CN109145852A - A kind of driver fatigue state recognition method for opening closed state based on eyes - Google Patents
A kind of driver fatigue state recognition method for opening closed state based on eyes Download PDFInfo
- Publication number
- CN109145852A CN109145852A CN201811009416.4A CN201811009416A CN109145852A CN 109145852 A CN109145852 A CN 109145852A CN 201811009416 A CN201811009416 A CN 201811009416A CN 109145852 A CN109145852 A CN 109145852A
- Authority
- CN
- China
- Prior art keywords
- driver
- eyeball
- eye
- fatigue
- state
- 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
- 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
- G06V40/18—Eye characteristics, e.g. of the iris
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Ophthalmology & Optometry (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Image Analysis (AREA)
- Traffic Control Systems (AREA)
- Eye Examination Apparatus (AREA)
Abstract
The invention discloses a kind of driver fatigue state recognition methods that closed state is opened based on eyes, including step 1: acquisition driver's video simultaneously carries out sub-frame processing, determines driver's face location;Step 2: driver eye positions being determined using calculus of finite differences, and Corner Detection is carried out to the white of the eye and eyeball boundary based on Harris algorithm, the area S for exposing eyeball are determined, as S≤0.35S0When, S0The area of eyeball when opening completely for human eye, then human eye is in closed-eye state;Step 3: determining driving fatigue coefficient k;Step 4: as k≤15%, driver is in waking state;As 15% < k≤50%, driver is in level-one fatigue, should remind driver;As k > 50%, driver is in second level fatigue, should sound an alarm, if driver is reactionless, force to stop.Framing can be carried out to driver's driving video and extracts image, and determining eyeball area is to determine that human eye opens closed state, it is as a result more acurrate to determine driver fatigue state according to driving fatigue coefficient.
Description
Technical field
The present invention relates to driving safety technical fields, and more particularly, the present invention relates to one kind to open closed state based on eyes
Driver fatigue state recognition method.
Background technique
Nowadays driver fatigue detection technique is more and more mature, and fatigue detection method can be divided mainly into three classes: based on driving
The person's of sailing behavioural characteristic, the detection method based on physiological driver's parameter and based on vehicle behavior feature.It is special according to driving behavior
Sign is detected: the behavioural characteristic of driver mainly includes two aspect of facial characteristics variation and hand exercise.Facial characteristics is main
Including head pose, eye state and mouth state;Hand exercise mainly includes the dynamics and rotation angle for operating steering wheel.It drives
The person's of sailing physiological parameter mainly includes electroencephalogram, electrocardiogram etc., but driver need to wear corresponding experimental facilities when due to detection,
There is certain interference for manipulation automobile, therefore applies and be subject to certain restrictions.Vehicle behavior mainly pass through detection direction disk corner,
The parameters such as car speed and angle of turn.
It is carried out in tired judgement existing based on the variation of driver's facial characteristics, when being judged by mouth, mainly
It is identified according to the opening width of mouth, but mouth opening width is very big when driver speaks or laughs at, will affect detection
Effect, accuracy reduce;It is main to be identified according to frequency of nodding when based on head pose, it needs to establish the three-dimensional of head and sits
Mark, as basic point with body certain point, it is also necessary to carry out projective transformation, and it is sometimes tired when can also lateral deviation head, it is computationally intensive;
When based on eyes closed degree, be broadly divided into two methods: the black picture element of eyeball is converted and is carried out based on perclos criterion
The state recognition of eyes, above-mentioned three kinds of methods can only carry out tired judgement, in the form of a single.
Summary of the invention
The present invention has designed and developed a kind of driver fatigue state recognition method that closed state is opened based on eyes, can be to driving
The person's of sailing driving video carries out framing and extracts image, and determines eyeball area to determine that human eye opens closed state, according to driving fatigue
Coefficient determines driver fatigue state, as a result more acurrate.
Technical solution provided by the invention are as follows:
A kind of driver fatigue state recognition method for being opened closed state based on eyes, is included the following steps:
Step 1: acquisition driver's video simultaneously carries out sub-frame processing, determines driver's face location;
Step 2: driver eye positions being determined using calculus of finite differences, and based on Harris algorithm to the white of the eye and eyeball boundary
Corner Detection is carried out, the area S for exposing eyeball is determined, as S≤0.35S0When, S0The area of eyeball when being opened completely for human eye, then
Human eye is in closed-eye state;
Step 3: determining driving fatigue coefficient are as follows:
Work as T0When > 0,
Work as T0When < 0,
Work as T0When=0,
Wherein, T0For environment temperature, T is vehicle interior temperature, and α is rainfall, and β is snowfall, and G is uitraviolet intensity, f (v),
G (v) is velocity function, and v is speed, and k is driving fatigue coefficient, and e is the truth of a matter of natural logrithm, N1For eye closing frame number, N is sum
Frame number;
Step 4: as k≤15%, driver is in waking state;
As 15% < k≤50%, driver is in level-one fatigue, should remind driver;
As k > 50%, driver is in second level fatigue, should sound an alarm, if driver is reactionless, force to stop.
Preferably, it in the step 1, acquires driver's video and extracts every frame image, be based on after pretreatment
Adaboost algorithm determines driver's face location.
Preferably, it in the step 2, chooses driver's top half face image and carries out difference, and not move
Background image of the image of target as difference.
Preferably, described to include: to the white of the eye and eyeball boundary progress Corner Detection based on Harris algorithm
Every frame image I (x, y) is calculated in the gradient I of x and y both directionx,Iy,
In formula,For convolution;
Calculate image I (x, y) x and y both direction product,
Ixx=Ix 2,Iyy=Iy 2,Ixy=Ix·Iy;
Using Gaussian function to Ix 2,Iy 2,Ix·IyGauss weighting is carried out, elements A, B, C of matrix M is obtained,
In formula, w is Gaussian function;
The Harris response R of each pixel is calculated, and zero is set to the R less than a certain threshold value t,
R={ R:detM- α (traceM)2< t },
In formula, detM is the determinant of matrix M, and traceM is the straight mark of matrix M, and α is empirical;
Non-maxima suppression is carried out in neighborhood, and determines the angle point in image.
Preferably, it is described expose eyeball area determination include:
When human eye is just opened completely, the angle point of three white of the eye and eyeball boundary is determined, then eyeball when human eye is opened completely
Area S0Are as follows:
In formula, a, b, c are respectively the linear distance between adjacent corner points;
When eyes have certain closure, it is based on Harris algorithm, determines the point in upper eyelid Yu eyeball demarcation line, this
When eyeball area S are as follows:
In formula, linear distance of the h between upper eyelid and the point of eyeball demarcation line.
Preferably, when continuous 5 frame image does not detect angle point, judge that driver is in sleep state.
It is of the present invention the utility model has the advantages that
(1) driver fatigue state recognition method of the present invention that closed state is opened based on eyes, can be to driver
Driving video carries out framing and extracts image, and determines eyeball area to determine that human eye opens closed state, according to driving fatigue coefficient
Determine driver fatigue state, it is as a result more acurrate.
(2) the present invention is based on the detection that Harris algorithm carries out eyes, it can not only differentiate the state of driver, it can be with
Judge the direction of motion of driver head, can be to prepare to turn left or turn right according to head movement walking direction vehicle.And
The area of black eyeball need to only be calculated when judge by carrying out fatigue, and calculation amount is small, detection accuracy height, and the white of the eye and black eyeball
Gray scale difference is very big, small by external interference, improves the effect of detection.
Detailed description of the invention
Fig. 1 is the flow chart of the driver fatigue state recognition method of the present invention that closed state is opened based on eyes.
Specific embodiment
Present invention will be described in further detail below with reference to the accompanying drawings, to enable those skilled in the art referring to specification text
Word can be implemented accordingly.
As shown in Figure 1, the present invention provides a kind of driver fatigue state recognition method that closed state is opened based on eyes, including
Following steps:
Step 1: acquisition driver's video simultaneously carries out sub-frame processing, determines driver's face location:
Frame image every for driver's video extraction of acquisition, is pre-processed, and interference and the enhancing image of noise are reduced
Effect carries out the positioning of face using adaboost algorithm.
Step 2: driver eye positions are determined using calculus of finite differences:
When carrying out the positioning of eyes with calculus of finite differences, in order to reduce calculation amount and improve accuracy, according to point of face
Cloth feature, interception top half facial image carry out difference.A frame is selected not have moving target at the beginning of motion detection
Background image of the image as difference, occur that present image and background image is started to do difference when moving target, when
At the end of moving object detection, background image is updated, carries out difference again when next moving target occurs.The knot of difference
Fruit can remove a part of noise, and can remove the static background region unrelated with moving object detection, using Background
As update mechanism, the variation of background and light can also be adapted to a certain extent.After carrying out difference processing, difference image
In only leave moving target and partial noise, be filtered hot-tempered processing again at this time.
Step 3: and Corner Detection is carried out to the white of the eye and eyeball boundary based on Harris algorithm, it specifically includes:
Every frame image I (x, y) is calculated in the gradient I of x and y both directionx,Iy,
In formula,For convolution;
Calculate image I (x, y) x and y both direction product,
Ixx=Ix 2,Iyy=Iy 2,Ixy=Ix·Iy;
Using Gaussian function to Ix 2,Iy 2,Ix·IyGauss weighting is carried out, elements A, B, C of matrix M is obtained,
In formula, w is Gaussian function;
The Harris response R of each pixel is calculated, and zero is set to the R less than a certain threshold value t,
R={ R:detM- α (traceM)2< t },
In formula, detM is the determinant of matrix M, and traceM is the straight mark of matrix M, and α is empirical;
Non-maxima suppression is carried out in neighborhood, and determines the angle point (i.e. Local modulus maxima) in image, and mobile is small
Window is smaller, and the angle point of detection is more accurate, therefore selects 3*3 size.
Certainly, when continuous 5 frame image does not detect angle point, judge that driver is in sleep state.
Step 4: determine the area S for exposing eyeball:
When human eye is just opened completely, the angle point of three white of the eye and eyeball boundary is determined, then eyeball when human eye is opened completely
Area S0Are as follows:
In formula, a, b, c are respectively the linear distance between adjacent corner points;
When eyes have certain closure, it is based on Harris algorithm, determines the point in upper eyelid Yu eyeball demarcation line, this
When eyeball area S are as follows:
In formula, linear distance of the h between upper eyelid and the point of eyeball demarcation line.
As S≤0.35S0When, then human eye is in closed-eye state.
Step 5: determining driving fatigue coefficient are as follows:
Work as T0When > 0,
Work as T0When < 0,
Work as T0When=0,
Wherein, T0For environment temperature (DEG C), T is vehicle interior temperature (DEG C), and α is rainfall (m), and β is snowfall (m), and G is purple
Outside line intensity (between 0~15), f (v), g (v) are velocity function, and v is speed (km/h), and k is driving fatigue coefficient, and e is nature
The truth of a matter of logarithm, N1For eye closing frame number, N is total frame number.
Step 6: as k≤15%, driver is in waking state;
As 15% < k≤50%, driver is in level-one fatigue, should remind driver;
As k > 50%, driver is in second level fatigue, should sound an alarm, if driver is reactionless, force to stop.
The driver fatigue state recognition method of the present invention that closed state is opened based on eyes can drive driver
Video carries out framing and extracts image, and determines eyeball area to determine that human eye opens closed state, to determine according to driving fatigue coefficient
Driver fatigue state, it is as a result more acurrate.
The present invention is based on the detections that Harris algorithm carries out eyes, can not only differentiate the state of driver, can also sentence
The direction of motion of disconnected driver head can be prepared to turn left or turn right according to head movement walking direction vehicle.And into
Row fatigue need to only calculate the area of black eyeball when judging, calculation amount is small, and detection accuracy is high, and the ash of the white of the eye and black eyeball
Degree difference is very big, small by external interference, improves the effect of detection.
Although the embodiments of the present invention have been disclosed as above, but its is not only in the description and the implementation listed
With it can be fully applied to various fields suitable for the present invention, for those skilled in the art, can be easily
Realize other modification, therefore without departing from the general concept defined in the claims and the equivalent scope, the present invention is simultaneously unlimited
In specific details and legend shown and described herein.
Claims (6)
1. a kind of driver fatigue state recognition method for opening closed state based on eyes, which comprises the steps of:
Step 1: acquisition driver's video simultaneously carries out sub-frame processing, determines driver's face location;
Step 2: driver eye positions being determined using calculus of finite differences, and the white of the eye and eyeball boundary are carried out based on Harris algorithm
Corner Detection determines the area S for exposing eyeball, as S≤0.35S0When, S0The area of eyeball when being opened completely for human eye, then human eye
In closed-eye state;
Step 3: determining driving fatigue coefficient are as follows:
Work as T0When > 0,
Work as T0When < 0,
Work as T0When=0,
Wherein, T0For environment temperature, T is vehicle interior temperature, and α is rainfall, and β is snowfall, and G is uitraviolet intensity, f (v), g (v)
For velocity function, v is speed, and k is driving fatigue coefficient, and e is the truth of a matter of natural logrithm, N1For eye closing frame number, N is total frame
Number;
Step 4: as k≤15%, driver is in waking state;
As 15% < k≤50%, driver is in level-one fatigue, should remind driver;
As k > 50%, driver is in second level fatigue, should sound an alarm, if driver is reactionless, force to stop.
2. the driver fatigue state recognition method of closed state is opened based on eyes as described in claim 1, which is characterized in that institute
It states in step 1, acquire driver's video and extracts every frame image, driver face is determined based on adaboost algorithm after pretreatment
Position.
3. the driver fatigue state recognition method of closed state is opened based on eyes as described in claim 1, which is characterized in that institute
It states in step 2, chooses driver's top half face image and carry out difference, and using the image of not moving target as difference
Background image.
4. the driver fatigue state recognition method of closed state is opened based on eyes as claimed in claim 3, which is characterized in that institute
It states and includes: to the white of the eye and eyeball boundary progress Corner Detection based on Harris algorithm
Every frame image I (x, y) is calculated in the gradient I of x and y both directionx,Iy,
In formula,For convolution;
Calculate image I (x, y) x and y both direction product,
Ixx=Ix 2,Iyy=Iy 2,Ixy=Ix·Iy;
Using Gaussian function to Ix 2,Iy 2,Ix·IyGauss weighting is carried out, elements A, B, C of matrix M is obtained,
In formula, w is Gaussian function;
The Harris response R of each pixel is calculated, and zero is set to the R less than a certain threshold value t,
R={ R:detM- α (traceM)2< t },
In formula, detM is the determinant of matrix M, and traceM is the straight mark of matrix M, and α is empirical;
Non-maxima suppression is carried out in neighborhood, and determines the angle point in image.
5. the driver fatigue state recognition method of closed state is opened based on eyes as claimed in claim 4, which is characterized in that institute
State expose eyeball area determination include:
When human eye is just opened completely, the angle point of three white of the eye and eyeball boundary is determined, then the face of eyeball when human eye is opened completely
Product S0Are as follows:
In formula, a, b, c are respectively the linear distance between adjacent corner points;
When eyes have certain closure, it is based on Harris algorithm, determines the point in upper eyelid Yu eyeball demarcation line, at this time eye
The area S of ball are as follows:
In formula, linear distance of the h between upper eyelid and the point of eyeball demarcation line.
6. the driver fatigue state recognition method of closed state is opened based on eyes as claimed in claim 5, which is characterized in that when
When continuous 5 frame image does not detect angle point, judge that driver is in sleep state.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811009416.4A CN109145852B (en) | 2018-08-31 | 2018-08-31 | Driver fatigue state identification method based on eye opening and closing state |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811009416.4A CN109145852B (en) | 2018-08-31 | 2018-08-31 | Driver fatigue state identification method based on eye opening and closing state |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109145852A true CN109145852A (en) | 2019-01-04 |
CN109145852B CN109145852B (en) | 2022-06-17 |
Family
ID=64825878
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811009416.4A Active CN109145852B (en) | 2018-08-31 | 2018-08-31 | Driver fatigue state identification method based on eye opening and closing state |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109145852B (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109703340A (en) * | 2019-02-12 | 2019-05-03 | 合肥京东方光电科技有限公司 | A kind of adjusting method of sunshading board, automobile and sunshading board |
CN109878304A (en) * | 2019-03-29 | 2019-06-14 | 合肥京东方光电科技有限公司 | Sunshading board, sunshading board control method and automobile |
CN111741250A (en) * | 2020-07-07 | 2020-10-02 | 全时云商务服务股份有限公司 | Method, device and equipment for analyzing participation degree of video conversation scene and storage medium |
CN113449670A (en) * | 2021-07-09 | 2021-09-28 | 浙江正元智慧科技股份有限公司 | Drowsiness detection method based on human eye state |
CN113449584A (en) * | 2020-03-24 | 2021-09-28 | 丰田自动车株式会社 | Eye opening degree calculation device |
CN113703335A (en) * | 2021-10-27 | 2021-11-26 | 江苏博子岛智能产业技术研究院有限公司 | Intelligent home brain control system based on internet of things and provided with brain-computer interface |
CN116469085A (en) * | 2023-03-30 | 2023-07-21 | 万联易达物流科技有限公司 | Monitoring method and system for risk driving behavior |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080062297A1 (en) * | 2006-09-08 | 2008-03-13 | Sony Corporation | Image capturing and displaying apparatus and image capturing and displaying method |
CN102054163A (en) * | 2009-10-27 | 2011-05-11 | 南京理工大学 | Method for testing driver fatigue based on monocular vision |
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 |
CN206914227U (en) * | 2017-06-22 | 2018-01-23 | 辽宁工业大学 | A kind of steering wheel deviates alarm set |
CN107943061A (en) * | 2018-01-09 | 2018-04-20 | 辽宁工业大学 | A kind of model automobile automatic Pilot experimental provision and method based on machine vision |
CN108309311A (en) * | 2018-03-27 | 2018-07-24 | 北京华纵科技有限公司 | A kind of real-time doze of train driver sleeps detection device and detection algorithm |
-
2018
- 2018-08-31 CN CN201811009416.4A patent/CN109145852B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080062297A1 (en) * | 2006-09-08 | 2008-03-13 | Sony Corporation | Image capturing and displaying apparatus and image capturing and displaying method |
CN102054163A (en) * | 2009-10-27 | 2011-05-11 | 南京理工大学 | Method for testing driver fatigue based on monocular vision |
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 |
CN206914227U (en) * | 2017-06-22 | 2018-01-23 | 辽宁工业大学 | A kind of steering wheel deviates alarm set |
CN107943061A (en) * | 2018-01-09 | 2018-04-20 | 辽宁工业大学 | A kind of model automobile automatic Pilot experimental provision and method based on machine vision |
CN108309311A (en) * | 2018-03-27 | 2018-07-24 | 北京华纵科技有限公司 | A kind of real-time doze of train driver sleeps detection device and detection algorithm |
Non-Patent Citations (10)
Title |
---|
DONALD E.ROBERTS等: "PREVENTION OF COLD INJURIES", 《MEDICAL ASPECTS OF HARSH ENVIRONMENT》 * |
吴昊: "高寒高海拔地区公路交通事故分析与预防对策研究——以青藏公路为例", 《中国优秀博硕士学位论文全文数据库(硕士)工程科技II辑》 * |
喻贵银: "大地雄魂――记国家***第一大地测量队", 《中国测绘》 * |
应建明: "浅析驾驶员疲劳驾驶监测技术", 《驾驶园》 * |
张军辉等: "恶劣环境中车辆执行伤员后送任务分析", 《科技创新导报》 * |
张志文等: "基于眼球运动状态检测的疲劳预警***研究", 《计算机与数字工程》 * |
肖赛等: "驾驶疲劳致因及监测研究进展", 《交通科技与经济》 * |
舒梅等: "基于累积帧差的人眼定位及模板提取", 《西华大学学报(自然科学版)》 * |
蒋文博等: "一种快速驾驶员疲劳检测方法", 《电子设计工程》 * |
黄家才等: "基于人脸关键点的疲劳驾驶检测研究", 《南京工程学院学报(自然科学版)》 * |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109703340A (en) * | 2019-02-12 | 2019-05-03 | 合肥京东方光电科技有限公司 | A kind of adjusting method of sunshading board, automobile and sunshading board |
CN109878304A (en) * | 2019-03-29 | 2019-06-14 | 合肥京东方光电科技有限公司 | Sunshading board, sunshading board control method and automobile |
CN113449584A (en) * | 2020-03-24 | 2021-09-28 | 丰田自动车株式会社 | Eye opening degree calculation device |
CN113449584B (en) * | 2020-03-24 | 2023-09-26 | 丰田自动车株式会社 | Eye opening degree calculating device |
CN111741250A (en) * | 2020-07-07 | 2020-10-02 | 全时云商务服务股份有限公司 | Method, device and equipment for analyzing participation degree of video conversation scene and storage medium |
CN113449670A (en) * | 2021-07-09 | 2021-09-28 | 浙江正元智慧科技股份有限公司 | Drowsiness detection method based on human eye state |
CN113449670B (en) * | 2021-07-09 | 2022-04-15 | 浙江正元智慧科技股份有限公司 | Drowsiness detection method based on human eye state |
CN113703335A (en) * | 2021-10-27 | 2021-11-26 | 江苏博子岛智能产业技术研究院有限公司 | Intelligent home brain control system based on internet of things and provided with brain-computer interface |
CN116469085A (en) * | 2023-03-30 | 2023-07-21 | 万联易达物流科技有限公司 | Monitoring method and system for risk driving behavior |
CN116469085B (en) * | 2023-03-30 | 2024-04-02 | 万联易达物流科技有限公司 | Monitoring method and system for risk driving behavior |
Also Published As
Publication number | Publication date |
---|---|
CN109145852B (en) | 2022-06-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109145852A (en) | A kind of driver fatigue state recognition method for opening closed state based on eyes | |
Tian et al. | Recognizing action units for facial expression analysis | |
CN108875642A (en) | A kind of method of the driver fatigue detection of multi-index amalgamation | |
Moriyama et al. | Meticulously detailed eye region model and its application to analysis of facial images | |
CN104013414B (en) | A kind of Study in Driver Fatigue State Surveillance System based on intelligent movable mobile phone | |
Ji et al. | Fatigue state detection based on multi-index fusion and state recognition network | |
CN108734086B (en) | Blink frequency and sight line estimation method based on eye area generation network | |
CN104269028B (en) | Fatigue driving detection method and system | |
CN104463191A (en) | Robot visual processing method based on attention mechanism | |
CN105739705A (en) | Human-eye control method and apparatus for vehicle-mounted system | |
CN110826440B (en) | Face changing video tampering detection method and system based on eye movement characteristics | |
CN109740477A (en) | Study in Driver Fatigue State Surveillance System and its fatigue detection method | |
CN106682603A (en) | Real time driver fatigue warning system based on multi-source information fusion | |
CN104331160A (en) | Lip state recognition-based intelligent wheelchair human-computer interaction system and method | |
Luo et al. | The driver fatigue monitoring system based on face recognition technology | |
Nakamura et al. | Driver drowsiness estimation from facial expression features computer vision feature investigation using a CG model | |
CN114155512A (en) | Fatigue detection method and system based on multi-feature fusion of 3D convolutional network | |
Panicker et al. | Open-eye detection using iris–sclera pattern analysis for driver drowsiness detection | |
Rakshita | Communication through real-time video oculography using face landmark detection | |
CN109376583A (en) | A kind of Driver Fatigue Detection that intelligent vehicle auxiliary drives | |
Wimmer et al. | Facial expression recognition for human-robot interaction–a prototype | |
Li et al. | Near-infrared-ray and side-view video based drowsy driver detection system: Whether or not wearing glasses | |
CN107977622A (en) | Eyes detection method based on pupil feature | |
Liu et al. | Automatic facial expression recognition based on local binary patterns of local areas | |
Pachouly et al. | Driver Drowsiness Detection using Machine Learning |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |