CN104809445A - Fatigue driving detection method based on eye and mouth states - Google Patents
Fatigue driving detection method based on eye and mouth states Download PDFInfo
- Publication number
- CN104809445A CN104809445A CN201510229231.4A CN201510229231A CN104809445A CN 104809445 A CN104809445 A CN 104809445A CN 201510229231 A CN201510229231 A CN 201510229231A CN 104809445 A CN104809445 A CN 104809445A
- Authority
- CN
- China
- Prior art keywords
- mouth
- image
- eye
- fatigue
- 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.)
- Granted
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
The invention belongs to the technical field of image processing and mode recognizing and relates to a fatigue driving detection method based on eye and mouth states. The method includes the steps of diver's video image acquisition, light compensation preprocessing, facial area detection, comprehensive fatigue judgment and fatigue alerting. The step of facial area detection includes eye detection and mouth detection; eye detection includes acquiring an eye area by means of a projection method, analyzing eye features, comparing the eye features to standard features, and performing k-means computation and eye fatigue judgment; mouth detection includes acquiring a mouth area by the mouth-map method, analyzing mouth features, comparing the mouth features to standard features, performing p-means computation and yawn judgement. According to the method, the eye feature parameter and the mouth feature parameter are combined for judgment; compared with the use of the single parameter, the method has higher rate and reliability of fatigue judgment; by the use of the method, traffic accidents caused by driver's fatigue driving can be greatly decreased; a new preventive measure is provided for ensuring life and property safety of drivers.
Description
Technical field
The invention belongs to image procossing and mode identification technology, be specifically related to the fatigue detection method of a kind of eye based on driver and mouth state.
Background technology
Along with developing rapidly of economy, the quantity of automobile is in continuous increase.Automobile is bringing traffic fast and easily simultaneously to the mankind, also for hidden danger has been buried in traffic safety, the fatigue driving of driver is the key factor causing traffic hazard.According to data statistics, the traffic hazard occurrence cause having 20% is fatigue driving, therefore makes in real time tired warning accurately to driver particularly important.
Through the research of experts and scholars' nearly decades, at present contact and contactless two classes are mainly contained to the detection method of driver fatigue:
One. contact, based on the detection of physiological driver's feature, this method needs to add some measuring equipments on the health of driver, detects the physiological parameter of driver, such as cardiogram, electroencephalogram, pulse etc.When driver fatigue, these physiological signals can change, and utilize the measurement variation of equipment to judge whether fatigue.
Two. contactless, be divided into the detection based on vehicle behavioural characteristic and the two kinds of methods of the detection based on Characteristics of drivers' behavior.Wherein, 1. based on the detection of vehicle behavioural characteristic: during driver fatigue, will reduce the Driving control ability of vehicle.Such as, when detect bearing circle for a long time motionless or conversion is frequent, car speed and angle of turn etc. are abnormal time, driver is just probably in fatigue state.Although this method can not disturb driving, due to the difference such as driving habits of condition of road surface, driver, be difficult to the accuracy ensureing testing result.2. based on the detection of Characteristics of drivers' behavior: judge that whether driver is tired by the eyes closed degree, frequency of wink, head position etc. that detect driver.When driver is in fatigue state, modal physiological behavior reaction is exactly that eyes close for a long time, frequency of wink reduces, cycle nictation is elongated, yawns, and head position exception etc., utilize the above-mentioned physiological reaction of Machine Vision Detection, treated identification just can judge that whether driver is tired.
In above-mentioned two class methods, the accuracy requirement of detection method to checkout equipment based on physiological driver's feature of contact is high, cost is high, and directly contacts with driver, can bring interference to driving.Although the detection method based on vehicle behavioural characteristic of contactless class can not disturb driving, due to the difference such as driving habits of condition of road surface, driver, be difficult to the accuracy ensureing testing result.Detection method based on Characteristics of drivers' behavior has driver noiseless, the advantage that accuracy is high and cost is low, is most widely used.This method normally detects face by image processing techniques, then extracts eyes, calculates the ratio in the unit interval shared by the eyes closed time based on PERCLOS principle, judges that whether driver is tired by comparing with threshold value.The testing requirement of this method to eyes is high, and in view of the ratio on face shared by eyes is relatively little, the size of human eye is also had any different, and judges that element is single, can cause the situation that tired judged result is undesirable.
Summary of the invention
The object of the present invention is to provide a kind of method for detecting fatigue driving based on eye and mouth state, improvement and bring new ideas in addition on the basis of fatigue detection method in the past, makes fatigue detection result even more ideal.
Method for detecting fatigue driving based on eye and mouth state of the present invention, comprises the following steps:
1. gather driver's video flowing, video flowing is converted to two field picture;
2. carry out the illumination compensation pre-service of image: with the brightness of pixel in " reference white " algorithm first detected image, obtain brightness value front 5% pixel, brightness value is set and is 255 at the gray-scale value of the pixel of front 5%, then to scale Serial regulation is carried out to RGB tri-components of image, obtain the image after illumination compensation;
3. detect human face region: the image after the illumination compensation that step 2 is obtained, distinguish colour of skin point and non-colour of skin point based on features of skin colors, obtain the bianry image of area of skin color, and the morphology processing of connectivity analysis is carried out to bianry image; Human face region is extracted with sciagraphy;
4. set eye and mouth feature primary standard value: suppose that driver is in waking state when entering pilothouse, the image this moment obtained is processed, the initial value of obtained eye state and mouth state is preserved as standard value;
5. carry out extraction and the signature analysis of ocular: horizontal and vertical projection is carried out to the human face region bianry image that step 3 obtains, be partitioned into the ocular comprising eyebrow, then carry out state analysis by this ocular feature, specifically comprise the following steps:
The ocular comprising eyebrow that the 5.1 pairs of steps 5 obtain carries out gray proces, obtain the gray level image of ocular, the x coordinate of this gray level image pixel is averaged, obtain the horizontal mean intensity of image slices vegetarian refreshments, average image there will be two obvious troughs, according to the difference of range difference d between two troughs, judge that eyes are opened or closed, the range difference d between two troughs initial pictures process obtained
0as with reference to standard, if d-d
0be greater than set threshold value, then eyes be judged to closure state, otherwise be normal condition;
5.2 eye fatigue judge: record the number of image frames that closes continuously of eyes with k, and when eyes closed often being detected, k adds 1, and when k is less than threshold value, if detect, eyes are opened, then k is initialized as 0; When k is greater than threshold value, illustrate it is not now nictation, be eye fatigue, wherein: k is integer type variable, counts with k, the initial value of k is 0;
6. carry out extraction and the signature analysis of mouth region: the latter half is got to the human face region that step 3 obtains, extract mouth region with following mathematic(al) representation, then carry out state analysis by this mouth region feature, specifically comprise the following steps:
Wherein:
c
rred chrominance component, C
bbe chroma blue component, n is human face region image slices vegetarian refreshments number, and η is C
r(x, y)
2mean value with
the estimation ratio of mean value;
The bianry image of 6.1 use mouth region, calculates the area s of mouth region; The mouth region area s obtained with initial pictures
0as reference standard value, the mouth region area s that calculating mouth region area s and initial pictures obtain
0ratio
if ratio is greater than set threshold value, be then judged as that face opens, otherwise be judged to normal; Wherein: the mouth region area s that mouth region area s and initial pictures obtain
0ratio
pixel number object ratio can be used
replace, n
0for initial mouth region pixel number, n is the mouth region pixel number of current frame image;
6.2 yawn judgement: the number of image frames of opening continuously with p value record face, and when often detecting that face opens, p adds 1; When p is less than threshold value, if detect, face is normal, then p is initialized as 0; When p is greater than threshold value, illustrate it is now yawning, driver is in fatigue state, and wherein: p is integer type variable, counts with p, the initial value of p is 0;
7. comprehensive tired judgement: according to step 5.2 and step 6.2, when eye fatigue being detected, or yawn, or when both occur, provide tired alarm simultaneously, driver is stopped and has a rest or change driver.
Above-mentioned step 5 and step 6 are synchronously carried out.
In conjunction with eye state and these two parameters of mouth state, the fatigue state to driver detects in the present invention.Wherein, when detecting eye state, make use of the changing features relation between eyebrow and eyes, and do not need eyes accurately to be detected, reducing hunting zone, is a kind of method of judgement eye state newly.In addition, even if when driver wears sunglasses or glasses, in conjunction with the detection to mouth feature, also can not cause undetected to the fatigue state of driver, make fatigue detecting effect even more ideal.
The present invention judges in conjunction with eye and mouth two characteristic parameters, compare the tired accuracy rate that judges with single parameter and reliability higher, enforcement of the present invention, can significantly reduce the traffic hazard caused due to driver tired driving, for ensureing the security of the lives and property of driver, provide a kind of new precautionary measures.
Accompanying drawing explanation
Fig. 1 is the process flow diagram 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
Fig. 3 is Detection results figure when normally opening eyes
Fig. 4 is the eyes gray-scale map of closed-eye state
Detection results figure when Fig. 5 is eyes closed
Embodiment
Below in conjunction with accompanying drawing, object of the present invention, concrete technical method and effect are described, so that those skilled in the art understands the present invention better.Present invention employs eye and whether mouth feature is tired to detect driver, as shown in Figure 1, the method comprises the following steps:
1. gather driver's video flowing, video flowing is converted to two field picture.
2. carry out the illumination compensation pre-service of image: illumination can change along with driving environment and time, very large on the extraction impact of features of skin colors, therefore first carry out illumination compensation, human face region can be extracted better.What use is a kind of " reference white " algorithm, first the brightness of pixel in detected image, obtain brightness value front 5% pixel, arranging brightness value at the average gray value of the pixel of front 5% is 255, by these pixels as " reference white ", then to scale Serial regulation is carried out to RGB tri-components of image, obtain the image after illumination compensation.
3. detect human face region: utilizing features of skin colors to detect face is a kind of rule of thumb.Image is transformed into HSV and YCbCr color space from RGB process, at YCbCr color space, luminance component Y and chrominance information CbCr is independently, utilizes the Clustering features of the colour of skin to be extracted by area of skin color well.At HSV color space, tone Hue has obvious different value at area of skin color and non-area of skin color.Following formula (1) is adopted to extract area of skin color:
C
r≥140 and C
r≤165 and C
b≥140and C
b≤195and
Hue≥0.01 and Hue≤0.1 (1)
Image after the illumination compensation that step 2 is obtained, utilize above-mentioned formula (1) to distinguish colour of skin point and non-colour of skin point, colour of skin point is set to 1, and non-colour of skin point is set to 0, obtain the bianry image of area of skin color, and the morphology processings such as connectivity analysis are carried out to bianry image; Find out face border with sciagraphy, then accurately extract human face region.
4. set eye and mouth feature primary standard value: the feature of waking state when entering pilothouse at first using driver, as with reference to standard, is preserved eigenwert now, compared with it by the eigenwert detected in driving procedure, and make whether tired judgement.Suppose that driver is in waking state when entering pilothouse, the image this moment obtained is processed, the initial value of obtained eye state and mouth state is preserved as standard value.
5. carry out extraction and the signature analysis of ocular: judge that opening of eyes is closed according to eyelid to the height h of eyebrow, when the eyes are occluded, eyelid movement is to eyes foot, and now height h is maximum; When normally opening eyes, eyelid movement is to eyes top, and now height h is minimum.Horizontal and vertical projection is carried out to the human face region bianry image that step 3 obtains, is partitioned into the ocular comprising eyebrow, then by above-mentioned principle, state analysis is carried out to this ocular feature, specifically comprise the following steps:
The ocular comprising eyebrow that the 5.1 pairs of steps 5 obtain carries out gray proces, obtain the gray level image of ocular, as shown in Figure 2 and Figure 4, the x coordinate of this gray level image is averaged, average image there will be two obvious troughs, according to the difference of range difference d between two troughs, can judge that eyes are opened or closed.Composition graphs 3 and Fig. 5 analysis, the range difference d between two troughs that initial pictures process is obtained
0as with reference to standard, if d-d
0be greater than set threshold value, then eyes be judged to closure state, otherwise be normal condition.
5.2 eye fatigue judge: general blink duration is about 0.3 second, exceed this time and then illustrate that driver may be in eye closing sleep state.By the number of image frames that k value record eyes close continuously, by k value and setting threshold value k
0comparison, judge whether blinking.K initial value is set to 0, and whenever eyes closed being detected, k adds 1.Threshold value k is less than at k
0when, if detect, eyes are opened, then k is initialized as 0; At k
0be greater than threshold value k
0when, illustrating it is not now nictation, is eye fatigue; Wherein: k is integer type variable, counts, k with k
0it is the number of image frames that the longest blink duration is corresponding.
6. carry out extraction and the signature analysis of mouth region: mouth, in the latter half of face, is only got face Lower Half and done detection and can improve detection efficiency and accuracy.In mouth region, redness is the strongest, and blueness is the most weak, and lip look and the colour of skin exist certain difference, gets the latter half to the human face region that step 3 obtains, and extracts mouth region with following mathematic(al) representation (2).When people is in fatigue state, except eyes close for a long time, also along with yawning phenomenon.When yawning, the amplitude that face opens is very large, and now the area in face region will be larger than area time normal, and the number of corresponding pixel also can many than time normal.By above-mentioned principle, state analysis is carried out to mouth provincial characteristics, specifically comprise the following steps:
Wherein:
c
rred chrominance component, C
bbe chroma blue component, n is human face region image slices vegetarian refreshments number, and η is C
r(x, y)
2mean value with
the estimation ratio of mean value;
The lip look region of extracting is converted to bianry image by 6.1, through burn into expansion, finds out largest connected territory, and does to fill process to pertusate face region, then calculates the area s of mouth region; The mouth region area s obtained with initial pictures
0as reference standard value, the mouth region area s that the area s of calculating mouth region and initial pictures obtain
0ratio
if ratio is greater than set threshold value, be then judged as that face opens, otherwise be judged to normal; Wherein: the mouth region area s that the area s of mouth region and initial pictures obtain
0ratio
pixel number object ratio can be used
replace, n
0for initial mouth region pixel number, n is the mouth region pixel number of current frame image.
6.2 yawn judgement: driver needs the situation of magnifying few when speaking, even if there are the needs of magnifying also can not last very long, can be far smaller than the yawning time.Once the yawning time is approximately 5 seconds more than to generalized case servant, the number of image frames of opening continuously with p value record face, and p initial value is 0, often detects that face opens p and adds 1; Threshold value p is less than at p
0when, if detect, face is normal, then p is initialized as 0; Threshold value p is greater than at p
0when, illustrate it is now yawning, driver is in fatigue state.Wherein: p is integer type variable, counts, p with p
0it is number of image frames corresponding in the time in 5 seconds.
7. comprehensive tired judgement: according to step 5.2 and step 6.2, when eye fatigue being detected, or yawn, or when both occur, provide tired alarm simultaneously, driver is stopped and has a rest or change driver.
Above-mentioned step 5.2 and step 6.2 are synchronously carried out.
Claims (2)
1., based on a method for detecting fatigue driving for eye and mouth state, it is characterized in that comprising the following steps:
1.1 gather driver's video flowing, and video flowing is converted to two field picture;
The 1.2 illumination compensation pre-service carrying out image: with the brightness of pixel in " reference white " algorithm first detected image, obtain brightness value front 5% pixel, brightness value is set and is 255 at the gray-scale value of the pixel of front 5%, then to scale Serial regulation is carried out to RGB tri-components of image, obtain the image after illumination compensation;
1.3 detect human face region: the image after the illumination compensation obtain step 1.2, distinguish colour of skin point and non-colour of skin point, obtain the bianry image of area of skin color, and carry out the morphology processing of connectivity analysis to bianry image based on features of skin colors; Human face region is extracted with sciagraphy;
1.4 setting eyes and mouth feature primary standard values: supposing that driver is in waking state when entering pilothouse, processing the image obtained this moment, preserve the initial value of obtained eye state and mouth state as standard value;
1.5 extraction and the signature analysises carrying out ocular: horizontal and vertical projection is carried out to the human face region bianry image that step 1.3 obtains, be partitioned into the ocular comprising eyebrow, then carry out state analysis by this ocular feature, specifically comprise the following steps:
1.5.1 gray proces is carried out to the ocular comprising eyebrow that step 1.5 obtains, obtain the gray level image of ocular, the x coordinate of this gray level image pixel is averaged, obtain the horizontal mean intensity of image slices vegetarian refreshments, average image there will be two obvious troughs, according to the difference of range difference d between two troughs, judge that eyes are opened or closed, the range difference d between two troughs initial pictures process obtained
0as with reference to standard, if d-d
0be greater than set threshold value, then eyes be judged to closure state, otherwise be normal condition;
1.5.2 eye fatigue judges: record the number of image frames that closes continuously of eyes with k, and when eyes closed often being detected, k adds 1, and when k is less than threshold value, if detect, eyes are opened, then k is initialized as 0; When k is greater than threshold value, illustrate it is not now nictation, be eye fatigue, wherein: k is integer type variable, counts with k, the initial value of k is 0;
1.6 extraction and the signature analysises carrying out mouth region: get the latter half to the human face region that step 1.3 obtains, extract mouth region with following mathematic(al) representation, then carry out state analysis by this mouth region feature, specifically comprise the following steps:
Wherein:
c
rred chrominance component, C
bbe chroma blue component, n is human face region image slices vegetarian refreshments number, and η is C
r(x, y)
2mean value with
the estimation ratio of mean value;
1.6.1 use the bianry image of mouth region, calculate the area s of mouth region; The mouth region area s obtained with initial pictures
0as reference standard value, the mouth region area s that calculating mouth region area s and initial pictures obtain
0ratio
if ratio is greater than set threshold value, be then judged as that face opens, otherwise be judged to normal; Wherein: the mouth region area s that mouth region area s and initial pictures obtain
0ratio
pixel number object ratio can be used
replace, n
0for initial mouth region pixel number, n is the mouth region pixel number of current frame image;
1.6.2 to yawn judgement: the number of image frames of opening continuously with p value record face, when often detecting that face opens, p adds 1; When p is less than threshold value, if detect, face is normal, then p is initialized as 0; When p is greater than threshold value, illustrate it is now yawning, driver is in fatigue state, and wherein: p is integer type variable, counts with p, the initial value of p is 0;
1.7 comprehensive tired judgements: according to step 1.5.2 and step 1.6.2, when eye fatigue being detected, or yawn, or when both occur, provide tired alarm simultaneously, driver is stopped and has a rest or change driver.
2., by the method for detecting fatigue driving based on eye and mouth state according to claim 1, it is characterized in that described step 1.5 and step 1.6 are synchronously carried out.
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 true CN104809445A (en) | 2015-07-29 |
| CN104809445B 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) |
Cited By (30)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105488957A (en) * | 2015-12-15 | 2016-04-13 | 小米科技有限责任公司 | Fatigue driving detection method and apparatus |
| 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 |
| CN105844252A (en) * | 2016-04-01 | 2016-08-10 | 南昌大学 | Face key part fatigue detection method |
| 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 |
| CN107292251A (en) * | 2017-06-09 | 2017-10-24 | 湖北天业云商网络科技有限公司 | A kind of Driver Fatigue Detection and system based on human eye state |
| CN107358151A (en) * | 2017-06-02 | 2017-11-17 | 广州视源电子科技股份有限公司 | A kind of eye motion detection method and device and vivo identification method and system |
| CN107578008A (en) * | 2017-09-02 | 2018-01-12 | 吉林大学 | Fatigue state detection method based on blocking characteristic 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 |
| CN108647616A (en) * | 2018-05-01 | 2018-10-12 | 南京理工大学 | Real-time drowsiness detection method based on facial characteristics |
| 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 |
| 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 |
| 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 |
| 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 |
| 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 |
| CN109657550A (en) * | 2018-11-15 | 2019-04-19 | 中科院微电子研究所昆山分所 | A kind of fatigue strength detection method and device |
| CN109977820A (en) * | 2019-03-14 | 2019-07-05 | 重庆邮电大学 | A kind of fatigue driving determination method |
| CN110025324A (en) * | 2017-12-13 | 2019-07-19 | 欧姆龙株式会社 | Device for estimating state, estimating state method and recording medium |
| 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 |
| CN110119676A (en) * | 2019-03-28 | 2019-08-13 | 广东工业大学 | A kind of Driver Fatigue Detection neural network based |
| 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***应用研究院 | The method that the driving behavior of driver is detected |
| WO2020034541A1 (en) * | 2018-08-14 | 2020-02-20 | 深圳壹账通智能科技有限公司 | Driver drowsiness detection method, computer readable storage medium, terminal device, and apparatus |
| CN111688709A (en) * | 2019-03-14 | 2020-09-22 | 本田技研工业株式会社 | Passenger observation device |
| CN111753674A (en) * | 2020-06-05 | 2020-10-09 | 广东海洋大学 | Fatigue driving detection and identification method based on deep learning |
| CN111950522A (en) * | 2020-08-27 | 2020-11-17 | 长沙理工大学 | Fatigue driving detection method based on human face features |
| 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 |
| 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 |
| CN115366909A (en) * | 2022-10-21 | 2022-11-22 | 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 |
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 |
|---|
| HSURL: "Face detection in color images", 《IEEE TRANSACTION ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE》 * |
| OMIDYEGANEH M: "Intelligent Driver drowsiness detedtion through fusion of yawning and eye closure", 《INTERNATIONAL CONFERENCE ONVIRTUAL ENVIRONMENTS HUMAN-COMPUTER INTERFACES AND MEASUREMENT SYSTEMS》 * |
Cited By (35)
| 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 |
| CN105488957A (en) * | 2015-12-15 | 2016-04-13 | 小米科技有限责任公司 | Fatigue driving detection method and apparatus |
| 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 |
| CN105844252A (en) * | 2016-04-01 | 2016-08-10 | 南昌大学 | Face key part fatigue detection method |
| 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 | A kind of eye motion detection method and device and vivo 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 |
| CN107292251A (en) * | 2017-06-09 | 2017-10-24 | 湖北天业云商网络科技有限公司 | A kind of Driver Fatigue Detection and system based on human eye state |
| CN107578008A (en) * | 2017-09-02 | 2018-01-12 | 吉林大学 | Fatigue state detection method based on blocking characteristic matrix algorithm and SVM |
| 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 |
| CN110025324A (en) * | 2017-12-13 | 2019-07-19 | 欧姆龙株式会社 | Device for estimating state, estimating state method and recording medium |
| 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 |
| WO2020034541A1 (en) * | 2018-08-14 | 2020-02-20 | 深圳壹账通智能科技有限公司 | Driver drowsiness detection method, computer readable storage medium, terminal device, and apparatus |
| 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 |
| CN109657550A (en) * | 2018-11-15 | 2019-04-19 | 中科院微电子研究所昆山分所 | A kind of fatigue strength 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 |
| CN111688709A (en) * | 2019-03-14 | 2020-09-22 | 本田技研工业株式会社 | 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 |
| CN110119676A (en) * | 2019-03-28 | 2019-08-13 | 广东工业大学 | A kind of Driver Fatigue Detection neural network based |
| 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***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 |
| CN115366909A (en) * | 2022-10-21 | 2022-11-22 | 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104809445B (en) | 2017-12-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104809445A (en) | Fatigue driving detection method based on eye and mouth states | |
| CN106530623B (en) | A kind of fatigue driving detection device and detection method | |
| Yan et al. | Real-time driver drowsiness detection system based on PERCLOS and grayscale image processing | |
| CN107292251B (en) | Driver fatigue detection method and system based on human eye state | |
| 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 | |
| Abtahi et al. | Driver drowsiness monitoring based on yawning detection | |
| Liu et al. | Drowsiness detection based on eyelid movement | |
| Nguyen et al. | Eye tracking system to detect driver drowsiness | |
| CN112241658B (en) | Fatigue driving early warning method based on depth camera | |
| CN108446600A (en) | A kind of vehicle driver's fatigue monitoring early warning system and method | |
| CN108053615A (en) | Driver tired driving condition detection method based on micro- expression | |
| CN106846734A (en) | A kind of fatigue driving detection device and method | |
| CN101593352A (en) | Driving safety monitoring system based on face orientation and visual focus | |
| CN106250801A (en) | Based on Face datection and the fatigue detection method of human eye state identification | |
| Tabrizi et al. | Open/closed eye analysis for drowsiness detection | |
| Liu et al. | A practical driver fatigue detection algorithm based on eye state | |
| CN109977930A (en) | Method for detecting fatigue driving and device | |
| CN102662470B (en) | A kind of method and system realizing eye operation | |
| Luo et al. | The driver fatigue monitoring system based on face recognition technology | |
| CN104809482A (en) | Fatigue detecting method based on individual learning | |
| Chen | Research on driver fatigue detection strategy based on human eye state | |
| CN103729646A (en) | Eye image validity detection method | |
| CN107480629A (en) | A kind of method for detecting fatigue driving and device based on depth information | |
| Tabrizi et al. | Drowsiness detection based on brightness and numeral features of eye image |
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 |