CN106682295A - Analysis method for evaluating real-time safety characteristics of drivers - Google Patents
Analysis method for evaluating real-time safety characteristics of drivers Download PDFInfo
- Publication number
- CN106682295A CN106682295A CN201611170129.2A CN201611170129A CN106682295A CN 106682295 A CN106682295 A CN 106682295A CN 201611170129 A CN201611170129 A CN 201611170129A CN 106682295 A CN106682295 A CN 106682295A
- Authority
- CN
- China
- Prior art keywords
- data
- driver
- car
- time
- real
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
Abstract
The invention belongs to the technical field of driving safety evaluation, and particularly relates to an analysis method for evaluating real-time safety characteristics of drivers. The method comprises the steps of S1, using a data collection module to collect real-time driving data, wherein the real-time driving data comprises the driving condition data of the local car and a front car, the acceleration of the local car, the velocities of the local car and the front car and the car link between the local car and the front car; S2, establishing a car-following model C=alfa*delta t based on the real-time driving data, wherein, C is a stability index, alfa is the driver sensitivity coefficient, delta t is the driver's response time, the model is fitted based on the collected data, a target function is the root-mean-square deviation; S3, based on the fitting result, outputting a model result, if the model result is danger, and warning the driver to take corresponding safety measures. The driver's condition is monitored in a real-time mode based on the driving data. Real-time warnings are triggered for unstable driving conditions of the driver. When the result indicates the car-following condition of the driver is unstable, warnings are sent to the driver to make the driver drive normally and prevent the incidence of traffic accidents.
Description
Technical field
The invention belongs to the technical field that drive safety is evaluated, more particularly to a kind of to be used for driver's actual time safety characteristic
The analysis method of assessment.
Background technology
Traffic safety is problem closely bound up with human health and development in global range, and Indian university of the U.S. grinds
Study carefully confirmation:At least 92.6% vehicle accident is relevant with human factorss.The Chinese authority's data report points out, 70% traffic thing
Therefore be driver's responsibility.It is the most factors of instability relatively in road traffic system that its reason is people, the physiology of people, psychology with
The change for space-time shows potential changeableness and undulatory property.Driver is the main body of people-Che-road system, and it is individual special
Property determine the quality of driving behavior, and then affect traffic safety, these characteristics include various direct factors (it is improper such as to note,
Bradykinesia, drive over the speed limit, neglect, improper measures etc.) and indirect factor (such as alcoholism, drug induced injury, lacking experience).
Accident research shows that about 90% vehicle accident is due to driver information handling failure, lacks the rows such as vigilance, technical ability is low
For caused.Any error that driver occurs in judgement, decision-making and operating process has the possibility for causing vehicle accident,
So particularly important to the real-time monitoring of driver's driving condition, this has remarkable effect in terms of preventing and reducing vehicle accident.
The current research to driver's actual time safety characteristic focus on by the collection analysises to driver's EEG signals with
Driver's whether fatigue driving, or the alcohol content of real-time monitoring driver are judged the analysis of driver's facial expression image
Judge whether drunk driving, or vehicle running state (steering wheel angle, car speed etc.) is analyzed judges driving behavior
Reasonability.There is the problems such as accuracy is inadequate, and practicality is not strong in above-mentioned driving condition supervision system, it is difficult to actually driving ring
Popularization and application in border.
The content of the invention
For the problems referred to above, the present invention proposes a kind of analysis method for driver's actual time safety characteristic evaluation, wraps
Include following steps:
Step 1, by the real-time travelling data of data collecting module collected, the real-time travelling data includes Ben Che and front truck
Transport condition data, the acceleration of this car, the spacing of the speed, Ben Che and front truck of Ben Che and front truck;
Step 2, following-speed model C=α Δ t are set up according to the real-time travelling data, wherein, C is stability indicator, α
It is the response time of driver for driver's sensitivity coefficient, Δ t, based on the data of collection models fitting, object function is carried out
For root-mean-square deviation RMSE;
Step 3, according to it is described fitting output model result, if the model result for danger, remind driver take
Corresponding safety measure.
The data acquisition module includes sensor acquisition module, video acquisition module, gps data acquisition module, utilizes
The sensor acquisition module, video acquisition module, gps data acquisition module collection real time data, specifically include:
Step 101, the sensor acquisition module gather the spacing of this car and front truck, and the gps data acquisition module is adopted
Collect the speed and acceleration of this car, the frequency of gathered data is 5Hz;
Step 102, according to the data of collection, the speed that obtains Ben Che and front truck is poor, the spacing of Ben Che and front truck, this car
Acceleration.
The step 101 also includes:The video analysis gathered by the video acquisition module obtain Ben Che with front truck
Spacing, the speed of this car and acceleration.
The step 2 is specifically included:
Step 201, using the parameter at the data scaling current time of 13 seconds before current time, the frequency of demarcation is 1Hz;
Step 202, the predictive value of rear car acceleration is obtained according to following-speed model fitting, and entered with actual acquired data
Row contrast, obtains root-mean-square deviation RMSE of the predictive value and the actual acquired data;
Step 203, all feasible values of traversal α and Δ t, wherein α ∈ [0,3], step-length 0.01, Δ t ∈ [0,2], step-length
0.2;When RMSE is minimum, parameter alpha, the calibration value of Δ t are obtained.
The step 3 is specifically included:
Step 301, according to model parameter α, the calibration value of Δ t, calculate and export the value of a C=α Δ t each second;
Step 302, the interval for judging C in C=α Δ t, wherein:
(1) if 0≤C=α are Δ t≤1/e, system absolute stability;
(2) if 1/e is < (C=α T)≤pi/2, system stability, but not absolute stability;
(3) if (C=α T) > pi/2s, system is unstable;
Step 303, analysis train tracing model stability, when C values fall in unstable interval or in a long time in gradually
During ascendant trend, then it is assumed that driver is it is possible that danger, now reminds driver to take corresponding safety measure.
The beneficial effects of the present invention is:
The present invention passes through a set of driver's driving condition safe early warning method of design, especially by the real-time driving number of collection
According to, using following-speed model fitting data, based on the unstable driving condition of model and parameters identification driver and to driver provide reality
When early warning.Stability analyses based on following-speed model are analyzed to the security feature of driver, the safety point to driver
Analysis has solid traffic flow theory to support.Based on the state of travelling data monitor in real time driver, unstable to driver can drive
State real-time early warning is sailed, when result display driver's train tracing model is unstable, reminds driver's normal driving, prevention to hand in time
Interpreter thus occur.
Description of the drawings
Fig. 1 is the real-time C values curve chart of driver;
Fig. 2 is the workflow schematic diagram of the analysis method for driver's actual time safety characteristic evaluation.
Specific embodiment
Below in conjunction with the accompanying drawings, embodiment is elaborated.
Embodiment one:
The invention provides a kind of analysis method for driver's actual time safety characteristic evaluation, it is characterised in that design one
Set driver's driving condition safe early warning method, system includes data acquisition, data processing and the part of early warning three.Wherein count
According to process part actual travelling data is analyzed using following-speed model, recognizes driver's labile state;Early warning portion
Divide according to data processed result, remind driver safety to drive in time, prevent and reduction vehicle accident.Comprise the steps:
Step 1, by the real-time travelling data of data collecting module collected, including the transport condition data of Ben Che and front truck:
The acceleration of this car, the spacing between the speed of Ben Che and front truck, two cars;
Step 2, the real-time travelling data obtained according to step 1 set up following-speed model, and based on the data of collection model is carried out
Fitting, object function is RMSE, the parameter alpha, Δ t in peg model;
Step 3, output model result, for dangerous situation, remind driver to take corresponding safety measure.
In the step 1, part of data acquisition includes sensor acquisition module, video acquisition module, gps data collection mould
Block, using above-mentioned module real time data is gathered, including:
Step 101, sensor acquisition module gather two car spacings, and gps data module gathers the speed and acceleration of this car
Information;Or the video analysis gathered by video acquisition module obtain two car spacings, speed and acceleration information, gathered data
Frequency is 5Hz;
Step 102, according to collection data, the speed that can obtain two cars based on newtonian motion mechanical knowledge is poor, spacing
With the acceleration of this car.
In the step 2, following-speed model is set up according to the real-time travelling data that step 1 is obtained, following-speed model is divided into linearly
Following-speed model and nonlinear car-following model etc., here we use linear following-speed model.Theoretical equation is:
Wherein,For the acceleration of this car,WithRespectively front truck and Ben Che
Speed, thereforeFor the speed difference of two cars.
Parameter alpha, the Δ t demarcated in above-mentioned linear model, including:
Step 201, the parameter in order to demarcate current time, were calculated using the data of 13 seconds before current time, were demarcated
Frequency be 1Hz, i.e., each second calculate once;
Step 202, the predictive value that rear car acceleration is obtained by models fitting, then contrasted with actual acquired data,
Calculating target function.Object function is both root-mean-square deviations RMSE, and root-mean-square error is less, and model-fitting degree is higher;
Step 203, all feasible values of traversal α and Δ t, wherein α ∈ [0,3], step-length 0.01, Δ t ∈ [0,2], step-length
0.2;When model-fitting degree obtains optimal solution, i.e. when RMSE is minimum, obtain parameter alpha, the calibration value of Δ t.
The step 3 output model result, according to following-speed model C=α Δs t be located interval, analyze with speed on for
Stability, concrete grammar includes:
Step 301, using the parameter demarcated in step 2, export the status information of a driver each second, that is, often
Second calculate C=α Δ t value;
Step 302, the interval for judging C=α Δ t, wherein:
(1) 0≤C=α Δ t≤1/e, system absolute stability;
(2) 1/e < (C=α T)≤pi/2, system stability, but not absolute stability;
(3) (C=α T) > pi/2s, system is unstable;
Step 303, analysis train tracing model stability, when C values fall in unstable interval or in a long time in gradually
During ascendant trend, it is believed that driver is it is possible that danger, now reminds driver's careful driving, or appropriate rest.
Embodiment two:
The invention provides a kind of method to the analysis in real time of driver safety characteristic, as shown in Fig. 2 including following step
Suddenly:
Step 1, by the real-time travelling data of data collecting module collected, including the transport condition data of Ben Che and front truck:
The acceleration of this car, the spacing between the speed of Ben Che and front truck, two cars;
Step 2, the real-time travelling data obtained according to step 1 set up following-speed model, and based on the data of collection model is carried out
Fitting, object function is RMSE, the parameter alpha, Δ t in peg model;
Step 3, output model result, for dangerous situation, remind driver to take corresponding safety measure.
For three above-mentioned big steps, by taking certain driving procedure as an example, the present invention is explained.
In the step 1, by the real-time travelling data of data collecting module collected, including:
Step 101, sensor acquisition module gather this car and front truck spacing, gps data module gather the speed of this car and
Acceleration information (or the video analysis gathered by video acquisition module obtain two car spacings, speed and acceleration information), adopts
Integrate the frequency of data as 5Hz;
Step 102, according to the data of collection, based on newtonian motion mechanical knowledge calculate two cars speed is poor, spacing and
The acceleration of car.Only show the front real time data for collecting for 3 seconds herein, as shown in table 1 (vehicle starts to be designated as 0 moment with speeding,
Start gathered data from 10s).
Front 3 seconds real time datas of the collection of table 1
The real-time travelling data obtained according to step 1 in the step 2 sets up linear following-speed model, and demarcates linear model
In parameter alpha, Δ t, including:
Step 201, the parameter in order to demarcate current time, were calculated using the data of 13 seconds before current time, were demarcated
Frequency be 1Hz, i.e., each second calculate once;
Step 202, the predictive value that rear car acceleration is obtained by models fitting, then contrasted with actual acquired data,
Calculating target function.Object function is both root-mean-square deviations RMSE, and root-mean-square error is less, and model-fitting degree is higher;
Step 203, all feasible values of traversal α and Δ t, wherein α ∈ [0,3], step-length 0.01, Δ t ∈ [0,2], step-length
0.2;When model-fitting degree obtains optimal solution, i.e. when RMSE is minimum, obtain parameter alpha, the calibration value of Δ t.
Repeat step 2, the real-time parameter α of the linear following-speed model for obtaining, Δ t, the data such as table of 20s only show herein before
Shown in 2 (gathered data from the beginning of 10s, the calibrating parameters data of 13s before current time, therefore first parameter for obtaining
Calibration value is from the beginning of 23s).
Time (s) | α(s^-1) | Δt(s) |
23 | 0.92 | 2.0 |
24 | 1.04 | 2,0 |
25 | 1.09 | 1.8 |
26 | 1.17 | 2.0 |
27 | 1.07 | 2.0 |
28 | 1.02 | 1.8 |
29 | 1.00 | 1.6 |
30 | 0.98 | 1.6 |
31 | 1.00 | 1.4 |
32 | 0.88 | 1.6 |
33 | 0.70 | 1.4 |
34 | 0.45 | 1.4 |
35 | 0.61 | 0.8 |
36 | 0.67 | 0.8 |
37 | 0.76 | 0.8 |
38 | 0.80 | 0.8 |
39 | 0.84 | 0.8 |
40 | 0.88 | 0.8 |
41 | 1.01 | 0.8 |
42 | 1.02 | 0.8 |
The real-time model parameter alpha of table 2, Δ t
The step 3 output model result, according to following-speed model C=α Δs t be located interval, analyze with speed on for
Stability, including:
Step 301, using the parameter demarcated in step 2, export the status information of a driver each second, that is, often
The value of C=α Δ t second is calculated, the real-time C values curve for obtaining is as shown in figure 1, up and down dotted line is respectively Critical Stability value and absolute
Critical Stability value;
Step 302, the interval for judging C=α Δ t, wherein:
(1) 0≤C=α Δ t≤1/e, system absolute stability;
(2) 1/e < (C=α T)≤pi/2, system stability, but not absolute stability;
(3) (C=α T) > pi/2s, system is unstable;
Step 303, analysis train tracing model stability, when C values fall in unstable interval or in a long time in gradually
During ascendant trend, it is believed that driver is it is possible that danger, now reminds driver's careful driving, or appropriate rest.Can by Fig. 1
To find out:In this is with speeding, it should driver is reminded at the 64th second.
This embodiment is only the present invention preferably specific embodiment, but protection scope of the present invention is not limited thereto,
Any those familiar with the art the invention discloses technical scope in, the change or replacement that can be readily occurred in,
All should be included within the scope of the present invention.Therefore, protection scope of the present invention should be with scope of the claims
It is defined.
Claims (5)
1. a kind of driver's actual time safety method of evaluating characteristic, it is characterised in that comprise the steps:
Step 1, by the real-time travelling data of data collecting module collected, the real-time travelling data includes the row of Ben Che and front truck
Sail status data:The spacing of the acceleration of this car, the speed of Ben Che and front truck, Ben Che and front truck;
Step 2, following-speed model C=α Δ t are set up according to the real-time travelling data, wherein, C is stability indicator, α to drive
The person's of sailing sensitivity coefficient, Δ t are the response time of driver, and based on the data of collection models fitting is carried out, and object function is equal
Root difference RMSE;
Step 3, according to it is described fitting output model result, if the model result for danger, remind driver take accordingly
Safety measure.
2. method according to claim 1, it is characterised in that the data acquisition module include sensor acquisition module,
Video acquisition module, gps data acquisition module, using the sensor acquisition module, video acquisition module, gps data collection
Module gathers real time data, specifically includes:
Step 101, the sensor acquisition module gather the spacing of this car and front truck, and the gps data acquisition module collection is originally
The speed and acceleration of car, the frequency of gathered data is 5Hz;
Step 102, according to the data of collection, the speed that obtains Ben Che and front truck is poor, spacing, the acceleration of this car of Ben Che and front truck
Degree.
3. method according to claim 2, it is characterised in that the step 101 also includes:By the video acquisition mould
The video analysis of block collection obtain spacing, the speed of this car and the acceleration of Ben Che and front truck.
4. method according to claim 1, it is characterised in that the step 2 is specifically included:
Step 201, using the parameter at the data scaling current time of 13 seconds before current time, the frequency of demarcation is 1Hz;
Step 202, the predictive value of rear car acceleration is obtained according to following-speed model fitting, and carry out with actual acquired data it is right
Than obtaining root-mean-square deviation RMSE of the predictive value and the actual acquired data;
Step 203, all feasible values of traversal α and Δ t, wherein α ∈ [0,3], step-length 0.01, Δ t ∈ [0,2], step-length 0.2;When
When root-mean-square deviation RMSE is minimum, parameter alpha, the calibration value of Δ t are obtained.
5. method according to claim 4, it is characterised in that the step 3 is specifically included:
Step 301, according to model parameter α, the calibration value of Δ t, calculate and export the value of a C=α Δ t each second;
Step 302, the interval for judging C in C=α Δ t, wherein:
(1) if 0≤C=α are Δ t≤1/e, system absolute stability;
(2) if 1/e is < (C=α T)≤pi/2, system stability, but not absolute stability;
(3) if (C=α T) > pi/2s, system is unstable;
Step 303, analysis train tracing model stability, when C values fall in unstable interval or be in a long time to be gradually increasing
During trend, then it is assumed that driver is it is possible that danger, now reminds driver to take corresponding safety measure.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611170129.2A CN106682295A (en) | 2016-12-16 | 2016-12-16 | Analysis method for evaluating real-time safety characteristics of drivers |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611170129.2A CN106682295A (en) | 2016-12-16 | 2016-12-16 | Analysis method for evaluating real-time safety characteristics of drivers |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106682295A true CN106682295A (en) | 2017-05-17 |
Family
ID=58869861
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611170129.2A Pending CN106682295A (en) | 2016-12-16 | 2016-12-16 | Analysis method for evaluating real-time safety characteristics of drivers |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106682295A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110033617A (en) * | 2019-04-19 | 2019-07-19 | 中国汽车工程研究院股份有限公司 | A kind of train tracing model assessment system and method towards natural driving data |
CN111735487A (en) * | 2020-05-18 | 2020-10-02 | 清华大学深圳国际研究生院 | Sensor, sensor calibration method and device, and storage medium |
CN113721609A (en) * | 2021-08-17 | 2021-11-30 | 江苏大学 | 4WID high-clearance sprayer trajectory tracking control method under sideslip condition |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101131321A (en) * | 2007-09-28 | 2008-02-27 | 深圳先进技术研究院 | Real-time safe interval measurement method and device used for vehicle anti-collision warning |
CN102592395A (en) * | 2012-02-21 | 2012-07-18 | 金建设 | School bus safety monitoring system |
CN102991498A (en) * | 2011-12-19 | 2013-03-27 | 王晓原 | Driver following behavior model based on multi-source information fusion |
CN103076187A (en) * | 2013-02-06 | 2013-05-01 | 西安费斯达自动化工程有限公司 | Small vehicle-mounted vehicle safety comprehensive detection system |
CN103303318A (en) * | 2013-06-07 | 2013-09-18 | 安徽工程大学 | Intelligent driving assistance system |
CN103531042A (en) * | 2013-10-25 | 2014-01-22 | 吉林大学 | Rear-end collision pre-warning method based on driver types |
CN105574537A (en) * | 2015-11-23 | 2016-05-11 | 北京高科中天技术股份有限公司 | Multi-sensor-based dangerous driving behavior detection and evaluation method |
CN105620489A (en) * | 2015-12-23 | 2016-06-01 | 深圳佑驾创新科技有限公司 | Driving assistance system and real-time warning and prompting method for vehicle |
CN106225789A (en) * | 2016-07-12 | 2016-12-14 | 武汉理工大学 | A kind of onboard navigation system with high security and bootstrap technique thereof |
CN106427998A (en) * | 2016-09-30 | 2017-02-22 | 江苏大学 | Control method for avoiding collision during emergent lane changing of vehicle in high-speed state |
-
2016
- 2016-12-16 CN CN201611170129.2A patent/CN106682295A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101131321A (en) * | 2007-09-28 | 2008-02-27 | 深圳先进技术研究院 | Real-time safe interval measurement method and device used for vehicle anti-collision warning |
CN102991498A (en) * | 2011-12-19 | 2013-03-27 | 王晓原 | Driver following behavior model based on multi-source information fusion |
CN102592395A (en) * | 2012-02-21 | 2012-07-18 | 金建设 | School bus safety monitoring system |
CN103076187A (en) * | 2013-02-06 | 2013-05-01 | 西安费斯达自动化工程有限公司 | Small vehicle-mounted vehicle safety comprehensive detection system |
CN103303318A (en) * | 2013-06-07 | 2013-09-18 | 安徽工程大学 | Intelligent driving assistance system |
CN103531042A (en) * | 2013-10-25 | 2014-01-22 | 吉林大学 | Rear-end collision pre-warning method based on driver types |
CN105574537A (en) * | 2015-11-23 | 2016-05-11 | 北京高科中天技术股份有限公司 | Multi-sensor-based dangerous driving behavior detection and evaluation method |
CN105620489A (en) * | 2015-12-23 | 2016-06-01 | 深圳佑驾创新科技有限公司 | Driving assistance system and real-time warning and prompting method for vehicle |
CN106225789A (en) * | 2016-07-12 | 2016-12-14 | 武汉理工大学 | A kind of onboard navigation system with high security and bootstrap technique thereof |
CN106427998A (en) * | 2016-09-30 | 2017-02-22 | 江苏大学 | Control method for avoiding collision during emergent lane changing of vehicle in high-speed state |
Non-Patent Citations (3)
Title |
---|
张亚平: "《交通流理论》", 30 September 2016 * |
杨达等: "《改进的基于安全距离的车辆跟驰模型》", 《北京工业大学学报》 * |
系统仿真学报: "《基于视频采集数据的跟车模型标定与验证》", 《系统仿真学报》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110033617A (en) * | 2019-04-19 | 2019-07-19 | 中国汽车工程研究院股份有限公司 | A kind of train tracing model assessment system and method towards natural driving data |
CN111735487A (en) * | 2020-05-18 | 2020-10-02 | 清华大学深圳国际研究生院 | Sensor, sensor calibration method and device, and storage medium |
CN113721609A (en) * | 2021-08-17 | 2021-11-30 | 江苏大学 | 4WID high-clearance sprayer trajectory tracking control method under sideslip condition |
CN113721609B (en) * | 2021-08-17 | 2024-04-12 | 江苏大学 | Track tracking control method for 4WID high-clearance sprayer under sideslip condition |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
TWI447039B (en) | Driving behavior analysis and warning system and method thereof | |
CN106875510B (en) | A kind of vehicle rollover method for early warning and system | |
CN104527647B (en) | Monitoring and evaluation method of driving behavior risk degrees | |
KR101327007B1 (en) | A system and method for detection of concentration grade wherein car driving | |
CN105261151B (en) | High-grade highway driver fatigue condition detection method based on operation behavior feature | |
JP4469297B2 (en) | Driving diagnosis method and apparatus | |
CN104207791B (en) | Fatigue driving detection method | |
CN107618512A (en) | Driving behavior safe evaluation method based on people's car environment multi-data source | |
CN108372785A (en) | A kind of non-security driving detection device of the automobile based on image recognition and detection method | |
CN107972671A (en) | A kind of driving behavior analysis system | |
CN113744563B (en) | Road-vehicle risk real-time estimation method based on track data | |
CN103473890A (en) | Driver fatigue real-time monitoring system and monitoring method based on multi-information | |
CN106682295A (en) | Analysis method for evaluating real-time safety characteristics of drivers | |
CN110766943B (en) | Monitoring method and system for judging bad driving behavior based on accident data | |
CN110901385B (en) | Active speed limiting method based on fatigue state of driver | |
CN107672600A (en) | A kind of pilotless automobile security system and method for controlling security | |
TW201800289A (en) | System and method for analyzing driving behavior regarding traffic accidents by integrating a GPS analysis module, G-sensor analysis module, image analysis module, and vehicular data analysis module as well as the reference to road-network info-database and traffic data info-base | |
CN114241750A (en) | Vehicle-road cooperative information interaction system and method based on intelligent road traffic risk early warning method | |
CN115179960A (en) | Multi-source data acquisition man-vehicle state comprehensive monitoring system and method | |
CN107150690B (en) | A kind of driving fatigue method for early warning based on roadmarking | |
CN106530714A (en) | Secondary traffic accident time prediction method based on traffic flow data | |
CN106910334A (en) | A kind of method and device that section situation is predicted based on big data | |
CN105427407A (en) | Security monitoring method of automobile | |
CN105575116B (en) | Auto navigation remote monitoring system | |
CN104636723B (en) | Driving method for early warning based on certain objects image analysing computer in video image |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170517 |