CN112233276A - Steering wheel corner statistical characteristic fusion method for fatigue state recognition - Google Patents
Steering wheel corner statistical characteristic fusion method for fatigue state recognition Download PDFInfo
- Publication number
- CN112233276A CN112233276A CN202011089356.9A CN202011089356A CN112233276A CN 112233276 A CN112233276 A CN 112233276A CN 202011089356 A CN202011089356 A CN 202011089356A CN 112233276 A CN112233276 A CN 112233276A
- Authority
- CN
- China
- Prior art keywords
- steering wheel
- statistical
- fatigue state
- sequence
- state identification
- 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
- 238000007500 overflow downdraw method Methods 0.000 title claims abstract description 11
- 239000011159 matrix material Substances 0.000 claims abstract description 28
- 230000004927 fusion Effects 0.000 claims abstract description 15
- 238000001914 filtration Methods 0.000 claims abstract description 6
- 238000000034 method Methods 0.000 claims description 19
- 238000005070 sampling Methods 0.000 claims description 11
- 206010016256 fatigue Diseases 0.000 description 38
- 238000012360 testing method Methods 0.000 description 9
- 238000001514 detection method Methods 0.000 description 4
- 239000000284 extract Substances 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000035479 physiological effects, processes and functions Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- 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
- G07C5/0808—Diagnosing performance data
-
- 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
-
- 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
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Auxiliary Drives, Propulsion Controls, And Safety Devices (AREA)
Abstract
The invention relates to the technical field of intelligent driving, and particularly discloses a steering wheel corner statistical characteristic fusion method for fatigue state identification, which comprises the steps of firstly, acquiring a steering wheel corner time sequence and a vehicle speed time sequence in real time, and filtering the steering wheel corner time sequence according to a set threshold value to obtain effective sample data; then, according to the size of a set time window, calculating the statistical characteristics of the fixed length samples; and finally, forming a statistical feature matrix by using the calculated statistical features, calculating a feature root of the statistical feature matrix, and finally extracting the feature root meeting the conditions as a fusion index vector of the statistical features of the steering wheel corner of the driver. The invention integrates the multiple statistical characteristics of the steering wheel corner, overcomes the instability brought by directly adopting one or more statistical indexes in the prior art, can effectively support the stable recognition of the fatigue state of a driver under the working condition of an actual vehicle, and shows higher engineering generalization capability to different drivers.
Description
Technical Field
The invention relates to the technical field of intelligent driving, in particular to a steering wheel corner statistical characteristic fusion method for fatigue state recognition.
Background
Fatigue driving is an important cause of traffic accidents. The steering wheel angle data can directly reflect the steering operation characteristics of a driver in real time and is important data for objectively and accurately reflecting the operation rule of the driver. Driver fatigue state detection based on steering wheel angle information has become one of the hot research contents and main technologies in the field of active safety of automobiles.
Under the working condition of an actual vehicle, due to long-time driving operation, the psychology and the physiology of a driver are in a fatigue state, so that the perception capability of the driver on the road environment, the situation judgment capability and the vehicle control capability are reduced, the tolerance error of the driver on the vehicle is increased, the control precision is reduced, and the statistical characteristic of the steering operation of the driver on a steering wheel becomes abnormal. However, due to the influence of road randomness and individual difference of drivers, the statistical index of the steering angle sequence of the vehicle steering wheel has strong instability, and the existing fatigue state identification technology based on the statistical characteristics of the steering wheel usually directly adopts one or more fixed statistical characteristics as system input, so that the fatigue state identification method based on the statistical characteristics of the steering wheel corner has poor generalization capability and poor system stability.
Disclosure of Invention
The invention provides a method for fusing statistical characteristics of steering wheel corners for identifying fatigue states, which solves the technical problems that: the existing fatigue state identification method based on the steering wheel corner statistical characteristics directly adopts one or more fixed statistical characteristics as system input, and has poor generalization capability and poor system stability.
In order to solve the technical problems, the invention provides a steering wheel corner statistical characteristic fusion method for fatigue state identification, which comprises the following steps:
s1, acquiring a steering wheel corner time sequence and a vehicle speed time sequence in real time according to a set sampling frequency;
s2, filtering the steering wheel corner time sequence according to a set steering angle absolute value threshold and a set speed threshold to obtain a steering wheel corner sequence sample with the speed higher than the speed threshold and the steering angle lower than the steering angle absolute value threshold;
s3, calculating the statistical characteristics of the steering wheel corner sequence samples with fixed lengths according to the set time window size;
s4, forming a statistical characteristic matrix by the statistical characteristics;
and S5, calculating a feature root of the statistical feature matrix, and extracting the feature root to be used as a fusion index vector of the statistical features of the steering wheel turning angle of the driver.
Further, in step S3, the fixed length of the steering wheel angle sequence is T, the set time window size is mT, m is 10 or more, and T is 100 or more.
Further, in the step S3, the statistical feature includes a variance T1Effective value T2Extremely poor T3Wave form coefficient T4Kurtosis T5Deviation T6Coefficient of variation T7Large amplitude percentage T8Small amplitude percentage T9Large mean value T10；
Wherein:
T3＝Xmax-Xmin，Xmax、Xminrepresents the maximum and minimum values of the sequence X (i), respectively;
further, c1Is set within a range of 2.5 + -0.25, c2Is set within a range of 0.5 + -0.25.
Further, in step S4, if the statistical feature matrix is represented as P, then:
wherein L ist(t＝1，2…m-1，m)＝(X1，X2…X199，X200)tAnd t represents the sequence number of the slice segments of the steering wheel angle sequence in a time window.
Further, in step S5, the calculating the feature root of the statistical feature matrix specifically includes the steps of:
s51. according to
Normalizing the steering wheel angle sequence in each time window, pstRepresents the elements of the sth column of the s-th row in the statistical characteristic matrix P,
s52, calculating a correlation coefficient matrix R of the statistical characteristic matrix P:
wherein,
q＝1，2，…，9，10；x，y＝1，2，…，m-1，m；
s53, solving a characteristic root lambda (lambda) of a correlation coefficient matrix R by adopting a Jacobian method1，λ2，…，λm-1，λm)。
Further, in step S5, extracting a feature root as a fusion index vector of the statistical features of the steering wheel angle of the driver specifically includes:
assuming that the fusion index vector is F, the vector element F of the fusion index vector is obtained by the following setting conditions:
Preferably, the set range of the sampling frequency is [20,200] Hz, the set range of the steering angle absolute value threshold value is 20 +/-2 degrees, and the set range of the speed threshold value is 70 +/-5 km/h.
Preferably, 10. ltoreq. m.ltoreq.50, 100. ltoreq. T.ltoreq.500.
Preferably, the sampling frequency is 100Hz, the steering angle absolute value threshold is 20 °, the speed threshold is 70km/h, m is 30, T is 200, ρ isset＝0.85。
The invention provides a method for fusing statistical characteristics of a steering wheel corner for identifying a fatigue state, which comprises the steps of firstly collecting a steering wheel corner time sequence and a vehicle speed time sequence in real time (step S1), and carrying out filtering processing on the steering wheel corner time sequence according to a set threshold value to obtain effective sample data (step S2), so that the method is mainly used for detecting fatigue of a driver under the conditions of high speed of a vehicle and small-range rotation of the steering wheel, and is beneficial to improving the accuracy of identifying the fatigue state;
then, according to the set time window size, calculating the statistical characteristics of the fixed length samples (step S3), so that each sample data segment has the same number of sampling points, thereby facilitating the extraction of the sequence statistical characteristics and the data analysis;
and finally, forming a statistical feature matrix by using the calculated statistical features (step S4), calculating a feature root of the statistical feature matrix, and finally extracting the feature root meeting the conditions as a fusion index vector of the statistical features of the steering wheel angle of the driver (step S5).
On the whole, the invention does not directly take the statistical characteristics of the steering wheel corner sequence of the driver as the input of the fatigue state identification system, but fuses the multiple statistical characteristics of the steering wheel corners, extracts the fatigue identification indexes fused with the multiple statistical characteristics and improves the stable contribution rate of the statistical performance indexes to the fatigue state identification of the driver. The method can effectively extract the fatigue characteristic statistical index of the steering wheel corner under the actual working condition, can effectively support the stable recognition of the fatigue state of a driver under the actual working condition, is convenient for engineering realization, and shows higher engineering generalization capability to different drivers.
Drawings
FIG. 1 is a flowchart illustrating steps of a method for fusing statistical characteristics of steering wheel angles for fatigue state identification according to an embodiment of the present invention;
fig. 2 is an application case diagram of a steering wheel angle statistical feature fusion method for fatigue state identification according to an embodiment of the present invention.
Detailed Description
The embodiments of the present invention will be described in detail below with reference to the accompanying drawings, which are given solely for the purpose of illustration and are not to be construed as limitations of the invention, including the drawings which are incorporated herein by reference and for illustration only and are not to be construed as limitations of the invention, since many variations thereof are possible without departing from the spirit and scope of the invention.
In order to overcome the instability and poor generalization capability brought by directly adopting one or more statistical indexes in the prior art, the embodiment of the invention provides a steering wheel corner statistical characteristic fusion method for fatigue state identification, which is shown in fig. 1 and comprises the following steps:
s1, acquiring a steering wheel corner time sequence and a vehicle speed time sequence in real time according to a set sampling frequency;
s2, filtering the steering wheel corner time sequence according to a set steering angle absolute value threshold and a set speed threshold to obtain a steering wheel corner sequence sample with the speed higher than the speed threshold and the steering angle lower than the steering angle absolute value threshold;
s3, calculating the statistical characteristics of steering wheel corner sequence samples with fixed lengths according to the set time window size;
s4, forming a statistical characteristic matrix by the statistical characteristics;
and S5, calculating a feature root of the statistical feature matrix, and extracting the feature root to be used as a fusion index vector of the steering wheel corner statistical feature of the driver.
Further, in step S1, the setting range of the sampling frequency is [20,200] Hz, and the present embodiment is preferably 100Hz, that is, there are 100 sampling points per second.
Further, in step S2, the steering angle absolute value threshold is set to be 20 ± 2 °, and the present embodiment is preferably 20 °; the speed threshold is set within a range of 70 + -5 km/h, and the preferred embodiment is 70 km/h. The method comprises the following steps of filtering a steering wheel turning time sequence according to a set threshold value to obtain effective sample data, so that the effective sample data are focused on the fatigue detection of a driver under the conditions of high speed of a vehicle and small-range rotation of a steering wheel, and the accuracy of fatigue state identification is improved.
Further, in step S3, the fixed length of the steering wheel angle sequence is T, the set time window size is mT, generally 10 ≦ m ≦ 50, 100 ≦ T ≦ 500, and preferably m ≦ 30 and T ≦ 200 in this embodiment, that is, 30 × 200 ≦ 6000 sampling points in each sequence sample, which facilitates the sequence statistical feature extraction and data analysis.
In step S3 of the present embodiment, the statistical feature includes a variance T1Effective value T2Extremely poor T3Wave form coefficient T4Kurtosis T5Deviation T6Coefficient of variation T7Large amplitude percentage T8Small amplitude percentage T9Large mean value T10；
Wherein:
T3＝Xmax-Xmin，Xmax、Xminrepresents the maximum and minimum values of the sequence X (i), respectively;
further, in step S4, the statistical feature matrix is represented as P, then:
wherein L ist(t＝1，2…m-1，m)＝(X1，X2…X199，X200)tAnd t represents the sequence number of the slice segments of the steering wheel angle sequence in a time window.
Further, in step S5, the calculating the feature root of the statistical feature matrix specifically includes the steps of:
s51. according to
Normalizing the steering wheel angle sequence in each time window, pstRepresents the elements of the sth column of the s-th row in the statistical characteristic matrix P,
s52, calculating a correlation coefficient matrix R of the statistical characteristic matrix P:
wherein,
q＝1，2，…，9，10；x，y＝1，2，…，m-1，m；
s53, solving a characteristic root lambda (lambda) of a correlation coefficient matrix R by adopting a Jacobian method1，λ2，…，λm-1，λm)。
Further, in step S5, extracting a feature root as a fusion index vector of the statistical features of the steering wheel angle of the driver specifically includes:
assuming that the fusion index vector is F, the vector element F of the fusion index vector is obtained by the following setting conditions:
According to the embodiment of the invention, the statistical characteristics of the steering wheel corner sequence of the driver are not directly used as the input of the fatigue state identification system, but the multiple statistical characteristics of the steering wheel corners are fused, the fatigue identification index fusing the multiple statistical characteristics is extracted, and the stable contribution rate of the statistical performance index to the fatigue state identification of the driver is improved. The method can effectively extract the fatigue characteristic statistical index of the steering wheel corner under the actual working condition, can effectively support the stable recognition of the fatigue state of a driver under the actual working condition, is convenient for engineering realization, and shows higher engineering generalization capability to different drivers.
As a specific implementation, as shown in fig. 2, the present invention is generally applied to a feature extraction process of a driver fatigue recognition system. In the case, the statistical characteristics of the steering wheel turning angle of the driver are sent to a prediction model based on a Support Vector Machine (SVM classifier in the figure) for training and fatigue state prediction. In the test of the secondary fatigue state identification of the driver, the fatigue correct detection rate of 384 test samples is 86.32%, and the variance of ten cross tests is 0.0078; in the test of three-level fatigue identification of a driver, the fatigue correct detection rate of 296 test samples is 84.13%, and the variance of ten cross tests is 0.0082; further, in order to compare the fatigue state identification effect directly adopting statistical characteristics, according to the application case, the same classifier is adopted, the 10 statistical indexes extracted in the step S3 of the invention are directly used as the input of the classifier, on the same test sample, the average accuracy of the secondary fatigue identification of the driver is 79.82%, and the variance of the ten-time cross tests is 0.0098; the average accuracy of the driver's three-level fatigue recognition was 75.09%, and the variance of the ten-time random cross-over test was 0.0106. The result shows that the statistical characteristics fused by the method have higher contribution degree to the fatigue state recognition rate and show better stability in a classification recognition system.
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and all such changes, modifications, substitutions, combinations, and simplifications are intended to be included in the scope of the present invention.
Claims (10)
1. A method for fusing statistical characteristics of steering wheel angles for fatigue state identification is characterized by comprising the following steps:
s1, acquiring a steering wheel corner time sequence and a vehicle speed time sequence in real time according to a set sampling frequency;
s2, filtering the steering wheel corner time sequence according to a set steering angle absolute value threshold and a set speed threshold to obtain a steering wheel corner sequence sample with the speed higher than the speed threshold and the steering angle lower than the steering angle absolute value threshold;
s3, calculating the statistical characteristics of the steering wheel corner sequence samples with fixed lengths according to the set time window size;
s4, forming a statistical characteristic matrix by the statistical characteristics;
and S5, calculating a feature root of the statistical feature matrix, and extracting the feature root to be used as a fusion index vector of the statistical features of the steering wheel turning angle of the driver.
2. A steering wheel angle statistical feature fusion method for fatigue state identification, according to claim 1, wherein: in step S3, the fixed length of the steering wheel angle sequence is T, the set time window size is mT, m is greater than or equal to 10, and T is greater than or equal to 100.
3. A steering wheel angle statistical feature fusion method for fatigue state identification as claimed in claim 2, wherein: in the step S3, the statistical feature includes a variance T1Effective value T2Extremely poor T3Wave form coefficient T4Kurtosis T5Deviation T6Coefficient of variation T7Large amplitude percentage T8Small amplitude percentage T9Large mean value T10；
Wherein:
T3＝Xmax-Xmin，Xmax、Xminrepresents the maximum and minimum values of the sequence X (i), respectively;
4. a steering wheel angle statistical feature fusion method for fatigue state identification as claimed in claim 3, wherein: c. C1Is set within a range of 2.5 + -0.25, c2Is set within a range of 0.5 + -0.25.
5. A method for fusion of statistical characteristics of steering wheel angles for fatigue state identification according to claim 3, wherein in step S4, if the statistical characteristic matrix is represented as P, then:
wherein L ist(t＝1，2…m-1，m)＝(X1，X2…X199，X200)tAnd t represents the sequence number of the slice segments of the steering wheel angle sequence in a time window.
6. The method for fusing statistical characteristics of steering wheel angles for fatigue state identification according to claim 5, wherein in step S5, calculating the characteristic root of the statistical characteristic matrix specifically comprises the steps of:
s51. according to
Normalizing the steering wheel angle sequence in each time window, pstRepresents the elements of the sth column of the s-th row in the statistical characteristic matrix P,
s52, calculating a correlation coefficient matrix R of the statistical characteristic matrix P:
wherein,
s53, solving a characteristic root lambda (lambda) of a correlation coefficient matrix R by adopting a Jacobian method1，λ2，…，λm-1，λm)。
7. The method for fusing statistical characteristics of steering wheel angles for fatigue state identification according to claim 6, wherein in step S5, the feature root is extracted as a fusion index vector of the statistical characteristics of the steering wheel angles of the driver, specifically:
assuming that the fusion index vector is F, the vector element F of the fusion index vector is obtained by the following setting conditions:
8. The method for fusing the statistical characteristics of the steering wheel angles for fatigue state identification according to any one of claims 2 to 7, wherein: the set range of the sampling frequency is [20,200] Hz, the set range of the absolute value threshold of the steering angle is 20 +/-2 degrees, and the set range of the speed threshold is 70 +/-5 km/h.
9. A steering wheel angle statistical feature fusion method for fatigue state identification, according to claim 8, wherein: m is more than or equal to 10 and less than or equal to 50, and T is more than or equal to 100 and less than or equal to 500.
10. The method for fusing the statistical characteristics of the steering wheel angles for fatigue state identification according to any one of claims 2 to 7, wherein: the sampling frequency is 100Hz, the steering angle absolute value threshold is 20 °, the speed threshold is 70km/h, m is 30, T is 200, ρset＝0.85。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011089356.9A CN112233276B (en) | 2020-10-13 | 2020-10-13 | Steering wheel corner statistical characteristic fusion method for fatigue state recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011089356.9A CN112233276B (en) | 2020-10-13 | 2020-10-13 | Steering wheel corner statistical characteristic fusion method for fatigue state recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112233276A true CN112233276A (en) | 2021-01-15 |
| CN112233276B CN112233276B (en) | 2022-04-29 |
Family
ID=74112413
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011089356.9A Active CN112233276B (en) | 2020-10-13 | 2020-10-13 | Steering wheel corner statistical characteristic fusion method for fatigue state recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112233276B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114493046A (en) * | 2022-03-17 | 2022-05-13 | 安波福电子(苏州)有限公司 | Fatigue driving prediction method |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101872171A (en) * | 2009-04-24 | 2010-10-27 | 中国农业大学 | Driver fatigue state recognition method and system based on information fusion |
| CN103578227A (en) * | 2013-09-23 | 2014-02-12 | 吉林大学 | Fatigue driving detection method based on GPS positioning information |
| CN104207791A (en) * | 2014-08-26 | 2014-12-17 | 江南大学 | Fatigue driving detection method |
| CN104688252A (en) * | 2015-03-16 | 2015-06-10 | 清华大学 | Method for detecting fatigue status of driver through steering wheel rotation angle information |
| CN104952210A (en) * | 2015-05-15 | 2015-09-30 | 南京邮电大学 | Fatigue driving state detecting system and method based on decision-making level data integration |
| CN105261151A (en) * | 2015-09-29 | 2016-01-20 | 中国第一汽车股份有限公司 | High-grade highway driver fatigue state detection method based on operation behavior characteristics |
| CN107316354A (en) * | 2017-07-12 | 2017-11-03 | 哈尔滨工业大学 | A kind of method for detecting fatigue driving based on steering wheel and GNSS data |
| CN109389806A (en) * | 2018-11-08 | 2019-02-26 | 山东大学 | Fatigue driving detection method for early warning, system and medium based on multi-information fusion |
| CN110781873A (en) * | 2019-12-31 | 2020-02-11 | 南斗六星系统集成有限公司 | Driver fatigue grade identification method based on bimodal feature fusion |
| CN110796207A (en) * | 2019-11-08 | 2020-02-14 | 中南大学 | Fatigue driving detection method and system |
| CN110901385A (en) * | 2019-12-31 | 2020-03-24 | 南斗六星系统集成有限公司 | Active speed limiting method based on fatigue state of driver |
-
2020
- 2020-10-13 CN CN202011089356.9A patent/CN112233276B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101872171A (en) * | 2009-04-24 | 2010-10-27 | 中国农业大学 | Driver fatigue state recognition method and system based on information fusion |
| CN103578227A (en) * | 2013-09-23 | 2014-02-12 | 吉林大学 | Fatigue driving detection method based on GPS positioning information |
| CN104207791A (en) * | 2014-08-26 | 2014-12-17 | 江南大学 | Fatigue driving detection method |
| CN104688252A (en) * | 2015-03-16 | 2015-06-10 | 清华大学 | Method for detecting fatigue status of driver through steering wheel rotation angle information |
| CN104952210A (en) * | 2015-05-15 | 2015-09-30 | 南京邮电大学 | Fatigue driving state detecting system and method based on decision-making level data integration |
| CN105261151A (en) * | 2015-09-29 | 2016-01-20 | 中国第一汽车股份有限公司 | High-grade highway driver fatigue state detection method based on operation behavior characteristics |
| CN107316354A (en) * | 2017-07-12 | 2017-11-03 | 哈尔滨工业大学 | A kind of method for detecting fatigue driving based on steering wheel and GNSS data |
| CN109389806A (en) * | 2018-11-08 | 2019-02-26 | 山东大学 | Fatigue driving detection method for early warning, system and medium based on multi-information fusion |
| CN110796207A (en) * | 2019-11-08 | 2020-02-14 | 中南大学 | Fatigue driving detection method and system |
| CN110781873A (en) * | 2019-12-31 | 2020-02-11 | 南斗六星系统集成有限公司 | Driver fatigue grade identification method based on bimodal feature fusion |
| CN110901385A (en) * | 2019-12-31 | 2020-03-24 | 南斗六星系统集成有限公司 | Active speed limiting method based on fatigue state of driver |
Non-Patent Citations (1)
| Title |
|---|
| 贾丽娟: "《基于实车方向盘操作特征的疲劳驾驶检测方法研究》", 《中国优秀博硕士学位论文全文数据库(硕士) 工程科技Ⅱ辑》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114493046A (en) * | 2022-03-17 | 2022-05-13 | 安波福电子(苏州)有限公司 | Fatigue driving prediction method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112233276B (en) | 2022-04-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111460919B (en) | Monocular vision road target detection and distance estimation method based on improved YOLOv3 | |
| CN105139070A (en) | Fatigue driving evaluation method based on artificial nerve network and evidence theory | |
| CN106408032A (en) | Fatigue driving detection method based on corner of steering wheel | |
| CN112793576B (en) | Lane change decision method and system based on rule and machine learning fusion | |
| CN110781873A (en) | Driver fatigue grade identification method based on bimodal feature fusion | |
| CN112233276B (en) | Steering wheel corner statistical characteristic fusion method for fatigue state recognition | |
| CN113753059B (en) | Method for predicting takeover capacity of driver under automatic driving system | |
| CN110991377A (en) | Monocular visual neural network-based front target identification method for automobile safety auxiliary system | |
| CN111340074B (en) | Driver braking intention identification method based on improved RBF neural network | |
| Chen et al. | Vehicle detection based on multifeature extraction and recognition adopting RBF neural network on ADAS system | |
| CN113313357A (en) | Traffic road safety evaluation method based on Gaussian process regression analysis | |
| CN115294767A (en) | Real-time detection and traffic safety early warning method and device for highway lane lines | |
| CN114446057A (en) | Accident high-incidence point identification early warning method and system based on intelligent network connection environment | |
| CN111612334A (en) | Driving behavior risk rating judgment method based on Internet of vehicles data | |
| CN104636748A (en) | License plate recognition method and device | |
| CN114241458A (en) | Driver behavior recognition method based on attitude estimation feature fusion | |
| CN112308136B (en) | Driving distraction detection method based on SVM-Adaboost | |
| CN114973212A (en) | Fatigue driving stopping method based on visual features, steering wheel operation detection and active intervention | |
| CN113642114A (en) | Modeling method for humanoid random car following driving behavior capable of making mistakes | |
| CN114564110B (en) | Driving learning ability detection method and system based on brain electrical data | |
| CN111775948B (en) | Driving behavior analysis method and device | |
| CN113859257B (en) | Surrounding vehicle driving intention identification method based on gray entropy weight and lateral ellipse threshold | |
| CN113252057A (en) | Method and system for identifying driving tendency based on high altitude navigation data | |
| Bhalerao et al. | Proposed design on driver behavioral analysis | |
| EP3654246A1 (en) | Method, vehicle, system, and storage medium for indicating anomalous vehicle scenario using encoder network and replay buffer |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |