CN108577869A - Based on the driving fatigue monitoring method and system for driving fingerprint - Google Patents
Based on the driving fatigue monitoring method and system for driving fingerprint Download PDFInfo
- Publication number
- CN108577869A CN108577869A CN201810405726.1A CN201810405726A CN108577869A CN 108577869 A CN108577869 A CN 108577869A CN 201810405726 A CN201810405726 A CN 201810405726A CN 108577869 A CN108577869 A CN 108577869A
- Authority
- CN
- China
- Prior art keywords
- driving
- fingerprint
- driver
- threshold value
- characteristic index
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/18—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state for vehicle drivers or machine operators
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/117—Identification of persons
- A61B5/1171—Identification of persons based on the shapes or appearances of their bodies or parts thereof
- A61B5/1172—Identification of persons based on the shapes or appearances of their bodies or parts thereof using fingerprinting
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6887—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient mounted on external non-worn devices, e.g. non-medical devices
- A61B5/6893—Cars
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
- A61B5/7267—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems involving training the classification device
Abstract
The invention discloses a kind of based on the driving fatigue monitoring method and system that drive fingerprint, and this approach includes the following steps:S1 the driving data of driver) is acquired by sensor;S2 the driving fingerprint characteristic metrics-thresholds of preset characteristic index algorithm computational representation driving fatigue) are passed through according to driving data;S3) extraction drives the history driving data information of fingerprint base, and match cognization is carried out to history driving data information and current driver's feature;S4 it) if successfully identifying driver, extracts driver's history and drives fingerprint threshold value record;S5) if without matched driver in historical record, by step S2) in method calculate under driver's normal driving state driving fingerprint threshold value in real time;S6) by step S4) and step S5) obtained driving fingerprint threshold value evaluates the driving fingerprint state acquired in real time, whether output driver is in the result of fatigue driving state.Recognition result of the present invention is accurate and does not influence driver's normal driving.
Description
Technical field
The present invention relates to intelligent driving technology more particularly to it is a kind of based on drive fingerprint driving fatigue monitoring method be
System.
Background technology
In recent years, as the research of field of traffic safety is gradually goed deep into, more and more vehicle safety miscellaneous functions are opened
It issues, many driving safety systems become ' standard configuration ' of vehicle.However, research shows that the principal element of threat driving safety is
Driver artificial origin, and the characteristics of existing driving assistance system (ADAS) can not well adapt to each driver, it leads
Cause shows barely satisfactory in terms of driver's adaptability and safety.
Existing driving fatigue monitoring method and system, majority are that unified early warning trigger condition is calculated by algorithm.
Such as《Driving fatigue detects and early warning》Publication No.:CN104240444A;《A kind of pre- police of driving fatigue based on roadmarking
Method》Publication No.:CN107150690A etc..Some methods (are divided by being classified to driver's driving style:Radical type, one
As type, cautious style etc.) although to a certain extent improve monitoring accuracy, but still can not accomplish accurate to driver's driving fatigue
Identification.
Our finger has unique fingerprint, has marked everyone unique identity.Similarly, we drive
Sailing behavior also has fine and close operation ' texture ', and ' driving fingerprint ' refers to just the unique driving behavior of driver.It presses
For the angle of driving behavior, ' driving fingerprint ' is exactly the operation behavior feature build-in attribute for driving individual human and showing.
The application of fingerprint is driven at this stage, mainly carries out feature by the driving behavior data obtained to vehicle sensors
Analysis, to which driver's identity be identified.It is not applied to carry out driving fatigue monitoring field by driving fingerprint.
The present invention can accurately identify the identity of driver and realize for the driving fatigue state prison for driving individual human
It surveys, to reach the driving safety auxiliaring effect of high-adaptability, high security.Simultaneity factor can in real time be driven based on driver
State is sailed, evaluation driving behavior realizes the accurate early warning of fatigue driving state, improves traffic safety.
Invention content
The technical problem to be solved in the present invention is for the defects in the prior art, to provide a kind of based on driving fingerprint
Driving fatigue monitoring method and system.
The technical solution adopted by the present invention to solve the technical problems is:It is a kind of to be monitored based on the driving fatigue for driving fingerprint
Method includes the following steps:
S1 the driving data of driver) is acquired by sensor;The driving data includes brake, gas pedal, vehicle
3-axis acceleration, opposite lane position and steering wheel angle data;
S2) special by the driving fingerprint of preset characteristic index algorithm computational representation driving fatigue according to driving data
Metrics-thresholds are levied, driving fingerprint characteristic index includes:The threshold value of Overturn ratio (SRR), the threshold of speed are turned under normal driving state
Value, the level threshold value of transverse direction and longitudinal acceleration and the typical driving security incident based on transverse direction/longitudinal acceleration
(critical incident events:Transverse acceleration absolute value is more than 1m/s2Or longitudinal acceleration absolute value is more than
1.5m/s2) etc..
S3) extraction drives the history driving data information of fingerprint base, to history driving data information and current driver
Feature carries out match cognization;
S4 it) if successfully identifying driver, extracts driver's history and drives fingerprint threshold value record;
S5) if without matched driver in historical record, by step S2) in method calculating the driver in real time just
Fingerprint threshold value is driven under normal driving condition;
S6) by step S4) and step S5) obtained driving fingerprint threshold value comments the driving fingerprint state acquired in real time
Whether valence, output driver are in the result of fatigue driving state.
By said program, the step S2) in pass through preset each characteristic index algorithm using driving data and calculate
The driving fingerprint characteristic index of driving fatigue is characterized, it is specific as follows:
It is for statistical analysis to acquire a period of time driver driving sensing data, and then obtains driver's specific characterization
Unique driving fingerprint characterizes metrics-thresholds under parameter;The driving fingerprint characteristic index includes:
To each characteristic index, the sensing data of extraction a period of time continuous normal driving state is (it is assumed that drive first
It is normal condition when the person of sailing drives vehicle for the first time) it carries out data prediction and calculates separately and obtain above-mentioned characteristic index, utilize K-
Means clustering algorithms take cluster centre k=1 respectively, and obtain central point parameter values α, i.e. standard value:
Wherein:xjFor the driving fingerprint characteristic index parameter of selection;
μiFor the mean value of the index parameter;
I is the serial number of cluster centre point;
J is the serial number of the index parameter;
The standard value α for respectively obtaining each characteristic index of the driver chooses the corresponding proportionality coefficient e of each characteristic index and obtains
Threshold value r of the index under normally travel state1And r2:
r1=α (1-e)
r2=α (1+e)
Driving fingerprint of the driver under normal driving state is obtained by the study lasting to driving fingerprint parameter
Parameter threshold range.
By said program, the driving fingerprint characteristic index is obtained by Principal Component Analysis.
A kind of Driving Fatigue Monitoring System based on driving fingerprint, including:
Data acquisition module, the driving data for acquiring driver by sensor;The driving data include brake,
Gas pedal, vehicle 3-axis acceleration, opposite lane position and steering wheel angle data;
Fingerprint characteristic metrics-thresholds computing module is driven, for being calculated by preset characteristic index according to driving data
The driving fingerprint characteristic metrics-thresholds of method computational representation driving fatigue, and store;Driving fingerprint characteristic index includes:Normal driving
The threshold value of Overturn ratio (SRR), the threshold value of speed, the level threshold value of transverse direction and longitudinal acceleration and based on cross are turned under state
To typical driving security incident (the critical incident events of/longitudinal acceleration:Transverse acceleration absolute value is more than
1m/s2Or longitudinal acceleration absolute value is more than 1.5m/s2) etc..
Driver's matching module believes history driving data for extracting the history driving data information for driving fingerprint base
Breath carries out match cognization with current driver's feature;If successful match identifies driver, driver's history driving is extracted
Fingerprint threshold value records;If real by driving fingerprint characteristic metrics-thresholds computing module without matched driver in historical record
When calculate under driver's normal driving state driving fingerprint threshold value;
Fatigue detecting judgment module, for being commented the driving fingerprint state acquired in real time according to driving fingerprint threshold value
Whether valence, output driver are in the result of fatigue driving state.
By said program, in the driving fingerprint characteristic metrics-thresholds computing module, the driving of computational representation driving fatigue
Fingerprint characteristic metrics-thresholds, it is specific as follows:
It is for statistical analysis to acquire a period of time driver driving sensing data, and then obtains driver's specific characterization
Unique driving fingerprint characterizes metrics-thresholds under parameter;The driving fingerprint characteristic index includes:
To each characteristic index, the sensing data of extraction a period of time continuous normal driving state is (it is assumed that drive first
It is normal condition when the person of sailing drives vehicle for the first time) it carries out data prediction and calculates separately and obtain above-mentioned characteristic index, utilize K-
Means clustering algorithms take cluster centre k=1 respectively, and obtain central point parameter values α, i.e. standard value:
Wherein:xjFor the driving fingerprint characteristic index parameter of selection;
μiFor the mean value of the index parameter;
I is the serial number of cluster centre point;
J is the serial number of the index parameter;
The standard value α for respectively obtaining each characteristic index of the driver chooses the corresponding proportionality coefficient e of each characteristic index and obtains
Threshold value r of the index under normally travel state1And r2:
r1=α (1-e)
r2=α (1+e)
Driving fingerprint of the driver under normal driving state is obtained by the study lasting to driving fingerprint parameter
Parameter threshold range.
The beneficial effect comprise that:Identification process of the present invention does not influence driver's normal driving, while personalized
Identifying system can realize the detection of real-time, accurate driver fatigue, and with the increase for driving number, fatigue detecting
Speed and accuracy can also be improved.
Description of the drawings
Present invention will be further explained below with reference to the attached drawings and examples, in attached drawing:
Fig. 1 is the method flow diagram of the embodiment of the present invention;
Fig. 2 is the method flow diagram of the embodiment of the present invention.
Specific implementation mode
In order to make the purpose , technical scheme and advantage of the present invention be clearer, with reference to embodiments, to the present invention
It is further elaborated.It should be appreciated that described herein, specific examples are only used to explain the present invention, is not used to limit
The fixed present invention.
As shown in Figure 1, the present invention has supplied a kind of based on the driving fatigue monitoring method for driving fingerprint, this method includes mainly
Two large divisions, driver drive the training process of fingerprint and based on the driving fatigue monitoring process for driving fingerprint.
The training process principle for driving fingerprint is that acquisition a period of time driver driving sensing data is for statistical analysis,
And then obtain unique driving fingerprint characterization metrics-thresholds under driver's specific characterization parameter.With drive duration increase,
The influence of automatic fitration achievement data caused by short time style changes.Drive the driving fatigue that fingerprint is specific driver
Characterization parameter.
Based on the driving fatigue monitoring process of fingerprint is driven obtained by the study lasting to driving fingerprint parameter
Driving fingerprint parameter threshold value of the driver under normal driving state, by real-time collection vehicle sensing data and with currently drive
It sails people's driving fingerprint threshold value to be compared, by judging whether the driving fingerprint parameter of current driver is more than under normal condition
Threshold value whether there is driving fatigue to monitor driver.
Following mode can be used in the training process:
The sensing data of extraction a period of time continuous normal driving state is (it is assumed that driver drives vehicle for the first time first
When be normal condition) carry out data prediction and calculate separately and obtain above-mentioned characteristic index, taken respectively using K-means clustering algorithms
Cluster centre k=1, and obtain central point parameter values α, i.e. standard value:
Wherein:xjFor the driving fingerprint characteristic index parameter of selection;
μiFor the mean value of the index parameter;
I is the serial number of cluster centre point;
J is the serial number of the index parameter;
The standard value α for respectively obtaining each characteristic index of the driver, the coefficient e for choosing different ratios obtain the index and exist
Threshold value r under normally travel state1And r2:
r1=α (1-e)
r2=α (1+e)
The range for exceeding its threshold value according to each characteristic index finally by certain algorithm, judges driving fatigue state.
Based on the driving fatigue monitoring method based on driving fingerprint that principles above proposes, the driving fingerprint for including mainly is instructed
Practice process and based on the driving fatigue monitoring process for driving fingerprint.This method be for vehicle driving individual human carry out it is real-time
Personalized fatigue monitoring.The process for driving fingerprint recognition is proceeded by when driver starts vehicle, according to driving fingerprint
The history of Auto-matching driver drives fingerprint characteristic data, and fingerprint threshold value is driven under normal driving state by comparing.We
Method is the process persistently carried out in driving procedure, can both eliminate and interfered caused by short time driving style changes, and
As the increase driving fatigue for driving duration monitors the accuracy for also more meeting driver's personal characteristics to improve monitoring and fits
Ying Xing.
Fingerprint training process is driven to mainly include the following steps that:
Step 1, the driving data of extraction vehicle sensors acquisition and caching, wherein sensing data include brake, throttle
Pedal, vehicle 3-axis acceleration, opposite lane position and steering wheel angle data.
Step 2, using Principal Component Analysis determine with the significantly correlated driving fingerprint of driving fatigue, according to sensitivity level
Determine the weight of each characteristic parameter.
Step 3, driver's the driving under normal driving state obtained by extraction step 2 according to driving sensing data
Fingerprint is sailed, the threshold value for driving each characteristic index of fingerprint under normal driving state is calculated.
Step 4 drives fingerprint characteristic by periodic analysis of history and real-time driver, to eliminate the driving of short time
Identification problem caused by style variation, constantly improve characteristic index threshold value is to improve monitoring accuracy.
For each driver for driving the vehicle using this method, with the increase of driver's driving time, driver
The levels of precision of speed and the fatigue driving state monitoring of identities match is also continuously available raising.
The vehicle carried driving fatigue monitoring system for driver's individual characteristic that the present invention announces, which, which can realize, works as
Auto-matching driver identity and historical data when vehicle has multiple drivers, moreover it is possible to realize and be referred to based on the driving for driving individual human
The driving fatigue of line personalization monitors.Automatic Pilot people matches as mentioned previously, voluntarily defeated before driving without driver
Enter drivers information, but sensing data is driven by handling and interior storage by starting to drive in a bit of time
It drives fingerprint to be matched, driving fatigue characterization parameter threshold value is extracted with automatic identification driver identity and from storage module.
What the application of driving fatigue monitoring was extracted after being matched with above-mentioned driver by the driving condition characteristic index that comparison acquires in real time
Trained metrics-thresholds are compared, to realize that the driving fatigue to current driver personalization monitors.This system with
Vehicle launch and open, entire identities match and the driving fatigue monitoring process of driving to vehicle or will not drive without other operations
The driving conditions for sailing people interfere, and can improve driving safety grade.
It is illustrated in figure 2 currently preferred system flow chart, first, vehicle sensory while driver starts vehicle
Device proceeds by driving data acquisition.
Driving data is transmitted to processor and work as above-mentioned driving fingerprint training method step obtains by subsequent sensor
Preceding driver drives fingerprint characteristic.
By the way that fingerprint characteristic and history driver's fingerprint matches in reservoir will be driven.If successful match extracts
The driving fingerprint parameter trained and threshold value recorded in memory;If no historical data matching, current driving acquisition is utilized
Data carry out above-mentioned driving fingerprint training process step and are stored into reservoir.
Through training after a period of time, the driver for driving fingerprint with being obtained by training that real-time collection analysis goes out is compared
Fingerprint threshold value is driven under normal driving state, judges the driving condition residing for driver.
According to said program, the present invention also provides a kind of based on the Driving Fatigue Monitoring System for driving fingerprint, including:
Data acquisition module, the driving data for acquiring driver by sensor;The driving data include brake,
Gas pedal, vehicle 3-axis acceleration, opposite lane position and steering wheel angle data;
Fingerprint characteristic metrics-thresholds computing module is driven, for being calculated by preset characteristic index according to driving data
The driving fingerprint characteristic metrics-thresholds of method computational representation driving fatigue, and store;Driving fingerprint characteristic index includes:Normal driving
The threshold value of Overturn ratio (SRR), the threshold value of speed, the level threshold value of transverse direction and longitudinal acceleration and based on cross are turned under state
To typical driving security incident (the critical incident events of/longitudinal acceleration:Transverse acceleration absolute value is more than
1m/s2Or longitudinal acceleration absolute value is more than 1.5m/s2) etc.;
Driver's matching module believes history driving data for extracting the history driving data information for driving fingerprint base
Breath carries out match cognization with current driver's feature;If successful match identifies driver, driver's history driving is extracted
Fingerprint threshold value records;If real by driving fingerprint characteristic metrics-thresholds computing module without matched driver in historical record
When calculate under driver's normal driving state driving fingerprint threshold value;
Fatigue detecting judgment module, for being commented the driving fingerprint state acquired in real time according to driving fingerprint threshold value
Whether valence, output driver are in the result of fatigue driving state.
It drives in fingerprint characteristic metrics-thresholds computing module, the driving fingerprint characteristic index threshold of computational representation driving fatigue
Value, it is specific as follows:
It is for statistical analysis to acquire a period of time driver driving sensing data, and then obtains driver's specific characterization
Unique driving fingerprint characterizes metrics-thresholds under parameter;The driving fingerprint characteristic index includes:
To each characteristic index, the sensing data of extraction a period of time continuous normal driving state is (it is assumed that drive first
It is normal condition when the person of sailing drives vehicle for the first time) it carries out data prediction and calculates separately and obtain above-mentioned characteristic index, utilize K-
Means clustering algorithms take cluster centre k=1 respectively, and obtain central point parameter values α, i.e. standard value:
Wherein:xjFor the driving fingerprint characteristic index parameter of selection;
μiFor the mean value of the index parameter;
I is the serial number of cluster centre point;
J is the serial number of the index parameter;
The standard value α for respectively obtaining each characteristic index of the driver chooses the corresponding proportionality coefficient e of each characteristic index and obtains
Threshold value r of the index under normally travel state1And r2:
r1=α (1-e)
r2=α (1+e)
Driving fingerprint of the driver under normal driving state is obtained by the study lasting to driving fingerprint parameter
Parameter threshold range.
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 (5)
1. a kind of based on the driving fatigue monitoring method for driving fingerprint, which is characterized in that include the following steps:
S1 the driving data of driver) is acquired by sensor;The driving data includes brake, gas pedal, three axis of vehicle
Acceleration, opposite lane position and steering wheel angle data;
S2) referred to by the driving fingerprint characteristic of preset characteristic index algorithm computational representation driving fatigue according to driving data
Threshold value is marked, driving fingerprint characteristic index includes:Turned under normal driving state the threshold value of Overturn ratio, the threshold value of speed, laterally with
And longitudinal acceleration level threshold value and typical driving security incident based on transverse direction/longitudinal acceleration:Transverse acceleration is exhausted
1m/s is more than to value2Or longitudinal acceleration absolute value is more than 1.5m/s2;
S3) extraction drives the history driving data information of fingerprint base, to history driving data information and current driver's feature
Carry out match cognization;
S4 it) if successfully identifying driver, extracts driver's history and drives fingerprint threshold value record;
S5) if without matched driver in historical record, by step S2) in method calculate the driver in real time and normally drive
Sail driving fingerprint threshold value under state;
S6) by step S4) and step S5) obtained driving fingerprint threshold value evaluates the driving fingerprint state acquired in real time,
Export the result whether driver is in fatigue driving state.
2. according to claim 1 based on the driving fatigue monitoring method for driving fingerprint, which is characterized in that the step
S2 referred to by the driving fingerprint characteristic of preset each characteristic index algorithm computational representation driving fatigue using driving data in)
Mark, it is specific as follows:
It is for statistical analysis to acquire a period of time driver driving sensing data, and then obtains driver's specific characterization parameter
Under unique driving fingerprint characterize metrics-thresholds;The driving fingerprint characteristic index includes:
To each characteristic index, the sensing data of extraction a period of time continuous normal driving state first carries out data and locates in advance
Reason, which calculates separately, obtains above-mentioned characteristic index, takes cluster centre k=1 respectively using K-means clustering algorithms, and obtain central point
Parameter values α, i.e. standard value:
Wherein:xjFor the driving fingerprint characteristic index parameter of selection;
μiFor the mean value of the index parameter;
I is the serial number of cluster centre point;
J is the serial number of the index parameter;
The standard value α for respectively obtaining each characteristic index of the driver, chooses the corresponding proportionality coefficient e of each characteristic index and obtains this and refer to
The threshold value r being marked under normally travel state1And r2:
r1=α (1-e)
r2=α (1+e)
Driving fingerprint parameter of the driver under normal driving state is obtained by the study lasting to driving fingerprint parameter
Threshold range.
3. according to claim 1 based on the driving fatigue monitoring method for driving fingerprint, which is characterized in that the step
S2 fingerprint characteristic index is driven in) to obtain by Principal Component Analysis.
4. it is a kind of based on the Driving Fatigue Monitoring System for driving fingerprint, including:
Data acquisition module, the driving data for acquiring driver by sensor;The driving data includes brake, throttle
Pedal, vehicle 3-axis acceleration, opposite lane position and steering wheel angle data;
Fingerprint characteristic metrics-thresholds computing module is driven, based on according to driving data by preset characteristic index algorithm
The driving fingerprint characteristic metrics-thresholds of characterization driving fatigue are calculated, and are stored;Driving fingerprint characteristic index includes:Normal driving state
The lower level threshold value for turning to the threshold value of Overturn ratio, the threshold value of speed, transverse direction and longitudinal acceleration and based on laterally/it is longitudinal plus
The typical driving security incident of speed:Transverse acceleration absolute value is more than 1m/s2Or longitudinal acceleration absolute value is more than 1.5m/s2;
Driver's matching module, for extract the history driving data information for driving fingerprint base, to history driving data information and
Current driver's feature carries out match cognization;If successful match identifies driver, extracts driver's history and drive fingerprint
Threshold value records;If being counted in real time without matched driver by driving fingerprint characteristic metrics-thresholds computing module in historical record
Calculate driving fingerprint threshold value under driver's normal driving state;
Fatigue detecting judgment module, it is defeated for being evaluated the driving fingerprint state acquired in real time according to driving fingerprint threshold value
Go out the result whether driver is in fatigue driving state.
5. according to claim 4 based on the Driving Fatigue Monitoring System for driving fingerprint, which is characterized in that the driving refers to
In line characteristic index threshold calculation module, the driving fingerprint characteristic metrics-thresholds of computational representation driving fatigue are specific as follows:
It is for statistical analysis to acquire a period of time driver driving sensing data, and then obtains driver's specific characterization parameter
Under unique driving fingerprint characterize metrics-thresholds;The driving fingerprint characteristic index includes:
To each characteristic index, the sensing data of extraction a period of time continuous normal driving state first carries out data and locates in advance
Reason, which calculates separately, obtains above-mentioned characteristic index, takes cluster centre k=1 respectively using K-means clustering algorithms, and obtain central point
Parameter values α, i.e. standard value:
Wherein:xjFor the driving fingerprint characteristic index parameter of selection;
μiFor the mean value of the index parameter;
I is the serial number of cluster centre point;
J is the serial number of the index parameter;
The standard value α for respectively obtaining each characteristic index of the driver, chooses the corresponding proportionality coefficient e of each characteristic index and obtains this and refer to
The threshold value r being marked under normally travel state1And r2:
r1=α (1-e)
r2=α (1+e)
Driving fingerprint parameter of the driver under normal driving state is obtained by the study lasting to driving fingerprint parameter
Threshold range.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810405726.1A CN108577869A (en) | 2018-04-29 | 2018-04-29 | Based on the driving fatigue monitoring method and system for driving fingerprint |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810405726.1A CN108577869A (en) | 2018-04-29 | 2018-04-29 | Based on the driving fatigue monitoring method and system for driving fingerprint |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108577869A true CN108577869A (en) | 2018-09-28 |
Family
ID=63620415
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810405726.1A Pending CN108577869A (en) | 2018-04-29 | 2018-04-29 | Based on the driving fatigue monitoring method and system for driving fingerprint |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108577869A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110428693A (en) * | 2019-07-31 | 2019-11-08 | 驭势科技(北京)有限公司 | User driving habits Training Methodology, training module, mobile unit and storage medium |
CN113257023A (en) * | 2021-04-13 | 2021-08-13 | 哈尔滨工业大学 | L3-level automatic driving risk assessment and takeover early warning method and system |
WO2021212274A1 (en) * | 2020-04-20 | 2021-10-28 | 南京天擎汽车电子有限公司 | Fatigue driving state detection method and apparatus, computer device, and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105426638A (en) * | 2015-12-24 | 2016-03-23 | 吉林大学 | Driver behavior characteristic identification device |
CN105632103A (en) * | 2016-03-11 | 2016-06-01 | 张海涛 | Method and device for monitoring fatigue driving |
CN105761329A (en) * | 2016-03-16 | 2016-07-13 | 成都信息工程大学 | Method of identifying driver based on driving habits |
CN106428015A (en) * | 2016-09-12 | 2017-02-22 | 惠州Tcl移动通信有限公司 | Intelligent driving assistant method and device |
-
2018
- 2018-04-29 CN CN201810405726.1A patent/CN108577869A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105426638A (en) * | 2015-12-24 | 2016-03-23 | 吉林大学 | Driver behavior characteristic identification device |
CN105632103A (en) * | 2016-03-11 | 2016-06-01 | 张海涛 | Method and device for monitoring fatigue driving |
CN105761329A (en) * | 2016-03-16 | 2016-07-13 | 成都信息工程大学 | Method of identifying driver based on driving habits |
CN106428015A (en) * | 2016-09-12 | 2017-02-22 | 惠州Tcl移动通信有限公司 | Intelligent driving assistant method and device |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110428693A (en) * | 2019-07-31 | 2019-11-08 | 驭势科技(北京)有限公司 | User driving habits Training Methodology, training module, mobile unit and storage medium |
WO2021212274A1 (en) * | 2020-04-20 | 2021-10-28 | 南京天擎汽车电子有限公司 | Fatigue driving state detection method and apparatus, computer device, and storage medium |
CN113257023A (en) * | 2021-04-13 | 2021-08-13 | 哈尔滨工业大学 | L3-level automatic driving risk assessment and takeover early warning method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108995653B (en) | Method and system for identifying driving style of driver | |
CN108995654B (en) | Driver state identification method and system | |
CN101030316B (en) | Safety driving monitoring system and method for vehicle | |
CN108577869A (en) | Based on the driving fatigue monitoring method and system for driving fingerprint | |
CN108248610B (en) | It is a kind of adaptively divert one's attention driving behavior monitoring and tampering devic | |
CN111753674A (en) | Fatigue driving detection and identification method based on deep learning | |
CN104240446A (en) | Fatigue driving warning system on basis of human face recognition | |
CN106448265A (en) | Collecting method and device of driver's driving behavior data | |
CN108682119A (en) | Method for detecting fatigue state of driver based on smart mobile phone and smartwatch | |
CN103559508A (en) | Video vehicle detection method based on continuous Adaboost | |
CN107316354B (en) | A kind of method for detecting fatigue driving based on steering wheel and GNSS data | |
CN111434553B (en) | Brake system, method and device, and fatigue driving model training method and device | |
CN110575163A (en) | Method and device for detecting driver distraction | |
Jeong et al. | Real-time driver identification using vehicular big data and deep learning | |
CN112016429A (en) | Fatigue driving detection method based on train cab scene | |
CN109559481A (en) | Drive risk intelligent identification Method, device, computer equipment and storage medium | |
CN114092922A (en) | Driver emotion recognition and behavior intervention method based on specificity | |
CN108021875A (en) | A kind of vehicle driver's personalization fatigue monitoring and method for early warning | |
CN106408032A (en) | Fatigue driving detection method based on corner of steering wheel | |
CN105320948A (en) | Image based gender identification method, apparatus and system | |
CN108438001A (en) | A kind of abnormal driving behavior method of discrimination based on Time Series Clustering analysis | |
CN108875617A (en) | Auxiliary driving method and device, vehicle | |
CN108596057B (en) | Information security management system based on face recognition | |
CN110263664A (en) | A kind of more occupant lanes are broken rules and regulations recognition methods and device | |
CN110422173A (en) | A kind of environment recognition methods |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180928 |