CN115089182B - Multi-dimensional driver risk perception capability assessment method - Google Patents
Multi-dimensional driver risk perception capability assessment method Download PDFInfo
- 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
Links
- 230000008447 perception Effects 0.000 title claims abstract description 38
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000004088 simulation Methods 0.000 claims abstract description 18
- 230000001133 acceleration Effects 0.000 claims description 52
- 210000001747 pupil Anatomy 0.000 claims description 33
- 230000036772 blood pressure Effects 0.000 claims description 25
- 230000004434 saccadic eye movement Effects 0.000 claims description 23
- 239000011159 matrix material Substances 0.000 claims description 22
- 238000011156 evaluation Methods 0.000 claims description 20
- 238000013210 evaluation model Methods 0.000 claims description 19
- 230000008569 process Effects 0.000 claims description 15
- 238000001514 detection method Methods 0.000 claims description 13
- 210000005252 bulbus oculi Anatomy 0.000 claims description 12
- 230000004424 eye movement Effects 0.000 claims description 7
- 210000001508 eye Anatomy 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 10
- 230000006872 improvement Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013139 quantization Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000011076 safety test Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
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
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Biophysics (AREA)
- Public Health (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Veterinary Medicine (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- General Physics & Mathematics (AREA)
- Ophthalmology & Optometry (AREA)
- Pathology (AREA)
- Child & Adolescent Psychology (AREA)
- Psychology (AREA)
- Social Psychology (AREA)
- Cardiology (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Psychiatry (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Hospice & Palliative Care (AREA)
- Computational Mathematics (AREA)
- Educational Technology (AREA)
- Theoretical Computer Science (AREA)
- Developmental Disabilities (AREA)
- Physiology (AREA)
- Pulmonology (AREA)
- General Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Traffic Control Systems (AREA)
- Algebra (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
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
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:
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 :
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;
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 :
Finally, a heart rate score model is established:
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 :
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;
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 :
Finally, a blood pressure score model is established:
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 :
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;
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 :
Finally, establishing an eyeball saccade amplitude score model:
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 :
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;
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 :
Finally, a gaze duration score model is established:
substep c, pupil diameter variability score model;
first, the average value of the pupil diameters of each driver during the whole driving process is calculatedAnd recording a pupil diameter data matrix z of each driver at each risk point ij :
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 diametersAnd pupil diameter data matrix z ij Obtaining a pupil diameter variability data matrix I ij :
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 :
Finally, establishing a pupil diameter variability score model:
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 wherein ,/> wherein />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
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 calculatedAnd the acceleration magnitude variance of the vehicles of all drivers at the risk point +.>
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:
wherein ,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 wherein ,/> wherein />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
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 calculatedAnd speed size variance of vehicles of all drivers at risk point +.>/>
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:
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 wherein ,/> wherein />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
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 calculatedAnd steering wheel angle magnitude variance +/of all drivers' vehicles at risk point>
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:
wherein ,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 wherein ,/> wherein />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
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 calculatedAnd the lateral acceleration magnitude variance of the vehicle of all drivers at the risk point +.>
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:
wherein ,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;
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:
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 :
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;
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 :
Finally, a heart rate score model is established:
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 :
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 :
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 :
Finally, a blood pressure score model is established:
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 :
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;
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 :
Finally, establishing an eyeball saccade amplitude score model:
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 :
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;
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 :
Finally, a gaze duration score model is established:
substep c, pupil diameter variability score model;
first, the average value of the pupil diameters of each driver during the whole driving process is calculatedAnd recording a pupil diameter data matrix z of each driver at each risk point ij :
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 diametersAnd pupil diameter data matrix z ij Obtaining a pupil diameter variability data matrix I ij :
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 :
Finally, establishing a pupil diameter variability score model:
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 wherein ,/> wherein />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
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 calculatedAnd the acceleration magnitude variance of the vehicles of all drivers at the risk point +.>
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:
wherein ,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 wherein ,/> wherein />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
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 calculatedAnd speed size variance of vehicles of all drivers at risk point +.>
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:
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 wherein ,/> wherein />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
Again, in calculating the q-th simulated driving, all drivers are in the windAverage steering wheel angle magnitude of vehicle at dangerous pointAnd steering wheel angle magnitude variance +/of all drivers' vehicles at risk point>
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:
wherein ,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 wherein ,/> wherein />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
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 calculatedAnd the lateral acceleration magnitude variance of the vehicle of all drivers at the risk point +.>
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:
wherein ,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;
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.
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)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CA2153323A1 (en) * | 1993-01-13 | 1994-07-21 | Michael Alan Hull | 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 |
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 |
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 |
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 |
-
2022
- 2022-05-23 CN CN202210562485.8A patent/CN115089182B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN115089182A (en) | 2022-09-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111428699B (en) | Driving fatigue detection method and system combining pseudo-3D convolutional neural network and attention mechanism | |
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 | |
CN105139070B (en) | fatigue driving evaluation method based on artificial neural network and evidence theory | |
CN110728824B (en) | Driver fatigue state detection and reminding method based on multi-source data | |
CN206757846U (en) | A kind of fatigue driving four-dimension monitoring system | |
Feng et al. | An on-board system for detecting driver drowsiness based on multi-sensor data fusion using Dempster-Shafer theory | |
CN108682119B (en) | Driver fatigue state detection method based on smart phone and smart watch | |
CN108926352B (en) | Driving fatigue detection method and system | |
CN212484555U (en) | Fatigue driving multi-source information detection system | |
CN113628448B (en) | Vehicle and fatigue driving relieving device thereof | |
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 | |
CN108021875A (en) | A kind of vehicle driver's personalization fatigue monitoring and method for early warning | |
CN105405253A (en) | Method and apparatus for monitoring fatigue state of driver | |
CN109858178A (en) | A kind of commercial vehicle drivers giving fatigue pre-warning method based on Intelligent bracelet | |
CN115089182B (en) | Multi-dimensional driver risk perception capability assessment method | |
Akbar et al. | Three drowsiness categories assessment by electroencephalogram in driving simulator environment | |
He et al. | Boosting transfer learning improves performance of driving drowsiness classification using EEG | |
CN117765684A (en) | Fatigue driving detection method | |
CN111881799B (en) | Driver fatigue detection method based on multisource information fusion difference judgment | |
Hassan et al. | Sigmoid wake probability model for high-resolution detection of drowsiness using electroencephalogram | |
CN114564110B (en) | Driving learning ability detection method and system based on brain electrical data | |
CN113903017A (en) | Fatigue driving detection method and system |
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 |