CN104809445B - method for detecting fatigue driving based on eye and mouth state - Google Patents
method for detecting fatigue driving based on eye and mouth state Download PDFInfo
- Publication number
- CN104809445B CN104809445B CN201510229231.4A CN201510229231A CN104809445B CN 104809445 B CN104809445 B CN 104809445B CN 201510229231 A CN201510229231 A CN 201510229231A CN 104809445 B CN104809445 B CN 104809445B
- Authority
- CN
- China
- Prior art keywords
- mouth
- image
- eye
- driver
- value
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/162—Detection; Localisation; Normalisation using pixel segmentation or colour matching
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Human Computer Interaction (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
Method for detecting fatigue driving category image procossing and mode identification technology based on eye and mouth state, the present invention comprise the following steps：Driver's video image acquisition, illumination compensation pretreatment, human face region detection, comprehensive fatigue judges, sends tired alarm；Wherein human face region detection includes eye detection and mouth detection；Eye detection includes obtaining ocular with sciagraphy, makees eye feature analysis, compared with standard feature, carries out the calculating of k values and the judgement of eye strain；Mouth detection includes obtaining mouth region with mouth map methods, makees mouth feature analysis, compared with standard feature, carries out p value calculating and the judgement yawned；The present invention is judged with reference to two characteristic parameters of eye and mouth, the accuracy rate and reliability judged compared with single parameter fatigue is higher, the traffic accident triggered due to driver tired driving can be greatly reduced in the implementation of the present invention, to ensure the security of the lives and property of driver, there is provided a kind of new precautionary measures.
Description
Technical field
The invention belongs to image procossing and mode identification technology, and in particular to a kind of eye and mouth based on driver
The fatigue detection method of state.
Background technology
With developing rapidly for economy, the quantity of automobile is being continuously increased.Automobile is bringing traffic efficient and convenient to the mankind
While, hidden danger also is buried for traffic safety, the fatigue driving of driver is to trigger a key factor of traffic accident.According to
Data statistics, the traffic accident occurrence cause for having 20% is fatigue driving, therefore accurately fatigue police in real time is made to driver
Accuse particularly important.
By the research of experts and scholars' recent decades, mainly there is contact and non-to the detection method of driver fatigue at present
The class of contact two：
One, contacts, based on the detection of physiological driver's feature, this method needs to add on the body of driver
Measuring apparatus, to detect the physiological parameter of driver, such as electrocardiogram, electroencephalogram, pulse etc..When driver fatigue, these
Physiological signal can change, and judge whether fatigue using the measurement variation of equipment.
Two, are contactless, are divided into two kinds of the detection based on vehicle behavioural characteristic and the detection based on Characteristics of drivers' behavior
Method.Wherein, the detection 1. based on vehicle behavioural characteristic：During driver fatigue, the Driving control ability of vehicle will be reduced.
Such as when detect that steering wheel is motionless for a long time or conversion frequently, car speed and angle of turn etc. it is abnormal when, driver is just very
It is likely to be in fatigue state.Although this method is without interference with driving, due to condition of road surface, the driving habit etc. of driver
Difference, it is difficult to ensure that the accuracy of testing result.2. the detection based on Characteristics of drivers' behavior：By the eyes for detecting driver
Closure, frequency of wink, head position etc. judge whether driver is tired.It is most common when driver is in fatigue state
Physiological behavior reaction be exactly that closure, frequency of wink reduce, blink that the cycle is elongated, yawns eyes for a long time, and head position
Exception etc. is put, using the above-mentioned physiological reaction of Machine Vision Detection, just can determine whether driver is tired through processing identification.
In above-mentioned two classes method, the detection method based on physiological driver's feature of contact will to the precision of detection device
High, cost height is sought, and is directly contacted with driver, interference can be brought to driving.Contactless class it is special based on vehicle behavior
Although the detection method of sign is without interference with driving, due to condition of road surface, the difference such as driving habit of driver, it is difficult to ensure that inspection
Survey the accuracy of result.Detection method based on Characteristics of drivers' behavior have it is noiseless to driver, accuracy it is high and also into
This low advantage, it is most widely used.This method detects face generally by image processing techniques, then extracts eye
Eyeball, the ratio in the unit interval shared by the eyes closed time is calculated based on PERCLOS principles, by relatively judging with threshold value
Whether driver is tired.This method is high to the testing requirements of eyes, in view of the ratio on face shared by eyes is relatively
Small, the size of human eye is also had any different, and judges that element is single, can cause the undesirable situation of tired judged result.
The content of the invention
It is an object of the invention to provide a kind of method for detecting fatigue driving based on eye and mouth state, in the past tired
Improved and innovated on the basis of labor detection method, make fatigue detection result even more ideal.
The method for detecting fatigue driving based on eye and mouth state of the present invention, comprises the following steps：
1. gathering driver's video flowing, video flowing is converted into two field picture；
2. carry out the illumination compensation pretreatment of image：With the brightness of pixel in " reference white " algorithm detection image first,
Pixel of the brightness value preceding 5% is obtained, setting brightness value is 255 in the gray value of preceding 5% pixel, then right to scale
Tri- components of RGB of image carry out Serial regulation, obtain the image after illumination compensation；
3. detect human face region：Image after the illumination compensation obtained to step 2, based on features of skin colors distinguish colour of skin point and
Non- colour of skin point, the bianry image of area of skin color is obtained, and the morphology processing of connectivity analysis is carried out to bianry image；With
Sciagraphy extracts human face region；
4. set eye and mouth feature primary standard value：Assuming that driver is in waking state when entering driver's cabin,
The image obtained this moment is handled, the initial value of resulting eye state and mouth state as standard value and is protected
Deposit；
5. carry out extraction and the signature analysis of ocular：The human face region bianry image progress obtained to step 3 is horizontal
And upright projection, the ocular being partitioned into including eyebrow, state analysis then is carried out with this ocular feature, specifically
Comprise the following steps：
The ocular including eyebrow that 5.1 pairs of steps 5 obtain carries out gray proces, obtains the gray scale of ocular
Image, the x coordinate of this gray level image pixel is averaged, the horizontal mean intensity of image slices vegetarian refreshments is obtained, in average image
On two obvious troughs occur, according to the difference of range difference d between two troughs, to judge that eyes are opened or closed
Close, the poor d of the distance between two troughs that initial pictures are handled to obtain0As normative reference, if d-d0More than set threshold
Value, then be judged to closure state by eyes, be otherwise normal condition；
5.2 eye fatigue judge：The number of image frames continuously closed with k record eyes, k adds 1 when often detecting eyes closed,
In the case where k is less than threshold value, if detecting, eyes are opened, and k is initialized as into 0；In the case where k is more than threshold value, explanation
It is not now blink, is eye fatigue, wherein：K is integer type variable, is counted with k, and k initial value is 0；
6. carry out extraction and the signature analysis of mouth region：Half part is removed to the human face region that step 3 obtains, use is following
Mathematic(al) representation extracts mouth region, then carries out state analysis with this mouth region feature, specifically includes the following steps：
Wherein：CrIt is red chrominance component, CbIt is chroma blue component, n is face
Area image pixel number, η are Cr(x,y)2Average value withAverage value estimation ratio；
6.1 use the bianry image of mouth region, calculate the area s of mouth region；The mouth region obtained with initial pictures
Area s0As normative reference value, the mouth region area s that mouth region area s obtains with initial pictures is calculated0Ratio
If ratio is more than set threshold value, it is judged as that face opens, is otherwise judged to normal；Wherein：Mouth region area s with it is initial
The mouth region area s that image obtains0RatioPixel number purpose ratio can be usedTo replace, n0For initial mouth
Area pixel point number, n are the mouth region pixel number of current frame image；
6.2 yawn judgement：The number of image frames continuously opened with p value record face, often detect that p adds 1 when face opens；
In the case where p is less than threshold value, if detecting, face is normal, and p is initialized as into 0；In the case where p is more than threshold value, explanation
It is now to yawn, driver is in fatigue state, wherein：P is integer type variable, is counted with p, and p initial value is 0；
7. synthesis fatigue judges：According to step 5.2 and step 6.2, when detecting eye fatigue, or yawn, or both
When occurring simultaneously, tired alarm is provided, driver is stopped and rests or change driver.
Above-mentioned step 5 and step 6 are synchronous progress.
The present invention combines eye state and the two parameters of mouth state to be detected to the fatigue state of driver.Its
In, when being detected to eye state, the changing features relation between eyebrow and eyes is make use of, without accurate detection
To eyes, hunting zone is reduced, is a kind of new method for judging eye state.In addition, wear sunglasses even in driver
Or in the case of glasses, with reference to the detection to mouth feature, will not also missing inspection be caused to the fatigue state of driver, make tired inspection
It is even more ideal to survey effect.
The present invention is judged with reference to two characteristic parameters of eye and mouth, to the standard of fatigue judgement compared with single parameter
Higher, the of the invention implementation of true rate and reliability, can be greatly reduced the traffic accident triggered due to driver tired driving, be
Ensure the security of the lives and property of driver, there is provided a kind of new precautionary measures.
Brief description of the drawings
Fig. 1 is the flow chart of the method for detecting fatigue driving based on eye and mouth state
Fig. 2 is the eyes gray-scale map of eyes-open state
Detection results figure when Fig. 3 is normal opens eyes
Fig. 4 is the eyes gray-scale map of closed-eye state
Detection results figure when Fig. 5 is eyes closed
Embodiment
The purpose of the present invention, particular technique method and effect are described below in conjunction with the accompanying drawings, so as to the skill of this area
Art personnel more fully understand the present invention.It is whether tired to detect driver present invention employs eye and mouth feature, such as Fig. 1 institutes
Show, this method comprises the following steps：
1. gathering driver's video flowing, video flowing is converted into two field picture.
2. carry out the illumination compensation pretreatment of image：Illumination can change with driving environment and time, special to the colour of skin
The extraction influence of sign is very big, therefore first carries out illumination compensation, can preferably extract human face region.What is used is a kind of " ginseng
Examine white " algorithm, the brightness of pixel first in detection image, pixel of the brightness value preceding 5% is obtained, brightness value is set preceding
The average gray value of 5% pixel is 255, i.e., using these pixels as " reference white ", then to scale to the RGB tri- of image
Individual component carries out Serial regulation, obtains the image after illumination compensation.
3. detect human face region：It is a kind of rule of thumb using features of skin colors detection face.By image from
RGB is transformed into HSV and YCbCr color spaces and handled, and in YCbCr color spaces, luminance component Y and chrominance information CbCr are
Independent, area of skin color can be extracted well using the Clustering features of the colour of skin.In HSV color spaces, tone Hue exists
Area of skin color and non-area of skin color have obvious different value.Area of skin color is extracted using following equation (1)：
Cr≥140 and Cr≤165 and Cb≥140and Cb≤195and
Hue≥0.01 and Hue≤0.1 (1)
Image after the illumination compensation obtained to step 2, colour of skin point and non-colour of skin point, skin are distinguished using above-mentioned formula (1)
Color dot is set to 1, and non-colour of skin point is set to 0, obtains the bianry image of area of skin color, and the number such as connectivity analysis is carried out to bianry image
Learn Morphological scale-space；Face border is found out with sciagraphy, then accurately extracts human face region.
4. set eye and mouth feature primary standard value：The spy of waking state when initially entering driver's cabin with driver
Sign is used as normative reference, preserves characteristic value now, is compared therewith with the characteristic value detected in driving procedure, and be made whether
The judgement of fatigue.Assuming that driver is in waking state when entering driver's cabin, the image obtained this moment is handled, by institute
Obtained eye state and the initial value of mouth state is as standard value and preserves.
5. carry out extraction and the signature analysis of ocular：Judge that opening for eyes is closed according to the height h of eyelid to eyebrow,
When the eyes are occluded, eyelid movement to eyes foot, now height h be maximum；When normal open eyes, eyelid movement to eye
Eyeball top, now height h is minimum.The human face region bianry image obtained to step 3 carries out horizontal and vertical projection, segmentation
The ocular gone out including eyebrow, state analysis then is carried out to this ocular feature with above-mentioned principle, specifically included
The following steps：
The ocular including eyebrow that 5.1 pairs of steps 5 obtain carries out gray proces, obtains the gray scale of ocular
Image, as shown in Figure 2 and Figure 4, the x coordinate of this gray level image is averaged, two obvious ripples occur on average image
Paddy, according to the difference of range difference d between two troughs, it can be determined that eyes are opened or closed.Analyzed with reference to Fig. 3 and Fig. 5,
The distance between two troughs that initial pictures are handled to obtain poor d0As normative reference, if d-d0More than set threshold value,
Eyes are then judged to closure state, are otherwise normal condition.
5.2 eye fatigue judge：The in general blink duration is 0.3 second or so, then illustrates to drive more than this time
Member is likely to be at eye closing sleep state.The number of image frames continuously closed with k values record eyes, passes through k values and given threshold k0's
Compare, judged to whether blinking.K initial values are arranged to 0, k adds 1 whenever eyes closed is detected.It is less than threshold value in k
k0In the case of, if detecting, eyes are opened, and k is initialized as into 0；In k0More than threshold value k0In the case of, illustrate be not now
Blink, is eye fatigue；Wherein：K is integer type variable, is counted with k, k0It is picture frame corresponding to the most long blink duration
Number.
6. carry out extraction and the signature analysis of mouth region：Mouth only takes face lower half to examine in the latter half of face
Survey can improve detection efficiency and the degree of accuracy.In mouth region, red is most strong, and blueness is most weak, and lip color and the colour of skin are deposited
In certain difference, half part is removed to the human face region that step 3 obtains, mouth region is extracted with following mathematic(al) representation (2).
When people is in fatigue state, except eyes close for a long time, the phenomenon yawned is accompanied by.When yawning, face opens
Amplitude it is very big, now the area in face region will than it is normal when area it is big, the number of corresponding pixel also can be than just
It is more when often.State analysis is carried out to mouth provincial characteristics with above-mentioned principle, specifically includes the following steps：
Wherein：CrIt is red chrominance component, CbIt is chroma blue component, n is face
Area image pixel number, η are Cr(x,y)2Average value withAverage value estimation ratio；
The lip color region extracted is converted to bianry image by 6.1, is expanded by burn into, is found out largest connected domain, and right
Filling processing is made in the face region of hole, then calculates the area s of mouth region；The mouth region face obtained with initial pictures
Product s0As normative reference value, the mouth region area s that the area s of mouth region and initial pictures obtain is calculated0Ratio
If ratio is more than set threshold value, it is judged as that face opens, is otherwise judged to normal；Wherein：The area s of mouth region with just
The mouth region area s that beginning image obtains0RatioPixel number purpose ratio can be usedTo replace, n0For initial mouth
Portion's area pixel point number, n are the mouth region pixel number of current frame image.
6.2 yawn judgement：Driver needs situation about magnifying few when speaking, even if there is the need magnified
Will also will not last very long, can the far smaller than time that yawn.The time that ordinary circumstance servant once yawns is about
It it is more than 5 seconds, the number of image frames continuously opened with p value record face, p initial values are 0, often detect that face opens p and adds 1；
It is less than threshold value p in p0In the case of, if detecting, face is normal, and p is initialized as into 0；It is more than threshold value p in p0In the case of, say
Bright is now to yawn, and driver is in fatigue state.Wherein：P is integer type variable, is counted with p, p0For 5 seconds
Corresponding number of image frames in time.
7. synthesis fatigue judges：According to step 5.2 and step 6.2, when detecting eye fatigue, or yawn, or both
When occurring simultaneously, tired alarm is provided, driver is stopped and rests or change driver.
Above-mentioned step 5.2 and step 6.2 are synchronous progress.
Claims (2)
1. a kind of method for detecting fatigue driving based on eye and mouth state, it is characterised in that comprise the following steps：
1.1 collection driver's video flowings, two field picture is converted to by video flowing；
1.2 carry out the illumination compensation pretreatment of image：With the brightness of pixel in " reference white " algorithm detection image first, obtain
Pixel of the brightness value preceding 5%, setting brightness value is 255 in the gray value of preceding 5% pixel, then to scale to image
Tri- components of RGB carry out Serial regulations, obtain the image after illumination compensation；
1.3 detection human face regions：Image after the illumination compensation obtained to step 1.2, based on features of skin colors distinguish colour of skin point and
Non- colour of skin point, the bianry image of area of skin color is obtained, and the morphology processing of connectivity analysis is carried out to bianry image；With
Sciagraphy extracts human face region；
1.4 setting eyes and mouth feature primary standard value：Assuming that driver is in waking state when entering driver's cabin, to this
Carve the image obtained to be handled, the initial value of resulting eye state and mouth state as standard value and is preserved；
1.5 carry out the extraction of ocular and signature analysis：The human face region bianry image progress that is obtained to step 1.3 it is horizontal and
Upright projection, the ocular being partitioned into including eyebrow, state analysis then is carried out with this ocular feature, specific bag
Include the following steps：
1.5.1 the ocular including eyebrow obtained to step 1.5 carries out gray proces, obtains the gray scale of ocular
Image, the x coordinate of this gray level image pixel is averaged, the horizontal mean intensity of image slices vegetarian refreshments is obtained, in average image
On two obvious troughs occur, according to the difference of range difference d between two troughs, to judge that eyes are opened or closed
Close, the poor d of the distance between two troughs that initial pictures are handled to obtain0As normative reference, if d-d0More than set threshold
Value, then be judged to closure state by eyes, be otherwise normal condition；
1.5.2 eye fatigue judges：The number of image frames continuously closed with k record eyes, k adds 1 when often detecting eyes closed,
In the case that k is less than threshold value, if detecting, eyes are opened, and k is initialized as into 0；In the case where k is more than threshold value, illustrate this
When be not blink, be eye fatigue, wherein：K is integer type variable, is counted with k, and k initial value is 0；
1.6 carry out the extraction of mouth region and signature analysis：Half part is removed to the human face region that step 1.3 obtains, use is following
Mathematic(al) representation extracts mouth region, then carries out state analysis with this mouth region feature, specifically includes the following steps：
<mrow>
<mi>mouth</mi>
<mo>_</mo>
<mi>map</mi>
<mo>=</mo>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>C</mi>
<mi>r</mi>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>&times;</mo>
<msup>
<mrow>
<mo>(</mo>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>C</mi>
<mi>r</mi>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>-</mo>
<mfrac>
<mrow>
<mi>&eta;</mi>
<mo>&times;</mo>
<msub>
<mi>C</mi>
<mi>r</mi>
</msub>
</mrow>
<msub>
<mi>C</mi>
<mi>b</mi>
</msub>
</mfrac>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>;</mo>
</mrow>
Wherein：CrIt is red chrominance component, CbIt is chroma blue component, n is human face region figure
As pixel number, η is Cr(x,y)2Average value withAverage value estimation ratio；
1.6.1 the bianry image of mouth region is used, calculates the area s of mouth region；The mouth region face obtained with initial pictures
Product s0As normative reference value, the mouth region area s that mouth region area s obtains with initial pictures is calculated0RatioIf
Ratio is more than set threshold value, then is judged as that face opens, and is otherwise judged to normal；Wherein：Mouth region area s and initial graph
As obtained mouth region area s0RatioPixel number purpose ratio can be usedTo replace, n0For initial mouth area
Domain pixel number, n are the mouth region pixel number of current frame image；
1.6.2 yawn judgement：The number of image frames continuously opened with p value record face, often detect that p adds 1 when face opens；
In the case that p is less than threshold value, if detecting, face is normal, and p is initialized as into 0；In the case where p is more than threshold value, illustrate this
When be to yawn, driver is in fatigue state, wherein：P is integer type variable, is counted with p, and p initial value is 0；
1.7 synthesis fatigues judge：According to step 1.5.2 and step 1.6.2, when detecting eye fatigue, or yawn, or both
When occurring simultaneously, tired alarm is provided, driver is stopped and rests or change driver.
2. the method for detecting fatigue driving based on eye and mouth state as described in claim 1, it is characterised in that described
Step 1.5 and step 1.6 are synchronous progress.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510229231.4A CN104809445B (en) | 2015-05-07 | 2015-05-07 | method for detecting fatigue driving based on eye and mouth state |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510229231.4A CN104809445B (en) | 2015-05-07 | 2015-05-07 | method for detecting fatigue driving based on eye and mouth state |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104809445A CN104809445A (en) | 2015-07-29 |
| CN104809445B true CN104809445B (en) | 2017-12-19 |
Family
ID=53694256
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510229231.4A Active CN104809445B (en) | 2015-05-07 | 2015-05-07 | method for detecting fatigue driving based on eye and mouth state |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104809445B (en) |
Families Citing this family (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105488957B (en) * | 2015-12-15 | 2018-06-12 | 小米科技有限责任公司 | Method for detecting fatigue driving and device |
| CN105631423A (en) * | 2015-12-29 | 2016-06-01 | 厦门瑞为信息技术有限公司 | Method for identifying human eye state by use of image information |
| CN105844252B (en) * | 2016-04-01 | 2019-07-26 | 南昌大学 | A kind of fatigue detection method of face key position |
| CN106203293A (en) * | 2016-06-29 | 2016-12-07 | 广州鹰瞰信息科技有限公司 | A kind of method and apparatus detecting fatigue driving |
| CN106485214A (en) * | 2016-09-28 | 2017-03-08 | 天津工业大学 | A kind of eyes based on convolutional neural networks and mouth state identification method |
| CN108932461A (en) * | 2017-05-27 | 2018-12-04 | 杭州海康威视数字技术股份有限公司 | A kind of fatigue detection method and device |
| CN107358151A (en) * | 2017-06-02 | 2017-11-17 | 广州视源电子科技股份有限公司 | Eye movement detection method and device and living body identification method and system |
| CN107292251B (en) * | 2017-06-09 | 2020-08-28 | 湖北天业云商网络科技有限公司 | Driver fatigue detection method and system based on human eye state |
| CN107578008B (en) * | 2017-09-02 | 2020-07-17 | 吉林大学 | Fatigue state detection method based on block feature matrix algorithm and SVM |
| CN107595307A (en) * | 2017-10-23 | 2018-01-19 | 湖南科技大学 | Fatigue driving detection device and detection method based on machine vision eye recognition |
| JP6711346B2 (en) * | 2017-12-13 | 2020-06-17 | オムロン株式会社 | State estimation apparatus, method and program therefor |
| CN108701214A (en) * | 2017-12-25 | 2018-10-23 | 深圳市大疆创新科技有限公司 | Image processing method, device and equipment |
| CN108647616A (en) * | 2018-05-01 | 2018-10-12 | 南京理工大学 | Real-time drowsiness detection method based on facial characteristics |
| CN108985245A (en) * | 2018-07-25 | 2018-12-11 | 深圳市飞瑞斯科技有限公司 | Determination method, apparatus, computer equipment and the storage medium of eye locations |
| CN109190515A (en) * | 2018-08-14 | 2019-01-11 | 深圳壹账通智能科技有限公司 | A kind of method for detecting fatigue driving, computer readable storage medium and terminal device |
| CN109409259A (en) * | 2018-10-11 | 2019-03-01 | 百度在线网络技术（北京）有限公司 | Drive monitoring method, device, equipment and computer-readable medium |
| CN109657550B (en) * | 2018-11-15 | 2020-11-06 | 中科院微电子研究所昆山分所 | Fatigue degree detection method and device |
| CN109409347A (en) * | 2018-12-27 | 2019-03-01 | 哈尔滨理工大学 | A method of based on facial features localization fatigue driving |
| CN109977820A (en) * | 2019-03-14 | 2019-07-05 | 重庆邮电大学 | A kind of fatigue driving determination method |
| JP7240910B2 (en) * | 2019-03-14 | 2023-03-16 | 本田技研工業株式会社 | Passenger observation device |
| CN110119676B (en) * | 2019-03-28 | 2023-02-03 | 广东工业大学 | Driver fatigue detection method based on neural network |
| CN110059599A (en) * | 2019-04-08 | 2019-07-26 | 盐城工学院 | Driving fatigue method for early warning |
| CN110077415A (en) * | 2019-04-23 | 2019-08-02 | 朱进军 | New-energy automobile safety monitoring system |
| CN110188655A (en) * | 2019-05-27 | 2019-08-30 | 上海蔚来汽车有限公司 | Driving condition evaluation method, system and computer storage medium |
| CN110309760A (en) * | 2019-06-26 | 2019-10-08 | 深圳市微纳集成电路与系统应用研究院 | The method that the driving behavior of driver is detected |
| CN111753674A (en) * | 2020-06-05 | 2020-10-09 | 广东海洋大学 | Fatigue driving detection and identification method based on deep learning |
| CN112016429A (en) * | 2020-08-21 | 2020-12-01 | 高新兴科技集团股份有限公司 | Fatigue driving detection method based on train cab scene |
| CN111950522A (en) * | 2020-08-27 | 2020-11-17 | 长沙理工大学 | Fatigue driving detection method based on human face features |
| CN114627450A (en) * | 2020-12-10 | 2022-06-14 | 北京巴塔科技有限公司 | Fatigue state detection device and fatigue detection method |
| CN115366909B (en) * | 2022-10-21 | 2023-04-07 | 四川省公路规划勘察设计研究院有限公司 | Dynamic early warning method and device for driver accidents in long and large longitudinal slope section and electronic equipment |
| CN116844219A (en) * | 2023-06-29 | 2023-10-03 | 深圳卓创智能科技有限公司 | Display method, device, equipment and storage medium for preventing eyestrain |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101281646A (en) * | 2008-05-09 | 2008-10-08 | 山东大学 | Method for real-time detection of driver fatigue based on vision |
| CN101732055A (en) * | 2009-02-11 | 2010-06-16 | 北京智安邦科技有限公司 | Method and system for testing fatigue of driver |
| CN102254151A (en) * | 2011-06-16 | 2011-11-23 | 清华大学 | Driver fatigue detection method based on face video analysis |
-
2015
- 2015-05-07 CN CN201510229231.4A patent/CN104809445B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101281646A (en) * | 2008-05-09 | 2008-10-08 | 山东大学 | Method for real-time detection of driver fatigue based on vision |
| CN101732055A (en) * | 2009-02-11 | 2010-06-16 | 北京智安邦科技有限公司 | Method and system for testing fatigue of driver |
| CN102254151A (en) * | 2011-06-16 | 2011-11-23 | 清华大学 | Driver fatigue detection method based on face video analysis |
Non-Patent Citations (2)
| Title |
|---|
| Face detection in color images;HsuRL;《IEEE transaction on pattern analysis and machine intelligence》;20021231;全文 * |
| Intelligent Driver drowsiness detedtion through fusion of yawning and eye closure;Omidyeganeh M;《international conference onvirtual environments human-computer interfaces and measurement systems》;20111231;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104809445A (en) | 2015-07-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104809445B (en) | method for detecting fatigue driving based on eye and mouth state | |
| CN107292251B (en) | Driver fatigue detection method and system based on human eye state | |
| CN106530623B (en) | A kind of fatigue driving detection device and detection method | |
| CN108446600A (en) | A kind of vehicle driver's fatigue monitoring early warning system and method | |
| Yan et al. | Real-time driver drowsiness detection system based on PERCLOS and grayscale image processing | |
| CN103714660B (en) | System for achieving fatigue driving judgment on basis of image processing and fusion between heart rate characteristic and expression characteristic | |
| CN112241658B (en) | Fatigue driving early warning method based on depth camera | |
| Abtahi et al. | Driver drowsiness monitoring based on yawning detection | |
| CN106846734B (en) | A kind of fatigue driving detection device and method | |
| CN107578008B (en) | Fatigue state detection method based on block feature matrix algorithm and SVM | |
| CN101593425B (en) | Machine vision based fatigue driving monitoring method and system | |
| Liu et al. | Driver fatigue detection through pupil detection and yawing analysis | |
| CN108309311A (en) | A kind of real-time doze of train driver sleeps detection device and detection algorithm | |
| Batista | A drowsiness and point of attention monitoring system for driver vigilance | |
| CN101593352A (en) | Driving safety monitoring system based on face orientation and visual focus | |
| CN107595307A (en) | Fatigue driving detection device and detection method based on machine vision eye recognition | |
| Tabrizi et al. | Open/closed eye analysis for drowsiness detection | |
| CN106548132A (en) | The method for detecting fatigue driving of fusion eye state and heart rate detection | |
| CN104881956A (en) | Fatigue driving early warning system | |
| Chen | Research on driver fatigue detection strategy based on human eye state | |
| CN107480629A (en) | A kind of method for detecting fatigue driving and device based on depth information | |
| CN110097012A (en) | The fatigue detection method of eye movement parameter monitoring based on N-range image processing algorithm | |
| Tabrizi et al. | Drowsiness detection based on brightness and numeral features of eye image | |
| JP4895874B2 (en) | Eye state determination device, eye state determination method, and eye state determination program | |
| CN104573743B (en) | A kind of facial image detection filter method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |