CN105631485A - Fatigue driving detection-oriented steering wheel operation feature extraction method - Google Patents
Fatigue driving detection-oriented steering wheel operation feature extraction method Download PDFInfo
- Publication number
- CN105631485A CN105631485A CN201610182241.1A CN201610182241A CN105631485A CN 105631485 A CN105631485 A CN 105631485A CN 201610182241 A CN201610182241 A CN 201610182241A CN 105631485 A CN105631485 A CN 105631485A
- Authority
- CN
- China
- Prior art keywords
- tired
- fatigue
- driver
- discriminant criterion
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/211—Selection of the most significant subset of features
- G06F18/2113—Selection of the most significant subset of features by ranking or filtering the set of features, e.g. using a measure of variance or of feature cross-correlation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a fatigue driving detection-oriented steering wheel operation feature extraction method. The method includes the following steps that: statistical analysis and comparison are performed on driver fatigue sample variables; the significance of difference of fatigue discrimination indexes under different fatigue levels is tested according to analysis results, and significance indexes are selected to construct fatigue discrimination indexes; with the classification performance of a support vector machine algorithm adopted as evaluation criteria, and a sequential floating forward selection algorithm adopted as a search strategy, a fatigue discrimination index approximate optimal selection algorithm is established, and an index system of driver fatigue state detection is established; with the index system of the driver fatigue state detection obtained through screening adopted as input, a driver fatigue state detection model can be built based on the support vector machine algorithm; and a driver fatigue state detection model considering individual difference and a fatigue detection model in lane deviation of vehicles are built based on the support vector machine algorithm. The method is suitable for generalization ability of different drivers and different operation states and can improve the recognition accuracy of the fatigue detection model.
Description
Technical field
The present invention relates to the detection technique field of driver fatigue state, specifically relate to a kind of bearing circle operating characteristics extracting method driving detection towards fatigue.
Background technology
The improper extension with motorway is day by day increased along with automobile quantity, the speed of a motor vehicle is more and more faster, and traffic safety situation is increasingly serious, and automobile traffic accident increases thereupon, not only cause mass casualties and huge financial loss, and result in many social concerns. Investigation display, tired driving is one of the most important hidden danger of traffic safety, and driver, when fatigue, to the perception ability of surrounding environment, travels judgement and the manipulation ability of vehicle significantly reduced, being easy to traffic accident. Along with strengthening and scientific and technical progress of people's awareness of safety, driver fatigue drives the main developing direction that discrimination technology has become technical field of vehicle safety, researching and developing high performance fatigue and drive differentiation and early warning technology, to improving, China's traffic safety status is significant.
The detection of driver fatigue state has the method for more research at present, can be roughly divided into the detection based on driver's physiological signal, the detection based on officer's physiological response feature, the detection three major types based on driver behavior behavior by the classification of detection.
One, tired driving is differentiated based on physiological signal (EEG signals, electrocardiosignal etc.)
Accuracy fatigue judged based on physiological signal is higher, but the metering system of contact, bring a lot of inconvenience and limitation to the practical application of driver fatigue detection, also it is difficult to be received by officer.
Two, drive based on driver's physiological response feature decision fatigue
Method of discrimination based on driver's physiological response feature refers to that the eyes characteristic utilizing driver, mouth motion feature etc. infer the tired state of driver, these information are considered as reflecting tired important feature, but owing to custom and the feature of different officers exists certain difference, detection algorithm difficulty is higher, judges that the robustness of driver status is not high by single facial expression feature.
Three, tired driving is differentiated based on driver behavior behavior
Driver behavior behavior is as also closely related with tired state in bearing circle operation, and difficulty is less on Data acquisition and issuance, become one of important fatigue detection method, but it is at present that the screening of bearing circle operating parameters is fuzzyyer, also effective algorithm of fatigue analysis is not carried out for this type of parameter, therefore, differentiate that the tired method driven is still without remarkable effect based on driver behavior behavior.
Summary of the invention
In order to solve prior art Problems existing, the present invention seeks to: a kind of bearing circle operating characteristics extracting method driving detection towards fatigue is provided, mainly for this detection mode at present at choice of parameters, the limitation that parameter is analyzed with tired judgement aspect exists, set up the data analysis platform based on MATLAB, and taking the classification performance of algorithm of support vector machine as interpretational criteria, to selection algorithm as search strategy before floating taking sequence, set up the approximate optimal selection algorithm of tired discriminant criterion, the index system of the Index Establishment driver fatigue state-detection of screening and tired correlation maximum. on this basis, for the tired key feature identified of the impact such as individual difference and vehicle thread-changing, by the self-learning method of individual difference, set up the driver fatigue state-detection model considering individual difference, distinguish initiatively thread-changing and deflect away from the performance characteristic difference in stage with tired deviation, set up fatigue detecting model when vehicle deflects away from track, can greatly improve the generalization ability that this recognition methods is applicable to different driver and multiple operational states, promote the recognition accuracy of fatigue detecting model.
The technical scheme of the present invention is:
A kind of bearing circle operating characteristics extracting method driving detection towards fatigue, it is characterised in that, comprise the following steps:
S01: tired performance characteristic analysis and tired discriminant criterion extract: driver fatigue sample variable carries out statistical study and contrast; According to analytical results, the N number of tired discriminant criterion of preliminary extraction, checks the significance of difference of discriminant criterion tired under different fatigue level, selects N1 significant indexes and build fatigue discriminant criterion in the N number of tired discriminant criterion extracted;
S02: tired discriminant criterion optimization: taking the classification performance of algorithm of support vector machine as interpretational criteria, to selection algorithm as search strategy before floating taking sequence, set up the approximate optimal selection algorithm of tired discriminant criterion, from N1 of primary election tired discriminant criterion, screen the index system of N2 Index Establishment driver fatigue state-detection;
S03: the foundation of driver fatigue state-detection model: to screen the driver fatigue state-detection index system obtained as input, set up driver fatigue state-detection model based on algorithm of support vector machine;
S04: the tired key factor of impact is extracted and algorithm optimization: set up the driver fatigue state-detection model considering individual difference based on SVM algorithm; Vehicle is deflected away from track event and is divided into initiatively thread-changing and tired deviation two quasi-mode caused, deflecting away from the performance characteristic difference in stage by comparing initiatively thread-changing and the tired deviation caused, setting up fatigue detecting model when vehicle deflects away from track.
Preferably, described step S01 sets up data analysis platform based on MATLAB, turn to wave characteristic analysis and the frequency distribution of operation and vehicle-state variable under driver's different fatigue state is compared.
Preferably, described step S01 utilizes the significance of difference of the tired discriminant criterion of one-factor analysis of variance method inspection, the index with significant difference is carried out multiple comparisons.
Preferably, described step S04 comprises: utilize driver to start one section of clear-headed data after driving as with reference to data, the performance characteristic of individuality is carried out from study, the average of the tired discriminant criterion extracted in reference data is as reference index, then individual character index is obtained with the ratio of tired discriminant criterion and reference index, utilize individual character index to build the feature space of driver fatigue pattern classification, set up the driver fatigue state-detection model considering individual difference based on SVM algorithm.
The invention also discloses a kind of bearing circle operating characteristics extraction system driving detection towards fatigue, it is characterised in that, comprising:
One tired performance characteristic analysis and tired discriminant criterion abstraction module, carry out statistical study and contrast to driver fatigue sample variable; According to analytical results, the N number of tired discriminant criterion of preliminary extraction, checks the significance of difference of discriminant criterion tired under different fatigue level, selects N1 significant indexes and build fatigue discriminant criterion in the N number of tired discriminant criterion extracted;
One tired discriminant criterion optimizes module, taking the classification performance of algorithm of support vector machine as interpretational criteria, to selection algorithm as search strategy before floating taking sequence, set up the approximate optimal selection algorithm of tired discriminant criterion, from N1 of primary election tired discriminant criterion, screen the index system of N2 Index Establishment driver fatigue state-detection;
Module set up by one tired state-detection model, to screen the driver fatigue state-detection index system obtained as input, sets up driver fatigue state-detection model based on algorithm of support vector machine;
One tired key factor is extracted and is optimized module with algorithm, sets up the driver fatigue state-detection model considering individual difference based on SVM algorithm; Vehicle is deflected away from track event and is divided into initiatively thread-changing and tired deviation two quasi-mode caused, deflecting away from the performance characteristic difference in stage by comparing initiatively thread-changing and the tired deviation caused, setting up fatigue detecting model when vehicle deflects away from track.
Preferably, described tired performance characteristic analysis and tired discriminant criterion abstraction module set up data analysis platform based on MATLAB, are compared by turn to wave characteristic analysis and the frequency distribution of operation and vehicle-state variable under driver's different fatigue state.
Preferably, described tired performance characteristic analysis and tired discriminant criterion abstraction module utilize the significance of difference of the tired discriminant criterion of one-factor analysis of variance method inspection, and the index with significant difference is carried out multiple comparisons.
Preferably, described tired key factor is extracted and is utilized with algorithm optimization module driver to start one section of clear-headed data after driving as with reference to data, the performance characteristic of individuality is carried out from study, the average of the tired discriminant criterion extracted in reference data is as reference index, then individual character index is obtained with the ratio of tired discriminant criterion and reference index, utilize individual character index to build the feature space of driver fatigue pattern classification, set up the driver fatigue state-detection model considering individual difference based on SVM algorithm.
Compared with prior art, it is an advantage of the invention that:
1. a kind of bearing circle operating characteristics extracting method detected of driving towards fatigue that the present invention proposes is by turning to the important parameter closely related with fatigue in operation and vehicle-state variable to carry out gather and analysis, achieve the non-contact detection to driver fatigue, and by the optimization to tired discriminant criterion, the foundation of individual difference self-learning algorithm and thread-changing operation fatigue model of cognition, improve accuracy rate and the generalization ability of tired identification further, efficiently solve based on the contact that the detection modes such as officer's physiological signal or physiological characteristic exist, the problems such as accuracy of detection is low.
2. the tired driving differentiation system in the present invention is applicable to all drivers, it is possible to is arranged on home-use car, is particularly useful for the professional driver of long-distance passenger traffic, long-distance shipping and carriage of special cargo industry. The popularization and application of this system is to the safety ensureing driver, occupant and vehicle-mounted cargo, and the incidence of much slower China traffic accident, particularly serious accident, has major and immediate significance, meanwhile will produce huge Social benefit and economic benefit.
Accompanying drawing explanation
Below in conjunction with drawings and Examples, the invention will be further described:
Fig. 1 is the schema that the present invention drives the bearing circle operating characteristics extracting method of detection towards fatigue;
Fig. 2 is the structure block diagram that the present invention drives the bearing circle operating characteristics extraction system of detection towards fatigue.
Embodiment
For making the object, technical solutions and advantages of the present invention clearly understand, below in conjunction with embodiment and with reference to accompanying drawing, the present invention is described in more detail. It is to be understood that these describe just exemplary, and do not really want to limit the scope of the invention. In addition, in the following description, the description to known features and technology is eliminated, to avoid the concept unnecessarily obscuring the present invention.
Embodiment:
As shown in Figure 1, 2, a kind of bearing circle operating characteristics extraction system driving detection towards fatigue, mainly comprise tired performance characteristic analysis and tired discriminant criterion abstraction module, tired discriminant criterion optimizes module, module set up by tired state-detection model, and tired key factor is extracted and optimized module four key modules with algorithm. The working method of each module is as follows:
Tired operating characteristics analysis and tired judge index extract: set up data analysis platform based on MATLAB, and turn to operation and the vehicle-state variable under driver's different fatigue state is carried out statistical study and contrast. According to analytical results, the fatigue characteristic in operation and vehicle-state variable time serial message is turned to carry out deep excavation to being hidden in, tentatively extract N number of tired discriminant criterion, and utilize one-factor analysis of variance method, the significance of difference of index under different fatigue level is checked, then the index with significant difference is carried out multiple comparisons, in the N number of index extracted, finally select N1 significant indexes build tired discriminant criterion as the basis setting up driver fatigue state-detection model.
Tired discriminant criterion optimization: taking the classification performance of algorithm of support vector machine as interpretational criteria, to selection algorithm as search strategy before floating taking sequence, setting up the approximate optimal selection algorithm of tired discriminant criterion, screen the index system of N2 Index Establishment driver fatigue state-detection from N1 of primary election tired discriminant criterion, result is as shown in table 1, SWA in table, SWAR, Yaw, LP be finger direction dish corner respectively, steering wheel angle speed, Vehicular yaw angle and vehicle horizontal position.
Table 1
The foundation of driver fatigue state-detection model: taking N2 index system as input, set up driver fatigue state-detection model based on algorithm of support vector machine. As shown in formula (1):
Wherein, x is unknown sample, (xi, yi) it is f1��f2��f3Support vector, l, m, n are f respectively1��f2��f3The number of support vector, ��i����i����iIt is the coefficient of corresponding support vector, b1��b2��b3It is f respectively1��f2��f3Constant term, K (xi, x) it is Radial basis kernel function. f1��f2��f3It is three two classification devices, wherein, f1Being clear-headed-very tired sorter, the sample of unknown Fatigued level is divided into two classes clear-headed, very tired by this sorter; f2Being clear-headed-tired sorter, this sorter is to f1Being determined as clear-headed sample to detect further, to the Fatigued level of this sample be clear-headed or fatigue makes final differentiation; f3Being fatigue-very tired sorter, this sorter is to f1Being determined as very tired sample and carry out identification, the Fatigued level exporting this sample is tired or very tired final differentiation result. Utilize 438 in sample storehouse sample (clear-headed 169, tired 158, very tired 111), 5 heavy cross validation methods are adopted to be tested by driver fatigue state-detection model, test result shows, driver fatigue level is divided into recognition accuracy clear-headed, tired, very tired three grades to be 86.1% by this model. Test result is as shown in table 2.
Table 2
The tired key factor of impact is extracted and algorithm optimization: for driver to the turning of the individual difference of vehicle operating and vehicle, to turning to, operation and vehicle state variable amount have an impact in thread-changings etc., reduce the problem of fatigue detecting tolerance range, the present invention adopts individual difference self-learning method, driver is utilized to start one section of clear-headed data after driving as with reference to data, the performance characteristic of individuality is carried out from study, the average of the tired discriminant criterion extracted in reference data is as reference index, then individual character index is obtained with the ratio of tired discriminant criterion and reference index, individual character index is utilized to build the feature space of driver fatigue pattern classification, the driver fatigue state-detection model considering individual difference is set up based on SVM algorithm, improve model and it is applicable to the different generalization ability of driver and the recognition accuracy of fatigue detecting model. simultaneously, for thread-changing on the impact of driver fatigue state-detection, vehicle is deflected away from track event and is divided into initiatively thread-changing and tired deviation two quasi-mode caused, vehicle deflects away from current track be divided into deflect away from and return just two stages to returning the process just arriving target track, the performance characteristic difference in stage is being deflected away from by comparing initiatively thread-changing and tired deviation, setting up fatigue detecting model when vehicle deflects away from track, result is as shown in table 3.
Table 3
Utilize this model the tired state of driver to be differentiated when vehicle deflects away from track, improve tired recognition accuracy further. Result is as shown in table 4, and the recognition accuracy of active thread-changing and tired deviation is 97.4% by this model, it is possible to when vehicle deflects away from track, the tired state of driver is carried out identification accurately and effectively.
Table 4
Should be understood that, the above-mentioned embodiment of the present invention is only for exemplary illustration or the principle explaining the present invention, and is not construed as limiting the invention. Therefore, any amendment of making when without departing from the spirit and scope of the present invention, equivalent replacement, improvement etc., all should be included within protection scope of the present invention. In addition, claims of the present invention are intended to contain in the equivalents falling into scope and border or this kind of scope and border whole change and modification.
Claims (8)
1. drive the bearing circle operating characteristics extracting method of detection towards fatigue for one kind, it is characterised in that, comprise the following steps:
S01: tired performance characteristic analysis and tired discriminant criterion extract: driver fatigue sample variable carries out statistical study and contrast; According to analytical results, the N number of tired discriminant criterion of preliminary extraction, checks the significance of difference of discriminant criterion tired under different fatigue level, selects N1 significant indexes and build fatigue discriminant criterion in the N number of tired discriminant criterion extracted;
S02: tired discriminant criterion optimization: taking the classification performance of algorithm of support vector machine as interpretational criteria, to selection algorithm as search strategy before floating taking sequence, set up the approximate optimal selection algorithm of tired discriminant criterion, from N1 of primary election tired discriminant criterion, screen the index system of N2 Index Establishment driver fatigue state-detection;
S03: the foundation of driver fatigue state-detection model: to screen the driver fatigue state-detection index system obtained as input, set up driver fatigue state-detection model based on algorithm of support vector machine;
S04: the tired key factor of impact is extracted and algorithm optimization: set up the driver fatigue state-detection model considering individual difference based on SVM algorithm; Vehicle is deflected away from track event and is divided into initiatively thread-changing and tired deviation two quasi-mode caused, deflecting away from the performance characteristic difference in stage by comparing initiatively thread-changing and the tired deviation caused, setting up fatigue detecting model when vehicle deflects away from track.
2. the bearing circle operating characteristics extracting method driving detection towards fatigue according to claim 1, it is characterized in that, described step S01 sets up data analysis platform based on MATLAB, turn to wave characteristic analysis and the frequency distribution of operation and vehicle-state variable under driver's different fatigue state is compared.
3. the bearing circle operating characteristics extracting method driving detection towards fatigue according to claim 1, it is characterized in that, described step S01 utilizes the significance of difference of the tired discriminant criterion of one-factor analysis of variance method inspection, the index with significant difference is carried out multiple comparisons.
4. the bearing circle operating characteristics extracting method driving detection towards fatigue according to claim 1, it is characterized in that, described step S04 comprises: utilize driver to start one section of clear-headed data after driving as with reference to data, the performance characteristic of individuality is carried out from study, the average of the tired discriminant criterion extracted in reference data is as reference index, then individual character index is obtained with the ratio of tired discriminant criterion and reference index, individual character index is utilized to build the feature space of driver fatigue pattern classification, the driver fatigue state-detection model considering individual difference is set up based on SVM algorithm.
5. drive the bearing circle operating characteristics extraction system of detection towards fatigue for one kind, it is characterised in that, comprising:
One tired performance characteristic analysis and tired discriminant criterion abstraction module, carry out statistical study and contrast to driver fatigue sample variable; According to analytical results, the N number of tired discriminant criterion of preliminary extraction, checks the significance of difference of discriminant criterion tired under different fatigue level, selects N1 significant indexes and build fatigue discriminant criterion in the N number of tired discriminant criterion extracted;
One tired discriminant criterion optimizes module, taking the classification performance of algorithm of support vector machine as interpretational criteria, to selection algorithm as search strategy before floating taking sequence, set up the approximate optimal selection algorithm of tired discriminant criterion, from N1 of primary election tired discriminant criterion, screen the index system of N2 Index Establishment driver fatigue state-detection;
Module set up by one tired state-detection model, to screen the driver fatigue state-detection index system obtained as input, sets up driver fatigue state-detection model based on algorithm of support vector machine;
One tired key factor is extracted and is optimized module with algorithm, sets up the driver fatigue state-detection model considering individual difference based on SVM algorithm; Vehicle is deflected away from track event and is divided into initiatively thread-changing and tired deviation two quasi-mode caused, deflecting away from the performance characteristic difference in stage by comparing initiatively thread-changing and the tired deviation caused, setting up fatigue detecting model when vehicle deflects away from track.
6. the bearing circle operating characteristics extraction system driving detection towards fatigue according to claim 5, it is characterized in that, described tired performance characteristic analysis and tired discriminant criterion abstraction module set up data analysis platform based on MATLAB, are compared by turn to wave characteristic analysis and the frequency distribution of operation and vehicle-state variable under driver's different fatigue state.
7. the bearing circle operating characteristics extraction system driving detection towards fatigue according to claim 5, it is characterized in that, described tired performance characteristic analysis and tired discriminant criterion abstraction module utilize the significance of difference of the tired discriminant criterion of one-factor analysis of variance method inspection, and the index with significant difference is carried out multiple comparisons.
8. the bearing circle operating characteristics extraction system driving detection towards fatigue according to claim 5, it is characterized in that, described tired key factor is extracted and is utilized with algorithm optimization module driver to start one section of clear-headed data after driving as with reference to data, the performance characteristic of individuality is carried out from study, the average of the tired discriminant criterion extracted in reference data is as reference index, then individual character index is obtained with the ratio of tired discriminant criterion and reference index, individual character index is utilized to build the feature space of driver fatigue pattern classification, the driver fatigue state-detection model considering individual difference is set up based on SVM algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610182241.1A CN105631485A (en) | 2016-03-28 | 2016-03-28 | Fatigue driving detection-oriented steering wheel operation feature extraction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610182241.1A CN105631485A (en) | 2016-03-28 | 2016-03-28 | Fatigue driving detection-oriented steering wheel operation feature extraction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105631485A true CN105631485A (en) | 2016-06-01 |
Family
ID=56046397
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610182241.1A Pending CN105631485A (en) | 2016-03-28 | 2016-03-28 | Fatigue driving detection-oriented steering wheel operation feature extraction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105631485A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105976567A (en) * | 2016-06-06 | 2016-09-28 | 清华大学 | Driver fatigue detection method based on vehicle pedal and vehicle following behavior |
| CN106384129A (en) * | 2016-09-13 | 2017-02-08 | 西安科技大学 | Driver driving state recognition method based on closed loop driving model |
| CN106408878A (en) * | 2016-12-16 | 2017-02-15 | 苏州清研微视电子科技有限公司 | Vehicle anticollision pre-warning system considering driver fatigue state and response capability |
| CN106448059A (en) * | 2016-06-06 | 2017-02-22 | 清华大学 | Wrist strap instrument based driver fatigue detection method |
| CN106874900A (en) * | 2017-04-26 | 2017-06-20 | 桂林电子科技大学 | A kind of tired driver detection method and detection means based on steering wheel image |
| CN109649397A (en) * | 2018-12-21 | 2019-04-19 | 福建省高技汽车服务有限公司 | A kind of fatigue driving detecting system based on car networking |
| CN112580736A (en) * | 2020-12-26 | 2021-03-30 | 浙江天行健智能科技有限公司 | Drunk driving vehicle identification method based on SVM algorithm |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103489010A (en) * | 2013-09-25 | 2014-01-01 | 吉林大学 | Fatigue driving detecting method based on driving behaviors |
| US20140210625A1 (en) * | 2013-01-31 | 2014-07-31 | Lytx, Inc. | Direct observation event triggering of drowsiness |
| CN103989471A (en) * | 2014-05-08 | 2014-08-20 | 东北大学 | Fatigue driving detection system and method based on EEG identification |
| US8930269B2 (en) * | 2012-12-17 | 2015-01-06 | State Farm Mutual Automobile Insurance Company | System and method to adjust insurance rate based on real-time data about potential vehicle operator impairment |
-
2016
- 2016-03-28 CN CN201610182241.1A patent/CN105631485A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8930269B2 (en) * | 2012-12-17 | 2015-01-06 | State Farm Mutual Automobile Insurance Company | System and method to adjust insurance rate based on real-time data about potential vehicle operator impairment |
| US20140210625A1 (en) * | 2013-01-31 | 2014-07-31 | Lytx, Inc. | Direct observation event triggering of drowsiness |
| CN103489010A (en) * | 2013-09-25 | 2014-01-01 | 吉林大学 | Fatigue driving detecting method based on driving behaviors |
| CN103989471A (en) * | 2014-05-08 | 2014-08-20 | 东北大学 | Fatigue driving detection system and method based on EEG identification |
Non-Patent Citations (1)
| Title |
|---|
| 屈肖蕾: "基于转向操作和车辆状态的疲劳驾驶检测方法研究", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 * |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105976567A (en) * | 2016-06-06 | 2016-09-28 | 清华大学 | Driver fatigue detection method based on vehicle pedal and vehicle following behavior |
| CN106448059A (en) * | 2016-06-06 | 2017-02-22 | 清华大学 | Wrist strap instrument based driver fatigue detection method |
| CN105976567B (en) * | 2016-06-06 | 2019-01-29 | 清华大学 | Driver Fatigue Detection based on pedal of vehicles and follow the bus behavior |
| CN106384129A (en) * | 2016-09-13 | 2017-02-08 | 西安科技大学 | Driver driving state recognition method based on closed loop driving model |
| CN106384129B (en) * | 2016-09-13 | 2018-07-20 | 西安科技大学 | A kind of driver's driving condition discrimination method based on closed loop driving model |
| CN106408878A (en) * | 2016-12-16 | 2017-02-15 | 苏州清研微视电子科技有限公司 | Vehicle anticollision pre-warning system considering driver fatigue state and response capability |
| CN106874900A (en) * | 2017-04-26 | 2017-06-20 | 桂林电子科技大学 | A kind of tired driver detection method and detection means based on steering wheel image |
| CN109649397A (en) * | 2018-12-21 | 2019-04-19 | 福建省高技汽车服务有限公司 | A kind of fatigue driving detecting system based on car networking |
| CN112580736A (en) * | 2020-12-26 | 2021-03-30 | 浙江天行健智能科技有限公司 | Drunk driving vehicle identification method based on SVM algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105631485A (en) | Fatigue driving detection-oriented steering wheel operation feature extraction method | |
| Chen et al. | Key feature selection and risk prediction for lane-changing behaviors based on vehicles’ trajectory data | |
| CN108313054B (en) | The autonomous lane-change decision-making technique of automatic Pilot and device and automatic driving vehicle | |
| CN104802737B (en) | Mobile phone based vehicle abnormality driving behavior detection method | |
| CN103996287B (en) | A kind of vehicle compulsory based on decision-tree model changes decision-making technique | |
| CN105620480B (en) | Intelligent vehicle independence lane-change opportunity decision-making technique | |
| CN105966396A (en) | Vehicle collision avoidance control method based on driver collision avoidance behavior | |
| CN106203330A (en) | A kind of vehicle classification method based on convolutional neural networks | |
| CN104494600B (en) | A kind of Driver intention recognition method based on SVM algorithm | |
| Deng et al. | Improved driving behaviors prediction based on fuzzy logic-hidden markov model (fl-hmm) | |
| Wang et al. | Evaluation of lane departure correction systems using a regenerative stochastic driver model | |
| CN106585635A (en) | Driving behavior scoring method and device | |
| CN101950355A (en) | Method for detecting fatigue state of driver based on digital video | |
| CN112793576B (en) | Lane change decision method and system based on rule and machine learning fusion | |
| CN110516746A (en) | A kind of driver's follow the bus behavior genre classification method based on no label data | |
| CN106777776A (en) | A kind of vehicle lane-changing decision-making technique based on supporting vector machine model | |
| CN103489010A (en) | Fatigue driving detecting method based on driving behaviors | |
| CN106408032A (en) | Fatigue driving detection method based on corner of steering wheel | |
| CN115782905B (en) | Automatic driving safety degree quantification system for driving vehicle | |
| US9415778B2 (en) | Apparatus and method for determining careless driving | |
| Phumphuang et al. | Driver identification using variance of the acceleration data | |
| Mammeri et al. | Design of a semi-supervised learning strategy based on convolutional neural network for vehicle maneuver classification | |
| CN106873595A (en) | A kind of is recognition methods with garage based on Timed Automata | |
| CN105911554A (en) | Target identification method based on ultrasonic sensor array | |
| CN102043941B (en) | Dynamic real-time relative relationship identification method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160601 |
|
| RJ01 | Rejection of invention patent application after publication |