CN109229108A - A kind of driving behavior safe evaluation method based on driving fingerprint - Google Patents
A kind of driving behavior safe evaluation method based on driving fingerprint Download PDFInfo
- Publication number
- CN109229108A CN109229108A CN201810890209.8A CN201810890209A CN109229108A CN 109229108 A CN109229108 A CN 109229108A CN 201810890209 A CN201810890209 A CN 201810890209A CN 109229108 A CN109229108 A CN 109229108A
- Authority
- CN
- China
- Prior art keywords
- driving
- fingerprint
- data
- driving behavior
- degree
- 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
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
- B60W40/09—Driving style or behaviour
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Mathematical Physics (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of based on the driving behavior safe evaluation method for driving fingerprint, comprising: S1, acquires driving behavior data by the sensor being arranged on vehicle；S2, according to the characteristic index of driving behavior data computational representation individual difference alienation driving behavior；S3, training set is chosen, characteristic index input Machine learning classifiers is trained, passes through Machine learning classifiers and driving fingerprint is calculated；S4, using driving behavior data to be evaluated as test set, compare itself and under normal driving state drive fingerprint between difference degree；Different degree weight of each parameter to driving safety in S5, calculating driving fingerprint；S6, the parameter that above-mentioned difference degree is calculated by Principle components analysis method, and the factor score by obtaining carries out overall merit to the safety of driving behavior.Method of the invention can fully consider the influence of Individual differences, obtain accurate, comprehensive, reliable driver's safety evaluation result.
Description
Technical field
The present invention relates to driving safety evaluation field more particularly to a kind of driving behavior safety evaluations based on driving fingerprint
Method.
Background technique
In recent years, with the development of onboard sensor technology, the research of field of traffic safety is gradually goed deep into, many automobile factorys
Commercial city is in active development personalization vehicle DAS (Driver Assistant System), to improve the reliability and adaptability of system entirety.And such system
The basis of system is exactly the identification and assessment to individual human driving performance is driven.Meanwhile by driving behavior individual difference in recent years
It is different the study found that the building of reasonable contemplation Individual differences personalized driving behavior model (driving fatigue detection model,
Lane keeps model and speed control forecasting model etc.) do not consider that the accuracy of individual differences model is higher compared to tradition, and
It is suitable for driver's individual character.
And existing driving safety evaluation method and system do not consider the influence of Individual differences, individual method or system
It also is only that driver is divided into different driving styles in a manner of classification.However, due to the presence of individual difference, even if
There is also significant differences for the driving performance for belonging between the driver of same driving style.
Hear that ' driving fingerprint ' we will recognize that fingerprint first.For biology, everyone has unique finger
Line marks everyone unique identity using different ' lines '.Similarly, for driving behavior angle, driving refers to
Line just refers to the unique driver behavior characteristic that everyone shows in driving procedure, and each characteristic index for driving fingerprint
It is exactly the unique driving fingerprint lines of driver.
The application for driving fingerprint at this stage mainly drives the otherness of fingerprint parameter, benefit by comparing different drivers
Driver's identity is recognized with classifier algorithm.It is not applied to carry out driving behavior safety evaluation using driving fingerprint.
The present invention has comprehensively considered the influence that driver's Individual differences assess driver, initiative to drive from individual
The angle for sailing state evaluates driving behavior, to substantially increase the reliability and accuracy of evaluation result.Meanwhile root
Fingerprint characteristic is driven according to driver acquired in machine learning, can accurately identify driver's identity and is comprehensively grasped current
Driving condition, so as to targetedly provide security strategy.
Summary of the invention
The technical problem to be solved by the present invention is to for driving safety assessment system under existing car networking environment because driving
Individual human variance factor causes low assessment result accuracy, poor reliability and traditional evaluation index method because not adapting to every
The personal driving habit characteristic of driver to be evaluated causes evaluation result not have convincingness and fairness.The present invention is by proposing one
Kind drives driver's safe evaluation method of fingerprint characteristic based on individual human is driven, to solve the above problems.
The technical solution adopted by the present invention to solve the technical problems is:
The present invention provides a kind of driving behavior safe evaluation method based on driving fingerprint, method includes the following steps:
S1, driving behavior data, including driver behavior data and vehicle fortune are acquired by the sensor being arranged on vehicle
Row status data；
S2, according to the characteristic index of driving behavior data computational representation individual difference alienation driving behavior, including statistical nature,
Morphological feature and frequecy characteristic；
S3, certain time length and continuous historical driving behavior data are chosen as training set, characteristic index is inputted into machine
Study strategies and methods are trained, and filter out driving style accidental data by Machine learning classifiers, and pass through statistical method meter
Calculation obtains the distribution characteristics and Variation Features of driver's each characteristic index under normal driving state, as fingerprint is driven, drives
Fingerprint includes multiple parameters；
S4, using driving behavior data to be evaluated as test set, compare driving behavior data and the driving in test set
Difference degree of the member between the driving fingerprint of the driving behavior data under normal driving state, and utilize the difference index of quantization
Characterize difference degree；
S5, by the method for sensitivity analysis or Significance Analysis, calculate each parameter in the driving fingerprint that step S3 is obtained
To the different degree weight of driving safety；
The driving fingerprint that difference degree and step S5 between S6, the driving fingerprint obtained in conjunction with step S4 obtain respectively is joined
Several different degree weights calculates the parameter of above-mentioned difference degree by Principle components analysis method, and the factor by obtaining obtains
The safety to driving behavior is divided to carry out overall merit.
Further, further include that pretreated method is carried out to driving behavior data in step S2 of the invention:
Preprocess method includes uniform sampling frequency and wavelet de-noising, and removal is because of the variation pair of driver's short time driving style
Learn interference caused by the process of its normal driving state.
Further, in step S2 of the invention further include: by the method for questionnaire survey to the characteristic index of acquisition into
Row screening, and retain and the high characteristic index of the driving safety degree of association.
Further, the multiple parameters that fingerprint includes are driven in step S3 of the invention are as follows:
Statistical nature includes: minimum value, maximum value, median, kurtosis, the degree of bias；
Morphological feature includes: data central tendency, dispersion tendency, distributional pattern；
Central tendency analysis includes: the statistical indicator of average, middle number and mode, indicates the central tendency of the data；
Dispersion tendency analysis includes: the statistical indicator of range, quartile deviation, mean difference, variance, standard deviation, data
Dispersion degree；
Quartile deviation Qd: it is the average value of the difference of upper quartile QU and lower quartile QL, its calculation formula is:
Qd=(QU-QL)/2
Interquartile range reflects the dispersion degree of intermediate 50% data, and numerical value is smaller, illustrates that intermediate data are more concentrated；
Its numerical value is bigger, illustrates that intermediate data are more dispersed.
Further, the Machine learning classifiers in step S3 of the invention include artificial neural network, support vector machines
And random forest.
Further, the method for the characteristic index of computational representation individual difference alienation driving behavior has in step S2 of the invention
Body are as follows:
Acquire historical driving behavior data, including driver behavior data and travel condition of vehicle data；Utilize quadratic interpolation
Or the unified each parameter sampling frequency of method extracted, then data are filtered by wavelet de-noising；Each ginseng is obtained by calculating
Several morphological features and statistical nature is as individual difference alienation driving behavior characteristic index.
The comprehensive evaluation result that step S6 is obtained includes: that different grades is divided into according to different threshold values, passes through difference
Grade intuitively judges the driving safety degree of driver.
The beneficial effect comprise that: it is of the invention based on the driving behavior safe evaluation method for driving fingerprint, be
Riding manipulation parameter and travel condition of vehicle parameter, onboard sensor based on onboard sensor acquisition are integrated in car, because
This is without repacking, while this method can constantly correct the driving fingerprint of driver's normal driving state based on history driving data,
And security evaluation process will not impact driving, driver's adaptability with height.
Detailed description of the invention
Present invention will be further explained below with reference to the attached drawings and examples, in attached drawing:
Fig. 1 is overview flow chart of the present invention；
Fig. 2 is driving data pretreatment schematic diagram of the present invention；
Fig. 3 is that the present invention drives fingerprint training schematic diagram；
Fig. 4 is that the present invention is based on the driving behavior security evaluation schematic diagrams for driving fingerprint.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, not
For limiting the present invention.
A specific embodiment of the invention provides a kind of driving safety evaluation method based on driving fingerprint, such as Fig. 1 institute
It is shown as overview flow chart of the present invention.This method main contents concentrate on three parts: driving data pretreatment, the instruction for driving fingerprint
Practice process and based on the driving behavior security evaluation process for driving fingerprint.
1, driving data preprocessing process
This part principle steps from the data that onboard sensor acquires as shown in Fig. 2, choose the company of one section of duration first
Continuous normal driving data as training set and are directed into MATLAB Data Analysis Software；Followed by secondary difference or extraction
The sample frequency of all kinds of different parameters is carried out unification by method；Wavelet Denoising Method is then carried out, to guarantee the availability of data, simultaneously
It is influenced caused by variation in the filtering short time as environmental factor or driving style.
2, the training process of fingerprint is driven
This part principle steps are as shown in Figure 3.
1) it calculates and drives fingerprint
Based on the data that above-mentioned work obtains, calculates separately the conduct such as statistical nature and morphological feature of each data parameters and drive
Fingerprint is sailed, to obtain to characterize the driving Fingerprint system of driver's driving behavior.
Statistical nature includes: minimum value, maximum value, median, kurtosis, degree of bias etc..
Morphological feature includes: data central tendency, dispersion tendency, distributional pattern etc..
Central tendency analysis, which can use the statistical indicators such as average, middle number and mode, indicates the central tendency of the data
(positively biased distribution, negative bias distribution etc.)；
Dispersion tendency analysis carrys out data mainly by statistical indicators such as range, quartile deviation, mean difference, variance, standard deviations
Dispersion degree.
Quartile deviation (Qd): it is that (QU, i.e., positioned at 75%), (25%) QL is located at upper quartile with lower quartile
The average value of difference.Its calculation formula is:
Qd=(QU-QL)/2
Interquartile range reflects the dispersion degree of intermediate 50% data, and numerical value is smaller, illustrates that intermediate data are more concentrated；
Its numerical value is bigger, illustrates that intermediate data are more dispersed.Interquartile range is not influenced by extreme value.
It is more because driving fingerprint characterization index system parameter, and the present invention is directed to study the connection for driving fingerprint and driving safety
System, therefore using modes such as questionnaire surveys, according to the correlation degree size (sensitivity point between the fingerprint and driving safety
Analysis or Significance Analysis), These parameters system is screened, it is final to obtain the driving fingerprint collection towards driving safety,
And the training set of fingerprint training is driven as individual driver in next step.
Sensitivity analysis principle formula:
Sensitivity=true positives number/(true positives number+false negative number) * 100%
Significance Analysis is substantially a variety of calculations of sensitivity of the function of many variables, for following formula:
Wherein, PiIndicate the reliability of object i, IiIndicate the different degree of object i, system reliability function R (P1, P2...,
Pn) it is about parameter P1, P2..., PnN-ary function.
2) it calculates driving individual human to be evaluated and drives fingerprint characteristic
It has constructed after driving fingerprint system, based on history driving data by there is the machine learning algorithm of supervision
(support vector machines etc.) is trained, to be screened out using the classifier after training because the reasons such as environment reason, emergency event are made
At driving style accidental data.To obtain the distribution rule of driver's driving fingerprint parameter different during normal driving
Rule and variation characteristic.Obtain driving the driving fingerprint of individual human by machine learning training.It is that this is driven that gained, which drives fingerprint,
Sail driving behavior performance characteristic of the people under normal driving state.
3, based on the driving behavior security evaluation process for driving fingerprint
The principle steps of this part are as shown in Figure 4.
The driver of one section of duration driving behavior data to be evaluated are chosen, and is calculated according to above-mentioned principle and is currently driven
Sail people's driving fingerprint characteristic to be measured, by driven under driver's normal driving state for being obtained with first part fingerprint characteristic into
Row compares, and recycles certain parameters (coefficient of variation, standard deviation and average value difference etc.) quantization is each therebetween to drive fingerprint
The otherness degree size of index.Final comprehensive characterization items drive the parameter of the difference degree of fingerprint, utilize principal component
The driving behavior level of security of analytic approach evaluation test object.
It is more clearly understood to make to invent, it is as follows now to introduce currently preferred implementation process:
The history driving data such as the riding manipulation and state of motion of vehicle of acquisition based on onboard sensor first, followed by
Quadratic interpolation or the unified each parameter sampling frequency of the method for extraction, then data are filtered by wavelet de-noising.Finally by
It calculates, the morphological feature and statistical nature for obtaining each parameter are as individual difference alienation driving behavior characteristic index.
The particular content of the quadratic interpolattion is as follows:
Linear interpolation is frequently used for known function f and wants the approximate method for obtaining other point values in the value of two o'clock, wherein p table
Linear interpolation polynomial:
Wherein: the variation function of f (x) expression data；x0Indicate the previous data point of interpolation；x1Indicate the latter number of interpolation
Strong point.
Using index obtained by aforementioned pretreatment as training set, for the training of classifier, (classifier can use Python
Scikit-learn machine learning library realize) classifier completed of training is for screening out because of originals such as environment reason, emergency events
The driving style accidental data because caused by.Then each characteristic index is obtained using statistical analysis based on the data obtained after classification to exist
Variation characteristic (dispersion tendency, central tendency and distributional pattern etc.) under normal driving state, and driven as what is studied
People is sailed in the feature of normal driving state, i.e. driving fingerprint.
Using data to be assessed as test set, driven under driver's normal driving state that it is obtained with above-mentioned calculating
Fingerprint is compared, and passes through the difference degree size of both the parameters such as the coefficient of variation, standard deviation and average value quantizations.
The parameter of above-mentioned characterization difference degree finally is calculated using Principal Component Analysis, and is integrated according to factor score
Evaluation, Principal Component Analysis can be realized using the form that SPSS Data Analysis Software and MATLAB are programmed.
It should be understood that for those of ordinary skills, it can be modified or changed according to the above description,
And all these modifications and variations should all belong to the protection domain of appended claims of the present invention.
Claims (7)
1. a kind of based on the driving behavior safe evaluation method for driving fingerprint, which is characterized in that method includes the following steps:
S1, driving behavior data are acquired by the sensor being arranged on vehicle, including driver behavior data and vehicle run shape
State data；
S2, according to the characteristic index of driving behavior data computational representation individual difference alienation driving behavior, including statistical nature, form
Feature and frequecy characteristic；
S3, certain time length and continuous historical driving behavior data are chosen as training set, characteristic index is inputted into machine learning
Classifier is trained, and filters out driving style accidental data by Machine learning classifiers, and calculate by statistical method
Fingerprint is driven as fingerprint is driven to the distribution characteristics and Variation Features of driver's each characteristic index under normal driving state
Including multiple parameters；
S4, using driving behavior data to be evaluated as test set, compare driving behavior data and the driver in test set and exist
The difference degree of driving behavior data under normal driving state driven between fingerprint, and characterized using the difference index of quantization
Difference degree；
S5, by the method for sensitivity analysis or Significance Analysis, calculate in the driving fingerprint that step S3 is obtained each parameter to driving
Sail safe different degree weight；
Driving each parameter of fingerprint that difference degree and step S5 between S6, the driving fingerprint obtained in conjunction with step S4 obtain
Different degree weight, calculates the parameter of above-mentioned difference degree by principal component analytical method, and the factor score by obtaining is to driving
The safety for sailing behavior carries out overall merit.
2. according to claim 1 based on the driving behavior safe evaluation method for driving fingerprint, which is characterized in that step S2
In further include that pretreated method is carried out to driving behavior data:
Preprocess method includes uniform sampling frequency and wavelet de-noising, and removal changes because of driver's short time driving style to study
It is interfered caused by the process of its normal driving state.
3. according to claim 1 based on the driving behavior safe evaluation method for driving fingerprint, which is characterized in that step S2
In further include: the characteristic index of acquisition is screened by the method for questionnaire survey, and is retained high with the driving safety degree of association
Characteristic index.
4. according to claim 1 based on the driving behavior safe evaluation method for driving fingerprint, which is characterized in that step S3
The middle multiple parameters for driving fingerprint and including are as follows:
Statistical nature includes: minimum value, maximum value, median, kurtosis, the degree of bias；
Morphological feature includes: data central tendency, dispersion tendency, distributional pattern；
Central tendency analysis includes: the statistical indicator of average, middle number and mode, indicates the central tendency of the data；
Dispersion tendency analysis include: range, quartile deviation, mean difference, variance, standard deviation statistical indicator, data it is discrete
Degree；
Quartile deviation Qd: it is the average value of the difference of upper quartile QU and lower quartile QL, its calculation formula is:
Qd=(QU-QL)/2
Interquartile range reflects the dispersion degree of intermediate 50% data, and numerical value is smaller, illustrates that intermediate data are more concentrated；It is counted
Value is bigger, illustrates that intermediate data are more dispersed.
5. according to claim 1 based on the driving behavior safe evaluation method for driving fingerprint, which is characterized in that step S3
In Machine learning classifiers include artificial neural network, support vector machines and random forest.
6. according to claim 1 based on the driving behavior safe evaluation method for driving fingerprint, which is characterized in that step S2
The method of the characteristic index of middle computational representation individual difference alienation driving behavior specifically:
Acquire historical driving behavior data, including driver behavior data and travel condition of vehicle data；Utilize quadratic interpolation or pumping
The unified each parameter sampling frequency of the method taken, then data are filtered by wavelet de-noising；Each parameter is obtained by calculating
Morphological feature and statistical nature are as individual difference alienation driving behavior characteristic index.
7. according to claim 1 based on the driving behavior safe evaluation method for driving fingerprint, which is characterized in that step S6
Obtained comprehensive evaluation result includes: that different grades is divided into according to different threshold values, is intuitively judged by different brackets
The driving safety degree of driver.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810890209.8A CN109229108B (en) | 2018-08-07 | 2018-08-07 | Driving behavior safety evaluation method based on driving fingerprints |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810890209.8A CN109229108B (en) | 2018-08-07 | 2018-08-07 | Driving behavior safety evaluation method based on driving fingerprints |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109229108A true CN109229108A (en) | 2019-01-18 |
| CN109229108B CN109229108B (en) | 2020-05-05 |
Family
ID=65070479
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810890209.8A Active CN109229108B (en) | 2018-08-07 | 2018-08-07 | Driving behavior safety evaluation method based on driving fingerprints |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109229108B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110533261A (en) * | 2019-09-06 | 2019-12-03 | 江苏物联网研究发展中心 | A kind of driving behavior analysis optimization system of transport truck |
| CN110623680A (en) * | 2019-08-30 | 2019-12-31 | 中国民用航空飞行学院 | Method for testing psychological health of civil aviation flight trainees |
| CN111038485A (en) * | 2019-12-30 | 2020-04-21 | 山东大学 | Hybrid electric vehicle control method and system based on driving style recognition |
| CN111598367A (en) * | 2019-02-20 | 2020-08-28 | 杭州海康威视数字技术股份有限公司 | Driving behavior evaluation method and device, computing equipment and storage medium |
| CN112336349A (en) * | 2020-10-12 | 2021-02-09 | 易显智能科技有限责任公司 | Method and related device for recognizing psychological state of driver |
| CN112651443A (en) * | 2020-12-28 | 2021-04-13 | 华北科技学院 | Driving style identification model evaluation method, device, medium and equipment based on machine learning |
| CN113641423A (en) * | 2021-08-31 | 2021-11-12 | 青岛海信传媒网络技术有限公司 | Display device and system starting method |
| RU2790883C1 (en) * | 2022-06-28 | 2023-02-28 | Общество с ограниченной ответственностью "ЛАБОРАТОРИЯ УМНОГО ВОЖДЕНИЯ" | Software and hardware complex collecting information about vehicle operation and calculated driving safety indicator |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007122362A (en) * | 2005-10-27 | 2007-05-17 | Toyota Motor Corp | State estimation method using neural network and state estimation apparatus using neural network |
| CN104527647A (en) * | 2014-12-15 | 2015-04-22 | 清华大学 | Monitoring and evaluation method of driving behavior risk degrees |
| CN105730450A (en) * | 2016-01-29 | 2016-07-06 | 北京荣之联科技股份有限公司 | Driving behavior analyzing method and evaluation system based on vehicle-mounted data |
| CN106218641A (en) * | 2016-08-04 | 2016-12-14 | 武汉理工大学 | A kind of vehicle new hand driver identifies and safe early warning method automatically |
| CN106585635A (en) * | 2016-11-25 | 2017-04-26 | 东软集团股份有限公司 | Driving behavior scoring method and device |
| JP2018039292A (en) * | 2016-09-05 | 2018-03-15 | 日産自動車株式会社 | Drive support method and drive support apparatus |
| CN108108766A (en) * | 2017-12-28 | 2018-06-01 | 东南大学 | Driving behavior recognition methods and system based on Fusion |
| KR20180068173A (en) * | 2016-12-13 | 2018-06-21 | 주식회사 티노스 | Safety driving supporting method based on driving style information |
| CN108216252A (en) * | 2017-12-29 | 2018-06-29 | 中车工业研究院有限公司 | A kind of subway driver vehicle carried driving behavior analysis method, car-mounted terminal and system |
| CN108284845A (en) * | 2017-01-09 | 2018-07-17 | 福特汽车公司 | Method and apparatus for assessing driving behavior |
-
2018
- 2018-08-07 CN CN201810890209.8A patent/CN109229108B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007122362A (en) * | 2005-10-27 | 2007-05-17 | Toyota Motor Corp | State estimation method using neural network and state estimation apparatus using neural network |
| CN104527647A (en) * | 2014-12-15 | 2015-04-22 | 清华大学 | Monitoring and evaluation method of driving behavior risk degrees |
| CN105730450A (en) * | 2016-01-29 | 2016-07-06 | 北京荣之联科技股份有限公司 | Driving behavior analyzing method and evaluation system based on vehicle-mounted data |
| CN106218641A (en) * | 2016-08-04 | 2016-12-14 | 武汉理工大学 | A kind of vehicle new hand driver identifies and safe early warning method automatically |
| JP2018039292A (en) * | 2016-09-05 | 2018-03-15 | 日産自動車株式会社 | Drive support method and drive support apparatus |
| CN106585635A (en) * | 2016-11-25 | 2017-04-26 | 东软集团股份有限公司 | Driving behavior scoring method and device |
| KR20180068173A (en) * | 2016-12-13 | 2018-06-21 | 주식회사 티노스 | Safety driving supporting method based on driving style information |
| CN108284845A (en) * | 2017-01-09 | 2018-07-17 | 福特汽车公司 | Method and apparatus for assessing driving behavior |
| CN108108766A (en) * | 2017-12-28 | 2018-06-01 | 东南大学 | Driving behavior recognition methods and system based on Fusion |
| CN108216252A (en) * | 2017-12-29 | 2018-06-29 | 中车工业研究院有限公司 | A kind of subway driver vehicle carried driving behavior analysis method, car-mounted terminal and system |
Non-Patent Citations (2)
| Title |
|---|
| 楚文慧，吴超仲等: "基于个性化行为模型的驾驶疲劳识别方法", 《中国安全科技学报》 * |
| 楚文慧，吴超仲等: "驾驶行为安全性评价研究综述", 《公路交通科技》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111598367A (en) * | 2019-02-20 | 2020-08-28 | 杭州海康威视数字技术股份有限公司 | Driving behavior evaluation method and device, computing equipment and storage medium |
| CN111598367B (en) * | 2019-02-20 | 2023-04-07 | 杭州海康威视数字技术股份有限公司 | Driving behavior evaluation method and device, computing equipment and storage medium |
| CN110623680A (en) * | 2019-08-30 | 2019-12-31 | 中国民用航空飞行学院 | Method for testing psychological health of civil aviation flight trainees |
| CN110533261A (en) * | 2019-09-06 | 2019-12-03 | 江苏物联网研究发展中心 | A kind of driving behavior analysis optimization system of transport truck |
| CN111038485A (en) * | 2019-12-30 | 2020-04-21 | 山东大学 | Hybrid electric vehicle control method and system based on driving style recognition |
| CN111038485B (en) * | 2019-12-30 | 2021-02-19 | 山东大学 | Hybrid electric vehicle control method and system based on driving style recognition |
| CN112336349A (en) * | 2020-10-12 | 2021-02-09 | 易显智能科技有限责任公司 | Method and related device for recognizing psychological state of driver |
| CN112336349B (en) * | 2020-10-12 | 2024-05-14 | 易显智能科技有限责任公司 | Method and related device for identifying psychological state of driver |
| CN112651443A (en) * | 2020-12-28 | 2021-04-13 | 华北科技学院 | Driving style identification model evaluation method, device, medium and equipment based on machine learning |
| CN113641423A (en) * | 2021-08-31 | 2021-11-12 | 青岛海信传媒网络技术有限公司 | Display device and system starting method |
| CN113641423B (en) * | 2021-08-31 | 2023-07-07 | 青岛海信传媒网络技术有限公司 | Display device and system starting method |
| RU2790883C1 (en) * | 2022-06-28 | 2023-02-28 | Общество с ограниченной ответственностью "ЛАБОРАТОРИЯ УМНОГО ВОЖДЕНИЯ" | Software and hardware complex collecting information about vehicle operation and calculated driving safety indicator |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109229108B (en) | 2020-05-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109229108A (en) | A kind of driving behavior safe evaluation method based on driving fingerprint | |
| CN105139070B (en) | fatigue driving evaluation method based on artificial neural network and evidence theory | |
| CN103020594B (en) | On-line study is utilized to eliminate the fatigue state detection method of driver individual difference | |
| EP3498559B1 (en) | Method for recognizing the driving style of a driver of a land vehicle, and corresponding apparatus | |
| CN101872171A (en) | Driver fatigue state recognition method and system based on information fusion | |
| Zylius | Investigation of route-independent aggressive and safe driving features obtained from accelerometer signals | |
| CN106250801A (en) | Based on Face datection and the fatigue detection method of human eye state identification | |
| CN111753674A (en) | Fatigue driving detection and identification method based on deep learning | |
| CN109649091A (en) | Monitoring system for tyres of automobile based on computer vision | |
| CN113743471B (en) | Driving evaluation method and system | |
| CN101620673A (en) | Robust face detecting and tracking method | |
| CN101987017A (en) | Electroencephalo-graph (EEG) signal identification and detection method for measuring alertness of driver | |
| CN107730835B (en) | A kind of fatigue of automobile driver recognition methods based on stress reaction ability | |
| CN109460703A (en) | A kind of non-intrusion type fatigue driving recognition methods based on heart rate and facial characteristics | |
| CN109664894A (en) | Fatigue driving safety pre-warning system based on multi-source heterogeneous data perception | |
| Huang et al. | P-FDCN based eye state analysis for fatigue detection | |
| CN106446849A (en) | Fatigue driving detection method | |
| Wang et al. | A probabilistic approach to measuring driving behavior similarity with driving primitives | |
| JP2021056983A (en) | Method and device for detecting driver abnormalities based on machine learning using vehicle can bus signal | |
| CN108537161A (en) | A kind of driving of view-based access control model characteristic is divert one's attention detection method | |
| CN108509999A (en) | It is a kind of indignation drive detection and safe early warning method | |
| CN108577869A (en) | Based on the driving fatigue monitoring method and system for driving fingerprint | |
| Bin et al. | A fatigue driving detection method based on multi facial features fusion | |
| Mangshor et al. | A real-time drowsiness and fatigue recognition using support vector machine | |
| CN116443025A (en) | Operation vehicle driver fatigue driving intervention system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |