CN106339692A - Fatigue driving state information determination method based on route offset detection and system - Google Patents
Fatigue driving state information determination method based on route offset detection and system Download PDFInfo
- Publication number
- CN106339692A CN106339692A CN201610807443.0A CN201610807443A CN106339692A CN 106339692 A CN106339692 A CN 106339692A CN 201610807443 A CN201610807443 A CN 201610807443A CN 106339692 A CN106339692 A CN 106339692A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- driving
- moment
- state
- fatigue
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/59—Context or environment of the image inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
- G06V20/597—Recognising the driver's state or behaviour, e.g. attention or drowsiness
-
- 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
- G07C5/085—Registering performance data using electronic data carriers
- G07C5/0866—Registering performance data using electronic data carriers the electronic data carrier being a digital video recorder in combination with video camera
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Traffic Control Systems (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a fatigue driving state information determination method based on route offset detection and a system. The method comprises steps that a vehicle state at the first moment is acquired; the vehicle state at the first moment is processed to acquire driving state characteristics at the first moment; the driving state characteristics at the first moment are inputted to a driving habit model; signal reconstruction is carried out to acquire a prediction driving state at the second moment; driving state characteristics at the second moment are acquired; operation of the driving state characteristics at the second moment is carried out according to the prediction driving state at the second moment to acquire a driving behavior offset index, and a fatigue state is determined according to the driving behavior offset index. The system comprises a data acquisition module, a processing module and a fatigue driving determination module. According to the system and the method, fatigue detection reliability and accuracy are improved through machine learning and the improved multi-information fusion technology.
Description
Technical field
The present invention relates to safe driving field, more particularly to a kind of fatigue driving state letter based on path deviations detection
Breath determines method and system.
Background technology
Research to fatigue driving detection mainly has detection (electromyogram, electroencephalogram, eye electricity based on physiological driver's parameter
Figure, sound frequency, breathing, pulse etc.), the detection (frequency of wink, pupil size etc.) based on Characteristics of drivers' behavior and being based on
The various ways methods such as the detection (travel speed, deviation, throttle and braking forces measuring) of vehicle behavioural characteristic.Wherein, examine
The angle surveying lane shift is by being positioned over the Road information in front of the camera collection vehicle of vehicle window front upper part, by calculating
Method detects angle during run-off-road.
Above measuring method is all that directly status information is detected and drawn with the conclusion of whether fatigue driving.However,
Because the information such as personal driving habit, reaction speed, physiological status vary with each individual it is impossible to seek unity of standard, therefore " normal " with
Jeopardize the very difficult quantization of safe " abnormal " characteristic parameter to define, the judgement conclusion of its fatigue state is inaccurate.
Content of the invention
It is an object of the invention to provide a kind of determine method based on the fatigue driving state information of path deviations detection
And system.
For achieving the above object, the invention provides following scheme:
A kind of method is determined based on the fatigue driving state information of path deviations detection, comprising:
Gather the vehicle-state in the first moment；
The vehicle-state in described first moment is processed, obtains the transport condition feature in the first moment；
The transport condition feature in described first moment is inputted driving habit model；
Signal is reconstructed, obtains the prediction driving condition for the second moment；Described second moment is later than described
One moment；
Obtain the transport condition feature in the second moment；
Row operation is entered to the transport condition feature in described second moment according to the prediction driving condition in described second moment, obtains
Obtain driving behavior offset target, determine the fatigue state of driver according to described driving behavior offset target.
Optionally, before the vehicle-state in the first moment of described collection, also include:
Gather the vehicle-state before the first moment；
Vehicle-state before first moment is processed, obtains transport condition feature；
Described transport condition feature is modeled, obtains driving habit model.
Optionally, the vehicle-state before the first moment of described collection, specifically includes:
The vehicle-state before the first moment is gathered during normal vehicle operation.
Optionally, described collection vehicle state, specifically includes:
Shoot path deviations state when lane line and barrier collection vehicle traveling；
The acceleration of acceleration collection vehicle of detection vehicle, deceleration and shift state；
Collection vehicle interior temperature and humidity；
The in-car sound of collection.
Optionally, described transport condition feature specifically includes: the time of vehicle at the uniform velocity traveling, vehicle shift lane line time
After number, vehicle shift track, the reaction time corrected, camera monitor the reaction that barrier rear vehicle is slowed down or hidden
Time, vehicle interior temperature, vehicle humidity, in-car noise is time in the range of single-frequency, by the machine learning of driving habit
Technology, driver run into barrier avoided or speed-down action average time.
The invention also discloses a kind of fatigue driving state information determining system based on path deviations detection, including data
Acquisition module, processing module, fatigue driving judge module；
Described data acquisition module is used for collection vehicle state；
Described processing module is used for described vehicle-state is processed, and obtains transport condition feature；By described traveling shape
State feature inputs driving habit model；
Described fatigue driving judge module is reconstructed to signal, obtains predicting driving condition；Driven according to described prediction
State enters row operation to described transport condition feature, obtains driving behavior offset target, according to described driving behavior offset target
Determine the fatigue state of driver.
Optionally, described data acquisition module specifically includes: camera, acceleration transducer, Temperature Humidity Sensor and wheat
Gram wind；
Described camera is used for by shooting path deviations state when lane line and barrier collection vehicle traveling；
Described acceleration transducer is used for acceleration, deceleration and the skew shape of the acceleration collection vehicle by detecting vehicle
State；
Described Temperature Humidity Sensor is used for gathering vehicle interior temperature and humidity；
Described microphone is used for gathering in-car sound.
Optionally, described transport condition feature specifically includes: the time of vehicle at the uniform velocity traveling, vehicle shift lane line time
After number, vehicle shift track, the reaction time corrected, camera monitor the reaction that barrier rear vehicle is slowed down or hidden
Time, vehicle interior temperature, vehicle humidity, in-car noise is time in the range of single-frequency, by the machine learning of driving habit
Technology, driver run into barrier avoided or speed-down action average time.
Optionally, described fatigue driving judge module is also modeled to described transport condition feature, obtains driving habit
Model.
Optionally, described fatigue driving judge module is modeled to described transport condition feature, specifically includes:
Described fatigue driving judge module is modeled to described transport condition feature during normal vehicle operation.
The specific embodiment being provided according to the present invention, the invention discloses following technique effect: the present invention utilizes engineering
Practise and multi-information merging technology, the detection of the study to the driving habit of driver and in-car external environment, realize tired to driver
The quantization of labor driving condition, substantially increases accuracy and the reliability of fatigue driving state detection.
Brief description
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to institute in embodiment
Need use accompanying drawing be briefly described it should be apparent that, drawings in the following description be only the present invention some enforcement
Example, for those of ordinary skill in the art, without having to pay creative labor, can also be according to these accompanying drawings
Obtain other accompanying drawings.
Fig. 1 determines fatigue driving in embodiment of the method for the present invention based on the fatigue driving state information that path deviations detect
Status information determines flow chart；
Fig. 2 determines driving habit in embodiment of the method for the present invention based on the fatigue driving state information that path deviations detect
The structure flow chart of model；
The knot of the fatigue driving state information determining system embodiment that Fig. 3 is detected based on path deviations for the embodiment of the present invention
Composition.
Specific embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation description is it is clear that described embodiment is only a part of embodiment of the present invention, rather than whole embodiments.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of not making creative work
Embodiment, broadly falls into the scope of protection of the invention.
It is an object of the invention to provide a kind of determine method based on the fatigue driving state information of path deviations detection
And system.
Understandable for enabling the above objects, features and advantages of the present invention to become apparent from, below in conjunction with the accompanying drawings and specifically real
The present invention is further detailed explanation to apply mode.
Fig. 1 determines fatigue driving in embodiment of the method for the present invention based on the fatigue driving state information that path deviations detect
Status information determines flow chart.
Referring to Fig. 1, described method is determined based on the fatigue driving state information of path deviations detection, comprising:
Step 101, the vehicle-state in the first moment of collection；
Step 102, is processed to the vehicle-state in described first moment, obtains the transport condition feature in the first moment；
Step 103, the transport condition feature in described first moment is inputted driving habit model；
Step 104, is reconstructed to signal, obtains the prediction driving condition for the second moment；Described second evening in moment
In described first moment；
Step 105, obtains the transport condition feature in the second moment；
Step 106, enters to the transport condition feature in described second moment according to the prediction driving condition in described second moment
Row operation, obtains driving behavior offset target, determines the fatigue state of driver according to described driving behavior offset target.
Above-mentioned steps complete during carrying out fatigue driving detection to vehicle.
Figure Fig. 2 is based on the fatigue driving state information that path deviations detect, the present invention determines that in embodiment of the method, driving is practised
The structure flow chart of used model.As shown in Fig. 2 this flow process includes:
Step 201, collection vehicle state；Using multi-information merging technology to vehicle-state Real-time Collection, including collecting vehicle
Interior ambient condition, car external environment state and vehicle running state.
Step 202, is processed to the vehicle-state collecting, and obtains transport condition feature；Described transport condition feature
For meeting the data of autoencoder network form；
Step 203, is modeled to described transport condition feature, obtains driving habit model；Described driving habit model
It is capable of vehicle driving state is predicted, obtain predicting driving condition.Described driving habit model is self-editing in stack
Build in code network.
Above-mentioned steps are to pass through machine learning during vehicle keeps normally travel in the state of driver regains consciousness
Complete, belong to the training stage of driving model.
The training stage of the present invention is to build driving habit model, the driving habit to driver by machine learning method
Real time record simultaneously learns, and in-car external environment is added in the factor to driver tired driving detection.The use of the present invention
Stage is to carry out many real time information detections by the technology of Multi-information acquisition to the fatigue driving state of driver, will examine
It is capable of the quantization to driver tired driving state in the real time information input model surveyed.This fatigue driving detection side
Method, is contrasted with normal transport condition by real time running state, can more accurately quantify the driving shape of driver
State, substantially increases the reliability of fatigue driving state monitoring.
Optionally, described collection vehicle state, specifically includes:
Shoot path deviations state when lane line and barrier collection vehicle traveling；
The acceleration of acceleration collection vehicle of detection vehicle, deceleration and shift state；
Collection vehicle interior temperature and humidity；
The in-car sound of collection.
Optionally, described vehicle-state is processed, obtain transport condition feature, specifically include:
Video image is pre-processed, then carries out greyscale transformation, Threshold segmentation (change or gradient image by both images
The two is changed), realize road being identified and following the tracks of, and obtain obstacle information；By the analysis to road and barrier, can
To obtain shape and the bearing of trend of road, the relative position of position in track for this car and other vehicle；
The acceleration of vehicle, deceleration and shift state are processed, obtains the velocity information of vehicle；
According to video image and velocity information, calculate time of vehicle at the uniform velocity traveling, the number of times of vehicle shift lane line,
Behind vehicle shift track correct reaction time, camera monitor barrier rear vehicle slowed down or hidden reaction when
Between；
The temperature collecting, humidity information and in-car acoustic information are processed, is calculated vehicle interior temperature, in-car wet
Degree and in-car noise are the time in the range of single-frequency；
Extract the information in driving habit model in real time, calculate the machine learning techniques by driving habit, driver meets
Avoided to barrier or speed-down action average time.
Optionally, the distance travelled of training stage will ensure more than 200 kilometers before operational phase the training stage.
Optionally, described transport condition feature is modeled carrying out by stack autoencoder network.
Optionally, described transport condition feature includes: the time t1 of vehicle at the uniform velocity traveling, the number of times of vehicle shift lane line
After r1, vehicle shift track correct reaction time t2, camera monitor barrier rear vehicle slowed down or hidden anti-
Between seasonable, t3, vehicle interior temperature n1, vehicle humidity n2, in-car noise are the time t4 in the range of single-frequency, pass through driving habit
Machine learning techniques, driver run into barrier avoided or speed-down action average time t5.
The computing formula of described driving behavior offset target s is:
S=a × t1 × r1+b × t2+c × t3+d × n1+f × n2+g × t4+h × t5
Driving condition is divided into three kinds of states, respectively abnormal driving state, fatigue driving state and between normal driving shape
Improper driving condition between state and fatigue driving state.Driving behavior offset target is set two benchmark: normal driving
Benchmark and fatigue driving benchmark.Normal driving benchmark between abnormal driving state and improper driving condition, fatigue driving
Benchmark is between improper driving condition and fatigue driving state.When the real-time result of calculation of driving behavior offset target s is little
When normal driving benchmark, judge driving condition for abnormal driving state；Real-time result of calculation as driving behavior offset target s
More than normal driving benchmark and less than fatigue driving benchmark when, judge driving condition for improper driving condition；Work as driving behavior
When the real-time result of calculation of offset target s is more than fatigue driving benchmark, judge driving condition for fatigue driving state.
Optionally, when judging driving condition for improper driving condition and fatigue driving state, system can send in real time
Alarm, reminds driver.
Optionally, the driving habit of different people differs, and the result after training is also different.Described driving habit
Model has the function of storing multiple different training results.Different people is carried out during fatigue driving state detection using corresponding
Driving habit model.
The structure chart of the fatigue driving state information determining system embodiment that Fig. 3 is detected based on path deviations for the present invention.
Referring to Fig. 3, the invention also discloses a kind of fatigue driving state information determining system based on path deviations detection,
Including data acquisition module 301, processing module 302, fatigue driving judge module 303；
Described data acquisition module 301 is used for collection vehicle state；
Described processing module 302 is used for described vehicle-state is processed, and obtains transport condition feature；By described traveling
State feature inputs driving habit model；
Described fatigue driving judge module 303 is reconstructed to signal, obtains predicting driving condition；Driven according to described prediction
State of sailing enters row operation to described transport condition feature, obtains driving behavior offset target, is referred to according to described driving behavior skew
Mark determines the fatigue state of driver.
Optionally, described data acquisition module 301 specifically includes: camera 304, acceleration transducer 305, humiture pass
Sensor 306 and microphone 307；
Described camera 304 is used for by shooting path deviations state when lane line and barrier collection vehicle traveling；
Described acceleration transducer 305 is used for acceleration, deceleration and the skew of the acceleration collection vehicle by detecting vehicle
State；
Described Temperature Humidity Sensor 306 is used for gathering vehicle interior temperature and humidity；
Described microphone 307 is used for gathering in-car sound.
Optionally, described transport condition feature specifically includes: the time t1 of vehicle at the uniform velocity traveling, vehicle shift lane line
After number of times r1, vehicle shift track, the reaction time t2 correcting, camera monitor that barrier rear vehicle is slowed down or hidden
Reaction time t3, vehicle interior temperature n1, vehicle humidity n2, in-car noise be time t4 in the range of single-frequency, by driving
Custom machine learning techniques, driver run into barrier avoided or speed-down action average time t5.
Optionally, described fatigue driving judge module 303 is also modeled to described transport condition feature, obtains driving and practises
Used model.
Optionally, described fatigue driving judge module 303 is modeled to described transport condition feature, specifically includes:
Described fatigue driving judge module 303 is built to described transport condition feature during normal vehicle operation
Mould, described fatigue driving judge module 303 is modeled to complete before fatigue detecting to described transport condition feature.Institute
Stating modeling process will ensure VMT Vehicle-Miles of Travel more than 200 kilometers.
Optionally, the computing formula of described driving behavior offset target s is:
S=a × t1 × r1+b × t2+c × t3+d × n1+f × n2+g × t4+h × t5
Optionally, described a kind of warning mould is also included based on the fatigue driving state information determining system of path deviations detection
Block 308, can send alarm when fatigue driving judge module 303 judges that driving condition is abnormal.
Specific case used herein is set forth to the principle of the present invention and embodiment, the saying of above example
Bright it is only intended to help and understands the method for the present invention and its core concept；Simultaneously for one of ordinary skill in the art, foundation
The thought of the present invention, all will change in specific embodiments and applications.In sum, this specification content is not
It is interpreted as limitation of the present invention.
Claims (10)
1. a kind of method is determined based on the fatigue driving state information of path deviations detection it is characterised in that include:
Gather the vehicle-state in the first moment；
The vehicle-state in described first moment is processed, obtains the transport condition feature in the first moment；
The transport condition feature in described first moment is inputted driving habit model；
Signal is reconstructed, obtains the prediction driving condition for the second moment；When described second moment is later than described first
Carve；
Obtain the transport condition feature in the second moment；
Row operation is entered to the transport condition feature in described second moment according to the prediction driving condition in described second moment, acquisition is driven
Sail behavior offset target, determine the fatigue state of driver according to described driving behavior offset target.
2. according to claim 1 a kind of method is determined based on the fatigue driving state information of path deviations detection, it is special
Levy and be, before the vehicle-state in the first moment of described collection, also include:
Gather the vehicle-state before the first moment；
Vehicle-state before first moment is processed, obtains transport condition feature；
Described transport condition feature is modeled, obtains driving habit model.
3. according to claim 2 a kind of method is determined based on the fatigue driving state information of path deviations detection, it is special
Levy the vehicle-state before being the first moment of described collection to specifically include:
The vehicle-state before the first moment is gathered during normal vehicle operation.
4. according to claim 1 and 2 a kind of method is determined based on the fatigue driving state information of path deviations detection, its
It is characterised by that described collection vehicle state specifically includes:
Shoot path deviations state when lane line and barrier collection vehicle traveling；
The acceleration of acceleration collection vehicle of detection vehicle, deceleration and shift state；
Collection vehicle interior temperature and humidity；
The in-car sound of collection.
5. according to claim 1 and 2 a kind of method is determined based on the fatigue driving state information of path deviations detection, its
It is characterised by, described transport condition feature specifically includes: the time of vehicle at the uniform velocity traveling, the number of times of vehicle shift lane line, car
Reaction time of correcting after offset lanes, camera monitor reaction time that barrier rear vehicle slowed down or hidden,
Vehicle interior temperature, vehicle humidity, in-car noise be time in the range of single-frequency, by the machine learning techniques of driving habit,
Driver run into barrier avoided or speed-down action average time.
6. a kind of fatigue driving state information determining system based on path deviations detection is it is characterised in that include data acquisition
Module, processing module, fatigue driving judge module；
Described data acquisition module is used for collection vehicle state；
Described processing module is used for described vehicle-state is processed, and obtains transport condition feature；Described transport condition is special
Levy input driving habit model；
Described fatigue driving judge module is reconstructed to signal, obtains predicting driving condition；According to described prediction driving condition
Described transport condition feature is entered with row operation, obtains driving behavior offset target, determined according to described driving behavior offset target
The fatigue state of driver.
7. a kind of fatigue driving state information determining system based on path deviations detection according to claim 6, it is special
Levy and be, described data acquisition module specifically includes: camera, acceleration transducer, Temperature Humidity Sensor and microphone；
Described camera is used for by shooting path deviations state when lane line and barrier collection vehicle traveling；
Described acceleration transducer is used for acceleration, deceleration and the shift state of the acceleration collection vehicle by detecting vehicle；
Described Temperature Humidity Sensor is used for gathering vehicle interior temperature and humidity；
Described microphone is used for gathering in-car sound.
8. a kind of fatigue driving state information determining system based on path deviations detection according to claim 6, it is special
Levy and be, described transport condition feature specifically includes: the time of vehicle at the uniform velocity traveling, the number of times of vehicle shift lane line, vehicle
The reaction time corrected after offset lanes, camera monitor the reaction time, car that barrier rear vehicle slowed down or hidden
Interior temperature, vehicle humidity, in-car noise be time in the range of single-frequency, by the machine learning techniques of driving habit, drive
The person of sailing run into barrier avoided or speed-down action average time.
9. a kind of fatigue driving state information determining system based on path deviations detection according to claim 6, it is special
Levy and be, described fatigue driving judge module is also modeled to described transport condition feature, obtains driving habit model.
10. a kind of fatigue driving state information determining system based on path deviations detection according to claim 9, it is special
Levy and be, described fatigue driving judge module is modeled to described transport condition feature, specifically includes:
Described fatigue driving judge module is modeled to described transport condition feature during normal vehicle operation.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2016101286927 | 2016-03-08 | ||
| CN201610128692 | 2016-03-08 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106339692A true CN106339692A (en) | 2017-01-18 |
| CN106339692B CN106339692B (en) | 2019-04-23 |
Family
ID=57823821
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610807443.0A Active CN106339692B (en) | 2016-03-08 | 2016-09-07 | A kind of fatigue driving state information determines method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106339692B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107958601A (en) * | 2017-11-22 | 2018-04-24 | 华南理工大学 | A kind of fatigue driving detecting system and method |
| CN108482380A (en) * | 2018-03-06 | 2018-09-04 | 知行汽车科技（苏州）有限公司 | The driving monitoring system of automatic adjusument sample frequency |
| CN109299784A (en) * | 2018-08-01 | 2019-02-01 | 广州大学 | A kind of auxiliary driving method neural network based, device and readable storage medium storing program for executing |
| CN110638473A (en) * | 2019-09-10 | 2020-01-03 | 中国平安财产保险股份有限公司 | Method, device, electronic device and storage medium for determining fatigue driving |
| CN110733508A (en) * | 2019-10-29 | 2020-01-31 | 深圳联安通达科技有限公司 | fatigue driving detection method and device |
| CN112687076A (en) * | 2020-12-15 | 2021-04-20 | 南通路远科技信息有限公司 | Method and device for preventing fatigue driving and bracelet |
| CN112949015A (en) * | 2019-12-10 | 2021-06-11 | 奥迪股份公司 | Modeling apparatus, assistance system, vehicle, method, and storage medium |
| CN113460060A (en) * | 2021-08-20 | 2021-10-01 | 武汉霖汐科技有限公司 | Driver fatigue degree evaluation system, control method, and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102717765A (en) * | 2012-07-09 | 2012-10-10 | 湖南赛格导航技术研究有限公司 | Fatigue driving detection method and anti-fatigue driving auxiliary device |
| CN104112335A (en) * | 2014-07-25 | 2014-10-22 | 北京机械设备研究所 | Multi-information fusion based fatigue driving detecting method |
| CN105261153A (en) * | 2015-11-03 | 2016-01-20 | 北京奇虎科技有限公司 | Vehicle running monitoring method and device |
-
2016
- 2016-09-07 CN CN201610807443.0A patent/CN106339692B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102717765A (en) * | 2012-07-09 | 2012-10-10 | 湖南赛格导航技术研究有限公司 | Fatigue driving detection method and anti-fatigue driving auxiliary device |
| CN104112335A (en) * | 2014-07-25 | 2014-10-22 | 北京机械设备研究所 | Multi-information fusion based fatigue driving detecting method |
| CN105261153A (en) * | 2015-11-03 | 2016-01-20 | 北京奇虎科技有限公司 | Vehicle running monitoring method and device |
Non-Patent Citations (3)
| Title |
|---|
| WANG HAILIN等: "Fatigue Driving Detection System Design Based on Driving Behavior", 《2010 INTERNATIONAL CONFERENCE ON OPTOELECTRONICS AND IMAGE PROCESSING》 * |
| 刘娜: "基于视觉的车道线识别与偏离预警方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 张晖: "基于驾驶行为的疲劳状态识别研究", 《中国优秀硕士学位论文全文数据库 工程科技||辑》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107958601A (en) * | 2017-11-22 | 2018-04-24 | 华南理工大学 | A kind of fatigue driving detecting system and method |
| CN108482380A (en) * | 2018-03-06 | 2018-09-04 | 知行汽车科技（苏州）有限公司 | The driving monitoring system of automatic adjusument sample frequency |
| CN108482380B (en) * | 2018-03-06 | 2019-09-06 | 知行汽车科技（苏州）有限公司 | The driving monitoring system of automatic adjusument sample frequency |
| CN109299784A (en) * | 2018-08-01 | 2019-02-01 | 广州大学 | A kind of auxiliary driving method neural network based, device and readable storage medium storing program for executing |
| CN109299784B (en) * | 2018-08-01 | 2022-02-18 | 广州大学 | Auxiliary driving method and device based on neural network and readable storage medium |
| CN110638473A (en) * | 2019-09-10 | 2020-01-03 | 中国平安财产保险股份有限公司 | Method, device, electronic device and storage medium for determining fatigue driving |
| CN110733508A (en) * | 2019-10-29 | 2020-01-31 | 深圳联安通达科技有限公司 | fatigue driving detection method and device |
| CN112949015A (en) * | 2019-12-10 | 2021-06-11 | 奥迪股份公司 | Modeling apparatus, assistance system, vehicle, method, and storage medium |
| CN112687076A (en) * | 2020-12-15 | 2021-04-20 | 南通路远科技信息有限公司 | Method and device for preventing fatigue driving and bracelet |
| CN113460060A (en) * | 2021-08-20 | 2021-10-01 | 武汉霖汐科技有限公司 | Driver fatigue degree evaluation system, control method, and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106339692B (en) | 2019-04-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106339692B (en) | A kind of fatigue driving state information determines method and system | |
| EP2201496B1 (en) | Inattentive state determination device and method of determining inattentive state | |
| CN110077398B (en) | Risk handling method for intelligent driving | |
| US7860813B2 (en) | Monitoring driving safety using semi-supervised sequential learning | |
| CN112224211A (en) | Driving simulation system based on multi-autonomous-body traffic flow | |
| CN105564436A (en) | Advanced driver assistance system | |
| CN107972671A (en) | A kind of driving behavior analysis system | |
| JP7155266B2 (en) | Systems and methods for racing data analysis using telemetry data and wearable sensor data | |
| CN110688877B (en) | Danger early warning method, device, equipment and storage medium | |
| CN107031622A (en) | For colliding the training algorithm avoided | |
| CN106485233A (en) | Drivable region detection method, device and electronic equipment | |
| JP5774847B2 (en) | Vehicle travel reproduction evaluation device | |
| CN112749210B (en) | Vehicle collision recognition method and system based on deep learning | |
| CN106373461A (en) | Driver training management service system and method | |
| Shirazi et al. | Detection of intoxicated drivers using online system identification of steering behavior | |
| Peng et al. | Intelligent method for identifying driving risk based on V2V multisource big data | |
| CN110032947A (en) | A kind of method and device that monitor event occurs | |
| CN110196587A (en) | Vehicular automatic driving control strategy model generating method, device, equipment and medium | |
| CN107316354A (en) | A kind of method for detecting fatigue driving based on steering wheel and GNSS data | |
| CN108926352A (en) | A kind of driving fatigue detection method and system | |
| Harkous et al. | A two-stage machine learning method for highly-accurate drunk driving detection | |
| CN116331221A (en) | Driving assistance method, driving assistance device, electronic equipment and storage medium | |
| KR101519217B1 (en) | Apparatus for judging driver inattention and method thereof | |
| CN108898795B (en) | Pedestrian state real-time analysis method and system based on mobile device | |
| Harkous et al. | Application of hidden Markov model on car sensors for detecting drunk drivers |
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 |