CN105975756A - Vehicle driving data-based sharp turn behavior recognition method - Google Patents

Vehicle driving data-based sharp turn behavior recognition method Download PDF

Info

Publication number
CN105975756A
CN105975756A CN201610279207.6A CN201610279207A CN105975756A CN 105975756 A CN105975756 A CN 105975756A CN 201610279207 A CN201610279207 A CN 201610279207A CN 105975756 A CN105975756 A CN 105975756A
Authority
CN
China
Prior art keywords
contribution ratio
data
variance contribution
zig zag
turn
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
Application number
CN201610279207.6A
Other languages
Chinese (zh)
Other versions
CN105975756B (en
Inventor
黄亮
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Rainbow Radio (beijing) New Technology Co Ltd
Original Assignee
Rainbow Radio (beijing) New Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Rainbow Radio (beijing) New Technology Co Ltd filed Critical Rainbow Radio (beijing) New Technology Co Ltd
Priority to CN201610279207.6A priority Critical patent/CN105975756B/en
Publication of CN105975756A publication Critical patent/CN105975756A/en
Application granted granted Critical
Publication of CN105975756B publication Critical patent/CN105975756B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16Z—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS, NOT OTHERWISE PROVIDED FOR
    • G16Z99/00—Subject matter not provided for in other main groups of this subclass

Landscapes

  • Steering Control In Accordance With Driving Conditions (AREA)
  • Combined Controls Of Internal Combustion Engines (AREA)

Abstract

The invention belongs to the technical field of vehicles, and specifically relates to a vehicle driving data-based sharp turn behavior recognition method. The method comprises the following steps: (1) acquiring vehicle driving data; (2) obtaining a turn factor through a principle component analysis method; (3) taking a threshold value of the turn factor; and (4) recognizing whether a moment has a sharp turn behavior or not through comparing the score of the turn factor at the moment and the threshold value: when the score of the turn factor is greater than or equal to the threshold value, the moment is a sharp turn moment. The method disclosed in the invention has the effects of overcoming the technical defects in the prior art and remarkably improving the recognition correctness and effectiveness of sharp turn behaviors.

Description

A kind of zig zag Activity recognition method based on vehicle operation data
Technical field
The invention belongs to technical field of vehicle, be specifically related to a kind of zig zag Activity recognition side based on vehicle operation data Method.
Background technology
Showing according to road traffic accident statistics, dangerous driving behavior is one of major reason causing vehicle accident, its Middle zig zag is the dangerous driving behavior that accident is occurred frequently.For automobile manufacturing enterprise, if it is possible to accurate evaluation driver Performance in driving behavior especially zig zag behavior, just can increase car for driving behavior more reasonable design vehicle The suitability, improve safety coefficient.
Along with the development of car networking, vehicle driving trace (such as: longitude, dimension) and vehicle physical feature is (such as: instantaneous Speed, acceleration, steering wheel angle) record and preservation be possibly realized, this makes research worker can utilize abundant vehicle row Sail data to assess driving behavior.
Zig zag is the driving behavior of a kind of danger close.During zig zag, vehicle can produce the biggest centrifugal force, thus easily Cause vehicle rollover, produce serious vehicle accident.2008, the general curve traffic accident quantity of China reached 7637 times, its In reach 1563 times due to the vehicle accident quantity that causes of zig zag.Therefore, need badly a kind of objective comprehensively, judging nicety rate high Zig zag decision method.
Summary of the invention
It is an object of the invention to for the deficiencies in the prior art, it is provided that a kind of high based on PCA, accuracy rate Zig zag Activity recognition method based on vehicle operation data.
The present invention solves the technical scheme of problem: a kind of zig zag Activity recognition method based on vehicle operation data, Comprise the steps:
(1) collection vehicle running data: described vehicle operation data includes that instantaneous oil consumption, instantaneous acceleration, steering wheel turn Dynamic angle, car speed, engine speed, steering wheel rotational angular velocity；
(2) turn factor is obtained by PCA: described instantaneous oil consumption, instantaneous acceleration, steering wheel are rotated Angle, car speed, engine speed, steering wheel rotational angular velocity, as 6 original index, are synthesized by PCA The main constituent of equal number, then chooses front four main constituents that accumulative variance contribution ratio is more than 85%, then the institute that will choose State front four main constituents using respective variance contribution ratio in the variance contribution ratio of all selected main constituents proportion as power Heavily carry out linear combination, form turn factor；
(3) turn factor is taken threshold value；
(4) by comparing turn factor identifies in the described moment to be whether anxious in the score in certain moment and the size of threshold value Turning behavior: when the score of turn factor is more than or equal to threshold value, the described moment is the zig zag moment.
Further, in described step (2), the step being obtained turn factor by PCA is included:
(2.1) according to the vehicle operation data gathered, data matrix X '=(x ' is set upij)n×p, wherein, n is record number, p For index number, x 'ijRepresent the data of the i-th row jth row, and i≤n, j≤p；Instantaneous oil consumption, instantaneous acceleration, steering wheel are rotated These 6 original index of angle, car speed, engine speed, steering wheel rotational angular velocity are as the original change of principal component analysis Amount, takes p=6；
(2.2) each achievement data is standardized, in order to eliminate indices in dimension and the difference of the order of magnitude, standard The method changed is by each data x 'ijFirst deduct the average (i.e. the column mean of data matrix) of jth index, then divided by jth The standard deviation (i.e. the row standard deviation of data matrix) of index, obtains data x after standardizationij, and then obtain standardized data square Battle array；The average of each index is 0, and variance is 1；
(2.3) set up covariance matrix R, covariance matrix R according to standardized data matrix can reflect between each index Dependency, each element R of covariance matrix RijRepresenting the covariance of i, j variable, computing formula is:
R i j = Σ k = 1 n x i k * x j k ,
Wherein k is integer, represents the kth value of i, j variable；
(2.4) eigenvalue and the characteristic vector of covariance matrix R are solved: obtain p by solving characteristic equation | λ E-R |=0 Eigenvalue λi, i=1,2 ... p, wherein E is unit matrix, and obtains respectively corresponding to eigenvalue λiCharacteristic vector, solution procedure Being to be decomposed by covariance matrix R, formula is:
R = Σ i = 1 p λ i e i e i T ,
Wherein, λiIt is the eigenvalue of covariance matrix R, eiIt is the characteristic vector of a length of p, ei TIt is eiTransposed vector；
Again by eigenvalue λiArrange according to order from big to small, obtain:
λ1>λ2>…>λp；
(2.5) variance contribution ratio of each main constituent and accumulative variance contribution ratio are calculated, and true according to accumulative variance contribution ratio Fixed final selected main constituent number:
The computing formula of variance contribution ratio is:
The computing formula of accumulative variance contribution ratio isI.e. ask accumulative for the variance contribution ratio of i before ranking With；
Choose front m the main constituent that accumulative variance contribution ratio is more than 85%, take m=4；
(2.6) main constituent calculating formula is write out by loading matrix:
Loading matrix is the matrix representing main constituent with original variable linear transformation relation, and the coefficient of loading matrix is the most every The value of individual main constituent characteristic of correspondence vector, writes out i-th main constituent f accordinglyiComputing formula:
fi=e1i*x1+e2i*x2+…+epi*xp,
Wherein, epiIt is the i-th component of pth characteristic vector, xpIt it is pth index；
(2.7) score of the turn factor of every record is calculated according to m the main constituent selected, turning of i-th record Curved factor siThe computing formula of score be:
s i = w ~ 1 f 1 i · + w ~ 2 f 2 i + ... + w ~ k f k i + ... + w ~ m f m i , 1 ≤ k ≤ m ;
Wherein any one fkiRepresent the i-th component of kth main constituent, coefficientComputing formula be:
w ~ k = w k Σ j = 1 m w j .
Further, in described step (3), the threshold value of described turn factor is 1.5.
Further, in described step (2.5), choose front four main constituents more than 85% of the accumulative variance contribution ratio.
Further, in described step (2.5), the variance contribution ratio of front four main constituents selected is respectively 43.7%, 22.8%, 16.8%, 11.4%, the coefficient of described front four main constituents then calculated in step (2.7) divides It is not 0.46,0.24,0.18,0.12, the therefore turn factor s of i-th recordiThe computing formula of score be:
si=0.46*f1i+0.24*f2i+0.18*f3i+0.12*f4i。
Further, the accumulation contribution rate of front four main constituents selected described in can reach more than 94.7%.
The invention have the benefit that the present invention utilizes the dimensionality reduction thought of PCA, multi objective is converted into comprehensive Close index, reduce the dimension of observation space, obtain topmost information, by by the several variablees main one-tenth relevant to zig zag Point analytic process carries out comprehensively, significantly improves the zig zag accuracy of Activity recognition, effectiveness.
Accompanying drawing explanation
Fig. 1 is the flow chart of zig zag Activity recognition method based on vehicle operation data of the present invention；
Fig. 2 is the contrast of steering wheel rotational angle in application the method for the invention turn factor obtained and experiment of turning Broken line graph.
Detailed description of the invention
Below in conjunction with the accompanying drawings and detailed description of the invention, the present invention is further illustrated.
As it is shown in figure 1, a kind of zig zag Activity recognition method based on vehicle operation data, comprise the steps:
(1) collection vehicle running data: described vehicle operation data includes that instantaneous oil consumption, instantaneous acceleration, steering wheel turn Dynamic angle, car speed, engine speed, steering wheel rotational angular velocity；
(2) turn factor is obtained by PCA: described instantaneous oil consumption, instantaneous acceleration, steering wheel are rotated Angle, car speed, engine speed, steering wheel rotational angular velocity, as 6 original index, are synthesized by PCA The main constituent of equal number, then chooses front four main constituents that accumulative variance contribution ratio is more than 85%, then the institute that will choose State front four main constituents using respective variance contribution ratio in the variance contribution ratio of all selected main constituents proportion as power Heavily carry out linear combination, form turn factor；
(3) turn factor is taken threshold value；
(4) by comparing turn factor identifies in the described moment to be whether anxious in the score in certain moment and the size of threshold value Turning behavior: when the score of turn factor is more than or equal to threshold value, the described moment is the zig zag moment.
In described step (2), the step being obtained turn factor by PCA is included:
(2.1) according to the vehicle operation data gathered, data matrix X '=(x ' is set upij)n×p, wherein, n is record number, p For index number, x 'ijRepresent the data of the i-th row jth row, and i≤n, j≤p；Instantaneous oil consumption, instantaneous acceleration, steering wheel are rotated These 6 original index of angle, car speed, engine speed, steering wheel rotational angular velocity are as the original change of principal component analysis Amount, takes p=6；
(2.2) each achievement data is standardized, in order to eliminate indices in dimension and the difference of the order of magnitude, standard The method changed is by each data x 'ijFirst deduct the average (i.e. the column mean of data matrix) of jth index, then divided by jth The standard deviation (i.e. the row standard deviation of data matrix) of index, obtains data x after standardizationij, and then obtain standardized data square Battle array；The average of each index is 0, and variance is 1；
(2.3) set up covariance matrix R, covariance matrix R according to standardized data matrix can reflect between each index Dependency, each element R of covariance matrix RijRepresenting the covariance of i, j variable, computing formula is:
R i j = Σ k = 1 n x i k * x j k ,
Wherein k is integer, represents the kth value of i, j variable；
(2.4) eigenvalue and the characteristic vector of covariance matrix R are solved: obtain p by solving characteristic equation | λ E-R |=0 Eigenvalue λi, i=1,2 ... p, wherein E is unit matrix, and obtains respectively corresponding to eigenvalue λiCharacteristic vector, solution procedure Being to be decomposed by covariance matrix R, formula is:
R = Σ i = 1 p λ i e i e i T ,
Wherein, λiIt is the eigenvalue of covariance matrix R, eiIt is the characteristic vector of a length of p, ei TIt is eiTransposed vector；
Again by eigenvalue λiArrange according to order from big to small, obtain:
λ1>λ2>…>λp；
(2.5) variance contribution ratio of each main constituent and accumulative variance contribution ratio are calculated, and true according to accumulative variance contribution ratio Fixed final selected main constituent number:
The computing formula of variance contribution ratio is:
The computing formula of accumulative variance contribution ratio isI.e. ask accumulative for the variance contribution ratio of i before ranking With；
Choose front m the main constituent that accumulative variance contribution ratio is more than 85%, take m=4；
(2.6) main constituent calculating formula is write out by loading matrix:
Loading matrix is the matrix representing main constituent with original variable linear transformation relation, and the coefficient of loading matrix is the most every The value of individual main constituent characteristic of correspondence vector, writes out i-th main constituent f accordinglyiComputing formula:
fi=e1i*x1+e2i*x2+…+epi*xp,
Wherein, epiIt is the i-th component of pth characteristic vector, xpIt it is pth index；
(2.7) score of the turn factor of every record is calculated according to m the main constituent selected, turning of i-th record Curved factor siThe computing formula of score be:
s i = w ~ 1 f 1 i + w ~ 2 f 2 i + ... + w ~ k f k i + ... + w ~ m f m i , 1 ≤ k ≤ m ;
Wherein any one fkiRepresent the i-th component of kth main constituent, coefficientComputing formula be:
w ~ k = w k Σ j = 1 m w j .
In described step (3), the threshold value of described turn factor is 1.5.
In described step (2.5), choose front four main constituents more than 85% of the accumulative variance contribution ratio.
In described step (2.5), the variance contribution ratio of front four main constituents selected is respectively 43.7%, and 22.8%, 16.8%, 11.4%, the coefficient of described front four main constituents then calculated in step (2.7) is respectively 0.46, and 0.24, 0.18,0.12, the therefore turn factor s of i-th recordiThe computing formula of score be:
si=0.46*f1i+0.24*f2i+0.18*f3i+0.12*f4i。
The accumulation contribution rate of described front four main constituents selected can reach more than 94.7%.
The method of the invention is used to test:
Relative to turning, in zig zag is defined as the short time, acutely change the behavior of steering wheel position.By by vehicle The instantaneous oil consumption of traveling, instantaneous acceleration, steering wheel rotational angle, car speed, engine speed, steering wheel rotational angular velocity These 6 indexs, are comprehensively a turn factor by PCA by it, use the score of turn factor to carry out Direct Recognition Zig zag behavior.Wherein, steering wheel position can be used for differentiating whether vehicle is in turn condition.Non-for steering wheel rotation status is remembered It is 0 ° for steering wheel position, to anticlockwise then steering wheel rotational angle less than 0 °, is more than to right rotation then steering wheel rotational angle 0°。
Fig. 2 represents that vehicle steering wheel in the turn factor and experiment of turning of the time period of the 1000-1100 second travelled turns The contrast broken line graph of dynamic angle.Wherein heavy line represents the fluctuation of turn factor score, and fine line represents steering wheel rotational angle Change, dotted line represents the change of car speed；Abscissa express time, the vertical coordinate on the left side represents steering wheel rotational angle, The vertical coordinate on the right represents turn factor.Binding experiment data, are set as the threshold value identifying the turn factor of zig zag behavior 1.5, i.e. present invention determine that the standard identifying the zig zag moment is: when certain moment turn factor score >=1.5, this moment is i.e. For the zig zag moment.
As in figure 2 it is shown, at 1015 seconds turn factor must be divided into 1.85, more than threshold value 1.5, be therefore identified as racing The curved moment.In conjunction with side's steering wheel rotational angle curve it will be seen that 1015 seconds these moment experienced by steering wheel position really Acute variation process, meanwhile, according to rate curve it will be seen that zig zag process is usually associated with the unexpected reduction of speed, this With real life, the situation that during zig zag, driver usually can bring to a halt simultaneously is consistent.Equally, the method for the invention also can Making a distinction normal turning process, as the rear vehicle at 1030 seconds also experienced by turning process, but this turning process is relative Relatively slowly, in therefore 1030 seconds these moment be not recognized as zig zag, tally with the actual situation.Other experimental stage is same Demonstrate the effectiveness of the method for the invention.
The ultimate principle of the present invention is:
The present invention is by means of PCA, and PCA is the statistical method of a kind of Data Dimensionality Reduction, it by In an orthogonal transformation, become to summarize a few index of original most information by original multiple index comprehensives, do not damage On the premise of losing important information, reduce the latitude of observation space.
In practical problem is studied, for comprehensively and systematically problem analysis, it is necessary to consider numerous influence factor.These relate to And factor be commonly referred to as index or variable.Because each index reflects some studied a question to varying degrees There is certain dependency between information, and index each other, thus the information of the statistical data reflection of gained is to a certain extent There is overlap.When with study of statistical methods Multivariable, variable can increase amount of calculation too much and increase the complexity of problem analysis Property, it is desirable to during carrying out quantitative analysis, the variable related to is less, and the quantity of information obtained is more.Principal component analysis Adapt to what this requirement produced just, be the ideal tools of such issues that solve.
On the whole, principal component analysis is intended to utilize the thought of dimensionality reduction, and multi objective is converted into a few aggregative indicator, Reduce the dimension of observation space, to obtain topmost information.Assume there be p index, the most at most have p aggregative indicator (main Composition).Not increasing due to population variance and do not subtract, the variance of front several aggregative indicatores is relatively big, and the variance of the most several aggregative indicatores is less. Strictly, only front several aggregative indicatores just deserve to be called " leading " composition, rear several aggregative indicatores actually " secondary " composition.In practice always It is that reservation is front several, several after ignoring.Retain how many main constituents and depend on that the cumulative variance of member-retaining portion is in variance summation Percentage.
Six original index are formed six main constituents through combination by the present invention, then choose accumulation contribution rate be 85% with On front four main constituents, more front four main constituents are carried out linear combination using its variance contribution ratio ratio as weight, finally Synthesizing aggregative indicator, i.e. a turn factor, then having judged the zig zag behavior of automobile by turn factor being taken threshold value.
The present invention is not limited to above-mentioned embodiment, in the case of without departing substantially from flesh and blood of the present invention, and art technology Personnel it is contemplated that any deformation, improve, replace and each fall within protection scope of the present invention.

Claims (6)

1. a zig zag Activity recognition method based on vehicle operation data, it is characterised in that comprise the steps:
(1) collection vehicle running data: described vehicle operation data includes instantaneous oil consumption, instantaneous acceleration, steering wheel angle of rotation Degree, car speed, engine speed, steering wheel rotational angular velocity；
(2) obtain turn factor by PCA: by described instantaneous oil consumption, instantaneous acceleration, steering wheel rotational angle, Car speed, engine speed, steering wheel rotational angular velocity, as 6 original index, synthesize identical by PCA The main constituent of quantity, then chooses front four main constituents that accumulative variance contribution ratio is more than 85%, then by choose described before Four main constituents are entered using respective variance contribution ratio proportion in the variance contribution ratio of all selected main constituents as weight Line linearity combines, and forms turn factor；
(3) turn factor is taken threshold value；
(4) identify whether the described moment is zig zag in the score in certain moment and the size of threshold value by comparing turn factor Behavior: when the score of turn factor is more than or equal to threshold value, the described moment is the zig zag moment.
Zig zag Activity recognition method based on vehicle operation data the most according to claim 1, it is characterised in that described In step (2), the step being obtained turn factor by PCA is included:
(2.1) according to the vehicle operation data gathered, data matrix X '=(x ' is set upij)n×p, wherein, n is record number, and p is for referring to Mark number, x 'ijRepresent the data of the i-th row jth row, and i≤n, j≤p；By instantaneous oil consumption, instantaneous acceleration, steering wheel angle of rotation These 6 original index of degree, car speed, engine speed, steering wheel rotational angular velocity as the original variable of principal component analysis, Take p=6；
(2.2) being standardized each achievement data, standardized method is by each data x 'ijFirst deduct jth index Average, then the standard deviation divided by jth index, obtain data x after standardizationij, and then obtain standardized data matrix；
(2.3) each element R of covariance matrix R, covariance matrix R is set up according to standardized data matrixijRepresent i, j variable Covariance, computing formula is:
R i j = Σ k = 1 n x i k * x j k ,
Wherein k is integer；
(2.4) eigenvalue and the characteristic vector of covariance matrix R are solved: obtain p feature by solving characteristic equation | λ E-R |=0 Value λi, i=1,2 ... p, wherein E is unit matrix；And obtain respectively corresponding to eigenvalue λiCharacteristic vector, solution procedure be by Covariance matrix R decomposes, and formula is:
R = Σ i = 1 p λ i e i e i T ,
Wherein, λiIt is the eigenvalue of covariance matrix R, eiIt is the characteristic vector of a length of p, ei TIt is eiTransposed vector；
Again by eigenvalue λiArrange according to order from big to small, obtain:
λ1>λ2>…>λp；
(2.5) calculate the variance contribution ratio of each main constituent and accumulative variance contribution ratio, and determine according to accumulative variance contribution ratio The most selected main constituent number:
The computing formula of variance contribution ratio is:
The computing formula of accumulative variance contribution ratio is
Choose front m the main constituent that accumulative variance contribution ratio is more than 85%, take m=4；
(2.6) main constituent calculating formula is write out by loading matrix:
The value of coefficient the most each main constituent characteristic of correspondence vector of loading matrix, writes out i-th main constituent f accordinglyiCalculating Formula:
fi=e1i*x1+e2i*x2+…+epi*xp,
Wherein, epiIt is the i-th component of pth characteristic vector, xpIt it is pth index；
(2.7) calculate the score of the turn factor of every record according to m main constituent selecting, i-th turning recorded because of Sub-siThe computing formula of score be:
s i = w ~ 1 f 1 i + w ~ 2 f 2 i + ... + w ~ k f k i + ... + w ~ m f m i , 1 ≤ k ≤ m ;
Wherein any one fkiRepresent the i-th component of kth main constituent, coefficientComputing formula be:
w ~ k = w k Σ j = 1 m w j .
Zig zag Activity recognition method based on vehicle operation data the most according to claim 1, it is characterised in that described In step (3), the threshold value of described turn factor is 1.5.
Zig zag Activity recognition method based on vehicle operation data the most according to claim 2, it is characterised in that described In step (2.5), choose front four main constituents more than 85% of the accumulative variance contribution ratio.
Zig zag Activity recognition method based on vehicle operation data the most according to claim 2, it is characterised in that described In step (2.5), the variance contribution ratio of front four main constituents selected is respectively 43.7%, and 22.8%, 16.8%, 11.4%, the coefficient of described front four main constituents then calculated in step (2.7) is respectively 0.46, and 0.24,0.18, 0.12, the therefore turn factor s of i-th recordiThe computing formula of score be:
si=0.46*f1i+0.24*f2i+0.18*f3i+0.12*f4i。
Zig zag Activity recognition method based on vehicle operation data the most according to claim 4, it is characterised in that described The accumulation contribution rate of front four main constituents selected can reach more than 94.7%.
CN201610279207.6A 2016-04-28 2016-04-28 A kind of zig zag Activity recognition method based on vehicle operation data Active CN105975756B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610279207.6A CN105975756B (en) 2016-04-28 2016-04-28 A kind of zig zag Activity recognition method based on vehicle operation data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610279207.6A CN105975756B (en) 2016-04-28 2016-04-28 A kind of zig zag Activity recognition method based on vehicle operation data

Publications (2)

Publication Number Publication Date
CN105975756A true CN105975756A (en) 2016-09-28
CN105975756B CN105975756B (en) 2019-01-29

Family

ID=56994910

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610279207.6A Active CN105975756B (en) 2016-04-28 2016-04-28 A kind of zig zag Activity recognition method based on vehicle operation data

Country Status (1)

Country Link
CN (1) CN105975756B (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106933211A (en) * 2017-04-18 2017-07-07 中南大学 It is a kind of to recognize the industrial process dynamically interval method and apparatus of adjustment
CN110047167A (en) * 2019-04-15 2019-07-23 上海经达信息科技股份有限公司 Vehicle zig zag number equivalent statistics method
CN110509925A (en) * 2019-08-29 2019-11-29 合肥工业大学 A kind of zig zag recognition methods based on car networking data
CN111246086A (en) * 2020-01-11 2020-06-05 深圳市豪恩汽车电子装备股份有限公司 Motor vehicle video recording controller, motor vehicle video recording control system and method

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001305154A (en) * 2000-02-14 2001-10-31 Mitsubishi Electric Corp Acceleration detector
JP2010023768A (en) * 2008-07-23 2010-02-04 Honda Motor Co Ltd Vehicle and vehicle condition estimation device
CN104484725A (en) * 2014-12-30 2015-04-01 大连楼兰科技股份有限公司 Driving risk assessment method based on principal component linear weighting
CN104978492A (en) * 2015-07-09 2015-10-14 彩虹无线（北京）新技术有限公司 Safety driving evaluation method based on telematics data flow
CN105046070A (en) * 2015-07-07 2015-11-11 吉林大学 Method for constructing city comprehensive working condition with turning performance
CN105320966A (en) * 2015-10-30 2016-02-10 东软集团股份有限公司 Vehicle driving state recognition method and apparatus

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001305154A (en) * 2000-02-14 2001-10-31 Mitsubishi Electric Corp Acceleration detector
JP2010023768A (en) * 2008-07-23 2010-02-04 Honda Motor Co Ltd Vehicle and vehicle condition estimation device
CN104484725A (en) * 2014-12-30 2015-04-01 大连楼兰科技股份有限公司 Driving risk assessment method based on principal component linear weighting
CN105046070A (en) * 2015-07-07 2015-11-11 吉林大学 Method for constructing city comprehensive working condition with turning performance
CN104978492A (en) * 2015-07-09 2015-10-14 彩虹无线（北京）新技术有限公司 Safety driving evaluation method based on telematics data flow
CN105320966A (en) * 2015-10-30 2016-02-10 东软集团股份有限公司 Vehicle driving state recognition method and apparatus

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
石琴等: "基于主成分分析和FCM聚类的行驶工况研究", 《环境科学研究》 *

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106933211A (en) * 2017-04-18 2017-07-07 中南大学 It is a kind of to recognize the industrial process dynamically interval method and apparatus of adjustment
CN106933211B (en) * 2017-04-18 2019-04-09 中南大学 A kind of method and apparatus that identification industrial process dynamic adjusts section
CN110047167A (en) * 2019-04-15 2019-07-23 上海经达信息科技股份有限公司 Vehicle zig zag number equivalent statistics method
CN110509925A (en) * 2019-08-29 2019-11-29 合肥工业大学 A kind of zig zag recognition methods based on car networking data
CN110509925B (en) * 2019-08-29 2021-03-23 合肥工业大学 Method for identifying sharp turn based on Internet of vehicles data
CN111246086A (en) * 2020-01-11 2020-06-05 深圳市豪恩汽车电子装备股份有限公司 Motor vehicle video recording controller, motor vehicle video recording control system and method

Also Published As

Publication number Publication date
CN105975756B (en) 2019-01-29

Similar Documents

Publication Publication Date Title
CN105975757B (en) A kind of anxious deceleration Activity recognition method based on vehicle operation data
Chen et al. A graphical modeling method for individual driving behavior and its application in driving safety analysis using GPS data
CN107284442B (en) A kind of longitudinally controlled method of negotiation of bends for automatic driving vehicle
CN105975756A (en) Vehicle driving data-based sharp turn behavior recognition method
CN104269026B (en) Fatigue driving real-time monitoring and early warning method based on Android platform
CN111428960B (en) Intelligent vehicle driving automatic evaluation method fusing multi-source vehicle-mounted sensor information
CN104494600B (en) A kind of Driver intention recognition method based on SVM algorithm
CN106585635B (en) Driving behavior methods of marking and device
CN107909678A (en) One kind driving risk evaluating method and system
CN106202872A (en) Vehicle driving behavior scoring method
CN107038860B (en) A kind of user's driving behavior methods of marking based on ADAS technology and regression model
DE102013222634A1 (en) A method of predicting a road friction coefficient and method of operating a motor vehicle
CN107953888A (en) A kind of road type recognition methods and system
KR20170115831A (en) Method and apparatus for guiding automobile insurance using driver recognizing
CN110239556B (en) Driver instant control ability sensing method
CN105808857A (en) Prediction method of automobile active safety system effectiveness on the basis of collision deformation depth
CN115588310A (en) Vehicle collision risk prediction method based on trajectory data
CN113581188A (en) Commercial vehicle driver driving style identification method based on Internet of vehicles data
Hampton et al. Evaluation of the accuracy of NASS/CDS Delta-V estimates from the enhanced WinSmash algorithm
CN112308136B (en) Driving distraction detection method based on SVM-Adaboost
Kar et al. Scotto: Real-time driver behavior scoring using in-vehicle data
CN105869412A (en) Method for identifying fast acceleration behaviors based on vehicle running data
CN108268678A (en) Driving behavior analysis method, apparatus and system
CN115688003A (en) Driver identification method and device, computer equipment and readable storage medium
CN114162132B (en) Driving mode identification method based on subjective and objective evaluation

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant