CN105976567B - Driver Fatigue Detection based on pedal of vehicles and follow the bus behavior - Google Patents
Driver Fatigue Detection based on pedal of vehicles and follow the bus behavior Download PDFInfo
- Publication number
- CN105976567B CN105976567B CN201610390463.2A CN201610390463A CN105976567B CN 105976567 B CN105976567 B CN 105976567B CN 201610390463 A CN201610390463 A CN 201610390463A CN 105976567 B CN105976567 B CN 105976567B
- Authority
- CN
- China
- Prior art keywords
- fatigue
- data sample
- driver
- relative velocity
- pedal
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/06—Alarms for ensuring the safety of persons indicating a condition of sleep, e.g. anti-dozing alarms
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C5/00—Registering or indicating the working of vehicles
- G07C5/08—Registering or indicating performance data other than driving, working, idle, or waiting time, with or without registering driving, working, idle or waiting time
- G07C5/0841—Registering performance data
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The present invention provides a kind of Driver Fatigue Detection based on pedal of vehicles and follow the bus behavior, comprising: the parameter in acquisition vehicle travel process；Using the method for fixed traveling time window, data are cut to obtain multiple fatigue data samples；Fatigue characteristic is extracted from each fatigue data sample；Wherein fatigue characteristic includes at least: relative velocity parameters, gas pedal parameter between following distance parameter and front truck, brake pedal parameter；Using fatigue characteristic as tired discriminant criterion collection, the sample cutting and classifier training of data are carried out based on the fatigue driving experiment carried out in advance.
Description
Technical field
The present invention relates to sensor technical fields, and it is tired to particularly relate to a kind of driver based on pedal of vehicles and follow the bus behavior
Labor detection method.
Background technique
Fatigue driving is to cause a major reason of road traffic accident.When driver enters fatigue state, reaction
It can slow up, the cognitive ability of ambient enviroment be declined, these can all become potential accident inducement.From American National
The statistical data of highway traffic safety management board (NHTSA) show the U.S. every year about 100,000 Traffic Collision accidents by tired
Please direct initiation is sailed.It is dead that these collision accidents cause annual about 1550 people, and 71000 people are injured and close to 12,500,000,000
The property loss of dollar.Domestic statistical data is shown in Chinese about 1966 road traffic accidents in 2009 and is driven by fatigue
Initiation is sailed, these accidents cause 1153 people death altogether and 2465 people are injured, and cause the property damage close to 42,940,000 yuan
It loses.In addition some survey reports point out, fatigue driving phenomenon is widely present in driver.2009, American National
The report of sleep foundation (NSF) points out that 54% adult driver had fatigue driving experience, wherein 28% driver
Report that oneself was once almost sleeping in startup procedure.
In summary, how preventing fatigue driving is the important issue for promoting traffic safety.Existing fatigue driving
Detection generallys use following methods:
Using machine vision means, eyes closed degree and the frequency of wink etc. of driver are captured by camera, directly
Its fatigue state is judged based on driver's facial expression feature.But the fatigue detection method based on machine vision needs in the car
Additionally add high-definition camera, higher cost.In addition this method also have invade driver's privacy suspicion, therefore be not easy by
User receives.
When driver enters fatigue state, operation behavior can be abnormal fluctuation, and then in the motion state of vehicle
It is embodied, therefore the abnormal operation Behavioral change by detecting driver can differentiate its fatigue state.Current base
It is moved in the driver fatigue detection technique of operation behavior mainly for steering wheel operation and lateral direction of car.In correlative study most often
There are mainly two types of the indexs of correlation of consideration, i.e. steering wheel recovery actions (SWM) and lateral direction of car station keeping accuracy (SDLP).Example
The tired detection system released such as German Bosch company, which passes through, calculates driver's steering operation frequency and the hurried steering row of capture
For come the fatigue state that detects driver.
But existing method effect, there are detection error, effect is not fine.
Summary of the invention
Unfavorable problem is monitored to fatigue driving for existing in the prior art, the technical problem to be solved by the present invention is to
There is provided it is a kind of it is at low cost, driver is driven in vehicle processes there is no any interference and fatigue driving state can accurately be reported
The alert Driver Fatigue Detection based on pedal of vehicles and follow the bus behavior.
To solve the above-mentioned problems, the embodiment of the present invention proposes a kind of driver based on pedal of vehicles and follow the bus behavior
Fatigue detection method, comprising:
Acquire the parameter in vehicle travel process；Using the method for fixed traveling time window, data are cut to obtain
Obtain multiple fatigue data samples；
Fatigue characteristic is extracted from each fatigue data sample；Wherein fatigue characteristic includes at least: following distance parameter, with
Relative velocity parameters, gas pedal parameter between front truck, brake pedal parameter；
Using fatigue characteristic as tired discriminant criterion collection, the sample of data is carried out based on the fatigue driving experiment carried out in advance
Cutting and classifier training.
Wherein, the method also includes: obtain fatigue data sample in speed minimum value, it is small to reject speed minimum value
In preset threshold.
Wherein, the preset threshold is 70km/h.
Wherein, the method also includes: the fatigue state of driver is divided into using SVM classifier awake, tired, very
Fatigue.
Wherein, the following distance parameter obtains by the following method:
It obtains following distance variance Var (Dist), following distance variance describes in a fatigue data sample with spacing
From fluctuation:
Wherein DistiIt is i-th of data point in a fatigue data sample,It is a following distance data sample
Average value；
It obtains following distance maximum value max (Dist): i.e. the maximum value of following distance in a fatigue data sample；
Vehicle is obtained apart from minimum value min (Dist): i.e. the minimum value of following distance in a fatigue data sample；
It obtains the very poor Range of following distance (Dist): i.e. the maximum value of following distance and most in a fatigue data sample
The difference of small value: Range (Dist)=max (Dist)-min (Dist).
Wherein, the relative velocity parameters between front truck obtain by the following method:
It obtains relative velocity variance Var (Vrel), relative velocity variance describes relatively fast in a fatigue data sample
The fluctuation of degree:
Wherein VreliIt is i-th of data point in a relative velocity data sample,It is a relative velocity data
The average value of sample；
It obtains relative velocity maximum value max (Vrel): i.e. relative velocity most maximum value in a fatigue data sample；
It obtains relative velocity minimum value min (Vrel): i.e. relative velocity most minimum value in a fatigue data sample；
It obtains the very poor Range of relative velocity (Vrel): i.e. relative velocity maximum value and phase in a fatigue data sample
To the difference of speed minimum value: Range (Vrel)=max (Vrel)-min (Vrel).
Wherein, the gas pedal parameter is measured by the throttle opening of vehicle, the throttle opening by with
Lower method obtains:
It obtains throttle opening variance Var (Trt):
Wherein TrtiIt is i-th of data point in a fatigue data sample,It is solar term in a fatigue data sample
The average value of door aperture；
It obtains throttle opening maximum value max (Trt): i.e. throttle opening maximum value in a fatigue data sample；
Obtain throttle operation time Trt_time: refer in a fatigue data sample time, driver operate throttle when
The sum of between；It is indicated with the non-zero points number of throttle opening；
Obtain throttle operation frequency Trt_freq: throttle operation frequency refers to that driver is to throttle in a fatigue data sample
The sum of number of operations；The throttle operation frequency is obtained by the sum of statistics throttle opening non-zero section.
Wherein, gas pedal parameter described in the brake pedal parameter is measured by the brake-cylinder pressure of vehicle, described
Brake-cylinder pressure is prepared by the following:
It obtains brake-cylinder pressure maximum value max (Brk): i.e. the maximum value of brake-cylinder pressure in a fatigue data sample；
Obtain brake pedal operation time Brk_time: i.e. driver operates brake pedal in a fatigue data sample
The sum of time is indicated with the non-zero points number of master cylinder pressure:
In one data sample of brake pedal operation time representation driver operate brake pedal time it is accumulative；.
Obtain brake pedal operation frequency Brk_freq: i.e. behaviour of the driver to brake pedal in a fatigue data sample
Make the sum of number；Brake pedal operation frequency is obtained by the sum of statistics brake-cylinder pressure non-zero section.
The advantageous effects of the above technical solutions of the present invention are as follows:
Technical solution of the present invention is mentioned whereby by the variation of driver's pedal operation and follow the bus behavior under fatigue state
Rise the accuracy of identification of driver fatigue detection device.The present invention and traditional only consideration steering wheel operation behavior and lateral direction of car are transported
Dynamic driver fatigue detection method is compared, and the synthesis fatigue detecting precision of driver can be further increased, and reduces algorithm essence
Lower caused false dismissal and frequent false alarm phenomenon are spent, the usage experience and traffic safety of user are promoted.
Detailed description of the invention
Fig. 1 is the method flow diagram in the embodiment of the present invention.
Specific embodiment
To keep the technical problem to be solved in the present invention, technical solution and advantage clearer, below in conjunction with attached drawing and tool
Body embodiment is described in detail.
Driver fatigue detection is carried out by method as shown in Figure 1 in the embodiment of the present invention.It specifically includes:
Parameter in step 1, acquisition vehicle travel process；
Step 2, using the method for fixed traveling time window, data are cut to obtain multiple fatigue data samples；
Step 3 is directed to each fatigue data sample, is carried out by the speed minimum value in fatigue data sample to sample
Screening.If sample of the speed minimum value lower than 70km/h will be considered as in vain, not as the candidate data sample of fatigue detecting.
This is because the traffic accident that fatigue driving generates is common under highway or sparse city expressway operating condition, in crowded city
It seldom will appear the traffic accident as caused by driver fatigue in city's road.Therefore in order to reduce the complexity of calculating, this hair
Ignore the sample that speed minimum value is lower than 70km/h in bright embodiment.
Step 4 extracts fatigue characteristic from each fatigue data sample.Wherein fatigue characteristic may include: following distance
Relative velocity parameters, brake pedal parameter between parameter, gas pedal parameter and front truck.
Wherein, which can characterize according to throttle opening.
The present invention proposes to step on the relative velocity parameters between following distance parameter, gas pedal parameter and front truck, braking
The typical pedal of vehicles of board parameter this four and follow the bus behavior differentiate feature as driver fatigue.It can in the embodiment of the present invention
To extract relative velocity parameters, the brake pedal between following distance parameter, gas pedal parameter and front truck with the following method
Parameter:
It is assumed that including N number of sampled data points in the fatigue data sample of a 60s, if the corresponding following distance of the data segment
Data are Dist (unit: m), and the relative velocity data with front truck is Vrel (unit: km/h), and throttle opening data are Trt
(unit: %), brake-cylinder pressure data are Brk (unit: MPa).For four kinds of data-signals as above, typical fatigue index is set
It counts as follows:
1. index related with following distance Dist:
1.1 following distance variance Var (Dist), following distance variance describe following distance in a fatigue data sample
Fluctuation:
Wherein DistiIt is i-th of data point in a fatigue data sample,It is a following distance data sample
Average value.
1.2 following distance maximum value max (Dist): the i.e. maximum value of following distance in a fatigue data sample.Follow the bus
The attainable farthest situation of follow the bus institute in a time window is described apart from maximum value.
1.3 following distance minimum value min (Dist): the i.e. minimum value of following distance in a fatigue data sample.Follow the bus
The attainable nearest situation of follow the bus institute in a time window is described apart from minimum value.
1.4 the very poor Range of following distance (Dist): i.e. the maximum value of following distance and minimum in a fatigue data sample
The difference of value；Following distance is very poor to describe the fluctuation of following distance in a data segment time:
Range (Dist)=max (Dist)-min (Dist).
2 indexs related with relative velocity Vrel:
2.1 relative velocity variance Var (Vrel), relative velocity variance describe relative velocity in a fatigue data sample
Fluctuation:
Wherein VreliIt is i-th of data point in a relative velocity data sample,It is a relative velocity data
The average value of sample.
2.2 relative velocity maximum value max (Vrel): i.e. relative velocity most maximum value in a fatigue data sample.Phase
The maximum value being likely to be breached in a fatigue data sample from vehicle and front truck relative velocity is described to speed maximum value.
2.3 relative velocity minimum value min (Vrel): i.e. relative velocity most minimum value in a fatigue data sample.Phase
The minimum value being likely to be breached in a fatigue data sample from vehicle and front truck relative velocity is described to speed minimum value.
The very poor Range of 2.4 relative velocities (Vrel): i.e. relative velocity maximum value in a fatigue data sample and opposite
The difference of speed minimum value；Relative velocity is very poor to describe the fluctuation of relative velocity in a data segment time
Range (Vrel)=max (Vrel)-min (Vrel).
3. index related with throttle opening Trt and throttle operation:
3.1 throttle opening variance Var (Trt):
Wherein TrtiIt is i-th of data point in a fatigue data sample,It is solar term in a fatigue data sample
The average value of door aperture；Throttle opening variance describes the fluctuation of throttle opening in a fatigue data sample, reflects
The stability of driver's throttle operation.
3.2 throttle opening maximum value max (Trt): i.e. throttle opening maximum value in a fatigue data sample；Solar term
Door aperture maximum value describes throttle opening when driver's throttle steps on most deep in a fatigue data sample.
3.3 throttle operation time Trt_time: referring in a fatigue data sample time, and driver operates the time of throttle
The sum of；It can be indicated with the non-zero points number of throttle opening；
In one data sample of throttle operation time representation driver operate throttle time it is accumulative.
3.4 throttle operation frequency Trt_freq: throttle operation frequency refers to that driver is to throttle in a fatigue data sample
The sum of number of operations.Wherein, driver steps on one pine one of throttle and is defined as a throttle operation.Throttle operation frequency can lead to
It crosses the sum of statistics throttle opening non-zero section to obtain, characterizes the frequent degree that driver pine is stepped on the gas.
4. index related with brake-cylinder pressure Brk and brake operating:
4.1 brake-cylinder pressure maximum value max (Brk): the i.e. maximum value of brake-cylinder pressure in a fatigue data sample；System
Dynamic cylinder Pressure maximum value describes the maximum braking force degree of driver in a data segment time.
4.2 brake pedal operation time Brk_time: i.e. driver operates brake pedal in a fatigue data sample
The sum of time is indicated with the non-zero points number of master cylinder pressure:
In one data sample of brake pedal operation time representation driver operate brake pedal time it is accumulative.
4.3 brake pedal operation frequency Brk_freq: i.e. behaviour of the driver to brake pedal in a fatigue data sample
Make the sum of number.Wherein, driver steps on one pine one of brake pedal and is defined as a brake operating.Brake pedal operation frequency can
To obtain by the sum of statistics brake-cylinder pressure non-zero section, the frequent degree that driver pine steps on braking is characterized.
Step 5, according in step 4 from extracted in fatigue data sample following distance parameter, gas pedal parameter, with before
Relative velocity parameters, brake pedal parameter between vehicle are real based on the fatigue driving carried out in advance as tired discriminant criterion collection
Test the sample cutting and classifier training for carrying out data.
Classifier of the present invention is SVM classifier, and the fatigue state of driver is divided into three grades, it may be assumed that awake,
It is tired, very tired.The classifier trained inputs as the driver fatigue spy in an effectively tired fatigue data sample
Sign.In the present invention, these fatigue characteristics include index related with pedal operation and follow the bus behavior described in step 4.Classifier
Output be one of three level of fatigue.When driver fatigue degree is " fatigue ", soft prompting is compared to it (such as
Bright indicator light)；When driver fatigue degree is " very tired ", alarm is carried out to it, is reminded driver to stop and is rested.
The above is a preferred embodiment of the present invention, it is noted that for those skilled in the art
For, without departing from the principles of the present invention, it can also make several improvements and retouch, these improvements and modifications
It should be regarded as protection scope of the present invention.
Claims (7)
1. a kind of Driver Fatigue Detection based on pedal of vehicles and follow the bus behavior characterized by comprising
Acquire the parameter in vehicle travel process；Using the method for fixed traveling time window, data are cut more to obtain
A fatigue data sample；
Fatigue characteristic is extracted from each fatigue data sample；Wherein fatigue characteristic includes at least: following distance parameter and front truck
Between relative velocity parameters, gas pedal parameter, brake pedal parameter；
Using fatigue characteristic as tired discriminant criterion collection, the sample cutting of data is carried out based on the fatigue driving experiment carried out in advance
With classifier training；
Wherein, the brake pedal parameter is measured by the brake-cylinder pressure of vehicle, and the brake-cylinder pressure passes through with lower section
Method obtains:
It obtains brake-cylinder pressure maximum value max (Brk): i.e. the maximum value of brake-cylinder pressure in a fatigue data sample；
Obtain brake pedal operation time Brk_time: i.e. driver operates the time of brake pedal in a fatigue data sample
The sum of, it is indicated with the non-zero points number of master cylinder pressure:
In one data sample of brake pedal operation time representation driver operate brake pedal time it is accumulative；
Obtain brake pedal operation frequency Brk_freq: i.e. operation time of the driver to brake pedal in a fatigue data sample
The sum of number；Brake pedal operation frequency is obtained by the sum of statistics brake-cylinder pressure non-zero section.
2. the Driver Fatigue Detection according to claim 1 based on pedal of vehicles and follow the bus behavior, feature exist
In, the method also includes: the speed minimum value in fatigue data sample is obtained, to reject speed minimum value less than preset threshold
's.
3. the Driver Fatigue Detection according to claim 2 based on pedal of vehicles and follow the bus behavior, feature exist
In the preset threshold is 70km/h.
4. the Driver Fatigue Detection according to claim 1 based on pedal of vehicles and follow the bus behavior, feature exist
In, the method also includes: the fatigue state of driver is divided into using SVM classifier awake, tired, very tired.
5. the Driver Fatigue Detection according to claim 1 based on pedal of vehicles and follow the bus behavior, feature exist
In the following distance parameter obtains by the following method:
It obtains following distance variance Var (Dist), following distance variance describes following distance in a fatigue data sample
Fluctuation:
Wherein DistiIt is i-th of data point in a fatigue data sample,It is the flat of a following distance data sample
Mean value；
It obtains following distance maximum value max (Dist): i.e. the maximum value of following distance in a fatigue data sample；
Vehicle is obtained apart from minimum value min (Dist): i.e. the minimum value of following distance in a fatigue data sample；
It obtains the very poor Range of following distance (Dist): i.e. the maxima and minima of following distance in a fatigue data sample
Difference: Range (Dist)=max (Dist)-min (Dist).
6. the Driver Fatigue Detection according to claim 1 based on pedal of vehicles and follow the bus behavior, feature exist
In the relative velocity parameters between front truck obtain by the following method:
It obtains relative velocity variance Var (Vrel), relative velocity variance describes relative velocity in a fatigue data sample
Fluctuation:
Wherein Vreli It is i-th of data point in a relative velocity data sample,It is a relative velocity data sample
This average value；
It obtains relative velocity maximum value max (Vrel): i.e. relative velocity most maximum value in a fatigue data sample；
It obtains relative velocity minimum value min (Vrel): i.e. relative velocity most minimum value in a fatigue data sample；
It obtains the very poor Range of relative velocity (Vrel): i.e. relative velocity maximum value and speed relatively in a fatigue data sample
Spend the difference of minimum value: Range (Vrel)=max (Vrel)-min (Vrel).
7. the Driver Fatigue Detection according to claim 1 based on pedal of vehicles and follow the bus behavior, feature exist
In the gas pedal parameter is measured by the throttle opening of vehicle, and the throttle opening is prepared by the following:
It obtains throttle opening variance Var (Trt):
Wherein TrtiIt is i-th of data point in a fatigue data sample,It is that air throttle is opened in a fatigue data sample
The average value of degree；
It obtains throttle opening maximum value max (Trt): i.e. throttle opening maximum value in a fatigue data sample；
Obtain throttle operation time Trt_time: refer in a fatigue data sample time, driver operate throttle time it
With；It is indicated with the non-zero points number of throttle opening；
Obtain throttle operation frequency Trt_freq: throttle operation frequency refers to that driver is to the behaviour of throttle in a fatigue data sample
Make the sum of number；The throttle operation frequency is obtained by the sum of statistics throttle opening non-zero section.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610390463.2A CN105976567B (en) | 2016-06-06 | 2016-06-06 | Driver Fatigue Detection based on pedal of vehicles and follow the bus behavior |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610390463.2A CN105976567B (en) | 2016-06-06 | 2016-06-06 | Driver Fatigue Detection based on pedal of vehicles and follow the bus behavior |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105976567A CN105976567A (en) | 2016-09-28 |
| CN105976567B true CN105976567B (en) | 2019-01-29 |
Family
ID=57010817
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610390463.2A Active CN105976567B (en) | 2016-06-06 | 2016-06-06 | Driver Fatigue Detection based on pedal of vehicles and follow the bus behavior |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105976567B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107203134B (en) * | 2017-06-02 | 2020-08-18 | 浙江零跑科技有限公司 | Front vehicle following method based on deep convolutional neural network |
| CN109927729B (en) * | 2019-03-07 | 2020-06-23 | 南京微达电子科技有限公司 | Method and device for estimating safe distance of continuous high-speed driving and evaluating and controlling stability |
| CN111959488B (en) * | 2020-08-04 | 2021-07-16 | 长城汽车股份有限公司 | Method and device for controlling vehicle, storage medium and vehicle |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101633358A (en) * | 2008-07-24 | 2010-01-27 | 通用汽车环球科技运作公司 | Adaptive vehicle control system with integrated driving style recognition |
| CN103552560A (en) * | 2013-11-01 | 2014-02-05 | 扬州瑞控汽车电子有限公司 | Driver driving state recognition-based lane departure alarming method |
| CN103578227A (en) * | 2013-09-23 | 2014-02-12 | 吉林大学 | Fatigue driving detection method based on GPS positioning information |
| KR20140037480A (en) * | 2012-09-19 | 2014-03-27 | 현대자동차주식회사 | Seat control device and method be considered human engineering |
| CN104688252A (en) * | 2015-03-16 | 2015-06-10 | 清华大学 | Method for detecting fatigue status of driver through steering wheel rotation angle information |
| CN105261151A (en) * | 2015-09-29 | 2016-01-20 | 中国第一汽车股份有限公司 | High-grade highway driver fatigue state detection method based on operation behavior characteristics |
| CN105631485A (en) * | 2016-03-28 | 2016-06-01 | 苏州阿凡提网络技术有限公司 | Fatigue driving detection-oriented steering wheel operation feature extraction method |
-
2016
- 2016-06-06 CN CN201610390463.2A patent/CN105976567B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101633358A (en) * | 2008-07-24 | 2010-01-27 | 通用汽车环球科技运作公司 | Adaptive vehicle control system with integrated driving style recognition |
| KR20140037480A (en) * | 2012-09-19 | 2014-03-27 | 현대자동차주식회사 | Seat control device and method be considered human engineering |
| CN103578227A (en) * | 2013-09-23 | 2014-02-12 | 吉林大学 | Fatigue driving detection method based on GPS positioning information |
| CN103552560A (en) * | 2013-11-01 | 2014-02-05 | 扬州瑞控汽车电子有限公司 | Driver driving state recognition-based lane departure alarming method |
| CN104688252A (en) * | 2015-03-16 | 2015-06-10 | 清华大学 | Method for detecting fatigue status of driver through steering wheel rotation angle information |
| CN105261151A (en) * | 2015-09-29 | 2016-01-20 | 中国第一汽车股份有限公司 | High-grade highway driver fatigue state detection method based on operation behavior characteristics |
| CN105631485A (en) * | 2016-03-28 | 2016-06-01 | 苏州阿凡提网络技术有限公司 | Fatigue driving detection-oriented steering wheel operation feature extraction method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105976567A (en) | 2016-09-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yang et al. | Examining lane change gap acceptance, duration and impact using naturalistic driving data | |
| CN107284355B (en) | A kind of Safety vehicle door unlatching processing method and system | |
| Zhang et al. | Driver fatigue detection based intelligent vehicle control | |
| CN102717765B (en) | Fatigue driving detection method and anti-fatigue driving auxiliary device | |
| CN110155046A (en) | Automatic emergency brake hierarchical control method and system | |
| CN105976567B (en) | Driver Fatigue Detection based on pedal of vehicles and follow the bus behavior | |
| CN105799512A (en) | Vehicle overspeed reminding method and system | |
| CN105488453A (en) | Detection identification method of no-seat-belt-fastening behavior of driver based on image processing | |
| CN103824420A (en) | Fatigue driving identification system based on heart rate variability non-contact measuring | |
| CN104637246A (en) | Driver multi-behavior early warning system and danger evaluation method | |
| CN104408878A (en) | Vehicle fleet fatigue driving early warning monitoring system and method | |
| CN106127126B (en) | The recognition methods of radical driving behavior based on three anxious data | |
| CN109740477A (en) | Study in Driver Fatigue State Surveillance System and its fatigue detection method | |
| CN104464192B (en) | Device and method for detection and early warning of unstable driving state of vehicle driver | |
| CN104331687B (en) | A kind of behavioral value method of not fastening the safety belt based on vehicular video analysis | |
| CN105632203B (en) | A kind of traffic security early warning method of traffic control and system | |
| CN104386046A (en) | Braking method, braking device and automobile | |
| CN107284449A (en) | A kind of traffic safety method for early warning and system, automobile, readable storage medium storing program for executing | |
| CN108492527B (en) | Fatigue driving monitoring method based on overtaking behavior characteristics | |
| Dua et al. | Drowsiness detection and alert system | |
| Zardosht et al. | Identifying driver behavior in preturning maneuvers using in-vehicle CANbus signals | |
| CN115279643A (en) | On-board active learning method and apparatus for training a perception network of an autonomous vehicle | |
| CN111483277A (en) | Tire underpressure identification method and system based on machine learning and storage medium | |
| CN108791300B (en) | Driving system with high intelligent degree | |
| CN114464012B (en) | Vehicle and pedestrian collision early warning method and system based on Internet of vehicles |
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 |