiological signal.

It should be noted that, the above method and process for determining a rising edge physiological signal based on a rising edge/falling edge of a target physiological signal and a rising edge/falling edge template are merely examples, and are not limited herein, and the process and the method are within the scope of the embodiments of the present invention as long as the process and the method are divided into rising edge/falling edge signals based on the target physiological signal and perform a related signal enhancement operation with the rising edge/falling edge template.

As an alternative embodiment, the step S106 of determining the heartbeat interval time of the physiological object based on the rising edge physiological signal and the falling edge physiological signal includes: determining a set of rising edge heartbeat intervals of the physiological subject based on the rising edge physiological signal and a set of falling edge heartbeat intervals of the physiological subject based on the falling edge physiological signal; merging the rising edge heartbeat interval set and the falling edge heartbeat interval set to obtain a target heartbeat interval set of the physiological object; an average value of a plurality of elements in the target heartbeat interval set is determined as a heartbeat interval time.

In this embodiment, a rising edge heartbeat interval set of the physiological object is determined based on the waveform diagram of the rising edge physiological signal, a falling edge heartbeat interval set of the physiological object is determined based on the waveform diagram of the falling edge physiological signal, then the rising edge heartbeat interval set and the falling edge heartbeat interval set are merged into a target heartbeat interval set of the physiological object, all elements in the target heartbeat interval set are summed and averaged, so as to obtain a heartbeat interval time of the physiological object, wherein the rising edge heartbeat interval can be used for representing the time when two adjacent heartbeat positions are separated in the waveform of the rising edge physiological signal, and the falling edge heartbeat interval can be used for representing the time when two adjacent heartbeat positions are separated in the waveform of the falling edge physiological signal.

As an alternative embodiment, the step S106 of determining a set of rising edge heartbeat intervals of the physiological object based on the rising edge physiological signal includes: extracting a time value corresponding to each wave peak value in a plurality of wave peak values which are larger than a first threshold value on a oscillogram of the rising edge physiological signal to obtain a plurality of first time values; calculating the difference value of every two adjacent first time values in the plurality of first time values to obtain a plurality of first time difference values; a set of the plurality of first time difference values is determined as a set of rising edge heartbeat intervals.

In this embodiment, a time value corresponding to each of all peak values that are greater than a first threshold on a waveform diagram of the rising edge physiological signal may be extracted to obtain all first time values, a difference between all adjacent two first time values in the plurality of first time values may be calculated to obtain a first time difference value, a set of all first time difference values may be determined as a rising edge heartbeat interval set, where the first threshold may be a peak threshold, the peak value that is greater than the first threshold may be used to characterize a position of one heartbeat at the peak, and the first time difference value may be used to characterize an interval time between two heartbeats in the rising edge physiological signal, it should be noted that the peak threshold may be pre-calibrated or experimentally determined data, and no specific limitation is made here.

As an alternative embodiment, the step S106 of determining a set of falling edge heartbeat intervals of the physiological object based on the falling edge physiological signal includes: extracting a time value corresponding to each of a plurality of wave valley values of which the oscillogram of the falling edge physiological signal is smaller than a second threshold value to obtain a plurality of second time values; calculating the difference value of every two adjacent second time values in the plurality of second time values to obtain a plurality of second time difference values; a set of the plurality of second time difference values is determined as a set of falling edge heartbeat intervals.

In this embodiment, a time value corresponding to each of a plurality of valley values smaller than a second threshold on a waveform diagram of the falling edge physiological signal may be extracted to obtain all second time values, a difference between all adjacent two second time values in the plurality of second time values may be calculated to obtain a second time difference, a set of all the calculated second time differences may be determined as a falling edge heartbeat interval set, where the second threshold may be a valley threshold, a valley value smaller than the second threshold may be used to represent a position of one heartbeat at the valley, and the second time difference may be used to represent an interval time of two heartbeats in the falling edge physiological signal.

As an alternative embodiment, in step S104, performing noise reduction processing on the original physiological signal to obtain a target physiological signal, includes: determining a maximum wave peak value in a plurality of wave peak values on a waveform diagram of the original physiological signal, and determining a third time value corresponding to the maximum wave peak value; and extracting a signal corresponding to the time range of the third time value from the target threshold value on the oscillogram, and performing correlation operation on the extracted signal and the original physiological signal to obtain a target physiological signal.

In this embodiment, a maximum peak value of all peak values in a waveform diagram of the original heartbeat signal is located, a position of the maximum peak value may be determined as a heartbeat position of the original physiological signal, a third time value corresponding to the heartbeat position is determined as a heartbeat interval representative value, the original physiological signal corresponding to a time period that is distant from the heartbeat interval representative value by a target threshold value is extracted, and correlation operation is performed on the extracted original physiological signal and the original physiological signal to obtain the target physiological signal, so as to achieve a technical effect of further reducing noise and reducing abnormal heartbeats of the original heartbeat signal, where the target threshold value may be half of a time length of two adjacent heartbeat intervals, which is only exemplified here and not particularly limited.

According to the embodiment of the invention, the original physiological signals of the physiological objects in the vehicle are collected, then the collected original physiological signals are subjected to noise reduction processing to obtain the target physiological signals, and finally the target physiological signals are processed according to the physiological signal samples of the physiological objects collected in the historical time period, so that the purposes of performing signal enhancement on the target physiological signals and determining the heartbeat intervals of the physiological objects are achieved, the technical problem of low collection accuracy of the physiological signals of the physiological objects in the vehicle is solved, and the technical effect of improving the collection accuracy of the physiological signals of the physiological objects in the vehicle is realized.

Example 2

The technical solutions of the embodiments of the present invention will be illustrated below with reference to preferred embodiments.

With the vehicle becoming the daily tool of riding instead of walk of people, the high frequency automobile rate of use makes the user in the car time longer and longer more, and the motorcar driving needs high concentration attention and good health state in order to guarantee to drive safety. Busy life makes more and more people be in sub-health state, needs to pay close attention to a plurality of physiological parameters of health in real time and carries out disease prevention, but the current correlation technique of gathering and processing physiological signal, definite heart rate still has the inaccurate problem of detection.

In a related art, there are provided a signal processing method, a signal processing apparatus, a vehicle, and a storage medium, which are applied to a vehicle including: safety belt, signal processing equipment, first triaxial acceleration sensor, wherein, signal processing equipment includes: the signal processing device is arranged at the chest position of a user when the user wears the safety belt, the first triaxial acceleration sensor is arranged in the vehicle, the distance between the first triaxial acceleration sensor and the user is larger than a preset distance, and the first triaxial acceleration sensor is connected with the signal processing device through a wire harness; the signal processing apparatus is for performing a signal processing method, the method including: when a user wears a safety belt, user information is collected; the heart rate and the breathing rate are determined from the physiological signals of the user. The embodiment of the invention is used for obtaining high-quality heart rate and respiratory rate for use.

In another related art, a vehicle-mounted human body information acquisition method, a device and a vehicle are specified. The vehicle human body information acquisition method comprises the following steps: acquiring UWB (Ultra Wide Band, UWB for short) human heartbeat information transmitted by a wireless carrier communication technology and human heartbeat interval information of a three-axis sensor transmitted by a three-axis acceleration sensor of a safety belt; acquiring slow time axis human heartbeat interval information and fast time axis human heartbeat interval information according to the UWB human heartbeat information; and acquiring heartbeat interval information according to the human heartbeat interval information of the slow time axis and the arbitrary heartbeat interval information of the fast time axis. The scheme can reduce the detection error caused by a single sensor and improve the heart rate detection accuracy effect in a vehicle-mounted scene; the heartbeat signal and the respiration signal obtained by the two sensors are mutually complementary, and the accuracy of the detection result is improved by combining a strategy.

However, none of the above methods considers processing the rising edge and the falling edge of the physiological signal, and there is still a technical problem that the accuracy of the heartbeat information of the human body detected by the vehicle is low.

However, the invention provides a method for detecting the heart rate of a vehicle-mounted safety belt, which includes the steps of collecting original physiological signals of physiological objects in a vehicle, then performing noise reduction processing on the collected original physiological signals to obtain target physiological signals, and finally processing the target physiological signals according to physiological signal samples of a plurality of physiological objects collected in a historical time period to achieve the purposes of performing signal enhancement on the target physiological signals and determining heartbeat intervals of the physiological objects, so that the technical problem of low collection accuracy of the physiological signals of the physiological objects in the vehicle is solved, and the technical effect of improving the collection accuracy of the physiological signals of the physiological objects in the vehicle is achieved.

Next, a signal processing method of a vehicle according to an embodiment of the present invention will be described by way of example.

Fig. 2 is a schematic diagram of a multi-sensor combined heart rate detection system 200 according to an embodiment of the present invention, as shown in fig. 2, the multi-sensor combined heart rate detection system 200 may include an accelerometer 202 placed on a seat belt, a signal processing device 204 and a meter display device 206, wherein the signal processing device 204 may include a preprocessing module 2042, a short-time autocorrelation module 2044, a signal enhancement module 2046 and a heartbeat interval extraction module 2048.

Optionally, the acceleration sensor 202 on the seat belt may be configured to collect heartbeat signals of the user, the preprocessing module 2042 is configured to perform preliminary noise reduction on the collected heartbeat signals, the short-time autocorrelation module 2044 may be configured to perform short-time autocorrelation processing on the preprocessed heartbeat signals, so as to achieve technical effects of further noise reduction and reduction of abnormal heartbeat intervals, the signal enhancement module 2046 may be configured to enhance the heartbeat signals by processing a rising edge and a falling edge respectively, extract the heartbeat intervals to obtain a heartbeat interval sequence more accurately, the heartbeat interval extraction module 2048 may be configured to perform heartbeat interval processing on the heartbeat signals on the rising edge and the falling edge respectively, and finally integrate the heartbeat intervals into a heartbeat interval of the whole heartbeat signal, so as to obtain a more accurate heartbeat interval sequence, and then transmit the heartbeat interval to the instrument display device 206 by wireless transmission, the instrument display device 206 may be configured to display the heartbeat interval time of the user, so as to find and solve a physical condition and a potential hazard of the user conveniently, thereby solving a technical problem of a low heartbeat extraction interval accuracy rate, and improving a technical effect of heartbeat extraction interval accuracy rate.

Fig. 3 is a flowchart of a heartbeat signal processing method of an onboard seat belt according to an embodiment of the present invention, and as shown in fig. 3, the method may include the following steps:

and step S302, an acceleration sensor placed on the safety belt collects heartbeat signals.

In the step S302 of the present invention, heartbeat signals in multiple directions may be acquired through an acceleration sensor placed on a seat belt of a vehicle, for example, heartbeat signals in three directions may be acquired through a three-axis acceleration sensor, and it should be noted that the acceleration sensor that acquires heartbeat signals on the seat belt is only an example, and is not limited herein.

Step S304, preprocessing the heartbeat signal.

In step S304 of the present invention, the variance of the heartbeat signal may be calculated, and the heartbeat interval may be processed.

Optionally, the variance of a section of acquired heartbeat signals is calculated first, if the variance exceeds a variance threshold, the heartbeat signals can be described as noise generated by body movement, if the variance is within the variance threshold, the heartbeat interval can be further processed, baseline drift in all directions is removed through filtering, a signal which can represent the heartbeat most can be extracted from the heartbeat signals acquired by the acceleration sensors in multiple directions by using principal component analysis, then the heartbeat signals processed by the above items are converted into a frequency domain by using a frequency spectrum, the frequency corresponding to the maximum peak value in the frequency domain can be determined as a heart rate, and the ratio of 60 to the heart rate can be determined as a representative value of the heartbeat interval in a certain time period, wherein the variance threshold can be a pre-calibrated or experimentally determined value, and specific values of the variance threshold and a determination method are not specifically limited herein.

For example, heartbeat signals of three directions of a user are acquired through an acceleration sensor deployed on a safety belt, variances of a section of acquired heartbeat signals are calculated (for example, if the variance obtained through experimental measurement is 1, the variance smaller than or equal to 1 can be represented within a variance threshold range, and if the variance is larger than 1, the variance can be represented as exceeding the variance threshold), when the variance exceeds the variance threshold, the acquired heartbeat signals can be described as noise generated by body movement of the user, the heartbeat signals at the moment are removed, heartbeat interval processing is performed on the heartbeat signals with the variance within the variance threshold range, as the normal heart rate of a human body is considered to be 60-100 times/min, baseline drift of each direction can be removed through band-pass filtering of 0.5-2 HZ, then the heartbeat signal which is most representative of the heartbeat at the position of the heart rate is extracted from the heartbeat signals acquired by the acceleration sensor of the three directions through principal component analysis, then the processed signals can be converted into a frequency domain through a frequency spectrum, the frequency corresponding to the maximum peak value in the frequency domain is determined, and the ratio of the heart rate of 60 to the heart rate at the moment is determined as a representative value of the heartbeat interval of the heartbeat of the user at the time.

As another example, if the maximum peak value of the frequency corresponding to 1HZ in the frequency domain is 60, the heart rate at this time is 60/min, and the ratio 1s of 60 to the heart rate 60 at this time can be determined as the representative value of the heart beat interval of the user at this time.

Step S306, the heartbeat signal is self-correlated in short time.

In step S306, the pre-processed heartbeat signal may be subjected to short-time autocorrelation.

Optionally, the maximum wave peak value of the preprocessed heartbeat signal is determined as a heartbeat position in the heartbeat signal in the period, and by taking half of the heartbeat interval of the heartbeat signal as the length, a section of heartbeat signal before and after the heartbeat position can be intercepted, and correlation operation can be performed according to the intercepted heartbeat signal and the preprocessed heartbeat signal, so that noise can be reduced, the heartbeat signal can be processed preliminarily, and abnormal heartbeat intervals can be reduced.

Optionally, the maximum peak of the preprocessed heartbeat signal in the frequency domain is positioned as the position of the heartbeat of the section of heartbeat signal, a section of heartbeat signal with the same length before and after the position of the heartbeat can be intercepted by taking a half of the interval between two heartbeats as the length, and correlation operation is performed on the intercepted heartbeat signal before and after the position of the heartbeat and the preprocessed heartbeat signal, so that the heartbeat signal after short-time autocorrelation processing is obtained.

For example, the maximum peak value of the preprocessed heartbeat signal is located to be 60, the position is the heartbeat position, if the time is 1s, the length can be half 0.5s of the representative value of the interval of the heartbeat signal, the heartbeat signals of 0.5-1.5 s before and after the heartbeat position can be intercepted, and then correlation operation can be performed according to the intercepted heartbeat signal and the preprocessed heartbeat signal, so that noise is reduced, the heartbeat signal is processed preliminarily, and the abnormal heartbeat interval is reduced.

It should be noted that, no specific limitation is imposed on the correlation operation performed on the intercepted heartbeat interval and the preprocessed heartbeat signal, and any operation that performs the operations on the intercepted heartbeat interval and the preprocessed heartbeat signal and can achieve the technical effects of reducing noise and reducing abnormal heartbeat interval is within the protection scope of the embodiment of the present invention.

Step S308, the heartbeat signal is enhanced.

In the above step S308 of the present invention, the heartbeat signal after being preprocessed and short-time auto-correlated is enhanced.

Optionally, according to waveforms acquired at the positions of the heartbeats of multiple users, a rising edge and a falling edge may be intercepted as prior templates, the rising edge template or the falling edge template may be respectively subjected to autocorrelation and convolution operations with the heartbeat signal after the short-time autocorrelation processing, and the heartbeat signals obtained after the autocorrelation and convolution operations are added and normalized, so that the purpose of enhancing the heartbeat signal may be achieved.

For example, the rising edge and the falling edge of the existing waveforms can be intercepted, then the rising edge and the falling edge can be used as prior templates, the rising edge templates and the heartbeat signals after short-time autocorrelation processing are subjected to autocorrelation and convolution, so that the rising edge heartbeat signals after autocorrelation and convolution operation are obtained, then the processed rising edge heartbeat signals can be added, and then normalization processing is carried out, so that the enhanced rising edge heartbeat signals are obtained.

For another example, the falling edge template and the heartbeat signal after the short-time autocorrelation processing may be subjected to autocorrelation and convolution, so as to obtain a falling edge heartbeat signal after autocorrelation and convolution operation, and then the processed falling edge heartbeat may be correlated, and then the post-normalization processing is performed, so as to obtain an enhanced falling edge heartbeat signal.

In step S310, a heartbeat interval is extracted.

In step S310 of the present invention, the heartbeat signal subjected to signal enhancement may be subjected to heartbeat interval processing.

Optionally, the peak values of the enhanced heartbeat signals of the rising edge and the falling edge are positioned, when the peak values exceed a certain peak threshold, the peak positions at this time can be determined as heartbeat positions, a heartbeat position difference value can be calculated, the heartbeat position difference value can be determined as heartbeat intervals, and then the heartbeat intervals of the rising edge and the falling edge can be summed and averaged, so that a more accurate heartbeat interval sequence can be obtained, wherein the peak threshold can be a pre-calibrated or experimentally determined value, and the value of the peak threshold is not specifically limited.

For example, the wave peak values of the enhanced rising edge heartbeat signal and the enhanced falling edge heartbeat signal can be located, when the wave peak value exceeds 0.5, it can be said that the wave peak value is greater than 0.5 and is a heartbeat position, and the difference value between two adjacent heartbeat positions can be determined as a heartbeat interval, for example, the positions of 0.5s and 1.4s are both the wave peak values and both exceed a peak threshold value of 0.5, then 0.5s and 1.4s can be determined as two adjacent heartbeat positions, the difference value of 0.9s is the heartbeat interval of the heartbeat signal, the enhanced falling edge heartbeat signal can be processed through the same steps as the above method, and finally the rising edge heartbeat interval and the falling edge heartbeat interval are summed and averaged, so that a more accurate heartbeat interval sequence can be obtained.

Example 3

According to the embodiment of the invention, the signal processing device of the vehicle is also provided. It should be noted that the signal processing device of the vehicle may be used to execute the signal processing method of the vehicle in embodiment 1.

Fig. 4 is a schematic diagram of a signal processing apparatus of a vehicle according to an embodiment of the present invention. As shown in fig. 4, the signal processing apparatus 400 of the vehicle may include: an acquisition unit 402, a noise reduction processing unit 404, and a determination unit 406.

An acquisition unit 402 for acquiring an original physiological signal of a physiological object in a vehicle.

The noise reduction processing unit 404 is configured to perform noise reduction processing on the original physiological signal to obtain a target physiological signal.

A determining unit 406, configured to determine a heartbeat interval time of the physiological object based on the target physiological signal and a reference physiological signal, where the reference physiological signal is a physiological signal of a plurality of physiological object samples acquired in a historical time period, and the heartbeat interval time is used to characterize a time between two adjacent heartbeat intervals of the physiological object.

Alternatively, the determining unit 404 may include: a first generation module for generating a rising edge template based on a rising edge signal of the reference physiological signal and generating a falling edge template based on a falling edge signal of the reference physiological signal; the first determination module is used for determining a rising edge physiological signal based on a target physiological signal and a rising edge template, and determining a falling edge physiological signal based on the target physiological signal and a falling edge template, wherein the rising edge physiological signal is a signal obtained after signal enhancement is carried out on the rising edge signal of the target physiological signal, and the falling edge physiological signal is a signal obtained after signal enhancement is carried out on the falling edge signal of the target physiological signal; and the second determination module is used for determining the heartbeat interval time of the physiological object based on the rising edge physiological signal and the falling edge physiological signal.

Optionally, the first determining module may include: the first autocorrelation calculating submodule is used for carrying out autocorrelation calculation on a rising edge signal and a rising edge template of the target physiological signal to obtain a first calculation result, and carrying out convolution calculation on the rising edge signal and the rising edge template of the target physiological signal to obtain a second calculation result; and the first normalization processing submodule is used for performing normalization processing on the sum of the first calculation result and the second calculation result to obtain a rising edge physiological signal.

Optionally, the first determining module may include: the second autocorrelation calculating module is used for performing autocorrelation calculation on the target physiological signal and the falling edge template to obtain a third calculation result, and performing convolution calculation on the falling edge signal of the target physiological signal and the falling edge template to obtain a fourth calculation result; and the second normalization processing submodule is used for performing normalization processing on the sum of the third calculation result and the fourth calculation result to obtain a falling edge physiological signal.

Optionally, the second determining module may include: the first determining submodule is used for determining a rising edge heartbeat interval set of the physiological object according to the rising edge physiological signal and determining a falling edge heartbeat interval set of the physiological object according to the falling edge physiological signal; the merging submodule is used for merging the rising edge heartbeat interval set and the falling edge heartbeat interval set to obtain a target heartbeat interval set of the physiological object; and the second determining submodule is used for determining the average value of a plurality of elements in the target heartbeat interval set as the heartbeat interval time.

Optionally, the second determining module may further include: the first extraction submodule is used for extracting a time value corresponding to each wave peak value in a plurality of wave peak values which are larger than a first threshold value on a waveform diagram of the rising edge physiological signal to obtain a plurality of first time values; a first calculation submodule: calculating the difference value of every two adjacent first time values in the plurality of first time values to obtain a plurality of first time difference values; and the third determining submodule is used for determining the set of the plurality of first time difference values as the rising edge heartbeat interval set.

Optionally, the second determining module may further include: the second extraction submodule is used for extracting a time value corresponding to each valley value in a plurality of valley values of which the oscillogram of the falling edge physiological signal is smaller than a second threshold value to obtain a plurality of second time values; the second calculation submodule is used for calculating the difference value of every two adjacent second time values in the plurality of second time values to obtain a plurality of second time difference values; the third calculation submodule is used for calculating the difference value of every two adjacent second time values in the plurality of second time values to obtain a plurality of second time difference values; and the fourth determining submodule is used for determining the set of the plurality of second time difference values as the set of the falling edge heartbeat intervals.

Alternatively, the noise reduction processing unit 304 may include: the third determining module is used for determining the maximum wave peak value in the plurality of wave peak values on the oscillogram of the original physiological signal and determining a third time value corresponding to the maximum wave peak value; and the processing module is used for extracting a signal corresponding to the oscillogram within a time range from the third time value to the target threshold value, and performing correlation operation on the extracted signal and the original physiological signal to obtain a target physiological signal.

According to an embodiment of the present invention, an acquisition unit acquires an original physiological signal of a physiological object in a vehicle; the noise reduction processing unit is used for carrying out noise reduction processing on the original physiological signal to obtain a target physiological signal; the determining unit is used for determining heartbeat interval time of the physiological object based on the target physiological signal and the reference physiological signal, wherein the reference physiological signal is a physiological signal of a plurality of physiological object samples acquired in a historical time period, and the heartbeat interval time is used for representing the time of two adjacent heartbeat intervals of the physiological object, so that the technical problem of low accuracy of acquiring the physiological signal of the physiological object in the vehicle is solved, and the technical effect of improving the accuracy of acquiring the physiological signal of the physiological object in the vehicle is realized.

Example 4

According to an embodiment of the present invention, there is also provided a computer-readable storage medium including a stored program, wherein the program executes the signal processing method of the vehicle described in embodiment 1.

Example 5

According to an embodiment of the present invention, there is also provided a processor for running a program, wherein the program is run to execute the signal processing method of the vehicle described in embodiment 1.

Example 6

According to an embodiment of the present invention, there is also provided a vehicle for executing the signal processing method of the vehicle of the embodiment of the present invention.

The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.

In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit may be implemented in the form of hardware, or may also be implemented in the form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.

The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.

Claims

1. A signal processing method of a vehicle, characterized by comprising:

acquiring an original physiological signal of a physiological object in a vehicle;

carrying out noise reduction processing on the original physiological signal to obtain a target physiological signal;

determining heartbeat interval time of the physiological object based on the target physiological signal and a reference physiological signal, wherein the reference physiological signal is a physiological signal of a plurality of physiological object samples collected in a historical time period, and the heartbeat interval time is used for representing the time between two adjacent heartbeats of the physiological object.

2. The method of claim 1, wherein determining the heartbeat interval time of the physiological subject based on the target physiological signal and the reference physiological signal comprises:

generating a rising edge template based on a rising edge signal of the reference physiological signal and generating a falling edge template based on a falling edge signal of the reference physiological signal;

determining a rising edge physiological signal based on the target physiological signal and the rising edge template, and determining a falling edge physiological signal based on the target physiological signal and the falling edge template, wherein the rising edge physiological signal is a signal obtained after signal enhancement is performed on the rising edge signal of the target physiological signal, and the falling edge physiological signal is a signal obtained after signal enhancement is performed on the falling edge signal of the target physiological signal;

determining a heartbeat interval time of the physiological subject based on the rising edge physiological signal and the falling edge physiological signal.

3. The method of claim 2, wherein determining a rising edge physiological signal based on the target physiological signal and the rising edge template comprises:

performing autocorrelation calculation on a rising edge signal of the target physiological signal and the rising edge template to obtain a first calculation result, and performing convolution calculation on the rising edge signal of the target physiological signal and the rising edge template to obtain a second calculation result;

and normalizing the sum of the first calculation result and the second calculation result to obtain the rising edge physiological signal.

4. The method of claim 2, wherein determining a falling edge physiological signal based on the target physiological signal and the falling edge template comprises:

performing autocorrelation calculation on a falling edge signal of the target physiological signal and the falling edge template to obtain a third calculation result, and performing convolution calculation on the falling edge signal of the target physiological signal and the falling edge template to obtain a fourth calculation result;

and normalizing the sum of the third calculation result and the fourth calculation result to obtain the falling edge physiological signal.

5. The method of claim 2, wherein determining a heartbeat interval time of the physiological subject based on the rising edge physiological signal and the falling edge physiological signal comprises:

determining a set of rising edge heartbeat intervals of the physiological subject based on the rising edge physiological signal and a set of falling edge heartbeat intervals of the physiological subject based on the falling edge physiological signal;

merging the rising edge heartbeat interval set and the falling edge heartbeat interval set to obtain a target heartbeat interval set of the physiological object;

determining an average of a plurality of elements in the target heartbeat interval set as the heartbeat interval time.

6. The method of claim 5, wherein determining a set of rising edge heartbeat intervals for the physiological subject based on the rising edge physiological signal comprises:

extracting a time value corresponding to each wave peak value in a plurality of wave peak values which are larger than a first threshold value on a oscillogram of the rising edge physiological signal to obtain a plurality of first time values;

calculating the difference value of every two adjacent first time values in the plurality of first time values to obtain a plurality of first time difference values;

determining the set of the plurality of first time difference values as the set of rising edge heartbeat intervals.

7. The method of claim 5, wherein determining a set of falling edge heartbeat intervals for the physiological subject based on the falling edge physiological signal comprises:

extracting a time value corresponding to each of a plurality of wave valley values smaller than a second threshold value on the oscillogram of the falling edge physiological signal to obtain a plurality of second time values;

calculating the difference value of every two adjacent second time values in the plurality of second time values to obtain a plurality of second time difference values;

determining the set of the plurality of second time difference values as the set of falling edge heartbeat intervals.

8. The method of claim 1, wherein denoising the original physiological signal to obtain a target physiological signal comprises:

determining a maximum wave peak value in a plurality of wave peak values on a waveform diagram of the original physiological signal, and determining a third time value corresponding to the maximum wave peak value;

and extracting a signal corresponding to the oscillogram within a time range from the third time value to a target threshold value, and performing correlation operation on the extracted signal and the original physiological signal to obtain the target physiological signal.

9. A signal processing apparatus of a vehicle, characterized by comprising:

an acquisition unit for acquiring an original physiological signal of a physiological object in a vehicle;

the noise reduction processing unit is used for carrying out noise reduction processing on the original physiological signal to obtain a target physiological signal;

the determining unit is configured to determine a heartbeat interval time of the physiological object based on the target physiological signal and a reference physiological signal, where the reference physiological signal is a physiological signal of a plurality of physiological object samples acquired in a historical time period, and the heartbeat interval time is used to represent a time between two adjacent heartbeats of the physiological object.

10. A vehicle characterized by being configured to execute a signal processing method of the vehicle according to any one of claims 1 to 8.