CN105574487A - Facial feature based driver attention state detection method - Google Patents
Facial feature based driver attention state detection method Download PDFInfo
- Publication number
- CN105574487A CN105574487A CN201510838005.6A CN201510838005A CN105574487A CN 105574487 A CN105574487 A CN 105574487A CN 201510838005 A CN201510838005 A CN 201510838005A CN 105574487 A CN105574487 A CN 105574487A
- Authority
- CN
- China
- Prior art keywords
- driver
- state
- fatigue
- eyelid
- follows
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/59—Context or environment of the image inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
- G06V20/597—Recognising the driver's state or behaviour, e.g. attention or drowsiness
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention relates to a facial feature based driver attention state detection method. The detection method is characterized by comprising the following steps of performing PERCLOS based driver fatigue state detection; performing blink frequency based driver fatigue state detection; performing sight line distribution based driver attention distraction state detection; and sending out early warning for driver fatigue and attention distraction state, wherein the early warning for fatigue or attention distraction state is carried out continuously for a certain time to avoid frequent switching between different states; the early warning priority is as follows: fatigue driving is greater than attention distraction that is greater than normal driving; and the attention state of the driver can be accurately detected through the physiological reaction characteristics of the driver, and early warning is sent out for driver fatigue and the attention distraction state; collection and extraction of the facial features of the driver are not included; the sampling efficiency of the adopted driver facial feature collection and extracting system is fHz; and the frequency for reading the driver facial feature is f<0> Hz.
Description
Technical field
The present invention relates to a kind of driver attention condition detection method, particularly relate to a kind of driver attention condition detection method based on facial characteristics, belong to intelligent vehicle safety and assist driving field.
Background technology
Driver fatigue and dispersion attention are the key factors causing road traffic accident, and research shows, the collision accident more than 23% is with almost collision accident is relevant with driver attention state.But along with the continuous increase of inter-vehicle information system, this phenomenon is on the rise.
The fatigue and the dispersion attention state that effectively detect driver are in real time the important measures improving travel safety and road improvement traffic environment.
At present, the method for carrying out driver attention state-detection can be roughly divided into five kinds:
1) based on the detection method of driver's physiological signal, as EEG, ECG, EOG etc.;
2) based on the detection method of driver's physiological reaction feature, as frequency of wink, direction of visual lines, face orientation etc.;
3) based on the detection method of driver's operation behavior, as steering wheel angle, steering wheel angle speed, accelerator open degree etc.;
4) based on the detection method of car status information, as the speed of a motor vehicle, lane shift amount etc.;
5) based on the detection method of information fusion technology, two or more detection methods above are merged.
Wherein, detection method based on driver's physiological reaction feature refers to the state of attention utilizing information nictation of driver, the motion of eyeball and head movement characteristic etc. to infer driver, Detection accuracy is higher, has become present stage driver fatigue and the main direction of studying of dispersion attention state-detection.
Patent 201110162468.7(driver fatigue detection method based on face video analysis) a kind of driver fatigue detection method based on face video analysis is proposed; first the method detects facial image, obtains the Primary Location of eyes, nose, face local organs; Then pinpoint human face characteristic point is obtained further; Final based on the accurate positioning result of multiframe human face characteristic point to be measured, quantificational description is carried out to facial motion feature, obtains people's fatigue detection result to be measured according to facial movement statistical indicator.
Patent No. 201010275567.1(is based on the driver fatigue condition detection method of digital video) propose a kind of driver fatigue condition detection method based on digital video.The method, on the basis of camera collection to image, first carries out the detection & localization of face; Then search human eye area and face region, human eye state and mouth states are judged; Finally, adopt sky-frequency domain character to merge and judge whether driver is in fatigue driving state with the method for svm classifier.
At present, the extraction aspect of driver's facial characteristics is mainly concentrated on based on the research of the detection method of driver's physiological reaction feature.But after successfully extracting driver's physiological reaction feature (eyelid size, number of winks, direction of visual lines etc.), there is certain problem by the physiological reaction feature of driver to the judgement aspect of driver attention state, be badly in need of perfect.Meanwhile, due between driver's Different Individual, there is some difference property, reduce further again the accuracy rate of existing driver fatigue and dispersion attention condition detecting system.
Summary of the invention
The object of the present invention is to provide a kind of driver attention condition detection method based on facial characteristics, it accurately detects the state of attention of driver by driver's physiological reaction feature (eyelid size, number of winks, direction of visual lines etc.) and carries out early warning to driver fatigue and dispersion attention state.Determine design parameter value and specify that detecting step.Do not comprise collection and the extraction of driver's facial characteristics, the sample frequency that the driver's facial characteristics adopted gathers extraction system is
, the frequency that the present invention reads driver's facial characteristics is
.
For solving the problems of the technologies described above, technical scheme of the present invention is achieved in that the driver attention condition detection method based on facial characteristics, it is characterized in that detecting step is as follows:
1. based on the driver fatigue state-detection of PERCLOS;
2. based on the driver fatigue state-detection of frequency of wink;
3. the driver attention disperse state based on sight line distribution detects;
4. the early warning of driver fatigue and dispersion attention state;
Tired or dispersion attention state should the early warning duration, avoids different conditions frequently to switch.Early warning priority: fatigue driving > dispersion attention > normal driving;
The wherein said driver fatigue state-detection based on PERCLOS comprises the steps:
1., for the difference of different driver, the initialization step of driver's eyelid dimension threshold is as follows
A. read and preserve front n group driver eyelid size: left eyelid
, right eyelid
; Eyelid is commonly called as eyelid, and long soft tissue before eyeball, shields to eyeball.Eyelid size is the sizes of eyes when opening;
B. driver's eyelid dimension threshold (left eyelid is calculated
, right eyelid
) as the Calculation Basis of PERCLOS, driver's eyelid dimension threshold computing formula is as follows:
2. based on
judgment criterion (that is: in unit interval, eyes closed is greater than 0.4 more than the ratio shared by 80%) to detect driver fatigue state step as follows:
A. the eyelid size of present frame is read: left eyelid
, right eyelid
;
B. the computing formula of catacleisis degree is as follows:
Wherein:
for left eye closes degree,
for right eye closes degree;
C. start timing when eyes closed is more than 80%, calculate
the number of times of driver's eyes closed more than 80% in s, computing formula is as follows:
Wherein:
for
the number of times of interior eyes closed more than 80%, the initial value at every turn starting timing is 0;
D.
computing formula as follows:
Wherein:
for reading the frequency of driver's eyelid size;
If
, then driver is in fatigue driving state, if
, then driver is in abnormal driving state.
The described driver fatigue state-detection based on frequency of wink comprises the steps:
1. as follows for different driver's unit interval (1min) interior number of winks variation range threshold value initialization step:
A. before driver starts driving
in time, the driver's number of winks in statistical unit time window (1min);
B. two continuous time window repetition rate be 50s;
C. before statistics
altogether interior
group driver number of winks composition characteristic vector
, calculate proper vector
middle driver's number of winks minimum value
and maximal value
, before calculating
driver's number of winks minimum value in time
and maximal value
, as this driver's abnormal driving state number of winks variation range
;
2. the driver fatigue state detecting step based on frequency of wink is as follows:
A. the interior driver's number of winks of statistical unit time window (1min)
;
B. two continuous time window repetition rate be 50s;
If c. number of winks drops in abnormal driving state variation range, namely
then driver is in abnormal driving state, if
or
then driver is in fatigue driving state.
The described driver attention disperse state based on sight line distribution detects and comprises the steps:
1., when facing road ahead for different driver, the step that watching area divides is as follows:
A. read and m group driver faces road ahead before preserving time, driver's direction of visual lines
;
B. all driver's direction of visual lines of front m group are in x durection component
constitutive characteristic vector from small to large ord
;
C. proper vector is calculated according to hundredths computing method
upper quartile
, lower quartile
and interquartile-range IQR
;
D. proper vector
in drop on interval
outer element is exceptional value, deletes
in remain after all exceptional values
individual element, will
individual element arranges from small to large ord and forms normal watching area x durection component new feature vector
;
E. proper vector is got
middle minimum value
, maximal value
form normal watching area x direction scope
;
F. all driver's direction of visual lines of front m group are in y durection component
constitutive characteristic vector from small to large ord
；
G. proper vector is calculated according to hundredths computing method
upper quartile
, lower quartile
and interquartile-range IQR
;
H. proper vector
in drop on interval
outer element is exceptional value, deletes
in remain after all exceptional values
individual element, will
individual element arranges from small to large ord and forms normal watching area y durection component new feature vector
；
I. proper vector is got
middle minimum value
, maximal value
form normal watching area y direction scope
;
2. the driver attention disperse state detecting step based on sight line distribution is as follows:
A. the direction of gaze of present frame is read:
;
If b. driver's direction of gaze departs from normal watching area, start timing, its computing formula is as follows:
Wherein:
for direction of gaze departs from normal watching area frequency of reckoning by time, the initial value at every turn starting timing is 0;
If c. continue to depart from the normal watching area time
more than 2s, then driver is in dispersion attention state, otherwise is abnormal driving state, the duration
computing formula is as follows:
Wherein:
for reading the frequency of driver's direction of visual lines.
The early warning of described driver fatigue or dispersion attention state comprises the steps:
1. when driver is in abnormal driving state, the green indicating lamp of early warning system is bright, display " normal driving ";
2. when driver is in fatigue driving state, the red led of early warning system is bright, plays warning sound, shows " fatigue driving ", until normal driving simultaneously;
3. when driver is in dispersion attention state, the yellow indicator lamp of early warning system is bright, plays warning sound, shows " dispersion attention ", until normal driving simultaneously;
4. early warning system is arranged on panel board place, and the early warning that sends easily is understood by driver and accepts.
Good effect of the present invention is by the initialization to different driver's eyelid dimension threshold, solves the problem of driver individual difference, improves versatility and the Detection accuracy of system; By the initialization to number of winks threshold value in driver's unit interval, solve the problem of driver individual difference.Meanwhile, two continuous time window repetition rate be 50s, reduce the false dismissed rate of driver fatigue state-detection; By the initialization to driver's abnormal driving state watching area, solve the problem of driver individual difference, in initialization procedure, delete exceptional value in the initialization procedure of abnormal driving state watching area, get rid of the interference of improper blinkpunkt, improve the accuracy rate of dispersion attention state-detection; Carry out different early warning to different driving condition, method for early warning is more easily understood by driver and is accepted.
Accompanying drawing explanation
Fig. 1 is of the present invention based on the driver's facial characteristics parameter threshold initialize flow block diagram in the driver attention condition detection method of facial characteristics.
Fig. 2 is the FB(flow block) of the driver attention condition detection method based on facial characteristics of the present invention.
Fig. 3 is of the present invention based on the driver attention status early warning FB(flow block) in the driver attention condition detection method of facial characteristics.
Embodiment
Below in conjunction with drawings and Examples, the present invention will be further described:
Embodiment 1
It is SmartEye that the driver's facial characteristics adopted gathers extraction system, and its sample frequency is 50Hz, and the reading frequency of driver's facial characteristics parameter is 50Hz.
As shown in Figure 2, the driver attention condition detection method based on facial characteristics of the present invention comprises the steps:
1. based on the driver fatigue state-detection of PERCLOS;
2. based on the driver fatigue state-detection of frequency of wink;
3. the driver attention disperse state based on sight line distribution detects;
4. the early warning of driver fatigue or dispersion attention state;
The driver fatigue state-detection based on PERCLOS described in technical scheme comprises the steps:
1. as shown in Figure 1, for different driver's difference, the initialized step of driver's eyelid dimension threshold is as follows:
A. read and preserve front 500 groups of driver's eyelid sizes: left eyelid
, right eyelid
;
B. driver's eyelid dimension threshold (left eyelid is calculated
, right eyelid
) as the Calculation Basis of PERCLOS, driver's eyelid dimension threshold computing formula is as follows:
2. as shown in Figure 2, adopt based on
judgment criterion (that is: in unit interval, eyes closed is greater than 0.4 more than the ratio shared by 80%) to detect driver fatigue state step as follows:
A. the eyelid size of present frame is read: left eyelid
, right eyelid
;
B. the computing formula of catacleisis degree is as follows:
Wherein:
for left eye closes degree,
for right eye closes degree;
C. when calculating P80, the present invention is not take time window as the ratio of eyes closed more than 80% in the computing unit unit of account time, but timing (calculating the ratio of driver's eyes closed more than 80% in 1s in this example) is started when driver's eyes closed is more than 80%, so both can reduce detection system operand and improve system performance, to the more important thing is when can avoid occurring that eyes closed is assigned to more than 80% in two continuous time windows, do not meet in each time window simultaneously
and there is false dismissal, improve Detection accuracy, this example calculation formula is as follows:
Wherein:
for the number of times of eyes closed in 1s more than 80%, the initial value at every turn starting timing is 0;
D.
computing formula as follows:
If
, then driver is in fatigue driving state, if
, then driver is in abnormal driving state.
The described driver fatigue state-detection based on frequency of wink comprises the steps:
1. different driver's frequency of wink is different, and consult Fig. 1, different driver's unit interval (1min) interior number of winks variation range threshold value initialization step is as follows:
A. driver started to drive in the front 30min time, the driver's number of winks in statistical unit time window (1min)
;
B. two continuous time window repetition rate be 50s;
C. front 30min totally 175 groups of driver's number of winks composition characteristic vectors
, calculate proper vector
interior driver's number of winks minimum value
and maximal value
, as this driver's abnormal driving state number of winks variation range
.
2. the driver fatigue state detecting step as shown in Figure 2, based on frequency of wink is as follows:
A. the interior driver's number of winks of statistical unit time window (1min)
;
B. two continuous time window repetition rate be 50s;
If c. number of winks drops in abnormal driving state variation range, namely
then driver is in abnormal driving state, if
or
then driver is in fatigue driving state.
The described driver attention disperse state based on sight line distribution detects and comprises the steps:
1., as shown in Figure 1, when facing road ahead for different driver, the step that watching area divides is as follows:
A. read and preserve front 30min m driver direction of visual lines altogether
,
;
B. all driver's direction of visual lines of front m group are in x durection component
constitutive characteristic vector from small to large ord
;
C. proper vector is calculated according to hundredths computing method
upper quartile
, lower quartile
and interquartile-range IQR
;
D. proper vector
in drop on interval
outer element is exceptional value, deletes
in remain after all exceptional values
individual element, will
individual element arranges from small to large ord and forms normal watching area x durection component new feature vector
;
E. proper vector is got
middle minimum value
, maximal value
form normal watching area x direction scope
;
F. all driver's direction of visual lines of front m group are in y durection component
constitutive characteristic vector from small to large ord
;
G. proper vector is calculated according to hundredths computing method
upper quartile
, lower quartile
and interquartile-range IQR
;
H. proper vector
in drop on interval
outer element is exceptional value, deletes
in remain after all exceptional values
individual element, will
individual element arranges from small to large ord and forms normal watching area y durection component new feature vector
;
I. proper vector is got
middle minimum value
, maximal value
form normal watching area y direction scope
.
2. the driver attention disperse state detecting step as shown in Figure 2, based on sight line distribution is as follows:
A. the direction of gaze of present frame is read:
;
If b. driver's direction of gaze departs from normal watching area, start timing, its computing formula is as follows:
Wherein:
for direction of gaze departs from normal watching area frequency of reckoning by time, the initial value at every turn starting timing is 0;
If c. continue to depart from the normal watching area time
more than 2s, then drive artificial dispersion attention state, the duration
computing formula is as follows:
As shown in Figure 3, early warning system of the present invention is arranged on panel board place, and the early warning of the driver fatigue described in technical scheme or dispersion attention state comprises the steps:
1. when driver is in abnormal driving state, the green indicating lamp of early warning system is bright, display " normal driving ".
2. when driver is in fatigue driving state, the red led of early warning system is bright, plays warning sound, shows " fatigue driving ", until normal driving simultaneously.
3. when driver is in dispersion attention state, the yellow indicator lamp of early warning system is bright, plays warning sound, shows " dispersion attention ", until normal driving simultaneously.
Claims (1)
1., based on the driver attention condition detection method of facial characteristics, it is characterized in that detecting step is as follows:
(1) based on the driver fatigue state-detection of PERCLOS;
(2) based on the driver fatigue state-detection of frequency of wink;
(3) the driver attention disperse state based on sight line distribution detects;
(4) early warning of driver fatigue and dispersion attention state;
Tired or dispersion attention state should the early warning duration, avoids different conditions frequently to switch; Early warning priority: fatigue driving > dispersion attention > normal driving;
The wherein said driver fatigue state-detection based on PERCLOS comprises the steps:
For the difference of different driver, the initialization step of driver's eyelid dimension threshold is as follows
A. read and preserve front n group driver eyelid size: left eyelid
, right eyelid
; Eyelid is commonly called as eyelid, and long soft tissue before eyeball, shields to eyeball, and eyelid size is the sizes of eyes when opening;
B. driver's eyelid dimension threshold (left eyelid is calculated
, right eyelid
) as the Calculation Basis of PERCLOS, driver's eyelid dimension threshold computing formula is as follows:
Based on
judgment criterion (that is: in unit interval, eyes closed is greater than 0.4 more than the ratio shared by 80%) to detect driver fatigue state step as follows:
A. the eyelid size of present frame is read: left eyelid
, right eyelid
;
B. the computing formula of catacleisis degree is as follows:
Wherein:
for left eye closes degree,
for right eye closes degree;
C. start timing when eyes closed is more than 80%, calculate
the number of times of driver's eyes closed more than 80% in s, computing formula is as follows:
Wherein:
for
the number of times of interior eyes closed more than 80%, the initial value at every turn starting timing is 0;
D.
computing formula as follows:
Wherein:
for reading the frequency of driver's eyelid size;
If
, then driver is in fatigue driving state, if
, then driver is in abnormal driving state;
The described driver fatigue state-detection based on frequency of wink comprises the steps:
(1) as follows for different driver's unit interval (1min) interior number of winks variation range threshold value initialization step:
A. before driver starts driving
in time, the driver's number of winks in statistical unit time window (1min);
B. two continuous time window repetition rate be 50s;
C. before statistics
altogether interior
group driver number of winks composition characteristic vector
, calculate proper vector
middle driver's number of winks minimum value
and maximal value
, before calculating
driver's number of winks minimum value in time
and maximal value
, as this driver's abnormal driving state number of winks variation range
;
(2) the driver fatigue state detecting step based on frequency of wink is as follows:
A. the interior driver's number of winks of statistical unit time window (1min)
;
B. two continuous time window repetition rate be 50s;
If c. number of winks drops in abnormal driving state variation range, namely
then driver is in abnormal driving state, if
or
then driver is in fatigue driving state;
The described driver attention disperse state based on sight line distribution detects and comprises the steps:
(1), when facing road ahead for different driver, the step that watching area divides is as follows:
A. read and m group driver faces road ahead before preserving time, driver's direction of visual lines
;
B. all driver's direction of visual lines of front m group are in x durection component
constitutive characteristic vector from small to large ord
;
C. proper vector is calculated according to hundredths computing method
upper quartile
, lower quartile
and interquartile-range IQR
;
D. proper vector
in drop on interval
outer element is exceptional value, deletes
in remain after all exceptional values
individual element, will
individual element arranges from small to large ord and forms normal watching area x durection component new feature vector
;
E. proper vector is got
middle minimum value
, maximal value
form normal watching area x direction scope
;
F. all driver's direction of visual lines of front m group are in y durection component
constitutive characteristic vector from small to large ord
；
G. proper vector is calculated according to hundredths computing method
upper quartile
, lower quartile
and interquartile-range IQR
;
H. proper vector
in drop on interval
outer element is exceptional value, deletes
in remain after all exceptional values
individual element, will
individual element arranges from small to large ord and forms normal watching area y durection component new feature vector
；
I. proper vector is got
middle minimum value
, maximal value
form normal watching area y direction scope
;
(2) the driver attention disperse state detecting step based on sight line distribution is as follows:
A. the direction of gaze of present frame is read:
;
If b. driver's direction of gaze departs from normal watching area, start timing, its computing formula is as follows:
Wherein:
for direction of gaze departs from normal watching area frequency of reckoning by time, the initial value at every turn starting timing is 0;
If c. continue to depart from the normal watching area time
more than 2s, then driver is in dispersion attention state, otherwise is abnormal driving state, the duration
computing formula is as follows:
Wherein:
for reading the frequency of driver's direction of visual lines;
The early warning of described driver fatigue or dispersion attention state comprises the steps:
(1) when driver is in abnormal driving state, the green indicating lamp of early warning system is bright, display " normal driving ";
(2) when driver is in fatigue driving state, the red led of early warning system is bright, plays warning sound, shows " fatigue driving ", until normal driving simultaneously;
(3) when driver is in dispersion attention state, the yellow indicator lamp of early warning system is bright, plays warning sound, shows " dispersion attention ", until normal driving simultaneously;
(4) early warning system is arranged on panel board place, and the early warning that sends easily is understood by driver and accepts.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510838005.6A CN105574487A (en) | 2015-11-26 | 2015-11-26 | Facial feature based driver attention state detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510838005.6A CN105574487A (en) | 2015-11-26 | 2015-11-26 | Facial feature based driver attention state detection method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105574487A true CN105574487A (en) | 2016-05-11 |
Family
ID=55884595
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510838005.6A Pending CN105574487A (en) | 2015-11-26 | 2015-11-26 | Facial feature based driver attention state detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105574487A (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106529193A (en) * | 2016-11-30 | 2017-03-22 | 上海明波通信技术股份有限公司 | Health examination system |
| CN106585629A (en) * | 2016-12-06 | 2017-04-26 | 广州市科恩电脑有限公司 | Automobile control method and device |
| CN106652353A (en) * | 2016-12-06 | 2017-05-10 | 广州市科恩电脑有限公司 | Traffic tool control method and device |
| CN106627529A (en) * | 2016-12-06 | 2017-05-10 | 广州市科恩电脑有限公司 | Intelligent monitoring method and device for vehicle |
| CN108446600A (en) * | 2018-02-27 | 2018-08-24 | 上海汽车集团股份有限公司 | A kind of vehicle driver's fatigue monitoring early warning system and method |
| CN109584507A (en) * | 2018-11-12 | 2019-04-05 | 深圳佑驾创新科技有限公司 | Driver behavior modeling method, apparatus, system, the vehicles and storage medium |
| CN109803583A (en) * | 2017-08-10 | 2019-05-24 | 北京市商汤科技开发有限公司 | Driver monitoring method, apparatus and electronic equipment |
| CN109859438A (en) * | 2019-01-30 | 2019-06-07 | 北京津发科技股份有限公司 | Safe early warning method, system, vehicle and terminal device |
| CN110287916A (en) * | 2019-06-28 | 2019-09-27 | 浙江吉利控股集团有限公司 | It is a kind of for judging the method and system of driver attention |
| WO2020042345A1 (en) * | 2018-08-28 | 2020-03-05 | 初速度（苏州）科技有限公司 | Method and system for acquiring line-of-sight direction of human eyes by means of single camera |
| CN110859609A (en) * | 2019-11-26 | 2020-03-06 | 郑州迈拓信息技术有限公司 | Multi-feature fusion fatigue driving detection method based on voice analysis |
| CN111291590A (en) * | 2018-12-06 | 2020-06-16 | 广州汽车集团股份有限公司 | Driver fatigue detection method, driver fatigue detection device, computer equipment and storage medium |
| CN111325172A (en) * | 2020-02-28 | 2020-06-23 | 英华达（上海）科技有限公司 | Device and method for achieving driving habit formation by sight line tracking |
| CN111476122A (en) * | 2020-03-26 | 2020-07-31 | 杭州鸿泉物联网技术股份有限公司 | Driving state monitoring method and device and storage medium |
| CN113792577A (en) * | 2021-07-29 | 2021-12-14 | 何泽仪 | Method and system for detecting attention state of students in online class and storage medium |
| CN114159064A (en) * | 2022-02-11 | 2022-03-11 | 深圳市心流科技有限公司 | Electroencephalogram signal based concentration assessment method, device, equipment and storage medium |
| US11386679B2 (en) | 2018-10-19 | 2022-07-12 | Shanghai Sensetime Intelligent Technology Co., Ltd. | Driving state analysis method and apparatus, driver monitoring system and vehicle |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102254151A (en) * | 2011-06-16 | 2011-11-23 | 清华大学 | Driver fatigue detection method based on face video analysis |
| CN104240446A (en) * | 2014-09-26 | 2014-12-24 | 长春工业大学 | Fatigue driving warning system on basis of human face recognition |
| CN104732251A (en) * | 2015-04-23 | 2015-06-24 | 郑州畅想高科股份有限公司 | Video-based method of detecting driving state of locomotive driver |
| CN104794856A (en) * | 2014-01-22 | 2015-07-22 | 径卫视觉科技（上海）有限公司 | Driver's attention comprehensive evaluation system |
-
2015
- 2015-11-26 CN CN201510838005.6A patent/CN105574487A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102254151A (en) * | 2011-06-16 | 2011-11-23 | 清华大学 | Driver fatigue detection method based on face video analysis |
| CN104794856A (en) * | 2014-01-22 | 2015-07-22 | 径卫视觉科技（上海）有限公司 | Driver's attention comprehensive evaluation system |
| CN104240446A (en) * | 2014-09-26 | 2014-12-24 | 长春工业大学 | Fatigue driving warning system on basis of human face recognition |
| CN104732251A (en) * | 2015-04-23 | 2015-06-24 | 郑州畅想高科股份有限公司 | Video-based method of detecting driving state of locomotive driver |
Non-Patent Citations (4)
| Title |
|---|
| HUACAI XIAN等: "The Effects of Using In-Vehicle Computer on Driver Eye Movements and Driving Performance", 《ADVANCES IN MECHANICAL ENGINEERING》 * |
| LISHENG JIN等: "Driver Sleepiness Detection System Based on Eye Movements Variables", 《ADVANCES IN MECHANICAL ENGINEERING》 * |
| 牛清宁: "基于信息融合的疲劳驾驶检测方法研究", 《中国博士学位论文全文数据库 工程科技Ⅱ辑》 * |
| 牛清宁等: "基于眼动特征的疲劳驾驶检测方法", 《哈尔滨工程大学学报》 * |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106529193A (en) * | 2016-11-30 | 2017-03-22 | 上海明波通信技术股份有限公司 | Health examination system |
| CN106585629A (en) * | 2016-12-06 | 2017-04-26 | 广州市科恩电脑有限公司 | Automobile control method and device |
| CN106652353A (en) * | 2016-12-06 | 2017-05-10 | 广州市科恩电脑有限公司 | Traffic tool control method and device |
| CN106627529A (en) * | 2016-12-06 | 2017-05-10 | 广州市科恩电脑有限公司 | Intelligent monitoring method and device for vehicle |
| CN106585629B (en) * | 2016-12-06 | 2019-07-12 | 广东泓睿科技有限公司 | A kind of control method for vehicle and device |
| CN109803583A (en) * | 2017-08-10 | 2019-05-24 | 北京市商汤科技开发有限公司 | Driver monitoring method, apparatus and electronic equipment |
| CN108446600A (en) * | 2018-02-27 | 2018-08-24 | 上海汽车集团股份有限公司 | A kind of vehicle driver's fatigue monitoring early warning system and method |
| WO2020042345A1 (en) * | 2018-08-28 | 2020-03-05 | 初速度（苏州）科技有限公司 | Method and system for acquiring line-of-sight direction of human eyes by means of single camera |
| US11386679B2 (en) | 2018-10-19 | 2022-07-12 | Shanghai Sensetime Intelligent Technology Co., Ltd. | Driving state analysis method and apparatus, driver monitoring system and vehicle |
| CN109584507A (en) * | 2018-11-12 | 2019-04-05 | 深圳佑驾创新科技有限公司 | Driver behavior modeling method, apparatus, system, the vehicles and storage medium |
| CN109584507B (en) * | 2018-11-12 | 2020-11-13 | 深圳佑驾创新科技有限公司 | Driving behavior monitoring method, device, system, vehicle and storage medium |
| CN111291590A (en) * | 2018-12-06 | 2020-06-16 | 广州汽车集团股份有限公司 | Driver fatigue detection method, driver fatigue detection device, computer equipment and storage medium |
| CN109859438A (en) * | 2019-01-30 | 2019-06-07 | 北京津发科技股份有限公司 | Safe early warning method, system, vehicle and terminal device |
| CN110287916A (en) * | 2019-06-28 | 2019-09-27 | 浙江吉利控股集团有限公司 | It is a kind of for judging the method and system of driver attention |
| CN110287916B (en) * | 2019-06-28 | 2021-11-16 | 浙江吉利控股集团有限公司 | Method and system for judging attention of driver |
| CN110859609A (en) * | 2019-11-26 | 2020-03-06 | 郑州迈拓信息技术有限公司 | Multi-feature fusion fatigue driving detection method based on voice analysis |
| CN111325172A (en) * | 2020-02-28 | 2020-06-23 | 英华达（上海）科技有限公司 | Device and method for achieving driving habit formation by sight line tracking |
| CN111325172B (en) * | 2020-02-28 | 2023-04-21 | 英华达（上海）科技有限公司 | Device and method for achieving driving habit development by sight tracking |
| CN111476122A (en) * | 2020-03-26 | 2020-07-31 | 杭州鸿泉物联网技术股份有限公司 | Driving state monitoring method and device and storage medium |
| CN113792577A (en) * | 2021-07-29 | 2021-12-14 | 何泽仪 | Method and system for detecting attention state of students in online class and storage medium |
| CN114159064A (en) * | 2022-02-11 | 2022-03-11 | 深圳市心流科技有限公司 | Electroencephalogram signal based concentration assessment method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105574487A (en) | Facial feature based driver attention state detection method | |
| CN108446600A (en) | A kind of vehicle driver's fatigue monitoring early warning system and method | |
| CN102054163B (en) | Method for testing driver fatigue based on monocular vision | |
| CN104183091B (en) | System for adjusting sensitivity of fatigue driving early warning system in self-adaptive mode | |
| CN105303830A (en) | Driving behavior analysis system and analysis method | |
| CN111428699A (en) | Driving fatigue detection method and system combining pseudo-3D convolutional neural network and attention mechanism | |
| CN105286802B (en) | Driver Fatigue Detection based on video information | |
| CN105719431A (en) | Fatigue driving detection system | |
| CN105389948A (en) | System and method for preventing fatigue driving of driver | |
| CN104794855A (en) | Driver's attention comprehensive assessment system | |
| CN108230619A (en) | Method for detecting fatigue driving based on multi-feature fusion | |
| CN106467057B (en) | The method, apparatus and system of lane departure warning | |
| CN106080194A (en) | The method for early warning of anti-fatigue-driving and system | |
| CN104637246A (en) | Driver multi-behavior early warning system and danger evaluation method | |
| CN103198616B (en) | Based on method for detecting fatigue driving and the system of the identification of driver's neck moving characteristic | |
| CN104318237A (en) | Fatigue driving warning method based on face identification | |
| CN108021875A (en) | A kind of vehicle driver's personalization fatigue monitoring and method for early warning | |
| CN102930693A (en) | Early warning system and method for safe driving | |
| CN107571797A (en) | Front truck driving information new line display methods and system | |
| CN105931430A (en) | Alarm sensitivity detection method and apparatus for driver state early warning system | |
| CN104269028A (en) | Fatigue driving detection method and system | |
| CN113378771A (en) | Driver state determination method and device, driver monitoring system and vehicle | |
| CN104068868A (en) | Method and device for monitoring driver fatigue on basis of machine vision | |
| CN108245863B (en) | Skiing blind area safety prompting system and control method thereof | |
| CN108154095A (en) | A kind of method, apparatus and vehicle of determining fatigue driving |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160511 |