CN115089182B - Multi-dimensional driver risk perception capability assessment method - Google Patents

Multi-dimensional driver risk perception capability assessment method Download PDF

Info

Publication number
CN115089182B
CN115089182B CN202210562485.8A CN202210562485A CN115089182B CN 115089182 B CN115089182 B CN 115089182B CN 202210562485 A CN202210562485 A CN 202210562485A CN 115089182 B CN115089182 B CN 115089182B
Authority
CN
China
Prior art keywords
driver
risk
equal
less
drivers
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202210562485.8A
Other languages
Chinese (zh)
Other versions
CN115089182A (en
Inventor
张增志
张泽凡
孟楷原
朱彤
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Changan University
Original Assignee
Changan University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Changan University filed Critical Changan University
Priority to CN202210562485.8A priority Critical patent/CN115089182B/en
Publication of CN115089182A publication Critical patent/CN115089182A/en
Application granted granted Critical
Publication of CN115089182B publication Critical patent/CN115089182B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
    • A61B5/18—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state for vehicle drivers or machine operators
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B3/00—Apparatus for testing the eyes; Instruments for examining the eyes
    • A61B3/10—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions
    • A61B3/11—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions for measuring interpupillary distance or diameter of pupils
    • A61B3/112—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions for measuring interpupillary distance or diameter of pupils for measuring diameter of pupils
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B3/00—Apparatus for testing the eyes; Instruments for examining the eyes
    • A61B3/10—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions
    • A61B3/113—Objective types, i.e. instruments for examining the eyes independent of the patients' perceptions or reactions for determining or recording eye movement
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B3/00—Apparatus for testing the eyes; Instruments for examining the eyes
    • A61B3/18—Arrangement of plural eye-testing or -examining apparatus
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
    • A61B5/163—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state by tracking eye movement, gaze, or pupil change
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/15—Correlation function computation including computation of convolution operations
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/021—Measuring pressure in heart or blood vessels
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Abstract

The invention relates to the technical field of traffic safety, in particular to a method for evaluating risk perception capability of a multi-dimensional driver. According to the invention, the risk perception capability of the driver is evaluated by adopting a driving simulation technology, the data are analyzed and processed, and the risk perception capability of the driver is quantitatively checked, so that the method is more objective and effective; according to the quantized score of the driver, the driving safety quality of the driver can be improved in a targeted manner, the driving capacity of the driver is improved, and the occurrence rate of road traffic safety accidents is further reduced.

Description

Multi-dimensional driver risk perception capability assessment method
Technical Field
The invention relates to the technical field of traffic safety, in particular to a method for evaluating risk perception capability of a multi-dimensional driver.
Background
Along with the continuous improvement of the occurrence rate of road traffic accidents, great loss is brought to the development of economy and society, and the evaluation method of the risk perception awareness of the driver based on the risk perception information of the driver, the physiological parameter change information and the vehicle operation information becomes a focus of social attention for improving the risk perception capability and the safety driving awareness of the driver. The assessment method of the risk perception awareness of the driver essentially takes the driver as a center, collects the perception awareness of the driver on the danger which is about to occur, the change of physiological parameters in the driving simulation operation process of the driver and the driving simulation operation information of the driver, and refers to a preset quantization standard and score weights of all parts in a quantization mode to obtain the risk perception ability score of the driver as the basis of whether the driver can drive the vehicle.
The related detection technology comprises a physiological characteristic detection technology, a video production technology and an automobile simulation driver. Various techniques have advantages, but certain limitations exist. The physiological characteristic detection technology is a relatively mature technology, has higher detection accuracy on parameters such as blood pressure, heart rate, brain waves and the like, and can have certain influence on driving operation of a driver. The video production technology is a technology which is relatively easy to operate, and can be randomly inserted into the potential safety hazard of the road, but the accuracy of judging the risk scene is lower. The automobile simulated driving device is advanced simulated driving test equipment, but compared with a real driving environment, the simulated driving device can weaken the influence of driving risks on physiological characteristics of a driver. Therefore, in order to improve the practicability of the risk awareness assessment of the driver, the risk perception capability of the driver is accurately expressed, the weights of the three test parts should be reasonably determined, and the credibility of the risk perception capability score is improved.
The research on traffic safety in China starts later, the safety driving simulation scene and corresponding research data are lacking, the risk assessment system is relatively imperfect, and the development of the national traffic safety test system is limited by the high cost of introducing the key technology of the foreign traffic safety test system.
Disclosure of Invention
Aiming at the problems in the prior art, the invention aims to provide a multi-dimensional assessment method for risk perception capability of a driver.
In order to achieve the above purpose, the present invention is realized by the following technical scheme.
A method of evaluating risk awareness of a multi-dimensional driver, comprising the steps of:
step 1, establishing a driver risk perception capability assessment model;
step 2, obtaining the total score of the driver to be evaluated on the driver risk perception capability evaluation model;
and 3, evaluating the risk perception capability of the driver to be evaluated according to the score of the driver.
Compared with the prior art, the invention has the beneficial effects that: the risk perception capability of the driver is evaluated by adopting a driving simulation technology, the data are analyzed and processed, and the risk perception capability of the driver is quantitatively checked, so that the method is more objective and effective; according to the quantized score of the driver, the driving safety quality of the driver can be improved in a targeted manner, the driving capacity of the driver is improved, and the occurrence rate of road traffic safety accidents is further reduced.
Drawings
The invention will now be described in further detail with reference to the drawings and to specific examples.
FIG. 1 is a flow chart of a method for evaluating risk awareness of a multi-dimensional driver according to the present invention.
Detailed Description
Embodiments of the present invention will be described in detail below with reference to examples, but it will be understood by those skilled in the art that the following examples are only for illustrating the present invention and should not be construed as limiting the scope of the present invention.
A method of evaluating risk awareness of a multi-dimensional driver, comprising the steps of:
step 1, establishing a driver risk perception capability assessment model;
sub-step 1.1, establishing a video detection score model;
specifically, the driver is enabled to watch n videos of normal driving road scenes, wherein the videos are inserted with the mark frames at the dangerous time, and the perception frames are inserted at the dangerous time perceived in the watching process;
establishing a video detection score model:
Figure GDA0004154966370000031
where x represents the number of logo frames in each video and y represents the number of perceived frames that the driver inserts in each video.
Sub-step 1.2, establishing a physiological parameter score model;
sub-step 1.21, enabling N drivers to use a vehicle simulation driving device to perform normal driving with M risk points added at a time; collecting heart rate, blood pressure and pupil diameter of N drivers in the driving process, and eyeball saccade amplitude and fixation duration of N drivers at each risk point by using a physiological recorder;
sub-step 1.22, establishing a heart rate score model;
first, a heart rate data matrix HR of each driver at each risk point is recorded ij ：
Figure GDA0004154966370000032
wherein ,hrNM Heart rate for nth driver at mth risk point; i is the number of the driver, i is more than or equal to 1 and less than or equal to N, and i is E Z; j is the number of the risk point, j is more than or equal to 1 and less than or equal to M, and j is less than or equal to Z;
second, calculate the average of the heart rate of each driver at all risk points
Figure GDA0004154966370000034
Figure GDA0004154966370000033
Again, the average μ of all drivers' heart rates at risk points is calculated hr And the variance sigma of heart rate of all drivers at risk points hr 2 ：
Figure GDA0004154966370000041
Figure GDA0004154966370000042
Finally, a heart rate score model is established:
Figure GDA0004154966370000043
wherein ,
Figure GDA0004154966370000044
mean heart rate of the driver at all risk points;
sub-step 1.23, establishing a blood pressure score model;
first, a blood pressure data matrix K of each driver at each risk point is recorded ij ：
Figure GDA0004154966370000045
wherein ,KNM Blood pressure at the mth risk point for the nth driver; i is the number of the driver, i is more than or equal to 1 and less than or equal to N, and i is E Z; j is the number of the risk point, j is more than or equal to 1 and less than or equal to M, and j is less than or equal to Z;
second, calculate the average of blood pressure for each driver at all risk points
Figure GDA0004154966370000046
Figure GDA0004154966370000047
Again, the average μ of the blood pressure of all drivers at the risk point is calculated k And the blood pressure variance sigma of all drivers at risk points k 2 ：
Figure GDA0004154966370000051
Figure GDA0004154966370000052
Finally, a blood pressure score model is established:
Figure GDA0004154966370000053
/>
wherein ,
Figure GDA0004154966370000054
mean blood pressure of the driver at all risk points;
sub-step 1.24, building an eye movement score model, the sub-steps are as follows:
a substep a, establishing an eyeball glance amplitude score model;
first, an eye saccade amplitude data matrix D for each driver at each risk point is recorded ij ：
Figure GDA0004154966370000055
wherein ,DNM The eyeball saccade amplitude of the nth driver at the Mth risk point; i is the number of the driver, i is more than or equal to 1 and less than or equal to N, and i is E Z; j is the number of the risk point, j is more than or equal to 1 and less than or equal to M, and j is less than or equal to Z;
second, calculate the mean value of the saccade amplitude for each driver at all risk points
Figure GDA0004154966370000056
Figure GDA0004154966370000057
Again, the average value μ of the saccade amplitudes of all drivers at the risk point is calculated D And the saccade amplitude variance sigma of all drivers at risk points D 2 :
Figure GDA0004154966370000058
Figure GDA0004154966370000061
Finally, establishing an eyeball saccade amplitude score model:
Figure GDA0004154966370000062
wherein ,
Figure GDA0004154966370000067
mean value of eyeball saccade amplitude of the driver at all risk points;
substep b, gazing at a duration score model;
first, a matrix T of data of duration of gaze of each driver at each risk point is recorded ij ：
Figure GDA0004154966370000063
wherein ,TNM For the duration of gaze of the nth driver at the mth risk point; i is the number of the driver, i is more than or equal to 1 and less than or equal to N, and i is E Z; j is the number of the risk point, j is more than or equal to 1 and less than or equal to M, and j is less than or equal to Z;
second, calculate the average of the gaze duration of each driver at all risk points
Figure GDA0004154966370000068
/>
Figure GDA0004154966370000064
Again, the average μ of the gaze durations of all drivers at the risk points is calculated T And the variance sigma of the duration of gaze of all drivers at the risk point T 2 ：
Figure GDA0004154966370000065
Figure GDA0004154966370000066
Finally, a gaze duration score model is established:
Figure GDA0004154966370000071
wherein ,
Figure GDA0004154966370000077
mean value of the duration of gaze of the driver at all risk points;
substep c, pupil diameter variability score model;
first, the average value of the pupil diameters of each driver during the whole driving process is calculated
Figure GDA0004154966370000078
And recording a pupil diameter data matrix z of each driver at each risk point ij ：
Figure GDA0004154966370000072
wherein ,zNM Pupil diameter for the nth driver at the mth risk point; i is the number of the driver, i is more than or equal to 1 and less than or equal to N, and i is E Z; j is the number of the risk point, j is more than or equal to 1 and less than or equal to M, and j is less than or equal to Z;
second, according to the average value of pupil diameters
Figure GDA0004154966370000079
And pupil diameter data matrix z ij Obtaining a pupil diameter variability data matrix I ij ：
Figure GDA0004154966370000073
Wherein, pupil diameter variability of the Nth driver at the Mth risk point
Figure GDA0004154966370000074
Again, calculate each driveMean value of pupil diameter variability of driver at all risk points
Figure GDA0004154966370000075
/>
Figure GDA0004154966370000076
From the times, the average value μ of pupil diameter variability at risk points for all drivers is calculated I And the pupil diameter variability variance sigma of all drivers at risk points I 2 ：
Figure GDA0004154966370000081
Figure GDA0004154966370000082
Finally, establishing a pupil diameter variability score model:
Figure GDA0004154966370000083
wherein ,
Figure GDA0004154966370000084
mean value of pupil diameter variability of the driver at all risk points;
step d, establishing an eye movement score model:
E y ＝0.3E D +0.3E T +0.4E I ；
and evaluating the saccade amplitude, the fixation duration and the pupil diameter variability by using an analytic hierarchy process to obtain the influence weights of the saccade amplitude, the fixation duration and the pupil diameter variability, wherein the influence weights are respectively 30% of the saccade amplitude, 30% of the fixation duration and 40% of the pupil diameter variability.
Sub-step 1.25, establishing a physiological parameter score model:
E p ＝0.3E hr +0.3E k +0.4E y ；
and (5) evaluating the heart rate, the blood pressure and the eye movement by using an analytic hierarchy process to obtain the influence weights of the heart rate, the blood pressure and the eye movement which are respectively 30% of the heart rate, 30% of the blood pressure and 40% of the eye movement.
Sub-step 1.3, establishing a vehicle operation score model;
sub-step 1.31, enabling N drivers to use a vehicle simulation driving device to perform normal driving with M risk points added for L (L > 10) times; the vehicle simulation driving device collects the acceleration, the speed, the steering wheel angle and the transverse acceleration of the vehicle at each risk point in each simulated driving of each driver;
sub-step 1.32, establishing an acceleration magnitude evaluation model;
first, record the acceleration data matrix of each driver at each risk point in L times of simulated driving
Figure GDA0004154966370000091
wherein ,/>
Figure GDA0004154966370000092
wherein />
Figure GDA0004154966370000093
Representing the acceleration magnitude of the vehicle of the nth driver at the mth risk point in the qth simulated driving; i is the number of the driver, i is more than or equal to 1 and less than or equal to N, and i is E Z; j is the number of the risk point, j is more than or equal to 1 and less than or equal to M, and j is less than or equal to Z; q is the number of simulated driving, q is more than or equal to 1 and less than or equal to L, and q is E Z;
second, in the q-th simulated driving, the average value of the acceleration magnitudes of the vehicle at all risk points for each driver is calculated
Figure GDA0004154966370000094
Figure GDA0004154966370000095
Again, in the q-th simulated driving, the average value of the acceleration magnitudes of the vehicles at the risk points of all the drivers is calculated
Figure GDA0004154966370000096
And the acceleration magnitude variance of the vehicles of all drivers at the risk point +.>
Figure GDA0004154966370000097
Figure GDA0004154966370000098
Figure GDA0004154966370000099
From the times, the average value mu of the acceleration magnitudes of the vehicles of all drivers at the risk points under the L times of simulated driving is calculated a And the acceleration magnitude variance (σ) of the vehicles of all drivers at the risk points a ) 2 ；
Finally, an acceleration evaluation model is established:
Figure GDA00041549663700000910
wherein ,
Figure GDA0004154966370000101
an average value of acceleration magnitudes for the driver at all risk points in 1 simulated driving;
sub-step 1.33, establishing a speed evaluation model;
first, record the speed data matrix of each driver at each risk point in L times of simulated driving
Figure GDA0004154966370000102
wherein ,/>
Figure GDA0004154966370000103
wherein />
Figure GDA0004154966370000104
Representing the speed of the vehicle of the nth driver at the mth risk point in the qth simulated driving; i is the number of the driver, i is more than or equal to 1 and less than or equal to N, and i is E Z; j is the number of the risk point, j is more than or equal to 1 and less than or equal to M, and j is less than or equal to Z; q is the number of simulated driving, q is more than or equal to 1 and less than or equal to L, and q is E Z;
second, in the q-th simulated driving, the average value of the speed of the vehicle at all risk points for each driver is calculated
Figure GDA0004154966370000105
Figure GDA0004154966370000106
Again, in the q-th simulated driving, the average value of the speed magnitudes of the vehicles at the risk points for all the drivers is calculated
Figure GDA0004154966370000107
And speed size variance of vehicles of all drivers at risk point +.>
Figure GDA0004154966370000108
/>
Figure GDA0004154966370000109
Figure GDA00041549663700001010
From the times, calculating the average value mu of the speed of the vehicles of all drivers at risk points under L times of simulated driving v And the speed magnitude variance (σ) of the vehicles of all drivers at the risk points v ) 2 ；
Finally, establishing a speed evaluation model:
Figure GDA0004154966370000111
wherein ,
Figure GDA0004154966370000112
a speed magnitude average for the driver at all risk points in 1 simulated driving;
sub-step 1.34, establishing a steering wheel angle evaluation model;
first, an angle data matrix of each driver in each risk point, which deviates from the straight direction, is recorded in L times of simulated driving
Figure GDA0004154966370000113
wherein ,/>
Figure GDA0004154966370000114
wherein />
Figure GDA0004154966370000115
Representing the steering wheel angle of the vehicle of the nth driver at the mth risk point in the q-th simulated driving; i is the number of the driver, i is more than or equal to 1 and less than or equal to N, and i is E Z; j is the number of the risk point, j is more than or equal to 1 and less than or equal to M, and j is less than or equal to Z; q is the number of simulated driving, q is more than or equal to 1 and less than or equal to L, and q is E Z;
second, in the q-th simulated driving, the average value of the steering wheel angle magnitudes of the vehicles at all risk points for each driver is calculated
Figure GDA0004154966370000116
Figure GDA0004154966370000117
Again, in the q-th simulated driving, the average value of the steering wheel angle magnitudes of the vehicles of all the drivers at the risk points is calculated
Figure GDA0004154966370000118
And steering wheel angle magnitude variance +/of all drivers' vehicles at risk point>
Figure GDA0004154966370000119
Figure GDA00041549663700001110
Figure GDA00041549663700001111
From the times, the average value mu of the steering wheel angles of the vehicles of all drivers at risk points under L times of simulated driving is calculated θ And the steering wheel angle magnitude variance (σ) of vehicles of all drivers at risk points θ ) 2 ；
Finally, a steering wheel angle evaluation model is established:
Figure GDA0004154966370000121
wherein ,
Figure GDA0004154966370000122
the average of the steering wheel angle magnitudes for the driver at all risk points in 1 simulated driving;
sub-step 1.35, establishing a lateral acceleration evaluation model;
first, the data matrix of the lateral acceleration of each driver at each risk point is recorded in L times of simulated driving
Figure GDA0004154966370000123
wherein ,/>
Figure GDA0004154966370000124
wherein />
Figure GDA0004154966370000125
Representing the magnitude of the lateral acceleration of the vehicle of the nth driver at the mth risk point in the qth simulated driving; i is the number of the driver, i is more than or equal to 1 and less than or equal to N, and i is E Z; j is the number of the risk point, j is more than or equal to 1 and less than or equal to M, and j is less than or equal to Z; q is the number of simulated driving, q is more than or equal to 1 and less than or equal to L, and q is E Z;
second, in the q-th simulated driving, the average value of the lateral acceleration of the vehicle at all risk points of each driver is calculated
Figure GDA0004154966370000126
Figure GDA0004154966370000127
Again, in the q-th simulated driving, the average value of the lateral acceleration magnitudes of the vehicles at the risk points of all the drivers is calculated
Figure GDA0004154966370000128
And the lateral acceleration magnitude variance of the vehicle of all drivers at the risk point +.>
Figure GDA0004154966370000129
Figure GDA00041549663700001210
Figure GDA00041549663700001211
From the times, the average value mu of the lateral acceleration of the vehicle at the risk point of all drivers under the L times of simulated driving is calculated b And the acceleration magnitude variance (σ) of the vehicles of all drivers at the risk points b ) 2 ；
Finally, establishing a transverse acceleration evaluation model:
Figure GDA0004154966370000131
wherein ,
Figure GDA0004154966370000133
the average value of the lateral acceleration of the driver at all risk points in 1 simulated driving; />
Sub-step 1.36, building a vehicle operation score model;
Figure GDA0004154966370000132
wherein ,rx1 Indicating the number of times the xth evaluation index is evaluated as "excellent", r x2 Indicates the number of times the xth evaluation index is evaluated as "good", r x3 Indicating the number of times the xth evaluation index is evaluated as "general", r x4 Indicating the number of times the xth evaluation index is evaluated as "poor"; wherein x=1, 2,3,4, x=1 represents the 1 st evaluation index as the acceleration magnitude, x=2 represents the 2 nd evaluation index as the speed magnitude, x=3 represents the 3 rd evaluation index as the steering wheel angle magnitude, x=4 represents the 4 th evaluation index as the lateral acceleration magnitude; r is R x The weight of the xth evaluation index is represented, and each evaluation index is evaluated by using a analytic hierarchy process to obtain R 1 ＝0.2，R 2 ＝0.3，R 3 ＝0.25，R 4 ＝0.25；
Sub-step 1.4, establishing a driver risk perception capability assessment model:
M total ＝(0.2Q 1 +0.4E p +0.4B)×100
and evaluating the video detection, the physiological parameters and the vehicle operation by using an analytic hierarchy process to obtain the influence weights of the video detection, the physiological parameters and the vehicle operation, wherein the influence weights are respectively 20% of the video detection, 40% of the physiological parameters and 40% of the vehicle operation.
Step 2, obtaining the total score of the driver to be evaluated on the driver risk perception capability evaluation model;
step 2.1, enabling a driver to be evaluated to watch n videos of normal driving road scenes inserted with the mark frames at the time when danger possibly occurs, and inserting the perception frames at the time when danger is perceived in the watching process; calculating to obtain video detection score Q of driver to be evaluated 1 ；
Step 2.2, enabling the driver to be evaluated to use a vehicle simulation driving device to perform normal driving with M risk points added at a time; collecting pupil diameters of a driver to be evaluated in the driving process, and heart rate, blood pressure, eyeball saccade amplitude and fixation duration of the driver to be evaluated at each risk point by using a physiological recorder;
sub-step 2.3, calculating to obtain heart rate average value, blood pressure average value, saccade amplitude average value, fixation duration average value and pupil diameter variability average value of the driver to be evaluated at all risk points, and calculating to obtain physiological parameter score E p ；
Step 2.4, enabling the driver to be evaluated to use a vehicle simulation driving device to perform normal driving with M risk points added for L times; the vehicle simulation driving device collects the acceleration, the speed, the steering wheel rotation angle and the transverse acceleration of the vehicle at each risk point in each simulated driving of each driver;
2.5, calculating to obtain a vehicle operation score B of the driver to be evaluated;
substep 2.6, calculating a total risk perception capability score M of the driver to be evaluated total 。
And 3, evaluating the risk perception capability of the driver to be evaluated according to the score of the driver.
Specifically, when 0.ltoreq.M total < 60, indicating poor risk awareness for the driver; when 60 is less than or equal to M total < 80, indicating that the driver risk awareness is general; when 80 is less than or equal to M total Less than or equal to 100, which indicates that the risk perception capability of the driver is stronger.
While the invention has been described in detail in this specification with reference to the general description and the specific embodiments thereof, it will be apparent to one skilled in the art that modifications and improvements can be made thereto. Accordingly, such modifications or improvements may be made without departing from the spirit of the invention and are intended to be within the scope of the invention as claimed.

Claims (3)

1. A method for evaluating risk awareness of a multi-dimensional driver, comprising the steps of:
step 1, establishing a driver risk perception capability assessment model;
the substeps of step 1 are as follows:
sub-step 1.1, establishing a video detection score model;
enabling a driver to watch n videos of normal driving road scenes inserted with the mark frames at dangerous time points, and inserting the perception frames at dangerous time points in the watching process;
establishing a video detection score model:
Figure FDA0004154966360000011
wherein x represents the number of logo frames in each video, and y represents the number of perceived frames that the driver inserts in each video;
sub-step 1.2, establishing a physiological parameter score model;
the physiological parameter scoring model is established, and the substeps are as follows:
sub-step 1.21, enabling N drivers to use a vehicle simulation driving device to perform normal driving with M risk points added at a time; collecting heart rate, blood pressure and pupil diameter of N drivers in the driving process, and eyeball saccade amplitude and fixation duration of N drivers at each risk point by using a physiological recorder;
sub-step 1.22, establishing a heart rate score model;
first, a heart rate data matrix HR of each driver at each risk point is recorded ij ：
Figure FDA0004154966360000012
wherein ,hrNM Heart rate for nth driver at mth risk point; i is the number of the driver, i is more than or equal to 1 and less than or equal to N, and i is E Z; j is the number of the risk point, j is more than or equal to 1 and less than or equal to M, and j is less than or equal to Z;
second, calculate the average of the heart rate of each driver at all risk points
Figure FDA0004154966360000021
Figure FDA0004154966360000022
Again, the average μ of all drivers' heart rates at risk points is calculated hr And the variance sigma of heart rate of all drivers at risk points hr 2 ：
Figure FDA0004154966360000023
Figure FDA0004154966360000024
Finally, a heart rate score model is established:
Figure FDA0004154966360000025
wherein ,
Figure FDA0004154966360000026
mean heart rate of the driver at all risk points;
sub-step 1.23, establishing a blood pressure score model;
first, record each driver at eachBlood pressure data matrix K of individual risk points ij ：
Figure FDA0004154966360000027
wherein ,KNM Blood pressure at the mth risk point for the nth driver; i is the number of the driver, i is more than or equal to 1 and less than or equal to N, and i is E Z; j is the number of the risk point, j is more than or equal to 1 and less than or equal to M, and j is less than or equal to Z;
second, calculate the mean value K of the blood pressure of each driver at all risk points i ：
Figure FDA0004154966360000031
Again, the average μ of the blood pressure of all drivers at the risk point is calculated k And the blood pressure variance sigma of all drivers at risk points k 2 ：
Figure FDA0004154966360000032
Figure FDA0004154966360000033
Finally, a blood pressure score model is established:
Figure FDA0004154966360000034
wherein ,
Figure FDA0004154966360000035
mean blood pressure of the driver at all risk points;
sub-step 1.24, building an eye movement score model, the sub-steps are as follows:
a substep a, establishing an eyeball glance amplitude score model;
first, an eye saccade amplitude data matrix D for each driver at each risk point is recorded ij ：
Figure FDA0004154966360000036
/>
wherein ,DNM The eyeball saccade amplitude of the nth driver at the Mth risk point; i is the number of the driver, i is more than or equal to 1 and less than or equal to N, and i is E Z; j is the number of the risk point, j is more than or equal to 1 and less than or equal to M, and j is less than or equal to Z;
second, calculate the mean value of the saccade amplitude for each driver at all risk points
Figure FDA0004154966360000037
Figure FDA0004154966360000038
Again, the average value μ of the saccade amplitudes of all drivers at the risk point is calculated D And the saccade amplitude variance sigma of all drivers at risk points D 2 :
Figure FDA0004154966360000041
Figure FDA0004154966360000042
Finally, establishing an eyeball saccade amplitude score model:
Figure FDA0004154966360000043
wherein ,
Figure FDA0004154966360000044
mean value of eyeball saccade amplitude of the driver at all risk points;
substep b, gazing at a duration score model;
first, a matrix T of data of duration of gaze of each driver at each risk point is recorded ij ：
Figure FDA0004154966360000045
wherein ,TNM For the duration of gaze of the nth driver at the mth risk point; i is the number of the driver, i is more than or equal to 1 and less than or equal to N, and i is E Z; j is the number of the risk point, j is more than or equal to 1 and less than or equal to M, and j is less than or equal to Z;
second, calculate the average of the gaze duration of each driver at all risk points
Figure FDA0004154966360000046
Figure FDA0004154966360000047
Again, the average μ of the gaze durations of all drivers at the risk points is calculated T And the variance sigma of the duration of gaze of all drivers at the risk point T 2 ：
Figure FDA0004154966360000051
/>
Figure FDA0004154966360000052
Finally, a gaze duration score model is established:
Figure FDA0004154966360000053
wherein ,
Figure FDA0004154966360000054
mean value of the duration of gaze of the driver at all risk points;
substep c, pupil diameter variability score model;
first, the average value of the pupil diameters of each driver during the whole driving process is calculated
Figure FDA0004154966360000055
And recording a pupil diameter data matrix z of each driver at each risk point ij ：
Figure FDA0004154966360000056
wherein ,zNM Pupil diameter for the nth driver at the mth risk point; i is the number of the driver, i is more than or equal to 1 and less than or equal to N, and i is E Z; j is the number of the risk point, j is more than or equal to 1 and less than or equal to M, and j is less than or equal to Z;
second, according to the average value of pupil diameters
Figure FDA0004154966360000057
And pupil diameter data matrix z ij Obtaining a pupil diameter variability data matrix I ij ：
Figure FDA0004154966360000058
Wherein, pupil diameter variability of the Nth driver at the Mth risk point
Figure FDA0004154966360000059
Again, each driver is calculated at all risk pointsAverage value of pupil diameter variability
Figure FDA00041549663600000510
Figure FDA0004154966360000061
From the times, the average value μ of pupil diameter variability at risk points for all drivers is calculated I And the pupil diameter variability variance sigma of all drivers at risk points I 2 ：
Figure FDA0004154966360000062
/>
Figure FDA0004154966360000063
Finally, establishing a pupil diameter variability score model:
Figure FDA0004154966360000064
wherein ,
Figure FDA0004154966360000065
mean value of pupil diameter variability of the driver at all risk points;
step d, establishing an eye movement score model:
E y ＝0.3E D +0.3E T +0.4E I ；
sub-step 1.25, establishing a physiological parameter score model:
E p ＝0.3E hr +0.3E k +0.4E y ；
sub-step 1.3, establishing a vehicle operation score model;
the vehicle operation score model is established, and the substeps are as follows:
sub-step 1.31, enabling N drivers to use a vehicle simulation driving device to perform normal driving with M risk points added for L times, wherein L is more than 10; the vehicle simulation driving device collects the acceleration, the speed, the steering wheel angle and the transverse acceleration of the vehicle at each risk point in each simulated driving of each driver;
sub-step 1.32, establishing an acceleration magnitude evaluation model;
first, record the acceleration data matrix of each driver at each risk point in L times of simulated driving
Figure FDA0004154966360000071
wherein ,/>
Figure FDA0004154966360000072
wherein />
Figure FDA0004154966360000073
Representing the acceleration magnitude of the vehicle of the nth driver at the mth risk point in the qth simulated driving; i is the number of the driver, i is more than or equal to 1 and less than or equal to N, and i is E Z; j is the number of the risk point, j is more than or equal to 1 and less than or equal to M, and j is less than or equal to Z; q is the number of simulated driving, q is more than or equal to 1 and less than or equal to L, and q is E Z;
second, in the q-th simulated driving, the average value of the acceleration magnitudes of the vehicle at all risk points for each driver is calculated
Figure FDA0004154966360000074
Figure FDA0004154966360000075
Again, in the q-th simulated driving, the average value of the acceleration magnitudes of the vehicles at the risk points of all the drivers is calculated
Figure FDA0004154966360000076
And the acceleration magnitude variance of the vehicles of all drivers at the risk point +.>
Figure FDA0004154966360000077
Figure FDA0004154966360000078
/>
Figure FDA0004154966360000079
From the times, the average value mu of the acceleration magnitudes of the vehicles of all drivers at the risk points under the L times of simulated driving is calculated a And the acceleration magnitude variance (σ) of the vehicles of all drivers at the risk points a ) 2 ；
Finally, an acceleration evaluation model is established:
Figure FDA00041549663600000710
wherein ,
Figure FDA0004154966360000081
an average value of acceleration magnitudes for the driver at all risk points in 1 simulated driving;
sub-step 1.33, establishing a speed evaluation model;
first, record the speed data matrix of each driver at each risk point in L times of simulated driving
Figure FDA0004154966360000082
wherein ,/>
Figure FDA0004154966360000083
wherein />
Figure FDA0004154966360000084
Representing the speed of the vehicle of the nth driver at the mth risk point in the qth simulated driving; i is the number of the driver and,
i is more than or equal to 1 and less than or equal to N, i is less than or equal to Z; j is the number of the risk point, j is more than or equal to 1 and less than or equal to M, and j is less than or equal to Z; q is the number of simulated driving, q is more than or equal to 1 and less than or equal to L, and q is E Z;
second, in the q-th simulated driving, the average value of the speed of the vehicle at all risk points for each driver is calculated
Figure FDA0004154966360000085
Figure FDA0004154966360000086
Again, in the q-th simulated driving, the average value of the speed magnitudes of the vehicles at the risk points for all the drivers is calculated
Figure FDA0004154966360000087
And speed size variance of vehicles of all drivers at risk point +.>
Figure FDA0004154966360000088
Figure FDA0004154966360000089
Figure FDA00041549663600000810
From the times, calculating the average value mu of the speed of the vehicles of all drivers at risk points under L times of simulated driving v And the speed magnitude variance (σ) of the vehicles of all drivers at the risk points v ) 2 ；
Finally, establishing a speed evaluation model:
Figure FDA0004154966360000091
wherein ,
Figure FDA0004154966360000092
a speed magnitude average for the driver at all risk points in 1 simulated driving;
sub-step 1.34, establishing a steering wheel angle evaluation model;
first, an angle data matrix of each driver in each risk point, which deviates from the straight direction, is recorded in L times of simulated driving
Figure FDA0004154966360000093
wherein ,/>
Figure FDA0004154966360000094
wherein />
Figure FDA0004154966360000095
Representing the steering wheel angle of the vehicle of the nth driver at the mth risk point in the q-th simulated driving; i is the number of the driver, i is more than or equal to 1 and less than or equal to N, and i is E Z; j is the number of the risk point, j is more than or equal to 1 and less than or equal to M, and j is less than or equal to Z; q is the number of simulated driving, q is more than or equal to 1 and less than or equal to L, and q is E Z;
second, in the q-th simulated driving, the average value of the steering wheel angle magnitudes of the vehicles at all risk points for each driver is calculated
Figure FDA0004154966360000096
Figure FDA0004154966360000097
Again, in calculating the q-th simulated driving, all drivers are in the windAverage steering wheel angle magnitude of vehicle at dangerous point
Figure FDA0004154966360000098
And steering wheel angle magnitude variance +/of all drivers' vehicles at risk point>
Figure FDA0004154966360000099
Figure FDA00041549663600000910
Figure FDA00041549663600000911
From the times, the average value mu of the steering wheel angles of the vehicles of all drivers at risk points under L times of simulated driving is calculated θ And the steering wheel angle magnitude variance (σ) of vehicles of all drivers at risk points θ ) 2 ；
Finally, a steering wheel angle evaluation model is established:
Figure FDA0004154966360000101
wherein ,
Figure FDA0004154966360000102
the average of the steering wheel angle magnitudes for the driver at all risk points in 1 simulated driving;
sub-step 1.35, establishing a lateral acceleration evaluation model;
first, the data matrix of the lateral acceleration of each driver at each risk point is recorded in L times of simulated driving
Figure FDA0004154966360000103
wherein ,/>
Figure FDA0004154966360000104
wherein />
Figure FDA0004154966360000105
Representing the magnitude of the lateral acceleration of the vehicle of the nth driver at the mth risk point in the qth simulated driving; i is the number of the driver, i is more than or equal to 1 and less than or equal to N, and i is E Z; j is the number of the risk point, j is more than or equal to 1 and less than or equal to M, and j is less than or equal to Z; q is the number of simulated driving, q is more than or equal to 1 and less than or equal to L, and q is E Z;
second, in the q-th simulated driving, the average value of the lateral acceleration of the vehicle at all risk points of each driver is calculated
Figure FDA0004154966360000106
Figure FDA0004154966360000107
Again, in the q-th simulated driving, the average value of the lateral acceleration magnitudes of the vehicles at the risk points of all the drivers is calculated
Figure FDA0004154966360000108
And the lateral acceleration magnitude variance of the vehicle of all drivers at the risk point +.>
Figure FDA0004154966360000109
Figure FDA00041549663600001010
Figure FDA00041549663600001011
From times, calculating L times under simulated drivingAverage value mu of the lateral acceleration of the vehicle at the risk point for all drivers b And the acceleration magnitude variance (σ) of the vehicles of all drivers at the risk points b ) 2 ；
Finally, establishing a transverse acceleration evaluation model:
Figure FDA0004154966360000111
wherein ,
Figure FDA0004154966360000112
the average value of the lateral acceleration of the driver at all risk points in 1 simulated driving;
sub-step 1.36, building a vehicle operation score model;
Figure FDA0004154966360000113
wherein ,rx1 Indicating the number of times the xth evaluation index is evaluated as "excellent", r x2 Indicates the number of times the xth evaluation index is evaluated as "good", r x3 Indicating the number of times the xth evaluation index is evaluated as "general", r x4 Indicating the number of times the xth evaluation index is evaluated as "poor"; wherein x=1, 2,3,4, x=1 represents the 1 st evaluation index as the acceleration magnitude, x=2 represents the 2 nd evaluation index as the speed magnitude, x=3 represents the 3 rd evaluation index as the steering wheel angle magnitude, x=4 represents the 4 th evaluation index as the lateral acceleration magnitude; r is R x Weight of the x-th evaluation index, R 1 ＝0.2，R 2 ＝0.3，R 3 ＝0.25，R 4 ＝0.25；
Sub-step 1.4, establishing a driver risk perception capability assessment model;
the driver risk perception capability assessment model is shown as follows:
M total ＝(0.2Q 1 +0.4E p +0.4B)×100；
step 2, obtaining the total score of the driver to be evaluated on the driver risk perception capability evaluation model;
and 3, evaluating the risk perception capability of the driver to be evaluated according to the score of the driver.
2. The method for assessing the risk awareness of a multi-dimensional driver of claim 1 wherein the sub-steps of step 2 are as follows:
step 2.1, enabling a driver to be evaluated to watch n videos of normal driving road scenes inserted with the mark frames at the time when danger possibly occurs, and inserting the perception frames at the time when danger is perceived in the watching process; calculating to obtain video detection score Q of driver to be evaluated 1 ；
Step 2.2, enabling the driver to be evaluated to use a vehicle simulation driving device to perform normal driving with M risk points added at a time; collecting pupil diameters of a driver to be evaluated in the driving process, and heart rate, blood pressure, eyeball saccade amplitude and fixation duration of the driver to be evaluated at each risk point by using a physiological recorder;
sub-step 2.3, calculating to obtain heart rate average value, blood pressure average value, saccade amplitude average value, fixation duration average value and pupil diameter variability average value of the driver to be evaluated at all risk points, and calculating to obtain physiological parameter score E p ；
Step 2.4, enabling the driver to be evaluated to use a vehicle simulation driving device to perform normal driving with M risk points added for L times; the vehicle simulation driving device collects the acceleration, the speed, the steering wheel rotation angle and the transverse acceleration of the vehicle at each risk point in each simulated driving of each driver;
2.5, calculating to obtain a vehicle operation score B of the driver to be evaluated;
substep 2.6, calculating a total risk perception capability score M of the driver to be evaluated total 。
3. The method for evaluating risk awareness of a multi-dimensional driver according to claim 1, wherein step 3, specifically, when the score of the driver to be evaluated is greater than or equal to 0 and less than 60, indicates that the risk awareness of the driver is poor; when the score of the driver to be evaluated is more than or equal to 60 and less than 80, the risk perception capability of the driver is general; when the score of the driver to be evaluated is 80 or more and 100 or less, the risk perception capability of the driver is high.
CN202210562485.8A 2022-05-23 2022-05-23 Multi-dimensional driver risk perception capability assessment method Active CN115089182B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210562485.8A CN115089182B (en) 2022-05-23 2022-05-23 Multi-dimensional driver risk perception capability assessment method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210562485.8A CN115089182B (en) 2022-05-23 2022-05-23 Multi-dimensional driver risk perception capability assessment method

Publications (2)

Publication Number Publication Date
CN115089182A CN115089182A (en) 2022-09-23
CN115089182B true CN115089182B (en) 2023-05-02

Family

ID=83289837

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210562485.8A Active CN115089182B (en) 2022-05-23 2022-05-23 Multi-dimensional driver risk perception capability assessment method

Country Status (1)

Country Link
CN (1) CN115089182B (en)

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO1994016423A1 (en) * 1993-01-13 1994-07-21 Roads Corporation A hazard perception test system
JP2014041314A (en) * 2012-08-24 2014-03-06 Suzuki Motor Corp Electric wheelchair driver evaluation device and electric wheelchair driver evaluation program
WO2016028228A1 (en) * 2014-08-21 2016-02-25 Avennetz Technologies Pte Ltd System, method and apparatus for determining driving risk
CN106491144B (en) * 2016-09-22 2019-07-05 昆明理工大学 A kind of test and evaluation method of the latent risk perceptions ability of driver
CN106570609A (en) * 2016-09-22 2017-04-19 昆明理工大学 Method for testing and evaluating dynamic risk perception ability of driver
US10825350B2 (en) * 2017-03-28 2020-11-03 Wichita State University Virtual reality driver training and assessment system
CN111657923A (en) * 2020-07-02 2020-09-15 哈尔滨工业大学 Method and system for testing danger perception capability of driver
CN113077129A (en) * 2021-03-19 2021-07-06 东南大学 Driver danger perception capability evaluation method suitable for high-altitude area
CN113378975A (en) * 2021-06-30 2021-09-10 哈尔滨理工大学 Method for evaluating difference of risk perception capability of electrician operating personnel
CN114220081A (en) * 2021-11-11 2022-03-22 长安大学 Construction method of driving behavior safety evaluation model based on real vehicle test
CN114492037A (en) * 2022-01-25 2022-05-13 长安大学 Method for testing danger perception capability of driver
CN114239423A (en) * 2022-02-25 2022-03-25 四川省公路规划勘察设计研究院有限公司 Method for constructing prediction model of danger perception capability of driver on long and large continuous longitudinal slope section

Also Published As

Publication number Publication date
CN115089182A (en) 2022-09-23

Similar Documents

Publication Publication Date Title
Eskandarian et al. Evaluation of a smart algorithm for commercial vehicle driver drowsiness detection
Zhenhai et al. Driver drowsiness detection based on time series analysis of steering wheel angular velocity
CN111428699A (en) Driving fatigue detection method and system combining pseudo-3D convolutional neural network and attention mechanism
CN102396009B (en) Alertness assessment device and method
García et al. Vision-based drowsiness detector for a realistic driving simulator
Feng et al. An on-board system for detecting driver drowsiness based on multi-sensor data fusion using Dempster-Shafer theory
CN105956548A (en) Driver fatigue state detection method and device
CN108926352B (en) Driving fatigue detection method and system
CN110509983A (en) A kind of steering-by-wire road feel feedback device suitable for different drive demands
CN110728824B (en) Driver fatigue state detection and reminding method based on multi-source data
US20200241525A1 (en) Computer-based apparatus system for assessing, predicting, correcting, recovering, and reducing risk arising from an operator?s deficient situation awareness
CN113753059B (en) Method for predicting takeover capacity of driver under automatic driving system
CN114194197B (en) Dangerous driving early warning method, dangerous driving early warning device, dangerous driving early warning equipment and dangerous driving early warning related system
CN105931430A (en) Alarm sensitivity detection method and apparatus for driver state early warning system
CN212484555U (en) Fatigue driving multi-source information detection system
CN108021875A (en) A kind of vehicle driver&#39;s personalization fatigue monitoring and method for early warning
CN110751381A (en) Road rage vehicle risk assessment and prevention and control method
CN106408032A (en) Fatigue driving detection method based on corner of steering wheel
CN115089182B (en) Multi-dimensional driver risk perception capability assessment method
He et al. Boosting transfer learning improves performance of driving drowsiness classification using EEG
CN113628448B (en) Vehicle and fatigue driving relieving device thereof
CN111881799A (en) Driver fatigue detection method based on multi-source information fusion difference judgment
CN112215111A (en) Method and related device for evaluating direction control capability of motor vehicle driver
CN113903017A (en) Fatigue driving detection method and system
Omidi et al. Non-intrusive methods used to determine the driver drowsiness: Narrative review articles

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant