CN102406507A - Method for monitoring fatigue degree of driver based on human body physiological signal - Google Patents
Method for monitoring fatigue degree of driver based on human body physiological signal Download PDFInfo
- Publication number
- CN102406507A CN102406507A CN201010286754XA CN201010286754A CN102406507A CN 102406507 A CN102406507 A CN 102406507A CN 201010286754X A CN201010286754X A CN 201010286754XA CN 201010286754 A CN201010286754 A CN 201010286754A CN 102406507 A CN102406507 A CN 102406507A
- Authority
- CN
- China
- Prior art keywords
- fatigue
- vector
- driver
- signal
- pulse
- 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
Images
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a method for monitoring fatigue degree of a driver based on a human body physiological signal, comprising a fatigue calibrating method and a fatigue detecting method. The calibrating method comprises the following steps of: collecting through a sensor and extracting pulse peak values and rates, heart rates and breathing rates N times within unit time to form a fatigue characteristic calibrating array; establishing the weight vector of each fatigue characteristic by using a main component analysis method; and adding weights into the calibrating array to construct a fatigue calibrating vector. The fatigue detecting method comprises the following steps of: adding the calibrated weights into a fatigue characteristic vector within unit time; calculating the Mahalanobis distance between the characteristic vector and the calibrating vector; judging the fatigue degree of the driver according to the distance dispersion degree of the Mahalanobis distance and early warning. In the invention, the fatigue characteristic of the driver is found on the basis of the traditional Chinese medicine theory by combining a modern signal processing method, and therefore, the method has remarkable societal and economic benefits and has important significance in reducing traffic accidents caused by fatigue driving.
Description
Technical field
The present invention relates to the fatigue monitoring method of a kind of driver of being used for, particularly online detection of the physiology signal when the driver drives and tired diagnostic method at driving procedure.
Background technology
In the reason of human death and morbidity, vehicle accident ranked nineth the position.Annual nearly 1,200,000 people in the whole world die wheel down, and driver's fatigue driving is to cause one of major reason of road traffic accident.The conservative estimation of American National instrument Transportation Security Administration, the annual vehicle accident that causes because of fatigue driving has 100,000 at least; Vehicle accident in the U.S. at least 18% in 2007 is caused by fatigue driving.20% of the annual road traffic death toll of Australia is caused by fatigue driving.France national police general administration accident report shows that the accident that causes because of fatigue driving accounts for 14.9% of personal injury accident, 20.6% of death by accident.In China, the vehicle accident that causes because of fatigue driving accounts for 20% of sum, 40%～80% of especially big vehicle accident, and the traffic mortality rate 83%.Fatigue driving with drive against traffic regulations, abominable road conditions, overload, braking ability and lack the passenger safety band and be called six big killers of car steering safety, directly or indirectly cause mass casualties and huge economic loss.Driving fatigue influences driver's vigilance and safe driving ability, worldwide causes widely to pay close attention to.The driver fatigue monitoring is the research content that improves vehicle active safety with the research of method for early warning.
Summary of the invention
The present invention provides a kind of fatigue of automobile driver monitoring method based on physiology signal; In order in the car steering process, to detect driver's fatigue state; Comprise tired scaling method and detection method, main through gathering driver's physiology signal and modern signal processing method, extract the driver fatigue characteristic; And by mahalanobis distance diagnostic method identification degree of fatigue, two kinds of methods are all accomplished in monitoring system.
Technical scheme provided by the invention is: a kind of fatigue of automobile driver monitoring method based on physiology signal; It is characterized in that: adopt pulse, heart rate and respiration pickup to gather driver's physiology signals such as pulse, heart rate and breathing; Pulse frequency, peak value, heart rate and respiratory frequency signal are constituted the fatigue characteristic vector; Utilize the method for principal component analysis (PCA) to confirm its each feature weight, judge its degree of fatigue through the mahalanobis distance method.This method comprises scaling method and fatigue detecting method; Scaling method is accomplished when the driver drives certain model vehicle for the first time, and same driver accomplishes any time the fatigue detecting method demarcating later.A kind of principle of the fatigue of automobile driver monitoring system based on physiology signal is as shown in Figure 1.
Wherein said scaling method may further comprise the steps:
Step 1, when the driver drives certain model vehicle for the first time, gather driver's physiology signals such as pulse, heart rate and breathing, through signal sampling, the discrete-time series of each acquired signal when obtaining the driver and driving for the first time;
Step 1.1, employing are installed on heart rate and the respiration pickup collection driver breath signal on the seat belt;
Step 1.2, employing are positioned the pulse transducer collection driver pulse signal of hand;
Step 2, pass through Fourier transformation, the pulse signal frequency content in the obtaining step 1;
Step 3, constitute with the frequency of the pulse signal in N unit interval and peak value, heart rate and respiratory frequency average and to demarcate matrix; N is 4 times; Unit interval is 60 seconds; The demarcation matrix is 4 * 4 square formation.
Step 4, to demarcating sample set, adopt the method for principal component analysis (PCA), obtain the principal component transform matrix and demarcate weight.
Step 4.1, the sample data of demarcating in the matrix is carried out centralization;
The eigenvalue and the characteristic vector of step 4.2, computer center's sample vector covariance matrix;
Step 4.3, select contribution rate biggest characteristic value character pair vector, i.e. the fatigue characteristic weight vector as the eigentransformation matrix;
Step 4.4, will demarcate in each parameter type of carrying out of sample set on average, obtain demarcating vector, and eigentransformation matrix premultiplication demarcated vector obtain fatigue criterion and demarcate vector.
Wherein said fatigue detecting method may further comprise the steps:
Step 1, after demarcation, gather the physiology signals such as driver's pulse, heart rate and breathing in the time per unit, through signal sampling, obtain the discrete-time series of each acquired signal;
Step 1.1, employing are installed on heart rate and the respiration pickup collection driver breath signal on the seat belt;
Step 1.2, employing are positioned the pulse transducer collection driver pulse signal of hand;
Step 2, pass through Fourier transformation, the pulse signal frequency content in the obtaining step 1;
Step 3, vectorial with frequency and peak value, heart rate and the respiratory frequency average formation fatigue characteristic of the pulse signal in the time per unit;
Step 4, the demarcation weight that obtains in the said step 4 of scaling method is added to the fatigue characteristic vector;
Step 4.1, the fatigue characteristic weight vector premultiplication fatigue characteristic sample set that obtains is obtained the fatigue characteristic sample;
Step 5, to fatigue characteristic vector and tired its mahalanobis distance of vector calculation of demarcating;
Step 6, differentiate the fatigue of automobile driver degree apart from dispersion degree through it;
Step 6.1, resulting distance sample is carried out cluster analysis;
If in step 6.2 testing process, distance surpasses demarcates ultimate range between the sample, promptly exports early warning.
The present invention is owing to adopt the fatigue of automobile driver monitoring method based on physiology signal, and its key technology is to have designed the human physiological signal treatment analytical method based on theory of Chinese medical science; For adapting to the needs of online detection, adopt the method for principal component analysis to extract characteristic, adopt mahalanobis distance diagnostic method and clustering method that the driver fatigue degree is discerned.
Description of drawings
Fig. 1 is that driver fatigue of the present invention is demarcated and testing process figure;
Fig. 2 is that driver fatigue monitoring method device of the present invention is arranged sketch map;
17-heart rate and respiration pickup among Fig. 2, the 18-pulse transducer.
The specific embodiment
In conjunction with accompanying drawing 1,2, specific embodiment of the present invention is explained:
Gather driver's pulse signal through pulse transducer;
Through being additional to heart rate and respiration pickup collection driver's heart rate signal and the breath signal on the seat belt.
In application process, be divided into and demarcate and two processes of fatigue detecting.
The process of demarcating mainly may further comprise the steps:
A, gather pulse, heart rate and breath signal, and pulse signal is carried out Fourier transformation;
B, through signal sampling, the discrete-time series of each acquired signal when obtaining the driver and driving for the first time;
C, constitute with the frequency of the pulse signal in N unit interval and peak value, heart rate and respiratory frequency average and to demarcate matrix;
D, to demarcating sample set, adopt the method for principal component analysis (PCA), obtain the principal component transform matrix and demarcate weight;
E, will demarcate in each parameter type of carrying out of sample set on average, obtain demarcating vector, and eigentransformation matrix premultiplication demarcated vector obtain fatigue criterion and demarcate vector.
The output result is the transformation matrix of principal component analysis and demarcates weight.Its concrete steps see also and shown in Figure 1ly are:
Get into calibration process 1; Pulse signal 2 when gathering first the driving under driver's waking state, heart rate signal 3 is inhaled signal 4; Pass through signal processing analysis; Pulse peak value and frequency, heart rate and respiratory frequency are combined into tired parameter calibration matrix 5, confirm its weight vector 6 through principal component analysis (PCA), and the directed amount 7 of fatigue criterion characteristic scalar and export fatigue detecting system to.
The fatigue detecting process mainly may further comprise the steps:
A, gather pulse, heart rate and breath signal, and pulse signal is carried out Fourier transformation;
B, through signal sampling, the discrete-time series of each acquired signal when obtaining the driver and driving for the first time;
C, constitute the fatigue characteristic matrix with the frequency of the pulse signal in N unit interval and peak value, heart rate and respiratory frequency average;
D, will detect the weight vector that obtains in the sample premultiplication calibration process, obtain the fatigue detecting sample characteristics;
E, the fatigue characteristic sample is asked its mahalanobis distance with demarcating vector, and according to its threshold value, the output judged result.
Its concrete steps are illustrated in figure 1 as:
Get into calibration process 8, the pulse signal 9 when gathering first the driving under driver's driving condition, heart rate signal 10; Breath signal 11 through signal processing analysis, is combined into tired parameter vector 12 with pulse peak value and frequency, heart rate and respiratory frequency; With detecting the weight vector that obtains in the sample premultiplication calibration process, obtain fatigue detecting sample characteristics 13, fatigue characteristic sample and demarcation vector are asked its mahalanobis distance 14; And according to its threshold value 15, output judged result to early warning 16.
Concrete principle and implementation method are following.
1, pulse, heart rate and breath signal have comprised the various physiological situations of human body, from pulse signal, can extract driver's fatigue characteristic, thereby reflect driver's fatigue conditions.Obtain the behavioral characteristics that the pulse pressure signal changes through temporal analysis and frequency domain analysis method.Temporal analysis is mainly found out the internal relation of some pulse condition characteristic and Human Physiology variation through analyzing main crest value.Frequency domain analysis mainly is through discrete fast Fourier transform, and the pulse wave curves of time domain is transformed to frequency domain, obtains the harmonic wave of different frequency characteristic, through the feature analysis to spectrum curve, extracts and the corresponding information of physiological pathology of human body.This method is simple and easy, and is directly perceived, each item index physiology univocal.
2, based on the weights of principal component analysis (PCA) and demarcate vectorial method for distilling.
Principal component analysis (Principal Component Analysis) method is calculated a new orthogonal basis for given data set, makes the projection of data on this new orthogonal basis change maximization.Among the present invention, adopt the PCA method to carry out that weights are confirmed and it is demarcated vector and confirms that its standard demarcates vector through this weights premultiplication.
Suppose s sample vector X
s=(x
1, x
2... x
n)
T, n is the dimension of sample vector.The meansigma methods
of at first obtaining all samples (N) is obtained the covariance matrix C of sample vector then:
C is a symmetrical matrix, can carry out diagonalization, and dimension is n * n.Calculate the eigenvalue of C
1, λ
2..., λ
nWith characteristic of correspondence vector u
1, u
2..., u
n, with the descending arrangement of each eigenvalue: λ
1>=λ
2>=...>=λ
nThe pairing eigenvalue of characteristic vector is big more, and its contribution when reconstruct is also big more, so can ignore the very little characteristic vector of those eigenvalues.Consider λ
1, λ
2..., λ
nIn before m biggest characteristic value, define variance contribution ratio and be:
The accumulative total variance contribution ratio of a current m principal component is enough big, and m principal component is as the sample characteristics vector after extracting before just can only getting.The computing formula of preceding m principal component is Y=U
TX
kU=(u wherein
1, u
2..., u
m), Y=(y
1, y
2..., y
m).
3, to meet mean vector be μ to the physiology signal sample of driver in driving procedure; Covariance is the normal distribution of V; Adopt mahalanobis distance to substitute original multicomponent signal sample; And, can satisfy the needs of online detection in the driving procedure according to discriminant by distance identification classification, accuracy of identification is higher.
Bidding is decided sample of signal and totally is G, and the distance of then any single sample X and overall G is that the distance table of X and average μ is shown D
2(X, G)=(X-μ) ' V
-1(X-μ)
Wherein V is that the nothing of population sample estimates that partially formula is:
Calculate fatigue detecting sample and the mahalanobis distance of demarcating sample among the present invention,, confirm threshold value W through the minimum error precision discrimination.Corresponding discriminating step is:
A. the estimated value
of computation of mean values vector
B. calculate the sample dispersion battle array of parent:
C. calculating the nothing of association's difference battle array estimates partially:
D. according to calculating each sample and the mahalanobis distance of demarcating sample, formulate following criterion according to getting threshold value W:
X ∈ G
1(fatigue state, output early warning) is when X>=W
X ∈ G
2(waking state, no abnormal) is when X＜W
The present invention is owing to adopt the fatigue of automobile driver monitoring method based on physiology signal, and its identification degree is high, and system is easy to set up, and algorithm is easy to realize.Guaranteeing that different drivers at the individual difference of driving different vehicle simultaneously, provide a kind of method of automatic judgement fatigue driving.Explanation at last: above embodiment is the unrestricted technical scheme described in the invention in order to explanation the present invention only; Therefore, although this description has been carried out detailed explanation to the present invention with reference to each above-mentioned embodiment, but still can make amendment or be equal to replacement the present invention; Its technical scheme and improvement thereof all should be encompassed in the middle of the claim scope of the present invention.
Claims (6)
1. the fatigue of automobile driver monitoring method based on physiology signal is characterized in that: adopt pulse, heart rate and respiration pickup to gather driver's physiology signals such as pulse, heart rate and breathing; Pulse frequency, peak value, heart rate and respiratory frequency signal are constituted the fatigue characteristic vector, utilize principal component analytical method (PCA) to confirm each feature weight, judge its degree of fatigue through the mahalanobis distance method; This method comprises tired scaling method and detection method; Scaling method is accomplished when the driver drives certain model vehicle for the first time, and same driver accomplishes any time the fatigue detecting method demarcating later;
Wherein said scaling method may further comprise the steps:
Step 1, when the driver drives certain model vehicle for the first time, gather driver's physiology signals such as pulse, heart rate and breathing, through signal sampling, the discrete-time series of each acquired signal when obtaining the driver and driving for the first time;
Step 2, pass through Fourier transformation, the pulse signal frequency content in the obtaining step 1;
Step 3, constitute with the frequency of the pulse signal in N unit interval and peak value, heart rate and respiratory frequency average and to demarcate matrix;
Step 4, to demarcating sample set, adopt the method for principal component analysis (PCA), obtain the principal component transform matrix and demarcate weight;
Wherein said fatigue detecting method may further comprise the steps:
Step 1, after demarcation, gather the physiology signals such as driver's pulse, heart rate and breathing in the time per unit, through signal sampling, obtain the discrete-time series of each acquired signal;
Step 2, pass through Fourier transformation, the pulse signal frequency content in the obtaining step 1;
Step 3, vectorial with frequency and peak value, heart rate and the respiratory frequency average formation fatigue characteristic of the pulse signal in the time per unit;
Step 4, the demarcation weight that obtains in the said step 4 of scaling method is added to the fatigue characteristic vector;
Step 5, to fatigue characteristic vector and tired its mahalanobis distance of vector calculation of demarcating;
Step 6, differentiate the fatigue of automobile driver degree apart from dispersion degree, and carry out early warning through it.
2. the fatigue of automobile driver monitoring method based on physiology signal according to claim 1 is characterized in that: the described step 1 of tired scaling method and detection method also comprises:
Step 1.1, employing are installed on heart rate and the respiration pickup collection driver breath signal on the seat belt;
Step 1.2, employing are positioned the pulse transducer collection driver pulse signal of hand.
3. the fatigue of automobile driver monitoring method based on physiology signal according to claim 1 is characterized in that: the described step 3 of scaling method also comprises: pulse peak value and frequency, heart rate and the respiratory frequency of extracting N unit interval constitute fatigue characteristic demarcation matrix; N is 4 times; Unit interval is 60 seconds; The demarcation matrix is 4 * 4 square formation.
4. the fatigue of automobile driver monitoring method based on physiology signal according to claim 1 is characterized in that: the described step 4 of scaling method also comprises:
Step 4.1, the sample data of demarcating in the matrix is carried out centralization;
The eigenvalue and the characteristic vector of step 4.2, computer center's sample vector covariance matrix;
Step 4.3, select contribution rate biggest characteristic value character pair vector, i.e. the fatigue characteristic weight vector as the eigentransformation matrix;
Step 4.4, will demarcate in each parameter type of carrying out of sample set on average, obtain demarcating vector, and eigentransformation matrix premultiplication demarcated vector obtain fatigue criterion and demarcate vector.
5. the fatigue of automobile driver monitoring method based on physiology signal according to claim 1 is characterized in that: the described step 4 of fatigue detecting method also comprises:
Step 4.1, the fatigue characteristic weight vector premultiplication fatigue characteristic sample set that obtains is obtained the fatigue characteristic sample.
6. the fatigue of automobile driver monitoring method based on physiology signal according to claim 1 is characterized in that: the described step 6 of fatigue detecting method also comprises:
Step 6.1, resulting distance sample is carried out cluster analysis;
If in step 6.2 testing process, distance surpasses the ultimate range of demarcating between the sample, early warning at once.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010286754 CN102406507B (en) | 2010-09-20 | 2010-09-20 | Method for monitoring fatigue degree of driver based on human body physiological signal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010286754 CN102406507B (en) | 2010-09-20 | 2010-09-20 | Method for monitoring fatigue degree of driver based on human body physiological signal |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102406507A true CN102406507A (en) | 2012-04-11 |
| CN102406507B CN102406507B (en) | 2013-10-23 |
Family
ID=45909057
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 201010286754 Expired - Fee Related CN102406507B (en) | 2010-09-20 | 2010-09-20 | Method for monitoring fatigue degree of driver based on human body physiological signal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102406507B (en) |
Cited By (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102813524A (en) * | 2012-08-10 | 2012-12-12 | 深圳市迈迪加科技发展有限公司 | Fatigue driving detection method |
| CN102881117A (en) * | 2012-06-15 | 2013-01-16 | 浙江吉利汽车研究院有限公司杭州分公司 | Watch capable of detecting fatigue of driver |
| CN103070687A (en) * | 2013-02-06 | 2013-05-01 | 南京理工大学 | Signal processing algorithm of non-contact type vital sign monitoring system |
| CN103318079A (en) * | 2013-04-09 | 2013-09-25 | 浙江吉利汽车研究院有限公司杭州分公司 | intelligentIntelligent sound box entertainment system |
| CN103932719A (en) * | 2013-01-18 | 2014-07-23 | 袁囡囡 | Fatigue driving detecting technology |
| CN103976749A (en) * | 2013-06-09 | 2014-08-13 | 湖南纽思曼导航定位科技有限公司 | Real-time fatigue prompting method and device |
| CN104112335A (en) * | 2014-07-25 | 2014-10-22 | 北京机械设备研究所 | Multi-information fusion based fatigue driving detecting method |
| CN104376685A (en) * | 2014-11-06 | 2015-02-25 | 无锡悟莘科技有限公司 | Fatigue driving preventing vehicle control method |
| CN105534531A (en) * | 2014-10-29 | 2016-05-04 | 上海华博信息服务有限公司 | Method and system for preventing fatigue driving |
| CN105741494A (en) * | 2016-03-29 | 2016-07-06 | 浙江吉利控股集团有限公司 | Driver fatigue monitoring method based on off-line data matching |
| CN106236047A (en) * | 2016-09-05 | 2016-12-21 | 合肥飞鸟信息技术有限公司 | The control method of driver fatigue monitoring system |
| CN106236046A (en) * | 2016-09-05 | 2016-12-21 | 合肥飞鸟信息技术有限公司 | Driver fatigue monitoring system |
| CN106314437A (en) * | 2016-08-30 | 2017-01-11 | 宇龙计算机通信科技(深圳)有限公司 | Fatigue driving preventing device and method and intelligent bracelet |
| CN106580282A (en) * | 2016-10-25 | 2017-04-26 | 上海斐讯数据通信技术有限公司 | Human body health monitoring device, system and method |
| CN107187467A (en) * | 2017-05-27 | 2017-09-22 | 中南大学 | Driver's monitoring method and system for operation safety and accident imputation |
| CN107187537A (en) * | 2017-05-27 | 2017-09-22 | 重庆邮电大学 | Electric bicycle assisted control system and method based on fatigue strength |
| CN108113657A (en) * | 2016-11-30 | 2018-06-05 | 天津职业技术师范大学 | A kind of Driver Fatigue Detection based on D-S evidence theory |
| CN108304745A (en) * | 2017-01-10 | 2018-07-20 | 普天信息技术有限公司 | A kind of driver's driving behavior detection method, device |
| CN108401415A (en) * | 2017-03-14 | 2018-08-14 | 深圳中兴力维技术有限公司 | monitoring method and monitoring device |
| CN108833024A (en) * | 2018-04-23 | 2018-11-16 | 温州市特种设备检测研究院 | A kind of channel wireless radio multi distribution field vehicle braking-distance figures transmission method |
| CN109147951A (en) * | 2018-09-19 | 2019-01-04 | 中国人民解放军第三0五医院 | A kind of alarming method by monitoring of mental alertness |
| CN109620269A (en) * | 2019-01-28 | 2019-04-16 | 深圳市赛梅斯凯科技有限公司 | Fatigue detection method, device, equipment and readable storage medium storing program for executing |
| CN110338821A (en) * | 2019-08-12 | 2019-10-18 | 深圳市发掘科技有限公司 | A kind of driver's driving condition recognition methods |
| CN110414554A (en) * | 2019-06-18 | 2019-11-05 | 浙江大学 | One kind being based on the improved Stacking integrated study fish identification method of multi-model |
| CN111376908A (en) * | 2018-12-11 | 2020-07-07 | 上海汽车集团股份有限公司 | Method and device for determining driving state of driver |
| CN111938599A (en) * | 2020-08-18 | 2020-11-17 | 湖南汽车工程职业学院 | Driver physical characteristic recognition-based fatigue driving monitoring system |
| CN112036352A (en) * | 2020-09-08 | 2020-12-04 | 北京嘀嘀无限科技发展有限公司 | Training method of fatigue detection model, and fatigue driving detection method and device |
| CN113071446A (en) * | 2021-02-26 | 2021-07-06 | 三三智能科技(苏州)有限公司 | Health index monitoring system based on automobile intelligent safety belt and data processing method thereof |
| CN114287940A (en) * | 2021-12-17 | 2022-04-08 | 深圳市海清视讯科技有限公司 | Fatigue detection method and device and electronic equipment |
| CN117104243A (en) * | 2023-10-24 | 2023-11-24 | 临朐弘泰汽车配件有限公司 | Fatigue driving monitoring system and steering wheel provided with same |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104146720B (en) * | 2014-08-06 | 2016-04-13 | 华侨大学 | A kind of checkout equipment of quick detection fatigue |
| TWI602143B (en) * | 2016-08-30 | 2017-10-11 | 華邦電子股份有限公司 | Fatigue detection apparatus and a fatigue detection method |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101530329A (en) * | 2009-03-06 | 2009-09-16 | 北京理工大学 | Semi-physical driving fatigue vision simulation system platform |
-
2010
- 2010-09-20 CN CN 201010286754 patent/CN102406507B/en not_active Expired - Fee Related
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101530329A (en) * | 2009-03-06 | 2009-09-16 | 北京理工大学 | Semi-physical driving fatigue vision simulation system platform |
Non-Patent Citations (2)
| Title |
|---|
| 张祖怀: "基于人体生理信号的驾驶疲劳研究方法及其应用", 《中国优秀博硕士学位论文全文数据库（硕士）工程科技II辑》, no. 12, 15 December 2006 (2006-12-15), pages 035 - 101 * |
| 毛喆: "基于驾驶员生理特征分析的驾驶疲劳状态识别方法研究", 《中国优秀博硕士学位论文全文数据库（硕士）信息科技辑》, no. 8, 15 August 2006 (2006-08-15), pages 138 - 591 * |
Cited By (40)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102881117A (en) * | 2012-06-15 | 2013-01-16 | 浙江吉利汽车研究院有限公司杭州分公司 | Watch capable of detecting fatigue of driver |
| CN102881117B (en) * | 2012-06-15 | 2014-11-12 | 浙江吉利汽车研究院有限公司杭州分公司 | Watch capable of detecting fatigue of driver |
| CN102813524A (en) * | 2012-08-10 | 2012-12-12 | 深圳市迈迪加科技发展有限公司 | Fatigue driving detection method |
| CN103932719A (en) * | 2013-01-18 | 2014-07-23 | 袁囡囡 | Fatigue driving detecting technology |
| CN103070687A (en) * | 2013-02-06 | 2013-05-01 | 南京理工大学 | Signal processing algorithm of non-contact type vital sign monitoring system |
| CN103318079B (en) * | 2013-04-09 | 2016-05-25 | 浙江吉利汽车研究院有限公司杭州分公司 | Intelligent sound entertainment systems |
| CN103318079A (en) * | 2013-04-09 | 2013-09-25 | 浙江吉利汽车研究院有限公司杭州分公司 | intelligentIntelligent sound box entertainment system |
| CN103976749A (en) * | 2013-06-09 | 2014-08-13 | 湖南纽思曼导航定位科技有限公司 | Real-time fatigue prompting method and device |
| CN104112335A (en) * | 2014-07-25 | 2014-10-22 | 北京机械设备研究所 | Multi-information fusion based fatigue driving detecting method |
| CN105534531A (en) * | 2014-10-29 | 2016-05-04 | 上海华博信息服务有限公司 | Method and system for preventing fatigue driving |
| CN104376685A (en) * | 2014-11-06 | 2015-02-25 | 无锡悟莘科技有限公司 | Fatigue driving preventing vehicle control method |
| CN105741494A (en) * | 2016-03-29 | 2016-07-06 | 浙江吉利控股集团有限公司 | Driver fatigue monitoring method based on off-line data matching |
| CN105741494B (en) * | 2016-03-29 | 2018-06-19 | 浙江吉利控股集团有限公司 | A kind of driver fatigue monitoring method based on Data Matching under line |
| CN106314437A (en) * | 2016-08-30 | 2017-01-11 | 宇龙计算机通信科技(深圳)有限公司 | Fatigue driving preventing device and method and intelligent bracelet |
| CN106236047A (en) * | 2016-09-05 | 2016-12-21 | 合肥飞鸟信息技术有限公司 | The control method of driver fatigue monitoring system |
| CN106236046A (en) * | 2016-09-05 | 2016-12-21 | 合肥飞鸟信息技术有限公司 | Driver fatigue monitoring system |
| CN106580282A (en) * | 2016-10-25 | 2017-04-26 | 上海斐讯数据通信技术有限公司 | Human body health monitoring device, system and method |
| CN108113657A (en) * | 2016-11-30 | 2018-06-05 | 天津职业技术师范大学 | A kind of Driver Fatigue Detection based on D-S evidence theory |
| CN108304745A (en) * | 2017-01-10 | 2018-07-20 | 普天信息技术有限公司 | A kind of driver's driving behavior detection method, device |
| CN108401415B (en) * | 2017-03-14 | 2020-11-17 | 深圳力维智联技术有限公司 | Monitoring method and monitoring device |
| CN108401415A (en) * | 2017-03-14 | 2018-08-14 | 深圳中兴力维技术有限公司 | monitoring method and monitoring device |
| CN107187467A (en) * | 2017-05-27 | 2017-09-22 | 中南大学 | Driver's monitoring method and system for operation safety and accident imputation |
| CN107187537A (en) * | 2017-05-27 | 2017-09-22 | 重庆邮电大学 | Electric bicycle assisted control system and method based on fatigue strength |
| CN108833024A (en) * | 2018-04-23 | 2018-11-16 | 温州市特种设备检测研究院 | A kind of channel wireless radio multi distribution field vehicle braking-distance figures transmission method |
| CN108833024B (en) * | 2018-04-23 | 2021-07-16 | 温州市特种设备检测研究院 | Multi-channel wireless distributed field vehicle brake data transmission method |
| CN109147951A (en) * | 2018-09-19 | 2019-01-04 | 中国人民解放军第三0五医院 | A kind of alarming method by monitoring of mental alertness |
| CN111376908B (en) * | 2018-12-11 | 2021-05-18 | 上海汽车集团股份有限公司 | Method and device for determining driving state of driver |
| CN111376908A (en) * | 2018-12-11 | 2020-07-07 | 上海汽车集团股份有限公司 | Method and device for determining driving state of driver |
| CN109620269A (en) * | 2019-01-28 | 2019-04-16 | 深圳市赛梅斯凯科技有限公司 | Fatigue detection method, device, equipment and readable storage medium storing program for executing |
| CN109620269B (en) * | 2019-01-28 | 2021-10-22 | 锦图计算技术(深圳)有限公司 | Fatigue detection method, device, equipment and readable storage medium |
| CN110414554A (en) * | 2019-06-18 | 2019-11-05 | 浙江大学 | One kind being based on the improved Stacking integrated study fish identification method of multi-model |
| CN110414554B (en) * | 2019-06-18 | 2022-03-22 | 浙江大学 | Stacking ensemble learning fish identification method based on multi-model improvement |
| CN110338821A (en) * | 2019-08-12 | 2019-10-18 | 深圳市发掘科技有限公司 | A kind of driver's driving condition recognition methods |
| CN111938599A (en) * | 2020-08-18 | 2020-11-17 | 湖南汽车工程职业学院 | Driver physical characteristic recognition-based fatigue driving monitoring system |
| CN112036352A (en) * | 2020-09-08 | 2020-12-04 | 北京嘀嘀无限科技发展有限公司 | Training method of fatigue detection model, and fatigue driving detection method and device |
| CN112036352B (en) * | 2020-09-08 | 2021-09-14 | 北京嘀嘀无限科技发展有限公司 | Training method of fatigue detection model, and fatigue driving detection method and device |
| CN113071446A (en) * | 2021-02-26 | 2021-07-06 | 三三智能科技(苏州)有限公司 | Health index monitoring system based on automobile intelligent safety belt and data processing method thereof |
| CN114287940A (en) * | 2021-12-17 | 2022-04-08 | 深圳市海清视讯科技有限公司 | Fatigue detection method and device and electronic equipment |
| CN117104243A (en) * | 2023-10-24 | 2023-11-24 | 临朐弘泰汽车配件有限公司 | Fatigue driving monitoring system and steering wheel provided with same |
| CN117104243B (en) * | 2023-10-24 | 2023-12-26 | 临朐弘泰汽车配件有限公司 | Fatigue driving monitoring system and steering wheel provided with same |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102406507B (en) | 2013-10-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102406507B (en) | Method for monitoring fatigue degree of driver based on human body physiological signal | |
| Wang et al. | Drowsy behavior detection based on driving information | |
| US10618522B2 (en) | Drowsiness detection and intervention system and method | |
| CN103531042B (en) | Based on the vehicle rear-end collision method for early warning of driver's type | |
| Chai | Drowsiness monitoring based on steering wheel status | |
| CN109147279B (en) | Driver fatigue driving monitoring and early warning method and system based on Internet of vehicles | |
| US8519853B2 (en) | Unobtrusive driver drowsiness detection system and method | |
| CN104269026B (en) | Fatigue driving real-time monitoring and early warning method based on Android platform | |
| Patel et al. | Applying neural network analysis on heart rate variability data to assess driver fatigue | |
| Picot et al. | Drowsiness detection based on visual signs: blinking analysis based on high frame rate video | |
| CN103337132B (en) | Tumble detection method for human body based on 3-axis acceleration sensor | |
| CN107618512A (en) | Driving behavior safe evaluation method based on people's car environment multi-data source | |
| CN108372785A (en) | A kind of non-security driving detection device of the automobile based on image recognition and detection method | |
| CN201169238Y (en) | Automobile safety device | |
| CN110901385A (en) | Active speed limiting method based on fatigue state of driver | |
| Hu et al. | Analysis on biosignal characteristics to evaluate road rage of younger drivers: A driving simulator study | |
| CN105799709A (en) | Method and device for recognizing sudden turn of vehicle | |
| Liu et al. | A review of driver fatigue detection: Progress and prospect | |
| CN109846459A (en) | A kind of fatigue driving state monitoring method | |
| Singh et al. | Physical and physiological drowsiness detection methods | |
| CN206124823U (en) | Intelligence children safety seat | |
| Lei et al. | Study on driving fatigue evaluation system based on short time period ECG signal | |
| CN110992709A (en) | Active speed limiting system based on fatigue state of driver | |
| Bi et al. | Detecting emergency situations by monitoring drivers' states from EEG | |
| Zhu et al. | Eeg-based system using deep learning and attention mechanism for driver drowsiness detection |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20131023 Termination date: 20190920 |