CN115862268A - Dangerous driving behavior grading early warning method based on multi-source internet data - Google Patents
Dangerous driving behavior grading early warning method based on multi-source internet data Download PDFInfo
- Publication number
- CN115862268A CN115862268A CN202211095421.8A CN202211095421A CN115862268A CN 115862268 A CN115862268 A CN 115862268A CN 202211095421 A CN202211095421 A CN 202211095421A CN 115862268 A CN115862268 A CN 115862268A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- early warning
- driving
- driving behavior
- behavior
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 230000006399 behavior Effects 0.000 claims abstract description 126
- 230000008569 process Effects 0.000 claims abstract description 12
- 238000011160 research Methods 0.000 claims abstract description 10
- 230000008859 change Effects 0.000 claims abstract description 9
- 230000001815 facial effect Effects 0.000 claims abstract description 7
- 239000011159 matrix material Substances 0.000 claims description 24
- 239000013598 vector Substances 0.000 claims description 6
- 230000006855 networking Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 5
- 238000011156 evaluation Methods 0.000 description 5
- 206010039203 Road traffic accident Diseases 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 241001282135 Poromitra oscitans Species 0.000 description 2
- 206010048232 Yawning Diseases 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000004399 eye closure Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000035790 physiological processes and functions Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000011158 quantitative evaluation Methods 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 230000028838 turning behavior Effects 0.000 description 1
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention discloses a dangerous driving behavior grading early warning method based on multi-source internet data, which comprises the following steps: acquiring positioning data information of a vehicle in real time, and analyzing to obtain current speed, continuous running time and position information; carrying out overspeed behavior research and judgment based on the current speed and the speed limit information of the road; positioning and video data are fully fused to realize lane-level positioning, and frequent lane change behavior study and judgment are realized based on the lane-level positioning; acquiring a facial image of a driver in real time, detecting the fatigue state of the driver by using a machine vision algorithm, and studying and judging fatigue driving behaviors by combining continuous driving time; and determining the index weight of the three dangerous driving behaviors based on an analytic hierarchy process, grading the danger degree, and realizing graded early warning. The invention can realize accurate identification of three dangerous driving behaviors of over-speed driving, frequent lane changing and fatigue driving based on multi-source internet data, and can carry out real-time dynamic grading early warning according to the grading of the danger degree, thereby effectively standardizing the driving behaviors and ensuring the traffic safety.
Description
Technical Field
The invention belongs to the field of traffic safety, and particularly relates to a dangerous driving behavior graded early warning method based on multi-source internet data.
Background
In recent years, the traffic transportation industry in China is rapidly developed, road infrastructure is continuously improved, meanwhile, the traffic safety problem is increasingly severe, and the frequency of traffic accidents is increased year by year. Among them, traffic accidents caused by dangerous driving behaviors of drivers occupy a large part of the traffic accidents. The dangerous driving behavior is detected in real time, effective early warning is issued to drivers in time, traffic accidents caused by the dangerous driving behavior can be effectively reduced, and traffic safety is guaranteed.
The existing patents and papers provide respective theoretical solutions for realizing real-time detection and timely and effective early warning of dangerous driving behaviors. The patent name: a vehicle driving behavior evaluation method based on an fuzzy analytic hierarchy process (patent number: CN 202210300077.5) discloses a vehicle driving behavior evaluation method based on a fuzzy analytic hierarchy process, which mainly analyzes data of a time stamp, longitude and latitude, a vehicle speed and a direction angle based on positioning data collected by vehicle-mounted positioning equipment, and calculates safety degree scores of six dangerous driving behaviors based on the data: overspeed behaviors, sharp turning behaviors, sharp acceleration behaviors, sharp deceleration behaviors, night driving behaviors and fatigue driving behaviors, and then, the safety degrees of the six dangerous driving behaviors are converted into a comprehensive dangerous driving behavior safety degree score by using a fuzzy analytic hierarchy process to evaluate the quality of the vehicle driving behaviors. The method is realized by the driving behavior evaluation result based on the positioning data, can finally obtain quantitative evaluation indexes, has the advantages of low cost, mature technology and the like, and still has a plurality of problems:
1) Firstly, the data source of the method is only single positioning data, and the evaluation result is greatly influenced by the positioning precision;
2) Secondly, the related research and judgment work of the fatigue driving behavior is only measured according to the continuous driving time length, and the fatigue state condition of a driver is ignored;
3) Finally, after the evaluation index of the driving behavior is obtained, the pertinence early warning work of the dangerous driving behavior is not further considered.
Disclosure of Invention
The invention aims to provide a dangerous driving behavior graded early warning method based on multi-source internet data.
The technical scheme for realizing the purpose of the invention is as follows: a dangerous driving behavior grading early warning method based on multi-source internet data comprises the following steps:
step 1, acquiring positioning data information of a current online vehicle in real time, and analyzing to obtain vehicle speed information, continuous running time information and vehicle position information;
step 2, carrying out overspeed behavior research and judgment based on the current vehicle running speed and the speed limit information of the road where the vehicle is located, and obtaining overspeed behavior risk degree parameters;
step 3, detecting the number of lane lines at the left end and the right end of the vehicle based on the vehicle position information and the external camera of the vehicle, realizing lane-level positioning, researching and judging the frequent lane changing behavior of the vehicle based on the lane-level positioning, and obtaining a frequent lane changing danger degree parameter;
step 4, acquiring facial images of a driver in real time through a camera in the vehicle, detecting the fatigue state of the driver by using a machine vision algorithm, and studying and judging fatigue driving behaviors by combining continuous driving time to obtain a risk degree parameter of the fatigue driving behaviors;
and 5, determining index weights of the three dangerous driving behaviors based on an analytic hierarchy process, grading the driving danger degree of the vehicle, and realizing graded early warning.
Preferably, an RTK positioning module based on a multi-mode GNSS is adopted in step 1 to realize centimeter-level positioning of the vehicle.
Preferably, in step 2, based on the current vehicle running speed and the speed limit information of the road where the vehicle is located, the specific rule for conducting the overspeed behavior research and judgment is as follows:
d 1 for the risk parameter of overspeed behavior, V is the real-time speed of the vehicle, V m The maximum driving speed threshold value of the automobile.
Preferably, the maximum driving speed threshold V m The method specifically comprises the following steps:
V m = road speed limit x (1-5%)
Preferably, the specific rule for implementing the study and judgment of the vehicle frequent lane changing behavior based on lane-level positioning is as follows:
in the formula, N change The number of times of lane changes of the vehicle within one minute before the present time, d 2 Is a frequent lane change risk parameter.
Preferably, the determination of fatigue driving in step 4 includes two parts of fatigue driving behavior and fatigue state, wherein the fatigue driving behavior is determined by comparing whether the currently recorded continuous driving time period T reaches the maximum allowable continuous driving time period T max And judging whether the driver is in the fatigue state or not, wherein the fatigue state is judged by acquiring facial images of the driver based on the camera in the vehicle, identifying and detecting fatigue characteristic behaviors through a machine vision algorithm.
Preferably, the specific method for obtaining the risk parameter of the fatigue driving behavior in the step 4 is as follows:
according to the current continuous driving time length T and the maximum allowable continuous driving time T of the vehicle recorded by the Internet of vehicles data max Obtaining the risk degree parameter d of the fatigue driving behavior 3 Comprises the following steps:
preferably, in step 5, the weights of the three dangerous driving behaviors influencing the driving risk level of the vehicle are calculated by an analytic hierarchy process, and the current driving behavior risk is calculated according to the weights, and the specific steps are as follows:
1) Constructing a decision matrix
According to the expert opinion, pairwise comparison is carried out on the three dangerous driving behaviors, the scale of the relative danger degree is determined, and the corresponding position of a judgment matrix is filled, so that the judgment matrix M is constructed as follows:
2) Decision matrix consistency check
Obtaining the maximum eigenvalue of the judgment matrix as lambda max =3.0037, calculate the consistency index CI:
when the order of the matrix is judged to be 3, the average random consistency index is RI =0.52, and the obtainable consistency ratio CR is:
therefore, the matrix M is judged to meet the consistency condition;
3) Method for calculating dangerous driving behavior weight by using characteristic value method
Obtaining the maximum eigenvalue lambda of the judgment matrix M max The corresponding feature vectors are:
[-0.4629,-0.1639,-0.8711] T
normalizing the feature vectors to obtain respective risk degree weights of three dangerous driving behaviors:
[0.3090,0.1095,0.5815] T
4) Calculating the risk index D of the current driving behavior
D＝0.3090d 1 +0.1095d 2 +0.5815d 3 。
Preferably, step 5 is to classify dangerous driving behavior levels according to the risk degree indexes, and determine corresponding graded early warning modes, specifically:
when the current driving behavior risk index D belongs to [0, 1), the early warning level is the first level, at the moment, the vehicle-mounted early warning system does not give an alarm, and only the collected driving data and the relevant risk index data are transmitted back to a background record in real time;
when the current driving behavior risk index D belongs to [1, 2), the early warning level is the second level, at the moment, the vehicle-mounted early warning system alarms in a language reminding mode and transmits related data back to a background record;
when the current driving behavior risk index D belongs to [2, 4), the early warning level is the third level, at the moment, the vehicle-mounted warning system issues a warning sound with the frequency lower than a set threshold value through a buzzer, and relevant data are transmitted back to a background record;
when the current driving behavior risk index D belongs to [4,6 ], the early warning level is the fourth level, at the moment, the vehicle-mounted warning system issues a warning sound with the frequency higher than a set threshold value through a buzzer, a warning lamp flashes at low frequency, and relevant data are transmitted back to a background for recording;
when the current driving behavior risk index D belongs to [6,10] or the obvious fatigue state of a driver is detected, the early warning level is the highest fifth level, at the moment, the vehicle-mounted alarm system issues alarm sound with the frequency higher than a set threshold value and the volume higher than the set threshold value through a buzzer, an alarm lamp flashes at high frequency, the driving authority is taken over by the automatic driving system, the current dangerous driving behavior is corrected, and related data are transmitted back to a background for recording.
Compared with the prior art, the invention has the following remarkable advantages:
(1) The method creatively combines a centimeter-level high-precision positioning technology with a machine vision technology, fully fuses centimeter-level positioning data and driving video data, and realizes high-robustness lane-level positioning;
(2) The invention can accurately identify three typical dangerous driving behaviors in real time in the whole course based on the driving data acquired by the vehicle-mounted positioning equipment and the internal and external bidirectional video monitoring equipment: compared with the prior art, the method provided by the invention is more comprehensive, more accurate and more reliable.
(3) The invention adopts AHP analytic hierarchy process, perfects the classification mechanism of the driving behavior danger degree, realizes the early warning schemes of different grades, and has higher practicability and integrity compared with other technical solutions.
Drawings
FIG. 1 is a schematic flow diagram of the present invention.
Detailed Description
In order to better understand the technical content of the present invention, specific embodiments are described below with reference to the accompanying drawings.
As shown in the attached figure 1, the dangerous driving behavior grading early warning method based on the multi-source internet data comprises the following specific steps:
step 1, acquiring positioning data information of a current internet vehicle in real time through vehicle-mounted high-precision positioning equipment, and analyzing to obtain vehicle speed information, continuous running time information and vehicle position information.
Specifically, in the embodiment, the acquired real-time vehicle speed is set to be 90km/h; the continuous driving time is 6h;
the RTK positioning module based on the multi-mode GNSS is used for acquiring the position of the vehicle with the precision reaching centimeter level, so that the research and judgment precision of dangerous driving behaviors related to subsequent positioning is ensured, and the false alarm rate is reduced.
Step 2, calculating the maximum driving speed threshold V of the automobile according to the road speed limit information m To perform overspeed behavior study and judgment. Considering the problems of GPS positioning accuracy and speed sensor transmission accuracy, etc., an error value of-5% and a maximum driving speed threshold value V are set m The method comprises the following specific steps:
V m = speed limit for road x (1-5%)
The real-time speed V of the automobile and the maximum driving speed threshold V of the automobile are obtained by analyzing the positioning data information m Obtaining the overspeed behavior risk degree parameter d 1 ：
Specifically, in the present embodiment, the current vehicle speed is 90km/h, the road speed limit is 60km/h, and the maximum driving speed threshold V is set m And =57km/h. D is obtained according to a calculation formula of the overspeed behavior risk degree parameter 1 ＝5.7895。
Step 3, detecting the number of lane lines at the left end and the right end of the vehicle based on the vehicle positioning information and the external camera, realizing accurate lane-level positioning, and carrying out research and judgment on the frequent lane changing behavior of the vehicle, wherein the specific rule is as follows:
in the formula, N change The number of times of lane changes of the vehicle within one minute before the current time, d 2 Is a frequent lane change risk parameter.
Specifically, in this embodiment, centimeter-level location information is mainly obtained by the vehicle-mounted high-precision positioning module, and the road grade and the number of lanes in the database are read based on the positioning information.
Specifically, in this embodiment, the detection of the lane line may be implemented by acquiring image data and performing preprocessing based on a RetinaNet deep learning method. And then, judging the lane by calculating the number of lane lines on the left side and the right side of the current position of the vehicle.
Specifically, in this embodiment, it is assumed that the traveling vehicle changes lanes 3 times in one minute before the current time, and d is calculated according to the frequent lane change behavior risk degree parameter calculation formula 2 ＝5。
And 4, acquiring facial images of the driver in real time through the camera in the vehicle, detecting the fatigue state of the driver by using a machine vision algorithm, and studying and judging the fatigue driving behavior by combining continuous driving time.
The research and judgment of the fatigue driving comprises two parts of fatigue driving behavior and fatigue state, wherein the fatigue driving behavior pass ratioWhether the continuous driving time length T reaches the maximum allowable continuous driving time T or not is compared with the currently recorded continuous driving time length T max Judging whether the driver is in the fatigue state or not, wherein the fatigue state is judged by acquiring facial images of the driver based on the camera in the vehicle, identifying and detecting the characteristic behaviors of head lowering, no front view, yawning and eye closing fatigue through a machine vision algorithm, and judging whether the driver is in the fatigue state or not
Specifically, in the present embodiment, for the detection of the fatigue state, an in-vehicle camera is used, deep learning is adopted, and the MTCNN and YOLOv5 networks are combined to detect the fatigue features of the driver such as head lowering, no front view, yawning, eye closure and the like, and the physiological state of the driver is monitored in real time to detect whether the fatigue driving symptom is generated.
Specifically, in the embodiment, the current continuous driving time T and the maximum allowable continuous driving time T of the vehicle are recorded according to the Internet of vehicles data max Obtaining the risk degree parameter d of the fatigue driving behavior 3 Comprises the following steps:
specifically, in the present embodiment, the maximum allowable continuous travel time T is set max Is 4h. If the obvious fatigue characteristics of the driver are not detected but the continuous driving time reaches 6h, d is obtained according to a calculation formula of the fatigue driving behavior risk degree parameter 3 ＝5。
And 5, determining index weights of the three dangerous driving behaviors based on an analytic hierarchy process, grading the driving danger degree of the vehicle, and realizing graded early warning.
The method comprises the following steps of calculating the weight of three dangerous driving behaviors influencing the driving danger level of a vehicle by an analytic hierarchy process, and calculating the current driving behavior danger degree by the weight, wherein the specific steps are as follows:
1) Constructing a decision matrix
According to expert opinions, pairwise comparison is carried out on the three dangerous driving behaviors, relative danger degree scales are determined, and corresponding positions of a judgment matrix are filled, so that the judgment matrix M is constructed as follows:
2) Decision matrix consistency check
Obtaining the maximum eigenvalue of the judgment matrix as lambda max =3.0037, calculate the consistency index CI:
when the order of the matrix is judged to be 3, the average random consistency index is RI =0.52, and the obtainable consistency ratio CR is:
therefore, the matrix M is judged to meet the consistency condition;
3) Method for calculating weight of dangerous driving behavior by using characteristic value method
Obtaining the maximum eigenvalue lambda of the judgment matrix M max The corresponding feature vectors are:
[-0.4629,-0.1639,-0.8711] T
normalizing the feature vectors to obtain respective risk degree weights of three dangerous driving behaviors:
[0.3090,0.1095,0.5815] T
4) Calculating the risk index D of the current driving behavior
D＝0.3090d 1 +0.1095d 2 +0.5815d 3 。
5) And (4) dividing dangerous driving behavior grades according to the risk degree indexes, and determining corresponding grading early warning modes.
When the current driving behavior risk index D belongs to [0, 1), the early warning level is the first level, at the moment, the vehicle-mounted early warning system does not give an alarm, and only the collected driving data and the relevant risk index data are transmitted back to a background record in real time;
when the current driving behavior risk index D belongs to [1, 2), the early warning level is the second level, at the moment, the vehicle-mounted early warning system alarms in a language reminding mode and transmits related data back to a background record;
when the current driving behavior risk index D belongs to [2, 4), the early warning level is the third level, and at the moment, the vehicle-mounted warning system issues a low-frequency warning sound through a buzzer and transmits related data back to a background for recording;
when the current driving behavior risk index D belongs to [4,6 ], the early warning level is the fourth level, at the moment, the vehicle-mounted warning system issues a high-frequency warning sound by a buzzer, a warning lamp flashes at a low frequency, and related data are transmitted back to a background for recording;
when the current driving behavior risk index D belongs to [6,10] or the obvious fatigue state of a driver is detected, the early warning level is the highest fifth level, at the moment, the vehicle-mounted warning system issues high-frequency and high-volume warning sound through the buzzer, the warning lamp flashes at high frequency, the driving authority is taken over by the automatic driving system, the current dangerous driving behavior is corrected, and relevant data are returned to a background for recording.
Specifically, in this embodiment, according to the index weight calculated by the analytic hierarchy process and the driving data, the risk index of the current driving behavior of the driver is:
D＝0.3090×5.7895+0.1095×5+0.5815×5＝5.2440
at the moment, the early warning level is the fourth level, the vehicle-mounted warning system issues a sharp warning sound through the buzzer, the warning lamp flashes at a low frequency, and related data are transmitted back to the background record.
The invention provides a dangerous driving behavior grading early warning method based on multi-source internet connection data under the background of rapid development of emerging technologies such as current intelligent internet connection, artificial intelligence and high-precision positioning technology. The invention can realize accurate identification of three dangerous driving behaviors of overspeed, frequent lane change and fatigue driving based on multi-source networking information of people, vehicles, roads and environments under the intelligent networking environment, and realize real-time dynamic graded early warning according to the rating of dangerous degrees, thereby effectively standardizing the driving behaviors and ensuring the traffic safety.
Although the present invention has been described with reference to the preferred embodiments, it is not intended to be limited thereto. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the invention. Therefore, the protection scope of the present invention should be determined by the appended claims.
Claims (9)
1. A dangerous driving behavior grading early warning method based on multi-source internet data is characterized by comprising the following steps:
step 1, acquiring positioning data information of a current networked vehicle in real time, and analyzing to obtain vehicle speed information, continuous running time information and vehicle position information;
step 2, carrying out overspeed behavior research and judgment based on the current vehicle running speed and the speed limit information of the road where the vehicle is located, and obtaining overspeed behavior risk degree parameters;
step 3, detecting the number of lane lines at the left end and the right end of the vehicle based on the vehicle position information and the external camera of the vehicle, realizing lane-level positioning, researching and judging the frequent lane changing behavior of the vehicle based on the lane-level positioning, and obtaining a frequent lane changing danger degree parameter;
step 4, acquiring facial images of a driver in real time through a camera in the vehicle, detecting the fatigue state of the driver by using a machine vision algorithm, and studying and judging fatigue driving behaviors by combining continuous driving time to obtain a risk degree parameter of the fatigue driving behaviors;
and 5, determining index weights of the three dangerous driving behaviors based on an analytic hierarchy process, grading the driving danger degree of the vehicle, and realizing graded early warning.
2. The dangerous driving behavior grading early warning method based on multi-source internet data as claimed in claim 1, wherein step 1 adopts an RTK positioning module based on multi-mode GNSS to realize centimeter-level positioning of the vehicle.
3. The dangerous driving behavior grading early warning method based on the multi-source internet data as claimed in claim 1, wherein the specific rule for carrying out overspeed behavior research and judgment based on the current vehicle running speed and the speed limit information of the road where the vehicle is located in the step 2 is as follows:
d 1 for the risk parameter of overspeed behavior, V is the real-time speed of the vehicle, V m The maximum driving speed threshold value of the automobile.
4. The dangerous driving behavior graded early warning method based on multi-source internet data according to claim 1, characterized in that a maximum driving speed threshold V m The method specifically comprises the following steps:
V m = speed limit for road x (1-5%)
5. The dangerous driving behavior grading early warning method based on the multi-source internet data as claimed in claim 1, wherein the specific rule for realizing the study and judgment of the vehicle frequent lane changing behavior based on the lane-level positioning is as follows:
in the formula, N change The number of times of lane changes of the vehicle within one minute before the present time, d 2 Is a frequent lane change risk parameter.
6. The dangerous driving behavior graded early warning method based on multi-source networking data as claimed in claim 1, wherein the research and judgment on fatigue driving in the step 4 comprises fatigue driving behavior and fatigue state, wherein the fatigue driving behavior is obtained by comparing whether the currently recorded continuous driving time T reaches the maximum allowable continuous driving time T max And judging whether the driver is in the fatigue state or not by acquiring facial images of the driver based on the camera in the vehicle and identifying and detecting fatigue characteristic behaviors through a machine vision algorithm.
7. The dangerous driving behavior grading early warning method based on the multi-source internet data as claimed in claim 1 or 6, wherein the specific method for obtaining the fatigue driving behavior risk degree parameter in the step 4 is as follows:
according to the current continuous driving time length T and the maximum allowable continuous driving time T of the vehicle recorded by the Internet of vehicles data max The comparison result of (a) to obtain a fatigue driving behavior risk degree parameter d 3 Comprises the following steps:
8. the dangerous driving behavior grading early warning method based on the multi-source internet data as claimed in claim 1, wherein in the step 5, weights of three dangerous driving behaviors influencing the vehicle driving danger grade are calculated through an analytic hierarchy process, and the current driving behavior danger degree is calculated through the weights, and the specific steps are as follows:
1) Constructing a decision matrix
According to expert opinions, pairwise comparison is carried out on the three dangerous driving behaviors, relative danger degree scales are determined, and corresponding positions of a judgment matrix are filled, so that the judgment matrix M is constructed as follows:
2) Decision matrix consistency check
Obtaining the maximum eigenvalue of the judgment matrix as lambda max =3.0037, the consistency index CI is calculated:
when the order of the matrix is judged to be 3, the average random consistency index is RI =0.52, and the obtainable consistency ratio CR is:
therefore, the matrix M is judged to meet the consistency condition;
3) Method for calculating weight of dangerous driving behavior by using characteristic value method
Obtaining the maximum eigenvalue lambda of the judgment matrix M max The corresponding feature vectors are:
[-0.4629,-0.1639,-0.8711] T
normalizing the feature vectors to obtain respective risk degree weights of three dangerous driving behaviors:
[0.3090,0.1095,0.5815] T
4) Calculating the risk index D of the current driving behavior
D＝0.3090d 1 +0.1095d 2 +0.5815d 3 。
9. The dangerous driving behavior graded early warning method based on the multi-source internet data as claimed in claim 8, wherein step 5 is to classify dangerous driving behavior grades according to the risk degree indexes and determine corresponding graded early warning modes, specifically:
when the current driving behavior risk index D belongs to [0, 1), the early warning level is the first level, at the moment, the vehicle-mounted early warning system does not give an alarm, and only the collected driving data and the relevant risk index data are transmitted back to a background record in real time;
when the current driving behavior risk index D belongs to [1, 2), the early warning level is the second level, at the moment, the vehicle-mounted early warning system alarms in a language reminding mode and transmits related data back to a background record;
when the current driving behavior risk index D belongs to [2,4 ], the early warning level is the third level, at the moment, the vehicle-mounted warning system issues a warning sound with the frequency lower than a set threshold value through a buzzer, and sends related data back to a background record;
when the current driving behavior risk index D belongs to [4,6 ], the early warning level is the fourth level, at the moment, the vehicle-mounted warning system issues a warning sound with the frequency higher than a set threshold value through a buzzer, a warning lamp flashes at low frequency, and relevant data are transmitted back to a background for recording;
when the current driving behavior risk index D belongs to [6,10] or the obvious fatigue state of a driver is detected, the early warning level is the highest fifth level, at the moment, the vehicle-mounted alarm system issues alarm sound with the frequency higher than a set threshold value and the volume higher than the set threshold value through a buzzer, an alarm lamp flashes at high frequency, the driving authority is taken over by the automatic driving system, the current dangerous driving behavior is corrected, and related data are transmitted back to a background for recording.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211095421.8A CN115862268A (en) | 2022-09-06 | 2022-09-06 | Dangerous driving behavior grading early warning method based on multi-source internet data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211095421.8A CN115862268A (en) | 2022-09-06 | 2022-09-06 | Dangerous driving behavior grading early warning method based on multi-source internet data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115862268A true CN115862268A (en) | 2023-03-28 |
Family
ID=85660832
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211095421.8A Withdrawn CN115862268A (en) | 2022-09-06 | 2022-09-06 | Dangerous driving behavior grading early warning method based on multi-source internet data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115862268A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117672003A (en) * | 2023-11-23 | 2024-03-08 | 北京悟空出行科技有限公司 | Vehicle remote monitoring system for car renting company |
| CN118013234A (en) * | 2024-04-08 | 2024-05-10 | 浙江吴霞科技有限公司 | Multi-source heterogeneous big data-based key vehicle driver portrait intelligent generation system |
-
2022
- 2022-09-06 CN CN202211095421.8A patent/CN115862268A/en not_active Withdrawn
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117672003A (en) * | 2023-11-23 | 2024-03-08 | 北京悟空出行科技有限公司 | Vehicle remote monitoring system for car renting company |
| CN117672003B (en) * | 2023-11-23 | 2024-05-14 | 北京悟空出行科技有限公司 | Vehicle remote monitoring system for car renting company |
| CN118013234A (en) * | 2024-04-08 | 2024-05-10 | 浙江吴霞科技有限公司 | Multi-source heterogeneous big data-based key vehicle driver portrait intelligent generation system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2020244288A1 (en) | Method and apparatus for evaluating truck driving behaviour based on gps trajectory data | |
| CN115862268A (en) | Dangerous driving behavior grading early warning method based on multi-source internet data | |
| CN110276953A (en) | Rule-breaking vehicle travel risk analysis method based on BEI-DOU position system | |
| Lyu et al. | Using naturalistic driving data to identify driving style based on longitudinal driving operation conditions | |
| CN106355883A (en) | Risk evaluation model-based traffic accident happening probability acquiring method and system | |
| CN106448265A (en) | Collecting method and device of driver's driving behavior data | |
| CN112201038A (en) | Road network risk assessment method based on risk of bad driving behavior of single vehicle | |
| CN111477005B (en) | Intelligent perception early warning method and system based on vehicle state and driving environment | |
| CN108769104B (en) | Road condition analysis and early warning method based on vehicle-mounted diagnosis system data | |
| CN112433519A (en) | Unmanned driving detection system and vehicle driving detection method | |
| CN109448384B (en) | A kind of highway danger traffic behavior recognition methods | |
| CN112380599A (en) | Bridge intelligent online monitoring and early warning system based on big data analysis | |
| CN114379559A (en) | Driving risk evaluation feature sketch method based on vehicle information acquisition system | |
| KR102477885B1 (en) | Safety analysis management server for evaluating autonomous driving roads | |
| CN117953715A (en) | Smart city traffic management system based on big data analysis | |
| CN113928333B (en) | Energy consumption reduction method and system based on auxiliary driving | |
| CN113359673A (en) | Automatic driving automobile performance judgment system based on big data | |
| CN116881778B (en) | Intelligent auxiliary teaching system safety early warning and protection function testing system and method | |
| CN113240901A (en) | Intelligent vehicle lane changing behavior risk level determination method and device | |
| CN117423233A (en) | Traffic transportation safety analysis system based on big data analysis | |
| CN116001800B (en) | Vehicle driving risk information acquisition method and device, electronic equipment and medium | |
| Liu et al. | Construction of driving behavior scoring model based on obd terminal data analysis | |
| CN114155742B (en) | Method for evaluating and early warning longitudinal driving risk of internet vehicle | |
| CN111775948B (en) | Driving behavior analysis method and device | |
| CN114756599A (en) | Driver abnormal speed change identification method based on vehicle GPS data |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20230328 |