CN103489010B - Method for detecting fatigue driving based on driving behavior - Google Patents
Method for detecting fatigue driving based on driving behavior Download PDFInfo
- Publication number
- CN103489010B CN103489010B CN201310442805.7A CN201310442805A CN103489010B CN 103489010 B CN103489010 B CN 103489010B CN 201310442805 A CN201310442805 A CN 201310442805A CN 103489010 B CN103489010 B CN 103489010B
- Authority
- CN
- China
- Prior art keywords
- fatigue
- driving
- conditions
- under
- road
- 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.)
- Expired - Fee Related
Links
Landscapes
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of method for detecting fatigue driving based on driving behavior, solve the problem that the road curvature factor existing for prior art can affect the accuracy rate carrying out method for detecting fatigue driving based on driving behavior, it constructs the Fatigue pattern grader of road alignment grader and correspondence, the road video of Real-time Collection vehicle and driving behavior information in vehicle travel process, extract the driving behavior parameter of driver under different road curvatures (straight way and bend) respectively, determine that present road is linear according to road alignment grader output result, and call the Fatigue pattern grader of correspondence, the identification to driver fatigue state can be realized, this method achieves the most accurately detection of fatigue driving.
Description
Technical field
The present invention relates to a kind of detection method of technical field of vehicle safety, specifically, the present invention relates to a kind of based on driving row
For method for detecting fatigue driving.
Background technology
Fatigue driving is one of principal element causing road traffic accident, and the vehicle accident caused due to fatigue driving every year accounts for
About the 20% of total number of accident, accounts for more than the 40% of especially big vehicle accident.Accordingly, it would be desirable to driver's driving condition is carried out in real time
Detection, when there is fatigue state, gives effective early warning, it is to avoid the generation of road traffic accident.
At present, method for detecting fatigue driving is broadly divided into the detection method of subjectively-based evaluation, inspection based on driver's physiological signal
Survey method, detection method based on driver's physiological reaction, detection method based on driving behavior and detection based on information fusion
Method.Wherein, there is scoring subjectivity, standards of grading disunity, testee's active concealment in the detection method of subjectively-based evaluation
Truth, cater to the problems such as subjective expectation.Detection method based on driver's physiological signal, invasive is strong, easily to driver
Produce interference, be difficult to be accepted.Detection method based on physiological reaction is mainly by Machine Vision Detection driver's facial characteristics,
Easily affected by factors such as light, Vehicular vibration, driver wear glasses.Detection method based on driving behavior is contactless inspection
Surveying, the normal driving behavior of driver will not be interfered by measurement process, and characteristic parameter (speed, steering wheel angle etc.) holds
Easily extract, it has also become study hotspot both at home and abroad.
Under fatigue driving state, wagon control ability is decreased obviously by driver, is therefore believed by the driving behavior that driver is current
Breath, it is possible to realize the detection to fatigue driving.But road curvature change is that (steering wheel turns initiation driver's manipulative behavior equally
Angle, steering wheel angle speed etc.) key factor changing, therefore, road curvature factor can affect to enter based on driving behavior
The accuracy rate of row method for detecting fatigue driving.
Summary of the invention
The standard carrying out method for detecting fatigue driving based on driving behavior can be affected for the road curvature factor solved existing for prior art
The really problem of rate, the present invention provides the method for detecting fatigue driving based on driving behavior of a kind of improvement, extracts different roads respectively
Under road curvature (straight way and bend), the driving behavior parameter of driver, establishes the fatigue of road alignment grader and correspondence
According to road alignment grader output result, pattern classifier, determines that present road is linear, and select the Fatigue pattern classification of correspondence
Device, it is achieved the identification to driver fatigue state, it is possible to eliminate road curvature factor and fatigue driving based on driving behavior is detected
The impact of accuracy, it is achieved that the most accurately detection of fatigue driving.
The present invention is achieved through the following technical solutions: described method for detecting fatigue driving based on driving behavior, it includes
Following steps:
1. build road alignment grader；
2. build Fatigue pattern grader；
3. the road video in collection vehicle traveling process, utilizes road alignment grader to judge that present road is linear；
4. gather driver's driving behavior information, and according to the output result of road alignment grader, select corresponding Fatigue pattern
Grader, it is achieved the identification to driver fatigue state.
Structure road alignment grader described in technical scheme comprises the following specific steps that:
1) gather N and open the road image of different road curvature, open straight way image including N1 and N2 opens bend image, its
In, N1 >=1000, N2 >=2000, set up the training storehouse of road alignment grader；
2) utilize feature extracting method to extract different types of road image features, use the method for statistical analysis to check in difference
The significance of characteristic parameter difference under road alignment (straight way, bend), and then filter out effective characteristic parameters group；
3) the effective characteristic parameters group filtered out is fully incorporated feature space, utilizes the method for machine learning to build road alignment and divide
Class device.
Structure Fatigue pattern grader described in technical scheme comprises the following specific steps that:
1) gathering m respectively, m >=50 driver is positioned at straight way under different driving conditions (normal driving, fatigue driving)
Under the conditions of driving behavior data and be positioned at the driving behavior data under the conditions of bend；
2) the fatigue driving effective characteristic parameters group under the conditions of straight way and the fatigue driving validity feature ginseng under the conditions of bend are extracted respectively
Array；
3) the Fatigue pattern grader under the conditions of straight way and the Fatigue pattern grader under the conditions of bend are built respectively.
Collection m respectively described in technical scheme, m >=50 driver is different driving conditions (normal driving, fatigue driving)
Under be positioned at the driving behavior data under the conditions of straight way and be positioned at bend under the conditions of driving behavior data comprise the following specific steps that:
(1) gathering m, m >=50 driver driving behavior data under normal driving conditions and road video, according to road
Driving behavior data are divided under the conditions of straight way driving behavior data under the conditions of driving behavior data and bend by video information；
(2) gathering m, m >=50 driver driving behavior data under the conditions of fatigue driving and road video, according to road
Driving behavior data are divided under the conditions of straight way driving behavior data under the conditions of driving behavior data and bend by video information；
Fatigue driving effective characteristic parameters group under the conditions of the straight way of extraction respectively described in technical scheme and the fatigue under the conditions of bend
Drive effective characteristic parameters group to comprise the following specific steps that:
(1) the fatigue driving characteristic parameter under the conditions of utilizing feature extracting method to extract straight way, uses the method inspection of statistical analysis
The significance of the characteristic parameter difference under different driving conditions (normal driving, fatigue driving), and then filter out straight way condition
Lower fatigue driving effective characteristic parameters group；
(2) the fatigue driving characteristic parameter under the conditions of utilizing feature extracting method to extract bend, uses the method inspection of statistical analysis
The significance of characteristic parameter difference under different driving conditions (normal driving, fatigue driving), and then under the conditions of filtering out bend
Fatigue driving effective characteristic parameters group；
Fatigue pattern grader under the conditions of the straight way of structure respectively described in technical scheme and the Fatigue pattern classification under the conditions of bend
Device comprises the following specific steps that:
(1) the fatigue driving effective characteristic parameters group under the conditions of the straight way that will filter out is fully incorporated feature space, utilizes engineering
The method practised builds Fatigue pattern grader under straight way；
(2) the fatigue driving effective characteristic parameters group under the conditions of the bend that will filter out is fully incorporated feature space, utilizes engineering
The method practised builds Fatigue pattern grader under bend.
Road video in collection vehicle traveling process described in technical scheme, utilizes road alignment grader to judge present road
Linear comprise the following specific steps that:
1) by vehicle-mounted camera Real-time Collection road image information；
2) extract the characteristic parameter of road image information, input road alignment grader, it is judged that present road is linear.
Collection driver's driving behavior information described in technical scheme, and according to the output result of road alignment grader, select
Corresponding Fatigue pattern grader, it is achieved the identification to driver fatigue state comprises the following specific steps that:
1) driving behavior collecting device Real-time Collection driver current driving behavior data are utilized；
2) if road alignment grader output result is straight way, then at the fatigue driving effective characteristic parameters group under the conditions of foundation straight way
Manage and calculate driving behavior data, and these data are input in the Fatigue pattern grader under the conditions of straight way, it is judged that currently drive
The fatigue state of people；
3) if road alignment grader output result is bend, then at the fatigue driving effective characteristic parameters group under the conditions of foundation bend
Manage and calculate driving behavior data, and these data are input in the Fatigue pattern grader under the conditions of bend, it is judged that currently drive
The fatigue state of people.
Compared with prior art, the method have the advantages that
1. the present invention realizes driver fatigue state based on driving behavior and detects in real time, constructs road alignment grader and right
The Fatigue pattern grader answered, in actual driving conditions, the road video in collection vehicle traveling process, real-time judge is current
Road alignment, calls the Tiredness model grader of correspondence, i.e. realizes the identification to driver fatigue state, eliminate road curvature
Impact on Detection accuracy.
2. the present invention improves fatigue driving Detection accuracy, is of value to popularization and application, can be greatly reduced and lead due to fatigue driving
Cause the incidence rate of pernicious vehicle accident.
Accompanying drawing explanation
Fig. 1 is the flow chart of method for detecting fatigue driving based on driving behavior.
Detailed description of the invention
Below in conjunction with the accompanying drawings and be embodied as example, technical scheme is described further:
The invention provides a kind of method for detecting fatigue driving based on driving behavior, and road curvature factor can affect based on driving
Behavior carries out the accuracy rate of method for detecting fatigue driving.Then, road curvature factor how is eliminated to carrying out tired based on driving behavior
Please the impact sailing detection method has become the significant challenge faced at present.Based on this, collection vehicle traveling process of the present invention
In road video and driving behavior information, extract the effective characteristic parameters under different road curvatures (straight way and bend) respectively
According to road alignment grader output result, group, determines that present road is linear, establishes the Fatigue pattern grader of correspondence, it is achieved
The most accurately detection to fatigue driving.This method specifically comprises the following steps that
1. structure road alignment grader:
1) gather N and open the road image of different road curvature, open (selecting 1000 in embodiment) straight way including N1
Image and N2 open (selecting 2000 in embodiment) bend image, set up the training storehouse of road alignment grader, wherein: N
>=3000, N1 >=1000, N2 >=2000；
2) based on class Haar-like method, the image in training storehouse is carried out feature extraction, use the method for variance analysis that extraction is had
The class Haar-like feature of effect carries out test of difference, and then filters out and there is significant difference on straight way image and bend image
Class Haar-like feature as effective characteristic parameters group；
3) the effective characteristic parameters group filtered out is fully incorporated feature space, uses AdaBoost algorithm to build road alignment
Grader.
2. structure Fatigue pattern grader:
Gather m(m >=50 respectively) name driver under different driving conditions be positioned at straight way under the conditions of and bend under the conditions of drive
Sail behavioral data, build the Fatigue pattern grader under the conditions of different road alignment:
1) gather m(m >=50 respectively) name driver under normal driving and fatigue driving state be positioned at straight way under the conditions of
Driving behavior data and be positioned at the driving behavior data under the conditions of bend:
(1) 50 drivers driving behavior data under normal driving conditions and road video are gathered, according to road video
Driving behavior data are divided under the conditions of straight way driving behavior data under the conditions of driving behavior data and bend by information；
(2) 50 drivers driving behavior data under the conditions of fatigue driving and road video are gathered, according to road video
Driving behavior data are divided under the conditions of straight way condition driving behavior data under driving behavior data and bend by information；
2) the fatigue driving effective characteristic parameters group under the conditions of straight way and the fatigue driving validity feature under the conditions of bend are extracted respectively
Parameter group:
(1) the fatigue driving characteristic parameter under the conditions of utilizing feature extracting method to extract straight way, uses the method inspection of variance analysis
Test the significance of characteristic parameter difference under different driving conditions (normal driving, fatigue driving), filter out and there is significance
The characteristic parameter of difference, as fatigue driving effective characteristic parameters group under the conditions of straight way, is designated as Ps:
Ps=[meansa, stdsa, ensa, stdsv, pns, sdlp], in formula, meansa be steering wheel angle average, stdsa be steering wheel
Corner standard deviation, ensa be steering wheel angle entropy, stdsv be that steering wheel angle velocity standard is poor, pns is zero-speed percentage ratio,
Sdlp is lane shift amount；
(2) the fatigue driving characteristic parameter under the conditions of utilizing feature extracting method to extract bend, uses the method inspection of variance analysis
Test the significance of characteristic parameter difference under different driving conditions (normal driving, fatigue driving), filter out and there is significance
The characteristic parameter of difference, as fatigue driving effective characteristic parameters group under the conditions of bend, is designated as Pc:
Pc=[cvsa, ensa, cvsv, maxsv, pns, sdlp], in formula, cvsa be the steering wheel angle coefficient of variation, ensa be steering wheel
Corner entropy, cvsv be steering wheel angle velocity mutation coefficient, maxsv be steering wheel angle velocity amplitude, pns be zero-speed percentage
Ratio, sdlp are lane shift amount；
3) the effective characteristic parameters group filtered out is fully incorporated feature space, uses support vector machine to build straight way condition respectively
Under Fatigue pattern grader and Fatigue pattern grader under the conditions of bend:
(1) fatigue driving effective characteristic parameters group P under the conditions of the straight way that will filter outsIt is fully incorporated feature space, utilizes and prop up
The method holding vector machine builds Fatigue pattern grader under straight way；
(2) fatigue driving effective characteristic parameters group P under the conditions of the bend that will filter outcIt is fully incorporated feature space, utilizes and prop up
The method holding vector machine builds Fatigue pattern grader under bend.
3., by the road video in vehicle-mounted camera Real-time Collection vehicular motion, utilize road alignment grader to judge current
Road alignment:
1) by vehicle-mounted camera Real-time Collection road image information；
2) extract effective class Haar-like feature of road image information, input road alignment grader, it is judged that present road line
Shape.
4. gather driver's driving behavior information, according to the output result of road alignment grader, select corresponding Fatigue pattern to divide
Class device, it is achieved the identification to driver fatigue state:
1) gather image by vehicle-mounted camera and calculate lane shift amount, by the CAN read direction dish corner of vehicle
With steering wheel angle speed；
2) if road alignment grader output result is straight way, then the fatigue driving effective characteristic parameters group under the conditions of straight way is extracted
Ps, and be entered in the Fatigue pattern grader under the conditions of straight way, it is judged that current driver fatigue state；3) if road
Linear grader output result is bend, then extract fatigue driving effective characteristic parameters group P under the conditions of bendc, and it is defeated
In the Fatigue pattern grader entered under the conditions of bend, it is judged that current driver fatigue state.
A specific embodiment of this method be given below:
1. structure road alignment grader:
1) road image of 3000 different road curvatures is gathered by vehicle-mounted camera, including 1000 straight way images
With 2000 bend images, set up the training storehouse of road alignment grader；
2) based on class Haar-like method, the image in training storehouse is carried out feature extraction, use the method for variance analysis that extraction is had
The class Haar-like feature of effect carries out test of difference, and then filters out and there is significant difference on straight way image and bend image
Class Haar-like feature as effective characteristic parameters group；
3) the effective characteristic parameters group filtered out is fully incorporated feature space, uses AdaBoost algorithm to build road alignment
Grader.
2. structure Fatigue pattern grader:
Gather respectively 50 drivers under different driving conditions be positioned at straight way under the conditions of and bend under the conditions of driving behavior number
According to, build the Fatigue pattern grader under the conditions of different road alignment:
1) driving behavior collecting device gathers 50 drivers respectively and is positioned at straight way under normal driving and fatigue driving state
Under the conditions of driving behavior data and be positioned at the driving behavior data under the conditions of bend:
(1) 50 drivers driving behavior data under normal driving conditions and road video are gathered, according to road video
Driving behavior data are divided under the conditions of straight way driving behavior data under the conditions of driving behavior data and bend by information；
(2) 50 drivers driving behavior data under the conditions of fatigue driving and road video are gathered, according to road video
Driving behavior data are divided under straight way driving behavior data under driving behavior data and bend by information；
2) the fatigue driving effective characteristic parameters group under the conditions of straight way and the fatigue driving validity feature under the conditions of bend are extracted respectively
Parameter group:
(1) the fatigue driving characteristic parameter under the conditions of utilizing feature extracting method to extract straight way, uses the method inspection of variance analysis
Test the significance of characteristic parameter difference under different driving conditions (normal driving, fatigue driving), filter out and there is significance
The characteristic parameter of difference, as fatigue driving effective characteristic parameters group under the conditions of straight way, is designated as Ps:
Ps=[meansa, stdsa, ensa, stdsv, pns, sdlp], in formula, meansa be steering wheel angle average, stdsa be steering wheel
Corner standard deviation, ensa be steering wheel angle entropy, stdsv be that steering wheel angle velocity standard is poor, pns is zero-speed percentage ratio,
Sdlp is lane shift amount；
(2) the fatigue driving characteristic parameter under the conditions of utilizing feature extracting method to extract bend, uses the method inspection of variance analysis
Test the significance of characteristic parameter difference under different driving conditions (normal driving, fatigue driving), filter out and there is significance
The characteristic parameter of difference, as fatigue driving effective characteristic parameters group under the conditions of bend, is designated as Pc:
Pc=[cvsa, ensa, cvsv, maxsv, pns, sdlp], in formula, cvsa be the steering wheel angle coefficient of variation, ensa be steering wheel
Corner entropy, cvsv be steering wheel angle velocity mutation coefficient, maxsv be steering wheel angle velocity amplitude, pns be zero-speed percentage
Ratio, sdlp are lane shift amount；
3) the effective characteristic parameters group filtered out is fully incorporated feature space, uses support vector machine to build straight way condition respectively
Under Fatigue pattern grader and Fatigue pattern grader under the conditions of bend:
(1) fatigue driving effective characteristic parameters group P under the conditions of the straight way that will filter outsIt is fully incorporated feature space, utilizes and prop up
The method holding vector machine builds Fatigue pattern grader under straight way；
(2) fatigue driving effective characteristic parameters group P under the conditions of the bend that will filter outcIt is fully incorporated feature space, utilizes and prop up
The method holding vector machine builds Fatigue pattern grader under bend.
3., by the road video in vehicle-mounted camera Real-time Collection vehicular motion, utilize road alignment grader to judge current
Road alignment:
1) by vehicle-mounted camera Real-time Collection road image information；
2) extract effective class Haar-like feature of road image information, input road alignment grader, it is judged that present road line
Shape.
4. gather driver's driving behavior information, according to the output result of road alignment grader, select corresponding Fatigue pattern to divide
Class device, it is achieved the identification to driver fatigue state:
1) gather image by vehicle-mounted camera and calculate lane shift amount, by the CAN read direction dish corner of vehicle
With steering wheel angle speed；
2) if road alignment grader output result is straight way, then the fatigue driving effective characteristic parameters group under the conditions of straight way is extracted
Ps, and be entered in the Fatigue pattern grader under the conditions of straight way, it is judged that current driver fatigue state；
3) if road alignment grader output result is bend, then the fatigue driving effective characteristic parameters group under the conditions of bend is extracted
Pc, and be entered in the Fatigue pattern grader under the conditions of bend, it is judged that current driver fatigue state.
More than being embodied as in example, the number of the road image gathering different road curvature is 3000, including 1000
Zhang Zhidao image and 2000 bend images, but the scope that the present invention gathers number to road image is not limited to the present embodiment, based on
Common knowledge, Primary Stage Data collection capacity is the biggest, and the accuracy that later data processes is the highest, therefore only provides end value in the present embodiment,
The i.e. example of minima；In like manner, originally it is embodied as in example gathering 50 drivers respectively at normal driving and fatigue driving state
Under be positioned at the driving behavior data under the conditions of straight way and be positioned at bend under the conditions of driving behavior data, this driving number does not limits
In 50, the present embodiment only provides the example of end value, i.e. minima.
Below it is only the concrete exemplary applications of the present invention, protection scope of the present invention is not constituted any limitation.Except above-described embodiment
Outward, the present invention can also have other embodiment.The technical scheme that all employing equivalents or equivalent transformation are formed, all falls within this
Invent within the scope of claimed.
Claims (5)
1. a method for detecting fatigue driving based on driving behavior, it is characterised in that the method comprises the following steps:
1) build road alignment grader, comprise the following steps:
1.1) gather N and open the road image of different road curvature, open straight way image including N1 and N2 opens bend image, wherein, N1 >=1000, N2 >=2000, set up the training storehouse of road alignment grader；
1.2) utilize feature extracting method to extract different types of road image features, use method inspection significance of characteristic parameter difference under different road alignments of statistical analysis, and then filter out effective characteristic parameters group；
1.3) the effective characteristic parameters group filtered out is fully incorporated feature space, utilizes the method for machine learning to build road alignment grader；
2) Fatigue pattern grader is built；
3) the road video in collection vehicle traveling process, utilizes road alignment grader to judge that present road is linear；
4) gather driver's driving behavior information, and according to the output result of road alignment grader, select corresponding Fatigue pattern grader, it is achieved the identification to driver fatigue state.
A kind of method for detecting fatigue driving based on driving behavior, it is characterised in that described structure Fatigue pattern grader comprises the following steps:
2.1) m is gathered respectively, the driving behavior data under the conditions of m >=50 driver being positioned at the driving behavior data under the conditions of straight way and being positioned at bend under normal driving and fatigue driving state；
2.2) the fatigue driving effective characteristic parameters group under the conditions of straight way and the fatigue driving effective characteristic parameters group under the conditions of bend are extracted respectively；
2.3) the Fatigue pattern grader under the conditions of straight way and the Fatigue pattern grader under the conditions of bend are built respectively.
A kind of method for detecting fatigue driving based on driving behavior, it is characterized in that, the described m that gathers respectively, the driving behavior data under the conditions of m >=50 driver being positioned at the driving behavior data under the conditions of straight way and being positioned at bend under normal driving and fatigue driving state comprise the following steps:
(1) m is gathered, m >=50 driver driving behavior data under normal driving conditions and road video, according to road video information, driving behavior data are divided under the conditions of straight way driving behavior data under the conditions of driving behavior data and bend；
(2) m is gathered, m >=50 driver driving behavior data under the conditions of fatigue driving and road video, according to road video information, driving behavior data are divided under straight way driving behavior data under driving behavior data and bend；
Fatigue driving effective characteristic parameters group under the conditions of the described straight way of extraction respectively and the fatigue driving effective characteristic parameters group under the conditions of bend comprise the following steps:
(1) the fatigue driving characteristic parameter under the conditions of utilizing feature extracting method to extract straight way, the method using statistical analysis checks the significance of the characteristic parameter difference under normal driving and fatigue driving state, and then filters out fatigue driving effective characteristic parameters group under the conditions of straight way；
(2) the fatigue driving characteristic parameter under the conditions of utilizing feature extracting method to extract bend, use method inspection significance of characteristic parameter difference under normal driving and fatigue driving state of statistical analysis, and then filter out fatigue driving effective characteristic parameters group under the conditions of bend；
Fatigue pattern grader under the conditions of the described straight way of structure respectively and the Fatigue pattern grader under the conditions of bend comprise the following steps:
(1) the fatigue driving effective characteristic parameters group under the conditions of the straight way that will filter out is fully incorporated feature space, utilizes the method for machine learning to build Fatigue pattern grader under straight way；
(2) the fatigue driving effective characteristic parameters group under the conditions of the bend that will filter out is fully incorporated feature space, utilizes the method for machine learning to build Fatigue pattern grader under bend.
A kind of method for detecting fatigue driving based on driving behavior, it is characterised in that the road video in described collection vehicle traveling process, utilizing road alignment grader to judge, present road is linear comprises the following steps:
3.1) by vehicle-mounted camera Real-time Collection road image information；
3.2) extract the characteristic parameter of road image information, input road alignment grader, it is judged that present road is linear.
A kind of method for detecting fatigue driving based on driving behavior, it is characterized in that, described collection driver's driving behavior information, and according to the output result of road alignment grader, select corresponding Fatigue pattern grader, it is achieved the identification to driver fatigue state comprises the following steps:
4.1) driving behavior collecting device Real-time Collection driver current driving behavior data are utilized；
4.2) if road alignment grader output result is straight way, then process and calculate driving behavior data according to the fatigue driving effective characteristic parameters group under the conditions of straight way, and these data are input in the Fatigue pattern grader under the conditions of straight way, it is judged that the fatigue state of current driver；
4.3) if road alignment grader output result is bend, then process and calculate driving behavior data according to the fatigue driving effective characteristic parameters group under the conditions of bend, and these data are input in the Fatigue pattern grader under the conditions of bend, it is judged that the fatigue state of current driver.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310442805.7A CN103489010B (en) | 2013-09-25 | 2013-09-25 | Method for detecting fatigue driving based on driving behavior |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310442805.7A CN103489010B (en) | 2013-09-25 | 2013-09-25 | Method for detecting fatigue driving based on driving behavior |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103489010A CN103489010A (en) | 2014-01-01 |
| CN103489010B true CN103489010B (en) | 2017-01-04 |
Family
ID=49829216
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310442805.7A Expired - Fee Related CN103489010B (en) | 2013-09-25 | 2013-09-25 | Method for detecting fatigue driving based on driving behavior |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103489010B (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104574821B (en) * | 2015-01-13 | 2017-05-24 | 上海优思通信科技有限公司 | Driving safety prompting device and method |
| CN105679092B (en) * | 2016-01-29 | 2018-05-04 | 深圳市美好幸福生活安全系统有限公司 | A kind of driving behavior analysis system and method |
| 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 |
| CN105844257B (en) * | 2016-04-11 | 2019-03-01 | 吉林大学 | The early warning system and method for road sign are missed based on machine vision travelling in fog day |
| CN105701972A (en) * | 2016-04-14 | 2016-06-22 | 苏州清研微视电子科技有限公司 | System for detecting fatigue driving by using driving behavior variability characteristics |
| CN106778528A (en) * | 2016-11-24 | 2017-05-31 | 四川大学 | A kind of method for detecting fatigue driving based on gaussian pyramid feature |
| CN106611169B (en) * | 2016-12-31 | 2018-10-23 | 中国科学技术大学 | A kind of dangerous driving behavior real-time detection method based on deep learning |
| CN110858290B (en) * | 2018-08-24 | 2023-10-17 | 比亚迪股份有限公司 | Driver abnormal behavior identification method, device, equipment and storage medium |
| CN109766777B (en) * | 2018-12-18 | 2021-08-13 | 东软集团股份有限公司 | Abnormal track detection method and device, storage medium and electronic equipment |
| CN111862533B (en) * | 2020-07-15 | 2021-11-12 | 广东卡仕达电子科技有限公司 | Vehicle joint navigation equipment and method based on big data |
| CN114299690A (en) * | 2021-12-28 | 2022-04-08 | 北京汇通天下物联科技有限公司 | Fatigue driving detection method, device, electronic device and storage medium |
Citations (2)
| 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 |
| CN103310202A (en) * | 2013-06-27 | 2013-09-18 | 西安电子科技大学 | System and method for guaranteeing driving safety |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102005026456B4 (en) * | 2005-06-09 | 2017-04-20 | Daimler Ag | Method for detecting fatigue |
-
2013
- 2013-09-25 CN CN201310442805.7A patent/CN103489010B/en not_active Expired - Fee Related
Patent Citations (2)
| 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 |
| CN103310202A (en) * | 2013-06-27 | 2013-09-18 | 西安电子科技大学 | System and method for guaranteeing driving safety |
Non-Patent Citations (1)
| Title |
|---|
| 基于方向盘操作的驾驶人疲劳状态实时检测方法;张希波，成波，冯睿嘉;《清华大学学报（自然科学版）》;20100731;第50卷(第7期);1072-1076 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103489010A (en) | 2014-01-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103489010B (en) | Method for detecting fatigue driving based on driving behavior | |
| CN103578227B (en) | Based on the method for detecting fatigue driving of GPS locating information | |
| CN104008645B (en) | One is applicable to the prediction of urban road lane line and method for early warning | |
| CN103996053B (en) | Lane departure alarm method based on machine vision | |
| CN105374212B (en) | The vehicle on highway lane recognition method and system sensed based on intelligent terminal | |
| CN102288121B (en) | Method for measuring and pre-warning lane departure distance based on monocular vision | |
| CN105005771B (en) | A kind of detection method of the lane line solid line based on light stream locus of points statistics | |
| CN102509418B (en) | Fatigue driving estimation and early-warning method and device of multi-sensor information fusion | |
| CN104029680B (en) | Lane Departure Warning System based on monocular cam and method | |
| CN107025432B (en) | A kind of efficient lane detection tracking and system | |
| CN110517521A (en) | A kind of lane departure warning method based on road car fusion perception | |
| CN103473762B (en) | A kind of method for detecting lane lines and device | |
| CN104573646A (en) | Detection method and system, based on laser radar and binocular camera, for pedestrian in front of vehicle | |
| CN102737248B (en) | Method and device for extracting characteristic points of lane line under complex road condition | |
| CN104129389A (en) | Method for effectively judging and recognizing vehicle travelling conditions and device thereof | |
| CN106209546A (en) | Based on binocular camera and area array cameras automatic with car system | |
| CN105069859B (en) | Vehicle running state monitoring method and device | |
| CN102252859B (en) | Road train straight-line running transverse stability automatic identification system | |
| CN103927754A (en) | Calibration method of on-board camera | |
| CN104794855A (en) | Driver's attention comprehensive assessment system | |
| CN104794856A (en) | Driver's attention comprehensive evaluation system | |
| CN104002809A (en) | Vehicle fork road segment detection device and detection method | |
| CN106887004A (en) | A kind of method for detecting lane lines based on Block- matching | |
| CN103473948B (en) | Piezoelectric cable laying structure and the trace lateral attitude recognition methods of overloaded vehicle wheel | |
| JP6967042B2 (en) | Driving evaluation device, driving evaluation system, driving evaluation method, program, and intersection attribute discrimination method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170104 Termination date: 20190925 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |