CN111311093A - Road intersection risk assessment and early warning method based on driver physiological data - Google Patents
Road intersection risk assessment and early warning method based on driver physiological data Download PDFInfo
- Publication number
- CN111311093A CN111311093A CN202010091611.7A CN202010091611A CN111311093A CN 111311093 A CN111311093 A CN 111311093A CN 202010091611 A CN202010091611 A CN 202010091611A CN 111311093 A CN111311093 A CN 111311093A
- Authority
- CN
- China
- Prior art keywords
- risk
- intersection
- vehicle
- substep
- data
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000012502 risk assessment Methods 0.000 title claims abstract description 24
- 239000011159 matrix material Substances 0.000 claims abstract description 35
- 230000003068 static effect Effects 0.000 claims description 25
- 230000008859 change Effects 0.000 claims description 23
- 238000001228 spectrum Methods 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000005096 rolling process Methods 0.000 claims description 3
- 230000003340 mental effect Effects 0.000 abstract description 6
- 238000011156 evaluation Methods 0.000 abstract description 5
- 238000012821 model calculation Methods 0.000 abstract description 2
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 5
- 230000000052 comparative effect Effects 0.000 description 3
- 230000003993 interaction Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 210000001186 vagus nerve Anatomy 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000005192 partition Methods 0.000 description 2
- 230000003304 psychophysiological effect Effects 0.000 description 2
- 238000013077 scoring method Methods 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 238000010183 spectrum analysis Methods 0.000 description 2
- 230000002889 sympathetic effect Effects 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 238000012952 Resampling Methods 0.000 description 1
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000010349 pulsation Effects 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000012954 risk control Methods 0.000 description 1
- 230000001502 supplementing effect Effects 0.000 description 1
- 230000001515 vagal effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- 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
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses an urban road intersection risk assessment and early warning method based on driver physiological data, which comprises the following steps: firstly, establishing an urban intersection vehicle risk assessment model; then calibrating the parameter w in the vehicle risk probability modeljDetermining a vehicle risk probability model corresponding to the current implementation intersection; then constructing a vehicle risk grade division matrix, and calculating a risk value of the target vehicle at the current implementation intersection; then, dividing the matrix according to the vehicle risk levels, determining the target vehicle risk level, and determining the risk level of the current implementation intersection; and finally, determining early warning information according to the risk level of the current implementation intersection, and early warning the vehicle entering the current implementation intersection. The urban road intersection risk assessment and early warning method based on the mental physiological data of the driver, provided by the invention, has the advantages of easiness in data acquisition, convenience in model calculation and capability of effectively carrying out traffic risk on the urban intersectionAnd (4) evaluation and early warning are issued, so that the operability is strong.
Description
Technical Field
The invention relates to the technical field of traffic safety, in particular to an urban road intersection risk assessment and early warning method based on driver physiological data.
Background
With the rapid increase of the level of urban motorization, the road running conditions are more and more complex and changeable. The urban road intersection is used as a key node in a traffic network, has the characteristics of complex traffic composition, various traffic behaviors, high conflict rate and the like, and is an important factor for restricting the smoothness and safety of urban roads. Therefore, the method has important significance in risk assessment and early warning method research of the intersection.
At present, methods for researching the safety of urban road intersections mainly fall into two categories. One is based on linear indexes, facility conditions, historical accident data and the like, and carries out qualitative and quantitative analysis on main factors influencing traffic safety of intersections and comprehensive evaluation on operation risks. The method is simple and feasible, but the evaluation result is macroscopic and static, and real-time risk control cannot be performed on the intersection. The other type is based on a traffic conflict technology, vehicle running tracks are extracted through videos and the like, threshold values such as Time-to-Collision (TTC) and the like are used as indexes, and real-Time running risks of intersections are evaluated. The method has more theoretical researches, but practical application is not developed due to the fact that conflict discrimination indexes are single, video identification accuracy is still insufficient and the like.
According to statistics, the number of people in the traffic accidents is about 90% of the main cause of the accidents, and therefore, the evaluation of the intersection risks from the viewpoint of the human factors of drivers is of great significance. At present, some scholars at home and abroad conduct research on the relevance of a driver human factor index monitoring method and traffic safety aiming at urban road intersection risk assessment, but a method capable of reflecting the characteristic of traffic time-varying property and reflecting the interaction and dynamic change of the driver human factor characteristic and the traffic environment is lacked.
Disclosure of Invention
Aiming at the problems in the prior art, the invention aims to provide an urban road intersection risk assessment and early warning method based on mental and physiological data of a driver, which can reflect the time-varying characteristics of traffic, can reflect the human factor characteristics, the interaction and the dynamic change of traffic environment, can realize the dynamic identification and real-time early warning of urban road intersection risks, and greatly improve the operation efficiency and the safety of intersections.
In order to achieve the purpose, the invention is realized by adopting the following technical scheme.
A risk assessment and early warning method for an urban road intersection based on mental and physiological data of a driver comprises the following steps:
step 1, establishing an urban intersection vehicle risk assessment model:
wherein F represents the risk value of the vehicle at the intersection, M represents the risk matrix, P represents the risk probability of the vehicle, E represents the risk loss of the vehicle, and w represents the risk loss of the vehiclejAttribute weight, x, representing the jth index in a vehicle risk probability modeljThe method comprises the steps of representing the value of a jth index in a vehicle risk probability model, representing the mass coefficient of a vehicle body by m, and representing the real-time speed of a vehicle driving into an intersection by v;
j is 1,2, and J represents J indexes which are respectively used for marking the electrocardiogram data of the driver, the traffic volume and static facilities at the intersection;
step 2, calibrating the parameter w in the vehicle risk probability modeljDetermining a vehicle risk probability model corresponding to the current implementation intersection;
step 3, constructing a vehicle risk grade division matrix;
step 4, calculating a risk value of the target vehicle at the current implementation intersection;
step 5, dividing the matrix according to the vehicle risk level, and determining the target vehicle risk level;
step 6, determining the risk level of the current implementation intersection according to the risk level of the target vehicle;
and 7, determining early warning information according to the risk level of the current implementation intersection, and early warning the vehicle entering the current implementation intersection.
The technical scheme of the invention has the characteristics and further improvements that:
(1) further, the driver electrocardiographic data includes: heart rate variability power spectrum Low Frequency (LF) rate of change, High Frequency (HF) rate of change, beat-to-beat interval RR interval Mean (MRR) and mean square error (SDNN).
(2) Further, the obtaining of the electrocardiogram data of the driver specifically comprises: recording a group of electrocardiogram data every 1 second of rolling from at least 5 minutes before the vehicle enters the current implementation intersection to the end of the vehicle exiting the current implementation intersection to obtain a plurality of groups of electrocardiogram data; and analyzing the multiple groups of electrocardio data to finally obtain the electrocardio data of the driver.
(3) Step 2 comprises the following substeps:
the substep 2.1, acquiring historical data sets of N vehicles passing through the intersection at the current implementation intersection, and determining the electrocardio data of a driver, the traffic data of K minutes before the vehicle enters the intersection, the static facility score of the intersection, the vehicle body quality coefficient and the real-time speed of the vehicle entering the intersection in each historical data set; wherein N and K are positive integers;
substep 2.2, using the electrocardio data of the driver, the traffic data of K minutes before the vehicle enters the intersection, the static facility score of the intersection, the vehicle body quality coefficient and the real-time speed of the vehicle entering the intersection in each historical data set determined in substep 2.1 as a group of samples to obtain N groups of samples;
substep 2.3, calibrating parameter w in the vehicle risk probability model according to the data in the N groups of samples obtained in substep 2.2j(J ═ 1, 2.., J), a vehicle corresponding to the currently implemented intersection is obtainedA risk probability model.
(4) Further, step 3 comprises the following substeps:
substep 3.1, calculating a risk probability value of each corresponding vehicle in the historical sample according to a vehicle risk probability model corresponding to the currently implemented intersection to obtain N risk probability values; dividing the N risk probability values into a plurality of cluster categories, and determining threshold values of risk probability division of different levels according to the cluster categories;
substep 3.2, calculating the risk loss value of each corresponding vehicle in the historical sample according to the data in the N groups of samples obtained in substep 2.2, and obtaining N risk loss values; and dividing the N risk loss values into a plurality of categories;
and a substep 3.3 of constructing a vehicle risk classification matrix according to the threshold values determined by the substep 3.1 and classified by the risk probability of different grades and the risk loss values of the plurality of classes classified by the substep 3.2.
Preferably, in substep 3.1, the determining the threshold for dividing the risk probabilities of different grades according to the cluster category specifically includes: and dividing the N risk probability values into a plurality of categories according to the danger degree by adopting a K-means algorithm, and clustering the risk probability values of the N vehicles to obtain the upper limit value and the lower limit value of each category, namely the threshold values for dividing the risk probabilities of different levels.
(5) Further, step 4 comprises the following substeps:
substep 4.1, having calibrated parameter w according to the currently implemented intersectionjThe vehicle risk probability model calculates the risk probability value of the target vehicle at the current implementation intersection;
substep 4.2, calculating a risk loss value of the target vehicle at the current implementation intersection;
and substep 4.3, calculating a risk value of the target vehicle at the current implementation intersection according to the intersection vehicle risk assessment model in the step 1.
(6) Further, step 5 comprises the following substeps:
substep 5.1, updating the threshold value of risk probability division according to the risk probability value of the target vehicle at the current implementation intersection calculated in substep 4.1;
substep 5.2, establishing an updated vehicle risk grade division matrix according to the updated risk probability division threshold value in substep 5.1;
and substep 5.3, determining the target vehicle risk level according to the updated vehicle risk level classification matrix.
Preferably, in substep 5.1, the updating the threshold for risk probability division is specifically: and calculating the risk probability value of the target vehicle at the current implementation intersection, supplementing the calculated risk probability value of the target vehicle to a historical data set, and re-clustering by using a K-means algorithm to realize dynamic update of the risk probability division threshold.
(7) Further, step 6 specifically includes: and backtracking and counting the proportion of the target vehicles with each risk level in a signal period before the currently implemented intersection every 10 seconds, and determining the risk level of the currently implemented intersection according to the proportion of the target vehicles with each risk level.
Compared with the prior art, the invention has the beneficial effects that:
according to the urban road intersection risk assessment and early warning method based on the mental physiological data of the driver, a risk assessment model suitable for the urban intersection is established, the mental electrical data, the traffic volume and the intersection static facility score of the driver are obtained according to the specific conditions of the current implemented intersection, parameter calibration is carried out, a risk probability model corresponding to the current implemented intersection is determined, a risk loss model is calculated by using the speed and the vehicle body quality coefficient when the vehicle enters the intersection, finally, the risk value of the current target vehicle at the implemented intersection is determined based on a risk matrix model, and the risk grade of the intersection is further obtained.
According to the urban intersection risk dynamic risk assessment method, the urban intersection risk is effectively assessed and early warned by using the risk assessment model suitable for the urban intersection, the traffic time-varying characteristics can be reflected, the characteristics of drivers, the interaction and the dynamic change of traffic environments can be reflected, the urban road intersection risk dynamic identification and real-time early warning are realized, and the operation efficiency and the safety of the intersection are greatly improved.
The urban road intersection risk assessment and early warning method based on the mental physiological data of the driver is easy to obtain data, convenient in model calculation, capable of effectively assessing traffic risks of urban intersections and issuing early warning, and high in operability.
Drawings
The invention is described in further detail below with reference to the figures and specific embodiments.
FIG. 1 is a schematic flow chart of an embodiment of a method for risk assessment and early warning at an intersection of an urban road based on psychophysiological data of a driver according to the present invention;
FIG. 2 is a power spectrum of a driver's electrocardiosignal according to an embodiment of the present invention;
fig. 3 is a vehicle risk classification matrix diagram according to an embodiment of 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 illustrative of the present invention and should not be construed as limiting the scope of the present invention.
Referring to fig. 1, an embodiment of the present invention provides an urban road intersection risk assessment and early warning method based on driver psychophysiological data, including the following steps:
step 1, establishing an urban intersection vehicle risk assessment model:
wherein F represents the risk value of the vehicle at the intersection, M represents the risk matrix, P represents the risk probability of the vehicle, E represents the risk loss of the vehicle, and w represents the risk loss of the vehiclejAttribute weight, x, representing the jth index in a vehicle risk probability modeljThe method comprises the steps of representing the value of a jth index in a vehicle risk probability model, wherein m represents a vehicle body mass coefficient of a vehicle, and v represents the real-time speed of the vehicle driving into an intersection;
j is 1,2, and J represents J indexes which are respectively used for marking the electrocardiogram data of the driver, the traffic volume and static facilities at the intersection.
Heart Rate Variability (HRV), which is generally a small fluctuation of the RR interval per beat, reflects the tone and balance of sympathetic and vagal activity of the heart, and the most commonly used analysis methods are time domain and frequency domain. The time domain analysis method is the simplest method for quantitatively describing the RR interval change characteristics, and the most common indexes are RR interval Mean (MRR) and mean square error (SDNN). The MRR can reflect the pulsation of the heart in unit time, and the smaller the MRR is, the more rapid the heartbeat of a driver is and the more tense the driver is in driving. The SDNN represents the fluctuation condition of the RR intervals, the larger the SDNN is, the more discrete the RR intervals are, and the larger the heartbeat fluctuation of the driver is. The frequency domain analysis method is to perform Fast Fourier Transform (FFT) operation on a section of relatively stable RR interval or instantaneous heart rate variation signal to obtain a power spectrogram with frequency (Hz) as a horizontal coordinate and Power Spectral Density (PSD) as a vertical coordinate for analysis. The heart rate variation power spectrum can separate main components of high frequency, low frequency and the like, a low frequency region (LF) reflects the dual regulation of the sympathetic nerve and the vagus nerve, a high frequency region (HF) generally reflects the activity of the vagus nerve, and when the vagus nerve is excited, the heart rate variation power spectrum can play the functions of protecting the body, restitution, recovering and accumulating energy and the like.
Therefore, in this embodiment, the electrocardiographic data of the driver selects 4 indexes of the change rate of the low frequency region (LF), the change rate of the high frequency region (HF), the average value of the RR intervals of the beat-to-beat intervals (MRR), and the mean square error (SDNN) in the power spectrum of the heart rate variability.
Therefore, in the present embodiment, the vehicle risk probability model has 6 indicators, i.e., J is 6, J is 1, 2.
For the acquisition of 6 indexes in the vehicle risk probability model, the following is specific:
wherein, the acquisition of driver electrocardio data, this embodiment provides two main kinds of acquisition equipment: one type of equipment can directly output electrocardio RR intervals of a driver, such as a bracelet capable of detecting heart rate and the like; another type of device outputs driver's electrocardiographic signal data, such as a BIOPAC physiological instrument.
The traffic data acquisition device may be a geomagnetic coil or a roadside radar or the like.
And the static facility score of the intersection is obtained by an expert scoring method.
It should be noted that the obtaining of the electrocardiographic data of the driver specifically includes: recording a group of electrocardiogram data every 1 second of rolling from at least 5 minutes before the vehicle enters the current implementation intersection to the end of the vehicle driving out of the current implementation intersection, obtaining a plurality of groups of electrocardiogram data, and respectively calculating the change of each index every 1 second. The electrocardiosignal of the driver is converted from a time domain to a frequency domain through fast Fourier transform (DFT), so that the electrocardio time-frequency domain index of the driver at the urban intersection is obtained.
The specific steps for processing the LF change rate, the HF change rate, the MRR and the SDNN indexes of the electrocardio of the driver are as follows:
(1) electrocardio RR interval data { x output by equipment such as a bracelet1,x2,...,xTAnd the number of the collected ECG RR interval samples is T, and the samples can be directly calculated in the next step.
The processing of the electrocardiosignals output by the BIOPAC physiological instrument and other devices comprises R wave extraction, wave crest detection of the electrocardiosignals and RR interval time sequence calculation. And deleting abnormal R-R interval data, then performing linear interpolation, and completing the whole data to obtain a final R-R interval time sequence. Resampling the R-R interval time series at a frequency of 4Hz to obtain an equidistant time series { x }1,x2,...,xTAnd the T is the number of collected electrocardio RR interval samples.
(2) Using the formula:the arithmetic mean of the new RR intervals is calculated to be the MRR. Using the formula:and calculating the mean square error of the new RR intervals to obtain SDNN.
(3) Converting the driver's electrocardiosignal from time domain to frequency domain by Fast Fourier Transform (FFT) to obtain frequency (Hz) as abscissa and Power Spectral Density (PSD)The power spectrum on the ordinate, as in fig. 2. As shown in the following table 1, the spectral analysis frequency division table separates low frequency band power (LF) from the power spectrum, using a preset formula:a low frequency band power (LF) rate of change is calculated. Separating high-frequency band power (HF) from the power spectrum, and utilizing a preset formula:a high frequency band power (HF) change rate is calculated.
TABLE 1 spectral analysis band partition Table
In addition, it should be noted that the static facility score of the intersection is obtained by an expert scoring method. Aspects of intersection static facility evaluation include: intersection conflict points, intersection geometric characteristics and traffic safety facilities. The geometrical characteristics of the intersection comprise the intersection type, the intersection angle, the sight distance, the lane arrangement, the physical canalization (lane marking, green belt, traffic island and the like), construction area influence and other factors; traffic safety facilities include the visibility and integrity of signs, markings, pavement, lighting, etc. And accumulating and adding the scores of all the scoring items to obtain the static facility score of the intersection.
The specific scoring index system is shown in table 2 below:
TABLE 2 static facilities scoring index system for intersections
For the vehicle risk loss model, the real-time speed of the vehicle entering the intersection can be acquired through equipment such as a vehicle-mounted OBD or a GPS. The vehicle body mass coefficient is a known constant, which is only related to the vehicle type, and can be obtained by comparison with a standard, and the standard for obtaining the vehicle body mass coefficient is shown in the following table 3 according to the notice of vehicle type classification and conversion coefficient investigation about adjusting road traffic conditions issued by the department of transportation.
TABLE 3 comparison standard table of vehicle body mass coefficient
Step 2, calibrating the parameter w in the vehicle risk probability modeljAnd determining a vehicle risk probability model corresponding to the current implementation intersection.
The method comprises the following substeps:
the substep 2.1, acquiring historical data sets of N vehicles passing through the intersection at the current implementation intersection, and determining the electrocardio data of a driver, the traffic data of K minutes before the vehicle enters the intersection, the static facility score of the intersection, the vehicle body quality coefficient and the real-time speed of the vehicle entering the intersection in each historical data set; wherein N and K are positive integers;
substep 2.2, using the electrocardio data of the driver, the traffic data of K minutes before the vehicle enters the intersection, the static facility score of the intersection, the vehicle body quality coefficient and the real-time speed of the vehicle entering the intersection in each historical data set determined in substep 2.1 as a group of samples to obtain N groups of samples;
substep 2.3, calibrating parameter w in the vehicle risk probability model according to the data in the N groups of samples obtained in substep 2.2jAnd (J) obtaining a vehicle risk probability model corresponding to the current implementation intersection.
In particular, the method comprises the following steps of,
(1) from the above steps, 6 indexes can be obtained: 5min before the vehicle enters the intersection, static facility scoring at the intersection, LF change rate, HF change rate, MRR and SDNN, and usingEquation (1) normalizes these 6 indices. For N samples and 6 risk probability identification indexes, forming an original index data matrix
(2) Carrying out nonnegativity processing and data translation on the original data to obtain a data matrix XijIn order to avoid the meaningless logarithm when the entropy is calculated, data translation is required according to the formula (2) and the formula (3).
For indices with higher numerical values and greater risk:
wherein, i is 1,2, and N, j is 1,2, 6;
for indices with smaller numbers and greater risk:
wherein, i is 1,2, and N, j is 1, 2.
(3) Determining weight by utilizing the concept of entropy information, and normalizing the numerical value, wherein the multi-attribute decision matrix is as follows:
the ith sample A under the jth index is expressed by formula (4)iDegree of contribution G ofij
Wherein, i is 1,2, and N, j is 1, 2.
(4) With Ej(equation 5) to expressSample pair index XjThe total contribution of the samples is obtained, and the contribution degree of each sample to the index is obtained.
Wherein, i is 1,2, and N, j is 1,2, 6; k is 1/ln (m), so that 0. ltoreq. E is ensuredj1 or less, i.e. EjThe maximum is 1.
When the contribution degrees of the samples tend to be consistent under a certain index, EjTo 1; especially when fully equal; the role of the property of the indicator in the decision making may not be considered, i.e. the weight of the indicator is zero at this moment.
(5) For the j-th index, index value XijThe larger the difference in (b), the greater the effect on risk probability identification, the smaller the entropy value. E obtained by the step (4)jAnd equation 6, the difference coefficient D of each index can be obtainedj。
Dj=1-Ej(6)
Each index attribute weight wjThe result is obtained by the formula (7),
to this end, the vehicle risk probability model parameter wjAnd after calibration is finished, the vehicle risk probability model corresponding to the current implementation intersection can be obtained.
And 3, constructing a vehicle risk grade division matrix.
The method comprises the following substeps:
substep 3.1, calculating a risk probability value of each corresponding vehicle in the historical sample according to a vehicle risk probability model corresponding to the currently implemented intersection to obtain N risk probability values; and dividing the N risk probability values into a plurality of cluster categories, and determining threshold values of risk probability division of different levels according to the cluster categories.
Specifically, a K-means algorithm is adopted to divide the N risk probability values into 5 clustering categories according to the extreme safety, the comparative safety, the danger, the comparative danger and the comparative risk, and the upper limit value and the lower limit value of each category are obtained, namely, the threshold values of the risk probability division of different levels.
Substep 3.2, calculating the risk loss value of each corresponding vehicle in the historical sample according to the data in the N groups of samples obtained in substep 2.2, and obtaining N risk loss values; and dividing the N risk loss values into a plurality of categories.
In technical Specifications for urban road engineering (GB51286-2018), the designed traveling speed of a main road in an urban road is specified to be 40-60 km/h; the designed traveling speed of the secondary trunk road is 30-50 km/h; the designed traveling speed of the branch is 20-40 km/h. In the embodiment, the urban plane intersection risk losses are divided into four types according to the designed driving speed of the urban road and the serious property of the accident consequence formulated by the traffic department in China, and the risk loss grades and the corresponding speed values are divided as listed in the following table 4.
TABLE 4 Risk loss grading Standard
And a substep 3.3 of constructing a vehicle risk classification matrix according to the threshold values determined by the substep 3.1 and classified by the risk probability of different grades and the risk loss values of the plurality of classes classified by the substep 3.2.
The urban intersection vehicle risk probability is divided into 5 grades, the vehicle risk loss is divided into 4 grades, an urban intersection vehicle risk grade division matrix (5 multiplied by 4) is obtained, and the risk matrix is divided into four grades according to an expert experience method, which is shown in the attached figure 3.
And 4, calculating the risk value of the target vehicle at the current implementation intersection.
The target vehicle carrying the driver's electrocardiographic detection device is equipped with an electronic tag (RFID). The target vehicle may be identified by the roadside device when entering the intersection. When the road side equipment identifies that the target vehicle enters the intersection, the electro-cardio LF change rate, the HF change rate, the MRR and SDNN indexes, the traffic data 5min before the vehicle enters the intersection, the vehicle body quality coefficient, the speed when the vehicle enters the intersection and the intersection static facility scoring data are counted and calculated.
The method specifically comprises the following substeps:
substep 4.1, having calibrated parameter w according to the currently implemented intersectionjThe vehicle risk probability model calculates the risk probability value of the target vehicle at the current implementation intersection.
Specifically, the electro-cardio LF (low frequency) change rate, the HF (high frequency) change rate, MRR (maximum resolution ratio) and SDNN indexes of a driver, the traffic volume 5min before the vehicle enters the intersection and the static facility score of the intersection are input into a risk probability model with the completed parameter calibration, and the risk probability value P of the target vehicle at the intersection is calculated by using a formula (8).
And substep 4.2, calculating the risk loss value of the target vehicle at the current implementation intersection.
Specifically, the vehicle body mass coefficient and the speed of the vehicle when the vehicle enters the intersection are input into the risk loss model, and the risk loss value E of the target vehicle at the intersection is calculated by using a formula (9).
And substep 4.3, calculating a risk value of the target vehicle at the current implementation intersection according to the intersection vehicle risk assessment model in the step 1.
And inputting the risk probability value P and the risk loss value E of the target vehicle at the intersection into a risk matrix model to obtain a vehicle risk value F.
F=M(P,E)
And 5, dividing the matrix according to the vehicle risk level, and determining the target vehicle risk level.
The method comprises the following substeps:
substep 5.1, updating the threshold value of risk probability division according to the risk probability value of the target vehicle at the current implementation intersection calculated in substep 4.1;
specifically, a risk probability value of the target vehicle at the current implementation intersection is calculated, the calculated risk probability value of the target vehicle is supplemented to a historical data set, clustering is carried out again by using a K-means algorithm, and dynamic updating of a risk probability division threshold value is achieved.
Substep 5.2, establishing an updated vehicle risk grade division matrix according to the updated risk probability division threshold value in substep 5.1;
and substep 5.3, determining the target vehicle risk level according to the updated vehicle risk level classification matrix.
Specifically, the calculated risk value is compared with the value in the vehicle risk grade division matrix constructed in the substep 5.2, so as to obtain the risk grade of the current target vehicle.
And 6, determining the risk level of the current implementation intersection according to the risk level of the target vehicle.
Specifically, the risk level of each target vehicle entering the currently implemented intersection within a signal period duration is calculated, the proportion of each risk level target vehicle at the currently implemented intersection within the signal period duration is counted, and the risk level of the currently implemented intersection within the signal period duration is determined according to the proportion of each risk level target vehicle.
And backtracking the vehicle statistical data in the previous signal period at intervals of 10s, and performing early warning in the next step according to the statistical data.
And 7, determining early warning information according to the risk level of the current implementation intersection, and early warning the vehicle entering the current implementation intersection.
Specifically, the early warning mode of this embodiment has two kinds, is roadside electronic display screen and on-vehicle early warning device respectively. The roadside electronic display screen issues early warning information in a text mode, and the vehicle-mounted early warning equipment issues the early warning information in a voice prompt mode.
In an exemplary manner, the first and second electrodes are,
taking an intersection of a certain city in China as an example, the intersection is a cross intersection, four lanes in two directions, and static facility data of the intersection is called from a database.
The method comprises the following steps of firstly, acquiring and processing historical data set driver electrocardiogram data, vehicle models and traffic volumes, and processing the data by the method to obtain six indexes, wherein the six indexes comprise: LF rate of change, HF rate of change, MRR, SDNN, traffic volume, static facilities score. Table 5 below is a partial data sample statistical result.
Table 5 partial data sample statistics table
The static facilities at the intersection are scored 7 in the daytime and 9 in the nighttime in a certain historical period, and the scoring is specifically shown in the following table 6:
table 6 static construction scoring table for implementing intersection
Secondly, parameter calibration:
constructing a multi-attribute decision matrix:
normalizing the multi-attribute decision matrix to obtain:
and calculating the decision matrix by using an entropy method to obtain the weight parameter value of each index. The calibration results of the weighting parameters of the intersection risk probability model are shown in table 7:
table 7 table of calibration results of risk probability model parameters of intersection
Thirdly, determining a vehicle risk probability value threshold:
utilizing the weighted value of each parameter in the vehicle risk probability model determined in the step, using the data after the normalization of each index of the historical vehicle and according to a formulaAnd respectively calculating the risk probability value of each historical vehicle.
The risk probability values of all vehicles are clustered according to 5 categories of very safe, comparatively safe, dangerous, comparatively dangerous and serious dangerous by using a K-means clustering algorithm to obtain upper and lower limit values of each category, as shown in Table 8.
TABLE 8 urban intersection risk probability value partition thresholds
Fourthly, calculating the risk level of the target vehicle:
take the calculation of one of the vehicles a as an example. The vehicle A is a small-sized passenger car, and the model coefficient of the vehicle A is 1. The time it was detected to enter the intersection was 13: and 14, the static facilities score of the corresponding intersection is 7 scores in daytime.
Calculating a risk probability value:
first, the detected data of the vehicle a is substituted into the history database for normalization, where table 9 is the original index of the vehicle a, and table 10 is the normalized index of the data of the vehicle a.
TABLE 9 original index for vehicle A
TABLE 10 original index for vehicle A
And then substituting the index of the vehicle A into the risk probability model to obtain the risk probability of the vehicle at the intersection.
Calculating the risk loss value of the vehicle A:
substituting the risk probability P and the risk loss value E into a risk matrix model:
F=M(P,E)=(0.420647,452)
the risk level of the vehicle is determined to be class iii risk by looking up the table in comparison with the risk level matrix shown in fig. 3.
In accordance with the above steps, the risk level of the other vehicle within one signal cycle time is computationally determined. And adding the calculated vehicle risk probability value into the historical vehicle risk probability value to obtain a new vehicle risk probability value set, clustering the new vehicle risk probability value set by using a K-means algorithm according to the method of the third step, and updating the risk probability division threshold value.
And fifthly, calculating the risk grade of the implemented intersection:
statistics shows that 20% of vehicles at the current intersection in one signal period belong to class III risk, 64% of vehicles belong to class II risk and 16% of vehicles belong to class I risk. The currently implemented intersection within the signal period is determined to be at class B risk according to the criteria shown in table 11.
And updating the statistical information every 10s, and carrying out early warning through the next step.
Table 11 standard table for risk grade division of intersection
Sixthly, issuing early warning information:
and issuing early warning information through a roadside electronic display board and vehicle-mounted equipment.
Although the present invention has been described in detail in this specification with reference to specific embodiments and illustrative embodiments, it will be apparent to those skilled in the art that modifications and improvements can be made thereto based on the present invention. Accordingly, such modifications and improvements are intended to be within the scope of the invention as claimed.
Claims (10)
1. A road intersection risk assessment and early warning method based on driver physiological data is characterized by comprising the following steps:
step 1, establishing an urban intersection vehicle risk assessment model,
wherein F represents the risk value of the vehicle at the intersection, M represents the risk matrix, P represents the risk probability of the vehicle, E represents the risk loss of the vehicle, and w represents the risk loss of the vehiclejAttribute weight, x, representing the jth index in a vehicle risk probability modeljThe method comprises the steps of representing the value of a jth index in a vehicle risk probability model, representing the mass coefficient of a vehicle body by m, and representing the real-time speed of a vehicle driving into an intersection by v;
j is 1,2, and J represents J indexes which are respectively used for marking the electrocardiogram data of the driver, the traffic volume and static facilities at the intersection;
step 2, calibrating the parameter w in the vehicle risk probability modeljDetermining a vehicle risk probability model corresponding to the current implementation intersection;
step 3, constructing a vehicle risk grade division matrix;
step 4, calculating a risk value of the target vehicle at the current implementation intersection;
step 5, dividing the matrix according to the vehicle risk level, and determining the target vehicle risk level;
step 6, determining the risk level of the current implementation intersection according to the risk level of the target vehicle;
and 7, determining early warning information according to the risk level of the current implementation intersection, and early warning the vehicle entering the current implementation intersection.
2. The method for assessing and warning the risk of a road intersection based on the physiological data of the driver as claimed in claim 1, wherein the driver's electrocardiogram data comprises: heart rate variability power spectrum Low Frequency (LF) rate of change, High Frequency (HF) rate of change, beat-to-beat interval RR interval Mean (MRR) and mean square error (SDNN).
3. The method for assessing and warning the risk of a road intersection based on the physiological data of the driver as claimed in claim 1, wherein the obtaining of the electrocardiogram data of the driver specifically comprises: recording a group of electrocardiogram data every 1 second of rolling from at least 5 minutes before the vehicle enters the current implementation intersection to the end of the vehicle exiting the current implementation intersection to obtain a plurality of groups of electrocardiogram data; and analyzing the multiple groups of electrocardio data to finally obtain the electrocardio data of the driver.
4. The method for assessing and warning the risk of a road intersection based on the physiological data of the driver as claimed in claim 1, wherein the step 2 comprises the following substeps:
the substep 2.1, acquiring historical data sets of N vehicles passing through the intersection at the current implementation intersection, and determining the electrocardio data of a driver, the traffic data of K minutes before the vehicle enters the intersection, the static facility score of the intersection, the vehicle body quality coefficient and the real-time speed of the vehicle entering the intersection in each historical data set; wherein N and K are positive integers;
substep 2.2, using the electrocardio data of the driver, the traffic data of K minutes before the vehicle enters the intersection, the static facility score of the intersection, the vehicle body quality coefficient and the real-time speed of the vehicle entering the intersection in each historical data set determined in substep 2.1 as a group of samples to obtain N groups of samples;
substep 2.3, calibrating parameter w in the vehicle risk probability model according to the data in the N groups of samples obtained in substep 2.2jAnd (J) obtaining a vehicle risk probability model corresponding to the current implementation intersection.
5. The method for assessing and warning the risk of a road intersection based on the physiological data of the driver as claimed in claim 4, wherein in substep 2.3, the parameter w in the probability model of risk of the vehicle is calibratedj(J ═ 1, 2.., J), specifically:
establishing an attribute decision matrix by using the electrocardio data of drivers, the traffic data of K minutes before the vehicle enters the intersection and the static facility score of the intersection in the N groups of samples, and calibrating the parameter w in the vehicle risk probability model by using an entropy methodj(j=1,2,...,J)。
6. The method for assessing and warning the risk of a road intersection based on the physiological data of the driver as claimed in claim 4, wherein the step 3 comprises the following substeps:
substep 3.1, calculating a risk probability value of each corresponding vehicle in the historical sample according to a vehicle risk probability model corresponding to the currently implemented intersection to obtain N risk probability values; dividing the N risk probability values into a plurality of cluster categories, and determining threshold values of risk probability division of different levels according to the cluster categories;
substep 3.2, calculating the risk loss value of each corresponding vehicle in the historical sample according to the data in the N groups of samples obtained in substep 2.2, and obtaining N risk loss values; and dividing the N risk loss values into a plurality of categories;
and a substep 3.3 of constructing a vehicle risk classification matrix according to the threshold values determined by the substep 3.1 and classified by the risk probability of different grades and the risk loss values of the plurality of classes classified by the substep 3.2.
7. The method for assessing and warning the risk of a road intersection based on the physiological data of the driver as claimed in claim 6, wherein the step 4 comprises the following substeps:
substep 4.1, having calibrated parameter w according to the currently implemented intersectionjThe vehicle risk probability model calculates the risk probability value of the target vehicle at the current implementation intersection;
substep 4.2, calculating a risk loss value of the target vehicle at the current implementation intersection;
and substep 4.3, calculating a risk value of the target vehicle at the current implementation intersection according to the intersection vehicle risk assessment model in the step 1.
8. The method for assessing and warning the risk of a road intersection based on the physiological data of the driver as claimed in claim 7, wherein the step 5 comprises the following substeps:
substep 5.1, updating the threshold value of risk probability division according to the risk probability value of the target vehicle at the current implementation intersection calculated in substep 4.1;
substep 5.2, establishing an updated vehicle risk grade division matrix according to the updated risk probability division threshold value in substep 5.1;
and substep 5.3, determining the target vehicle risk level according to the updated vehicle risk level classification matrix.
9. The method for evaluating and warning the risk of a road intersection based on the physiological data of the driver according to claim 1, wherein the step 6 specifically comprises the following steps: and counting the proportion of the target vehicles at each risk level in one signal period of the currently implemented intersection, and determining the risk level of the currently implemented intersection according to the proportion of the target vehicles at each risk level.
10. The method for assessing and warning the risk of a road intersection based on the physiological data of the driver as claimed in claim 9, wherein statistical data in the time length of the previous signal period is backtracked every 10s, and warning is issued according to the analysis result of the statistical data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010091611.7A CN111311093B (en) | 2020-02-13 | 2020-02-13 | Road intersection risk assessment and early warning method based on driver physiological data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010091611.7A CN111311093B (en) | 2020-02-13 | 2020-02-13 | Road intersection risk assessment and early warning method based on driver physiological data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111311093A true CN111311093A (en) | 2020-06-19 |
CN111311093B CN111311093B (en) | 2023-09-05 |
Family
ID=71160051
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010091611.7A Active CN111311093B (en) | 2020-02-13 | 2020-02-13 | Road intersection risk assessment and early warning method based on driver physiological data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111311093B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112530164A (en) * | 2020-11-30 | 2021-03-19 | 长安大学 | Active driving safety early warning method and system for high-altitude area road |
CN112862276A (en) * | 2021-01-26 | 2021-05-28 | 电子科技大学 | Vehicle networking platform and method for defining risk preference of driver by combining longitudinal direction and transverse direction |
CN113468698A (en) * | 2021-06-30 | 2021-10-01 | 上海理工大学 | Traffic flow model parameter calibration method facing intersection traffic trajectory discreteness |
CN114781791A (en) * | 2022-03-11 | 2022-07-22 | 山东高速建设管理集团有限公司 | High-speed service area risk identification method based on holographic sensing data |
CN115063766A (en) * | 2022-06-17 | 2022-09-16 | 公安部交通管理科学研究所 | Automatic driving automobile operation safety assessment and early warning method |
WO2024139285A1 (en) * | 2022-12-28 | 2024-07-04 | 深圳云天励飞技术股份有限公司 | Traffic intersection management method and apparatus, electronic device and storage medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104354698A (en) * | 2014-12-12 | 2015-02-18 | 山东交通学院 | System and method for distinguishing stress of driver based on electrocardiosignals and geographic information |
WO2016028228A1 (en) * | 2014-08-21 | 2016-02-25 | Avennetz Technologies Pte Ltd | System, method and apparatus for determining driving risk |
AU2015271971A1 (en) * | 2015-02-01 | 2016-08-18 | Fisher, Phyllis MS | A vehicle driver monitoring method, arrangement, system, software and application |
CN107909854A (en) * | 2017-12-13 | 2018-04-13 | 北京交通大学 | A kind of braking method for early warning and system based on brain wave |
CN108230676A (en) * | 2018-01-23 | 2018-06-29 | 同济大学 | A kind of intersection pedestrian's street crossing methods of risk assessment based on track data |
CN108615110A (en) * | 2018-04-23 | 2018-10-02 | 吉林大学 | The driving risk evaluating system of view-based access control model characteristic |
CN109389824A (en) * | 2017-08-04 | 2019-02-26 | 华为技术有限公司 | A kind of appraisal procedure and device driving risk |
-
2020
- 2020-02-13 CN CN202010091611.7A patent/CN111311093B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2016028228A1 (en) * | 2014-08-21 | 2016-02-25 | Avennetz Technologies Pte Ltd | System, method and apparatus for determining driving risk |
CN104354698A (en) * | 2014-12-12 | 2015-02-18 | 山东交通学院 | System and method for distinguishing stress of driver based on electrocardiosignals and geographic information |
AU2015271971A1 (en) * | 2015-02-01 | 2016-08-18 | Fisher, Phyllis MS | A vehicle driver monitoring method, arrangement, system, software and application |
CN109389824A (en) * | 2017-08-04 | 2019-02-26 | 华为技术有限公司 | A kind of appraisal procedure and device driving risk |
CN107909854A (en) * | 2017-12-13 | 2018-04-13 | 北京交通大学 | A kind of braking method for early warning and system based on brain wave |
CN108230676A (en) * | 2018-01-23 | 2018-06-29 | 同济大学 | A kind of intersection pedestrian's street crossing methods of risk assessment based on track data |
CN108615110A (en) * | 2018-04-23 | 2018-10-02 | 吉林大学 | The driving risk evaluating system of view-based access control model characteristic |
Non-Patent Citations (1)
Title |
---|
朱彤;杨晓光;白玉;许建;马国胜: "道路交叉口车辆碰撞动态风险估计方法", vol. 023, no. 004 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112530164A (en) * | 2020-11-30 | 2021-03-19 | 长安大学 | Active driving safety early warning method and system for high-altitude area road |
CN112862276A (en) * | 2021-01-26 | 2021-05-28 | 电子科技大学 | Vehicle networking platform and method for defining risk preference of driver by combining longitudinal direction and transverse direction |
CN112862276B (en) * | 2021-01-26 | 2023-04-28 | 电子科技大学 | Longitudinal and transverse combined Internet of vehicles device and method for defining risk preference of driver |
CN113468698A (en) * | 2021-06-30 | 2021-10-01 | 上海理工大学 | Traffic flow model parameter calibration method facing intersection traffic trajectory discreteness |
CN114781791A (en) * | 2022-03-11 | 2022-07-22 | 山东高速建设管理集团有限公司 | High-speed service area risk identification method based on holographic sensing data |
CN114781791B (en) * | 2022-03-11 | 2023-09-29 | 山东高速建设管理集团有限公司 | High-speed service area risk identification method based on holographic perception data |
CN115063766A (en) * | 2022-06-17 | 2022-09-16 | 公安部交通管理科学研究所 | Automatic driving automobile operation safety assessment and early warning method |
CN115063766B (en) * | 2022-06-17 | 2024-05-24 | 公安部交通管理科学研究所 | Automatic driving automobile operation safety assessment and early warning method |
WO2024139285A1 (en) * | 2022-12-28 | 2024-07-04 | 深圳云天励飞技术股份有限公司 | Traffic intersection management method and apparatus, electronic device and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN111311093B (en) | 2023-09-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111311093B (en) | Road intersection risk assessment and early warning method based on driver physiological data | |
CN113743471B (en) | Driving evaluation method and system | |
CN109493566B (en) | Fatigue driving prediction method based on GPS data | |
CN103895649B (en) | A kind of driver safety driving warning method | |
CN103247091A (en) | Driving evaluation system and driving evaluation method | |
CN101491443A (en) | Relational model of driver fatigue and vehicle riding trail | |
CN107095670A (en) | Time of driver's reaction Forecasting Methodology | |
CN113112796B (en) | Construction method and system of driving behavior characteristics and driving behavior analysis method | |
CN112116263B (en) | Traffic intersection risk level assessment method and device, electronic equipment and storage medium | |
CN110562261B (en) | Method for detecting risk level of driver based on Markov model | |
CN106780266B (en) | Principal component contribution degree parameter-based accident hotspot internal characteristic analysis and driving guidance method | |
CN107095671A (en) | Driving fatigue recognition methods and system | |
CN110781873A (en) | Driver fatigue grade identification method based on bimodal feature fusion | |
CN110533909A (en) | A kind of driving behavior analysis method and system based on traffic environment | |
CN111563555A (en) | Driver driving behavior analysis method and system | |
CN113753059B (en) | Method for predicting takeover capacity of driver under automatic driving system | |
CN106859674A (en) | A kind of upland highway driver gives birth to mental load degree characterizing method | |
CN113160564A (en) | Traffic safety early warning analysis method and device and computer equipment | |
CN113581188A (en) | Commercial vehicle driver driving style identification method based on Internet of vehicles data | |
CN111657923A (en) | Method and system for testing danger perception capability of driver | |
CN107150690B (en) | A kind of driving fatigue method for early warning based on roadmarking | |
CN110867075B (en) | Method for evaluating influence of road speed meter on reaction behavior of driver under rainy condition | |
CN117238126A (en) | Traffic accident risk assessment method under continuous flow road scene | |
CN109649399A (en) | A kind of driver distraction's method of discrimination based on lateral running speed | |
Lv et al. | Compact vehicle driver fatigue recognition technology based on EEG signal |
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 |