CN113415285A - Driver alertness assessment method and system - Google Patents

Abstract

The invention relates to the technical field of automatic driving, in particular to a method, a device, equipment and a readable storage medium for evaluating the alertness of a driver, wherein the method comprises the following steps: acquiring crisis triggering time and monitoring data, wherein the crisis triggering time is the moment when a crisis starts to occur, and the monitoring data is eye movement information and electrocardiogram information of a driver during driving; calculating physiological index data according to the crisis triggering time and the monitoring data; the method comprises the steps of acquiring monitoring data used for monitoring eye movement information and electrocardio information of a driver for a certain period of time before crisis triggering, quickly calculating the reaction time of the driver in the current state, and providing a corresponding driver-side data index for an automobile auxiliary driving system, so that the automobile auxiliary driving system can judge whether the driver is alert at present when crisis happens more accurately.

Description

Driver alertness assessment method and system

Technical Field

The invention relates to the technical field of automatic driving, in particular to a method and a system for evaluating the alertness of a driver.

Background

In the beginning of the 90 s of the 20 th century, scientific research institutions and companies involved in the research of the alertness of drivers, and the existing driver alertness identification method does not utilize the time characteristic of the change of the alertness to predict the reaction time of the driver.

Disclosure of Invention

The invention aims to provide a method, a device and equipment for evaluating the alertness of a driver and a readable storage medium, so as to improve the problems.

In order to achieve the above object, the embodiments of the present application provide the following technical solutions:

in one aspect, an embodiment of the present application provides a method for assessing a driver alertness, where the method includes: acquiring crisis triggering time and monitoring data, wherein the crisis triggering time is the moment when a crisis starts to occur, and the monitoring data is eye movement information and electrocardiogram information of a driver during driving; calculating physiological index data according to the crisis triggering time and the monitoring data, wherein the physiological index data is information reflecting the concentration degree of the attention of the driver; and constructing an evaluation model, bringing the physiological index data into the evaluation model, and calculating to obtain a predicted reaction duration, wherein the predicted reaction duration is the estimated duration from the occurrence of the crisis to the response action of the driver.

Preferably, after the calculating the predicted reaction time length, the method further includes:

acquiring the current vehicle speed per hour;

calculating to obtain crisis processing duration according to the current vehicle speed per hour, wherein the crisis processing duration is duration required by a driver for processing crisis according to the current vehicle speed;

and comparing the crisis processing time length with the predicted reaction time length, and if the crisis processing time length is greater than or equal to the predicted reaction time length, sending a warning instruction to a warning device, wherein the warning instruction is an instruction for enabling the warning device to send out a warning prompt tone.

Preferably, if the crisis processing duration is greater than or equal to the predicted reaction duration, after sending a warning instruction to a warning device, the method further includes:

acquiring eye movement data in a current unit time period, and calling the monitoring data, wherein the monitoring data comprises first time period eye movement data;

calculating to obtain a first state value according to the first period eye movement data;

calculating to obtain a current eye movement state value according to the eye movement data in the current unit time period;

and calculating to obtain a first difference value according to the first state value and the current eye movement state value, wherein the difference value reflects the change amplitude of the eye movement information before and after the driver hears the warning prompt tone.

And taking corresponding risk avoidance measures according to the first difference value.

Preferably, according to the first difference value, taking a corresponding risk avoidance measure includes:

acquiring a first threshold value, wherein the first threshold value is the minimum value of the preset first difference values;

and comparing the first threshold value with the first difference value, if the first difference value is smaller than the first threshold value, sending an emergency braking instruction to a braking system, and sending a warning light flashing instruction to a vehicle machine system.

Preferably, if the crisis processing duration is greater than or equal to the predicted reaction duration, after sending a warning instruction to a warning device, the method further includes:

acquiring heartbeat data in a current unit time period, and calling the monitoring data, wherein the monitoring data comprises first time period heartbeat data;

calculating to obtain a second state value according to the first period heartbeat data;

calculating to obtain a current cardiac state value according to the heartbeat data in the current unit time period;

and calculating to obtain a second difference value according to the first state value and the current cardiac state value, wherein the second difference value reflects the amplitude of the change of the heartbeat information before and after the driver hears the warning prompt tone.

And taking corresponding risk avoidance measures according to the second difference value.

Preferably, according to the second difference value, taking a corresponding risk avoidance measure includes:

acquiring a second threshold value, wherein the second threshold value is a preset minimum value of the second difference value;

comparing the second threshold value with the second difference value, if the second difference value is smaller than the second threshold value, sending an emergency braking instruction to a braking system, and sending a warning light flashing instruction to a vehicle machine system;

and receiving a trigger state of the collision trigger, and if the trigger state is triggered, sending rescue information to a rescue center.

Preferably, the calculating physiological index data according to the crisis triggering time and the monitoring data includes:

calling the crisis triggering time and the monitoring data;

intercepting first data to be detected from the monitoring data according to the crisis triggering time, wherein the first data to be detected is eye movement information and electrocardiogram information of the driver in a period of time before the crisis occurs;

and calculating to obtain the physiological index data according to the first to-be-detected data, wherein the first to-be-detected data comprises first eye movement monitoring data, first cardiac movement monitoring data and first monitoring duration, and the physiological index data comprises eye movement index data and electrocardiogram index data.

Preferably, the calculating the physiological index data according to the first to-be-detected data includes:

acquiring a preset equipartition value, and calling the first eye movement monitoring data;

dividing the first monitoring duration into at least two first sub-monitoring durations according to the preset equal value;

respectively calling each first sub-eye movement monitoring data corresponding to each first sub-monitoring duration from the first eye movement monitoring data according to each first sub-monitoring duration;

calculating to obtain sub-eye movement index data corresponding to each first sub-eye movement monitoring data according to each first sub-eye movement monitoring data;

and calculating to obtain the first eye movement monitoring data according to at least two sub-eye movement index data.

Preferably, the calculating the physiological index data according to the first to-be-detected data further includes:

retrieving the first cardiac monitoring data;

calculating R-R interval index data according to the first cardiac monitoring data, wherein the R-R interval index data comprise an R-R interval average value, an R-R interval standard deviation, a frequency that an adjacent R-R interval difference value is larger than 50ms and a percentage that the adjacent R-R interval difference value is larger than 50 ms;

and calculating to obtain energy data according to the first cardiac monitoring data, wherein the energy data comprise low-frequency signal energy of 0.04-0.15 Hz, high-frequency signal energy of 0.15-0.40 Hz and a low-frequency high-frequency ratio, and the electrocardiogram index data comprise R-R interval data and energy data.

Preferably, the calculating R-R interval indicator data according to the first cardiac monitoring data comprises:

retrieving the first cardiac monitoring data;

sequentially filtering, electromyographic signal removal, power frequency signal removal and correction processing are carried out on the first cardiac monitoring data to obtain processed first cardiac monitoring data;

sequentially detecting the processed first cardiac monitoring data by an interval spectrum method and a difference method, and screening out R-R interval data;

calculating the average R-R interval, standard deviation of R-R intervals, frequency of adjacent R-R interval difference values greater than 50ms, and percentage of adjacent R-R interval difference values greater than 50ms from the R-R interval data.

Preferably, the calculating energy data according to the first cardiac monitoring data includes:

retrieving the first cardiac monitoring data;

converting the first cardiac monitoring data from a time domain to a frequency domain through a fast Fourier algorithm, and obtaining corresponding frequency domain data;

and calculating the low-frequency signal energy of 0.04-0.15 Hz, the high-frequency signal energy of 0.15-0.40 Hz and the low-frequency high-frequency ratio according to the frequency domain data.

Preferably, after the calculating the predicted reaction time length, the method further includes:

acquiring emergency measure implementation time, wherein the emergency measure implementation time is the moment when the driver starts to take the corresponding measures;

calculating actual reaction duration according to the emergency measure implementation time and the crisis triggering time, wherein the actual reaction duration is duration from crisis occurrence to countermeasure taking of the driver;

and calculating to obtain the average absolute error and the root mean square error corresponding to the evaluation model according to the actual reaction time length and the predicted reaction time length.

In a second aspect, an embodiment of the present application provides a driver alertness assessment system, including:

a driver alertness assessment system, comprising:

the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring crisis triggering time and monitoring data, the crisis triggering time is the moment when a crisis starts to occur, and the monitoring data is eye movement information and electrocardiogram information of a driver during driving;

the first calculation module is used for calculating physiological index data according to the crisis triggering time and the monitoring data, wherein the physiological index data is information reflecting the concentration degree of the attention of the driver;

and the second calculation unit is used for constructing an evaluation model, substituting the physiological index data into the evaluation model, and calculating to obtain a predicted reaction duration, wherein the predicted reaction duration is estimated from the occurrence of a crisis to the time for the driver to take a countermeasure.

In a third aspect, embodiments of the present application provide a driver alertness assessment device, which includes a memory and a processor. The memory is used for storing a computer program; the processor is adapted to carry out the steps of the above-described driver alertness assessment method when executing the computer program.

In a fourth aspect, the present application provides a readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the above-mentioned driver alertness assessment method.

The invention has the beneficial effects that:

according to the method, the system and the device, the monitoring data of the eye movement information and the electrocardio information of the driver in a certain period of time before the crisis triggering is acquired, the reaction time of the driver in the current state is rapidly calculated, and the corresponding data index of the driver side is provided for the automobile assistant driving system, so that the automobile assistant driving system can judge whether the driver is alert at present or not when the crisis occurs more accurately.

Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by the practice of the embodiments of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.

Fig. 1 is a flow chart of a method for assessing the alertness of a driver according to an embodiment of the present invention.

Fig. 2 is a schematic structural diagram of a driver alertness evaluation system according to an embodiment of the present invention.

Fig. 3 is a schematic structural diagram of a second computing unit according to an embodiment of the present invention.

Fig. 4 is a schematic structural diagram of a fifteenth computing unit according to an embodiment of the present invention.

Fig. 5 is a schematic structural diagram of a driver alertness evaluation apparatus according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, 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 some, but not all, embodiments of the present invention. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. 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: like reference numbers or letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined or explained in subsequent figures. Meanwhile, in the description of the present invention, the terms "first", "second", and the like are used only for distinguishing the description, and are not to be construed as indicating or implying relative importance.

Example 1

As shown in fig. 1, the present embodiment provides a driver alertness assessment method including step S1, step S2, and step S3.

S1, acquiring crisis triggering time and monitoring data, wherein the crisis triggering time is the moment when a crisis starts to occur, and the monitoring data is eye movement information and electrocardiogram information of a driver during driving;

when the alertness of the driver is reduced, the eye movement signal of the driver is changed obviously. If the saccade speed and frequency are reduced, the blink frequency and the eyelid closure degree are increased, in the embodiment, the original eye movement video is processed by iView X software to obtain eye movement signal basic data which comprises the fixation start-stop time and fixation point coordinates, the saccade start-stop time, the saccade speed and the blink start-stop time, the required eye movement information can be obtained through statistics and calculation, specifically, for each test time of a subtask, the start time of a guide vehicle brake lamp in the subtask is taken as 0 time during feature extraction, the eye movement data in a section of-30/s-0/s is taken as a feature extraction unit of the test time, and is taken as a time window with the duration of 5/s for division into 6 sections, each time window respectively calculates the eye movement feature, and finally, the feature data of 6 time windows are averaged to be taken as the eye movement feature index of the test time;

the electrocardiosignal is composed of a series of repeated wave groups, one wave group comprises a P wave, a QRS wave group, a T wave and a U wave, wherein the QRS wave group is most sensitive to the change of alertness, the electrocardiosignal can be analyzed from two aspects of time domain and frequency domain, the time domain characteristic can intuitively reflect the functional state of a nervous system, the frequency domain characteristic has the characteristics of high accuracy and good sensitivity, and the time domain characteristic and the frequency domain characteristic are combined to better reflect the change of alertness of a driver.

Secondly, the extraction of the electrocardio information of the driver comprises the following steps:

extracting electrocardio characteristics, firstly filtering original electrocardio data by adopting a band-pass filter with the bandwidth of 0.01-45/Hz, removing artifacts such as myoelectricity and power frequency signals, and correcting baseline drift. And then, detecting the QRS complex by using an interspectral method through a difference principle to obtain R-R interval data, and calculating a time domain index according to the R-R interval. In the aspect of frequency domain, the electrocardio data is converted from time domain to frequency domain through fast Fourier algorithm, and then the corresponding energy value is calculated according to the index frequency band range. The analysis range of the electrocardio data is consistent with the eye movement data, and the data of 30/s before the crisis trigger is taken as an analysis unit.

S2, calculating to obtain physiological index data according to the crisis triggering time and monitoring data, wherein the physiological index data is information reflecting the concentration degree of attention of the driver and comprises eye movement index data and electrocardio index data;

the method for obtaining the eye movement index data comprises the following steps: firstly, calling the crisis triggering time and the monitoring data;

then, according to the crisis triggering time, intercepting first data to be detected from the monitoring data, wherein the first data to be detected is eye movement information and electrocardiogram information of the driver in a period of time before the crisis occurs;

then, acquiring a preset equal score value, and calling the first eye movement monitoring data; dividing the first monitoring duration into at least two first sub-monitoring durations according to the preset equal value; respectively calling each first sub-eye movement monitoring data corresponding to each first sub-monitoring duration from the first eye movement monitoring data according to each first sub-monitoring duration; calculating to obtain sub-eye movement index data corresponding to each first sub-eye movement monitoring data according to each first sub-eye movement monitoring data;

and finally, calculating to obtain the first eye monitoring data according to at least two sub-eye movement index data, wherein the first eye monitoring data comprises average fixation time length, fixation time percentage, average saccade amplitude, blink frequency, eye closing time proportion, average pupil diameter and pupil diameter variation coefficient.

The method for obtaining the electrocardiogram index data comprises the following steps:

firstly, calling the crisis triggering time and the monitoring data;

then, according to the crisis triggering time, intercepting first data to be detected from the monitoring data, wherein the first data to be detected is eye movement information and electrocardiogram information of the driver in a period of time before the crisis occurs;

finally, the first cardiac monitoring data is called; calculating R-R interval index data according to the first cardiac monitoring data, wherein the R-R interval index data comprise an R-R interval average value, an R-R interval standard deviation, a frequency that an adjacent R-R interval difference value is larger than 50ms and a percentage that the adjacent R-R interval difference value is larger than 50 ms; according to the first cardiac monitoring data, calculating to obtain energy data, wherein the energy data comprise low-frequency signal energy of 0.04-0.15 Hz, high-frequency signal energy of 0.15-0.40 Hz and a low-frequency high-frequency ratio, the electrocardiogram index data comprise R-R interval data and energy data, and the electrocardiogram index data comprise R-R interval average values, R-R interval standard deviations, frequency of adjacent R-R interval difference values larger than 50ms, percentage of adjacent R-R interval difference values larger than 50ms and low-frequency signal energy of 0.04-0.15 Hz.

And S3, constructing an evaluation model, substituting the physiological index data into the evaluation model, and calculating to obtain a predicted reaction duration, wherein the predicted reaction duration is estimated from the occurrence of the crisis to the time of taking a countermeasure by the driver.

The assessment model is an existing LSTM model combined with an attention mechanism, in the embodiment, the reaction duration of the driver in the current state is quickly calculated by collecting monitoring data for monitoring eye movement information and electrocardio information of the driver for a certain duration before crisis triggering, and corresponding data indexes of a driver end are provided for the automobile assistant driving system, so that the automobile assistant driving system can judge whether the driver is alert at present when crisis occurs more accurately.

In a specific embodiment of the present disclosure, after the calculating the predicted reaction duration, the method further includes:

acquiring the current vehicle speed per hour;

calculating to obtain a crisis handling time length according to the current vehicle speed, wherein the crisis handling time length is a time length required by a driver to handle a crisis according to the current vehicle speed, namely the latest reaction time length allowed for the driver at the current speed;

the contrast time length is handled with the size of prediction reaction time length, if time length is handled to the crisis is more than or equal to prediction reaction time length sends warning instruction to warning device, warning instruction is for being used for making warning device sends the instruction of warning prompt tone, and it is more than or equal to detect time length is handled to the crisis as the system the prediction reaction time length, when the proruption crisis under current speed of time can't be handled to driver's attention degree under the current state promptly, promptly the driver probably does not notice the emergence of crisis like the brake light of front truck lights suddenly, needs increase driver's attention through warning prompt tone this moment, both lets the driver notice the brake warning.

In a specific embodiment of the present disclosure, after sending a warning instruction to a warning device if the crisis handling duration is greater than or equal to the predicted reaction duration, the method further includes:

acquiring eye movement data in a current unit time period, and calling the monitoring data, wherein the monitoring data comprises first time period eye movement data;

calculating to obtain a first state value according to the first period eye movement data;

calculating to obtain a current eye movement state value according to the eye movement data in the current unit time period;

and calculating to obtain a first difference value according to the first state value and the current eye movement state value, wherein the difference value reflects the change amplitude of the eye movement information before and after the driver hears the warning prompt tone.

And taking corresponding risk avoidance measures according to the first difference value.

The method comprises the steps that the state of a driver in the current state is detected immediately after a warning prompt tone is sent by the system, the amplitude of the eye movement data change of the driver before and after the warning prompt tone is sent is detected, if the amplitude of the change is smaller than a preset amplitude value, namely a first threshold value, the system judges that the driver does not receive warning prompt, and at the moment, the system automatically takes the risk avoiding measures, such as automatic emergency braking and the like.

In a specific embodiment of the present disclosure, taking a corresponding risk avoidance measure according to the first difference value includes:

acquiring a first threshold value, wherein the first threshold value is the minimum value of the preset first difference values;

and comparing the first threshold value with the first difference value, if the first difference value is smaller than the first threshold value, sending an emergency braking instruction to a braking system, and sending a warning light flashing instruction to a vehicle machine system.

The method comprises the steps that the state of a driver in the current state is detected immediately after a warning prompt tone is sent by the system, the amplitude of the eye movement data change of the driver before and after the warning prompt tone is sent is detected, if the amplitude of the change is smaller than a preset amplitude value, namely a first threshold value, the system judges that the driver does not receive warning prompt, and at the moment, the system automatically takes the risk avoiding measures, such as automatic emergency braking and the like.

In a specific embodiment of the present disclosure, after sending a warning instruction to a warning device if the crisis handling duration is greater than or equal to the predicted reaction duration, the method further includes:

acquiring heartbeat data in a current unit time period, and calling the monitoring data, wherein the monitoring data comprises first time period heartbeat data;

calculating to obtain a second state value according to the first period heartbeat data;

calculating to obtain a current cardiac state value according to the heartbeat data in the current unit time period;

and calculating to obtain a second difference value according to the second state value and the current cardiac state value, wherein the second difference value reflects the amplitude of the change of the heartbeat information before and after the driver hears the warning prompt tone.

And taking corresponding risk avoidance measures according to the second difference value.

The method comprises the steps that the state of a driver in the current state is detected immediately after a warning prompt tone is sent by the system, the amplitude of variation of cardiac data of the driver is detected before and after the warning prompt tone is sent, if the variation amplitude is smaller than a preset amplitude value, namely a second threshold value, the system judges that the driver does not receive warning prompt, and at the moment, the system automatically takes the risk avoiding measures, such as automatic emergency braking and the like.

In a specific embodiment of the present disclosure, taking a corresponding risk avoidance measure according to the second difference value includes:

acquiring a second threshold value, wherein the second threshold value is a preset minimum value of the second difference value;

comparing the second threshold value with the second difference value, if the second difference value is smaller than the second threshold value, sending an emergency braking instruction to a braking system, and sending a warning light flashing instruction to a vehicle machine system;

and receiving a trigger state of the collision trigger, and if the trigger state is triggered, sending rescue information to a rescue center.

The method comprises the steps that the state of a driver in the current state is detected immediately after a warning prompt tone is sent by the system, the amplitude of the eye movement data change of the driver before and after the warning prompt tone is sent is detected, if the amplitude of the change is smaller than a preset amplitude value, namely a second threshold value, the system judges that the driver does not receive warning prompt, and at the moment, the system automatically takes the risk avoiding measures, such as automatic emergency braking and the like.

In a specific embodiment of the present disclosure, the calculating physiological indicator data according to the crisis triggering time and the monitoring data includes:

calling the crisis triggering time and the monitoring data;

intercepting first data to be detected from the monitoring data according to the crisis triggering time, wherein the first data to be detected is eye movement information and electrocardiogram information of the driver in a period of time before the crisis occurs;

and calculating to obtain the physiological index data according to the first to-be-detected data, wherein the first to-be-detected data comprises first eye movement monitoring data, first cardiac movement monitoring data and first monitoring duration, and the physiological index data comprises eye movement index data and electrocardiogram index data.

In a specific embodiment of the present disclosure, the calculating the physiological index data according to the first to-be-detected data includes:

acquiring a preset equipartition value, and calling the first eye movement monitoring data;

dividing the first monitoring duration into at least two first sub-monitoring durations according to the preset equal value;

respectively calling each first sub-eye movement monitoring data corresponding to each first sub-monitoring duration from the first eye movement monitoring data according to each first sub-monitoring duration;

calculating to obtain sub-eye movement index data corresponding to each first sub-eye movement monitoring data according to each first sub-eye movement monitoring data;

and calculating to obtain the first eye movement monitoring data according to at least two sub-eye movement index data.

In a specific embodiment of the present disclosure, the calculating the physiological index data according to the first to-be-detected data further includes:

retrieving the first cardiac monitoring data;

calculating R-R interval index data according to the first cardiac monitoring data, wherein the R-R interval index data comprise an R-R interval average value, an R-R interval standard deviation, a frequency that an adjacent R-R interval difference value is larger than 50ms and a percentage that the adjacent R-R interval difference value is larger than 50 ms;

and calculating to obtain energy data according to the first cardiac monitoring data, wherein the energy data comprise low-frequency signal energy of 0.04-0.15 Hz, high-frequency signal energy of 0.15-0.40 Hz and a low-frequency high-frequency ratio, and the electrocardiogram index data comprise R-R interval data and energy data.

In a specific embodiment of the present disclosure, the calculating R-R interval indicator data according to the first cardiac monitoring data includes:

retrieving the first cardiac monitoring data;

sequentially filtering, electromyographic signal removal, power frequency signal removal and correction processing are carried out on the first cardiac monitoring data to obtain processed first cardiac monitoring data;

sequentially detecting the processed first cardiac monitoring data by an interval spectrum method and a difference method, and screening out R-R interval data;

calculating the average R-R interval, standard deviation of R-R intervals, frequency of adjacent R-R interval difference values greater than 50ms, and percentage of adjacent R-R interval difference values greater than 50ms from the R-R interval data.

In a specific embodiment of the present disclosure, the calculating energy data according to the first cardiac monitoring data includes:

retrieving the first cardiac monitoring data;

converting the first cardiac monitoring data from a time domain to a frequency domain through a fast Fourier algorithm, and obtaining corresponding frequency domain data;

and calculating the low-frequency signal energy of 0.04-0.15 Hz, the high-frequency signal energy of 0.15-0.40 Hz and the low-frequency high-frequency ratio according to the frequency domain data.

In a specific embodiment of the present disclosure, after the calculating the predicted reaction duration, the method further includes:

acquiring emergency measure implementation time, wherein the emergency measure implementation time is the moment when the driver starts to take the corresponding measures;

calculating actual reaction duration according to the emergency measure implementation time and the crisis triggering time, wherein the actual reaction duration is duration from crisis occurrence to countermeasure taking of the driver;

and calculating to obtain the average absolute error and the root mean square error corresponding to the evaluation model according to the actual reaction time length and the predicted reaction time length.

Example 2

As shown in fig. 2 to 4, the present embodiment provides a driver alertness evaluation system including:

the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring crisis triggering time and monitoring data, the crisis triggering time is the moment when a crisis starts to occur, and the monitoring data is eye movement information and electrocardiogram information of a driver during driving;

the first calculation module is used for calculating physiological index data according to the crisis triggering time and the monitoring data, wherein the physiological index data is information reflecting the concentration degree of the attention of the driver;

and the second calculation module is used for constructing an evaluation model, substituting the physiological index data into the evaluation model, and calculating to obtain a predicted reaction duration, wherein the predicted reaction duration is estimated from the occurrence of a crisis to the time for the driver to take a countermeasure.

Preferably, the second calculation module includes:

the first acquisition unit is used for acquiring the current vehicle speed per hour;

the first calculation unit is used for calculating and obtaining the crisis handling time length according to the current vehicle speed, wherein the crisis handling time length is the time length required by a driver for handling the crisis according to the current vehicle speed;

and the second calculation unit is used for comparing the crisis processing time length with the predicted reaction time length, and if the crisis processing time length is greater than or equal to the predicted reaction time length, sending a warning instruction to a warning device, wherein the warning instruction is used for enabling the warning device to send out a warning prompt tone.

Preferably, the second calculation unit includes:

the second acquisition unit is used for acquiring eye movement data in the current unit time period and calling the monitoring data, and the monitoring data comprises first time period eye movement data;

the third calculating unit is used for calculating to obtain a first state value according to the first period eye movement data;

the fourth calculation unit is used for calculating to obtain a current eye movement state value according to the eye movement data in the current unit time period;

and the fifth calculating unit is used for calculating to obtain a first difference value according to the first state value and the current eye movement state value, and the difference value reflects the amplitude of the change of the eye movement information before and after the driver hears the warning prompt tone.

And the sixth calculating unit is used for taking corresponding risk avoiding measures according to the first difference value.

Preferably, the sixth calculation unit includes:

a seventh calculating unit, configured to obtain a first threshold, where the first threshold is a preset minimum value of the first difference value;

and the eighth calculating unit is used for comparing the first threshold value with the first difference value, and if the first difference value is smaller than the first threshold value, sending an emergency braking instruction to a braking system and sending a warning lamp flashing instruction to the vehicle machine system.

Preferably, the second computing unit further includes:

the third acquisition unit is used for acquiring heartbeat data in the current unit time period and calling the monitoring data, wherein the monitoring data comprises first time period heartbeat data;

the ninth calculating unit is used for calculating to obtain a second state value according to the first period heartbeat data;

a tenth calculating unit, configured to calculate a current cardiac state value according to the heartbeat data in the current unit time period;

and the eleventh calculating unit is used for calculating a second difference value according to the second state value and the current cardiac state value, wherein the second difference value reflects the amplitude of the change of the heartbeat information before and after the driver hears the warning prompt tone.

And the twelfth calculating unit is used for taking corresponding risk avoiding measures according to the second difference value.

Preferably, the twelfth calculation unit includes:

a fourth obtaining unit, configured to obtain a second threshold, where the second threshold is a preset minimum value of the second difference value;

the thirteenth calculating unit is used for comparing the second threshold value with the second difference value, and if the second difference value is smaller than the second threshold value, sending an emergency braking instruction to a braking system and sending a warning lamp flashing instruction to the vehicle machine system;

the first receiving unit is used for receiving the trigger state of the collision trigger, and if the trigger state is triggered, the first receiving unit sends rescue information to the rescue center.

Preferably, the first calculation module includes:

the first calling unit is used for calling the crisis triggering time and the monitoring data;

a fourteenth calculating unit, configured to intercept, according to the crisis triggering time, first to-be-detected data from the monitored data, where the first to-be-detected data is eye movement information and electrocardiogram information of the driver in a period of time before a crisis occurs;

and a fifteenth calculating unit, configured to calculate to obtain the physiological indicator data according to the first to-be-detected data, where the first to-be-detected data includes first eye movement monitoring data, first cardiac movement monitoring data, and a first monitoring duration, and the physiological indicator data includes eye movement indicator data and electrocardiogram indicator data.

Preferably, the fifteenth calculation unit includes:

a fifth obtaining unit, configured to obtain a preset equipartition value, and call the first eye movement monitoring data;

a sixteenth calculating unit, configured to divide the first monitoring duration into at least two first sub-monitoring durations according to the preset equal-score value;

a seventeenth calculating unit, configured to respectively call each first sub-eye movement monitoring data corresponding to each first sub-monitoring duration from the first eye movement monitoring data according to each first sub-monitoring duration;

an eighteenth calculating unit, configured to calculate, according to each of the first sub-eye movement monitoring data, to obtain each sub-eye movement index data corresponding to the first sub-eye movement monitoring data;

and a nineteenth calculating unit, configured to calculate to obtain the first eye movement monitoring data according to at least two sub-eye movement index data.

Preferably, the fifteenth calculation unit further includes:

the second calling unit is used for calling the first cardiac monitoring data;

a twentieth calculating unit, configured to calculate R-R interval indicator data according to the first cardiac monitoring data, where the R-R interval indicator data includes an R-R interval average value, an R-R interval standard deviation, a frequency that an adjacent R-R interval difference value is greater than 50ms, and a percentage that an adjacent R-R interval difference value is greater than 50 ms;

and the twenty-first calculating unit is used for calculating to obtain energy data according to the first cardiac monitoring data, wherein the energy data comprise low-frequency signal energy of 0.04-0.15 Hz, high-frequency signal energy of 0.15-0.40 Hz and a low-frequency high-frequency ratio, and the electrocardiogram index data comprise R-R interval data and energy data.

In a third aspect, embodiments of the present application provide a driver alertness assessment device, which includes a memory and a processor. The memory is used for storing a computer program; the processor is adapted to carry out the steps of the above-described driver alertness assessment method when executing the computer program.

In a fourth aspect, the present application provides a readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the above-mentioned driver alertness assessment method.

Example 3

Corresponding to the above method embodiments, the disclosed embodiments also provide a driver alertness assessment device, and a driver alertness assessment device described below and a driver alertness assessment method described above may be referred to with respect to each other.

Fig. 5 is a block diagram illustrating a driver alertness assessment device 800 according to an exemplary embodiment. As shown in fig. 5, the electronic device 800 may include: a processor 801, a memory 802. The electronic device 800 may also include one or more of a multimedia component 803, an input/output (I/O) interface 804, and a communications component 805.

The processor 801 is configured to control the overall operation of the electronic device 800, so as to complete all or part of the steps of the above-described method for assessing the alertness of the driver. The memory 802 is used to store various types of data to support operation at the electronic device 800, such as instructions for any application or method operating on the electronic device 800 and application-related data, such as contact data, transmitted and received messages, pictures, audio, video, and so forth. The Memory 802 may be implemented by any type of volatile or non-volatile Memory device or combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read-Only Memory (EPROM), Programmable Read-Only Memory (PROM), Read-Only Memory (ROM), magnetic Memory, flash Memory, magnetic disk or optical disk. The multimedia components 803 may include screen and audio components. Wherein the screen may be, for example, a touch screen and the audio component is used for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may further be stored in the memory 802 or transmitted through the communication component 805. The audio assembly also includes at least one speaker for outputting audio signals. The I/O interface 804 provides an interface between the processor 801 and other interface modules, such as a keyboard, mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the electronic device 800 and other devices. Wireless communication, such as Wi-Fi, bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination of one or more of them, so that the corresponding communication component 805 may include: Wi-Fi module, bluetooth module, NFC module.

In an exemplary embodiment, the electronic Device 800 may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components for performing the driver alertness assessment method described above.

In another exemplary embodiment, there is also provided a computer-readable storage medium including program instructions which, when executed by a processor, implement the steps of the above-described driver alertness assessment method. For example, the computer readable storage medium may be the memory 802 described above including program instructions that are executable by the processor 801 of the electronic device 800 to perform the driver alertness assessment method described above.

Example 4

Corresponding to the above method embodiment, the disclosed embodiment also provides a readable storage medium, and a readable storage medium described below and a driver alertness assessment method described above can be correspondingly referred to each other.

A readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the driver alertness assessment method of the above-mentioned method embodiment.

The readable storage medium may be a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and various other readable storage media capable of storing program codes.

The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (10)

1. A driver alertness assessment method, comprising:

acquiring crisis triggering time and monitoring data, wherein the crisis triggering time is the moment when a crisis starts to occur, and the monitoring data is eye movement information and electrocardiogram information of a driver during driving;

calculating physiological index data according to the crisis triggering time and the monitoring data, wherein the physiological index data is information reflecting the concentration degree of the attention of the driver;

and constructing an evaluation model, bringing the physiological index data into the evaluation model, and calculating to obtain a predicted reaction duration, wherein the predicted reaction duration is the estimated duration from the occurrence of the crisis to the response action of the driver.

2. The driver alertness assessment method according to claim 1, wherein said calculating a predicted reaction duration further comprises:

acquiring the current vehicle speed per hour;

calculating to obtain crisis processing duration according to the current vehicle speed per hour, wherein the crisis processing duration is duration required by a driver for processing crisis according to the current vehicle speed;

and comparing the crisis processing time length with the predicted reaction time length, and if the crisis processing time length is greater than or equal to the predicted reaction time length, sending a warning instruction to a warning device, wherein the warning instruction is an instruction for enabling the warning device to send out a warning prompt tone.

3. The method for assessing the alertness of a driver according to claim 2, wherein after sending a warning instruction to a warning device if the crisis handling duration is greater than or equal to the predicted reaction duration, the method further comprises:

acquiring eye movement data in a current unit time period, and calling the monitoring data, wherein the monitoring data comprises first time period eye movement data;

calculating to obtain a first state value according to the first period eye movement data;

calculating to obtain a current eye movement state value according to the eye movement data in the current unit time period;

calculating to obtain a first difference value according to the first state value and the current eye movement state value, wherein the difference value reflects the change amplitude of eye movement information before and after the driver hears the warning prompt tone;

and taking corresponding risk avoidance measures according to the first difference value.

4. The method for assessing the alertness of a driver according to claim 3, wherein taking corresponding risk avoidance measures according to the first difference value comprises:

acquiring a first threshold value, wherein the first threshold value is the minimum value of the preset first difference values;

and comparing the first threshold value with the first difference value, if the first difference value is smaller than the first threshold value, sending an emergency braking instruction to a braking system, and sending a warning light flashing instruction to a vehicle machine system.

5. The method for assessing the alertness of a driver according to claim 2, wherein after sending a warning instruction to a warning device if the crisis handling duration is greater than or equal to the predicted reaction duration, the method further comprises:

acquiring heartbeat data in a current unit time period, and calling the monitoring data, wherein the monitoring data comprises first time period heartbeat data;

calculating to obtain a second state value according to the first period heartbeat data;

calculating to obtain a current cardiac state value according to the heartbeat data in the current unit time period;

and calculating to obtain a second difference value according to the second state value and the current cardiac state value, wherein the second difference value reflects the amplitude of the change of the heartbeat information before and after the driver hears the warning prompt tone.

And taking corresponding risk avoidance measures according to the second difference value.

6. The method for assessing the alertness of a driver according to claim 5, wherein taking corresponding risk avoidance measures according to the second difference value comprises:

acquiring a second threshold value, wherein the second threshold value is a preset minimum value of the second difference value;

comparing the second threshold value with the second difference value, if the second difference value is smaller than the second threshold value, sending an emergency braking instruction to a braking system, and sending a warning light flashing instruction to a vehicle machine system;

and receiving a trigger state of the collision trigger, and if the trigger state is triggered, sending rescue information to a rescue center.

7. The method for assessing the alertness of a driver according to claim 1, wherein the calculating physiological index data from the crisis triggering time and the monitoring data comprises:

calling the crisis triggering time and the monitoring data;

intercepting first data to be detected from the monitoring data according to the crisis triggering time, wherein the first data to be detected is eye movement information and electrocardiogram information of the driver in a period of time before the crisis occurs;

and calculating to obtain the physiological index data according to the first to-be-detected data, wherein the first to-be-detected data comprises first eye movement monitoring data, first cardiac movement monitoring data and first monitoring duration, and the physiological index data comprises eye movement index data and electrocardiogram index data.

8. The method for assessing the alertness of a driver according to claim 7, wherein the calculating the physiological index data based on the first data to be detected includes:

acquiring a preset equipartition value, and calling the first eye movement monitoring data;

dividing the first monitoring duration into at least two first sub-monitoring durations according to the preset equal value;

respectively calling each first sub-eye movement monitoring data corresponding to each first sub-monitoring duration from the first eye movement monitoring data according to each first sub-monitoring duration;

calculating to obtain sub-eye movement index data corresponding to each first sub-eye movement monitoring data according to each first sub-eye movement monitoring data;

and calculating to obtain the first eye movement monitoring data according to at least two sub-eye movement index data.

9. The method for assessing the alertness of a driver according to claim 7, wherein the calculating of the physiological index data from the first data to be detected further comprises:

retrieving the first cardiac monitoring data;

calculating R-R interval index data according to the first cardiac monitoring data, wherein the R-R interval index data comprise an R-R interval average value, an R-R interval standard deviation, a frequency that an adjacent R-R interval difference value is larger than 50ms and a percentage that the adjacent R-R interval difference value is larger than 50 ms;

and calculating to obtain energy data according to the first cardiac monitoring data, wherein the energy data comprise low-frequency signal energy of 0.04-0.15 Hz, high-frequency signal energy of 0.15-0.40 Hz and a low-frequency high-frequency ratio, and the electrocardiogram index data comprise R-R interval data and energy data.

10. A driver alertness assessment system, comprising:

the system comprises an acquisition module, a display module and a display module, wherein the acquisition module is used for acquiring crisis triggering time and monitoring data, the crisis triggering time is the moment when a crisis starts to occur, and the monitoring data is eye movement information and electrocardiogram information of a driver during driving;

the first calculation module is used for calculating physiological index data according to the crisis triggering time and the monitoring data, wherein the physiological index data is information reflecting the concentration degree of the attention of the driver;

and the second calculation module is used for constructing an evaluation model, substituting the physiological index data into the evaluation model, and calculating to obtain a predicted reaction duration, wherein the predicted reaction duration is estimated from the occurrence of a crisis to the time for the driver to take a countermeasure.

Images