CN105769120B - Method for detecting fatigue driving and device - Google Patents
Method for detecting fatigue driving and device Download PDFInfo
- Publication number
- CN105769120B CN105769120B CN201610056984.4A CN201610056984A CN105769120B CN 105769120 B CN105769120 B CN 105769120B CN 201610056984 A CN201610056984 A CN 201610056984A CN 105769120 B CN105769120 B CN 105769120B
- Authority
- CN
- China
- Prior art keywords
- human eye
- driver
- image
- state
- fatigue
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
- A61B5/6813—Specially adapted to be attached to a specific body part
- A61B5/6825—Hand
- A61B5/6826—Finger
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B2503/00—Evaluating a particular growth phase or type of persons or animals
- A61B2503/20—Workers
- A61B2503/22—Motor vehicles operators, e.g. drivers, pilots, captains
Landscapes
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Animal Behavior & Ethology (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Physics & Mathematics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
- Emergency Alarm Devices (AREA)
Abstract
This application discloses a kind of driver tired driving detection method and detection devices, which comprises receives the direct picture of the driver of acquisition;Face datection is carried out in the image of acquisition;Human eye and/or mouth are further positioned in the face detected;The method also includes: it is based on deep neural network model, the human eye and/or mouth that detect are positioned, identify the state of human eye;The variation for tracking the state of human eye in multiple image, judges whether driver is tired.By above-mentioned detection method and device, can in real time, high robust and accurately detect fatigue driving.
Description
Technical field
The present disclosure relates generally to vehicle security drive technical fields, and in particular to the fatigue driving based on deep neural network
Detection method and device.
Background technique
With the development of the social economy, motor vehicles sharply increase, the traffic accident caused by fatigue driving present more next
More multiple trend.For this phenomenon, various fatigue-driving detection technologies are produced, including the physiology based on driver
The fatigue-driving detection technology of feature.When driver fatigue, can show to bow, the physiological characteristics such as eye closing frequency increases.It is logical
Monitoring device is crossed, detects these physiological characteristics of driver, it can be determined that whether driver is tired.Physiology based on driver is special
The fatigue-driving detection technology of sign has the characteristics that non-contact, at low cost, accuracy is high, therefore, is widely adopted in current
Fatigue driving detection device.
The fatigue driving detection device of the current physiological characteristic based on driver, it is fixed mostly by image processing techniques
Position face, then in the range of face analyze eyes state, judge whether fatigue.Specifically, usually there are two types of methods, a kind of
It is to obtain human eye opening and closing status information using visible image capturing head and carry out detection identification, according to organs such as eyes, mouth, noses
Feature and mutual geometry site carry out, this method under the strong light and dark ambient conditions accuracy rate by
To very big influence, moreover, traditional human eye detection parser for being based purely on image, if colour of skin Pupil Segmentation detects, to making an uproar
Sound not robust, can not accurately be partitioned into human eye area and be identified.Algorithm of the another kind based on deep learning model, by right
A large amount of facial image sample architecture face model spaces, judge that face whether there is according to similarity.Although this method is quasi-
True rate is promoted, but this method is computationally intensive, can not on embedded device real time execution, cannot be practical.
Summary of the invention
Brief summary of the present invention is given below, in order to provide the basic reason about certain aspects of the invention
Solution.It should be appreciated that this summary is not an exhaustive overview of the invention.It is not intended to determine key of the invention
Or pith, nor is it intended to limit the scope of the present invention.Its purpose only provides certain concepts in simplified form, with
This is as the preamble in greater detail discussed later.
The present invention propose it is a kind of can in real time, high robust and the method for accurately carrying out fatigue driving detection.
In the first aspect of the present invention, the present invention provides a kind of method for detecting fatigue driving, comprising: receives the driving of acquisition
The direct picture of member;Face datection is carried out in the image of acquisition;Human eye and/or mouth are further positioned in the face detected
Bar;Wherein, the method also includes:
Based on deep neural network model, the human eye and/or mouth that detect are positioned, identify the state of human eye;
The variation for tracking the state of human eye in multiple image, judges whether driver is tired.
Preferably, above-mentioned fatigue driving method be based on deep neural network model, to the human eye and/or mouth detected into
Row positioning includes: that facial image input human face characteristic point is returned convolutional neural networks model, and regression forecasting is down-sampled at one
Low-resolution image in the boundary position of human eye and/or mouth.
Preferably, it further includes from the drop that above-mentioned fatigue driving method, which carries out positioning to the human eye and/or mouth that detect,
Eyes area image is cut out in the low-resolution image of sampling, input eye areas divides deep neural network model, prediction
The probability graph for belonging to human eye area on another down-sampled low-resolution image is partitioned into the image slices that human eye area is included
Element, and the opening and closing state of human eye is judged accordingly.
Preferably, in above-mentioned fatigue driving method, the variation of the human eye state includes the variation of human eye opening and closing size.
Preferably, in above-mentioned fatigue driving method, the variation of the human eye state includes the variation of the human eye opening and closing frequency.
Preferably, the method for detecting fatigue driving further include nose is further positioned in the face detected, and
Based on deep neural network model, the nose detected is positioned.
Preferably, the method for detecting fatigue driving further includes carrying out Image Acquisition using monocular infrared camera.
Preferably, the method for detecting fatigue driving further includes the positioning mouth area from down-sampled low-resolution image
Domain, cuts out mouth region image, input mouth region segmentation deep neural network model, and classification judges mouth opening and closing shape
State.
Preferably, the method for detecting fatigue driving further includes being made different etc. according to the different situations of the fatigue of detection
The early warning of grade.
In the second aspect of the present invention, the present invention also provides a kind of driver tired driving detection devices, including face to examine
It surveys device, human eye positioning device and tired judgment means, the human face detection device and is used for the activity in received driver
The face of driver is detected in image, the human eye positioning device is used in the face, positions the eyes of driver, from
And determine the state of driver's eyes, the fatigue judgment means, for the state according to the driver's eyes, described in judgement
Whether driver is tired;Wherein,
The human eye positioning device is based on deep neural network model, positions to the human eye and/or mouth that detect,
Identify the state of human eye;
The variation of the state of human eye, judges whether driver is tired in the fatigue judgment means tracking multiple image.
Preferably, the human eye positioning device includes human eye coarse localization device, and the human eye coarse localization device is used for
Facial image input human face characteristic point is returned into convolutional neural networks model, regression forecasting is in a down-sampled low resolution figure
The boundary position of human eye and/or mouth as in, and then identify the state of human eye.
Preferably, the human eye positioning device include further comprise human eye accurate positioning device, the human eye is accurately fixed
Position device, for cutting out eyes area image, input eye areas segmentation depth mind from down-sampled low-resolution image
Through network model, prediction belongs to the probability graph of human eye area on another down-sampled low-resolution image, is partitioned into human eye area
The image pixel that domain is included, and the opening and closing state of human eye is judged accordingly.
Preferably, the driver tired driving detection device further includes mouth accurate positioning device, and the mouth is accurate
Positioning device cuts out mouth region image, input mouth area for positioning mouth region from down-sampled low-resolution image
Regional partition deep neural network model, classification judge mouth opening and closing state.
Preferably, the driver tired driving detection device further comprises fatigue driving warning device, the fatigue
It drives the fatigue driving degree that warning device is used to judge according to driver tired driving detection device and issues alarm to driver
Information.
Preferably, the driver tired driving detection device further comprises image collecting device, described image acquisition
Device is used to acquire the direct picture of driver.
By driver tired driving detection method according to the present invention and detection device, can be realized it is inexpensive quickly,
Accurately, the robustly driver fatigue state detection device based on image, so that embedded device does not need any human-computer interaction
It is whether in a state of fatigue that driver can be obtained in real time, provide safety protective prompting or early warning for driver.
Detailed description of the invention
Below with reference to the accompanying drawings illustrate embodiments of the invention, the invention will be more easily understood it is above and its
Its objects, features and advantages.Component in attached drawing is intended merely to show the principle of the present invention.In the accompanying drawings, identical or similar
Technical characteristic or component will be indicated using same or similar appended drawing reference.
Fig. 1 is the flow chart of driver tired driving detection method according to the present invention;
Fig. 2 is the composition schematic diagram of driver tired driving detection device according to the present invention;
Fig. 3 and Fig. 4 shows the position view for installing driver tired driving detection device according to the present invention.
Specific embodiment
Embodiments of the present invention will be described below with reference to the accompanying drawings.It is retouched in an attached drawing of the invention or a kind of embodiment
The elements and features stated can be combined with elements and features shown in one or more other attached drawings or embodiment.It answers
When note that for purposes of clarity, being omitted known to unrelated to the invention, those of ordinary skill in the art in attached drawing and explanation
Component and processing expression and description.
Fig. 1 is the flow chart for the method for detecting fatigue driving that the embodiment of the present invention one provides.It is comprised the following steps that
Firstly, receiving the positive live image of driver using camera acquisition in step S101.Such as with 640*
The resolution acquisition image of 480 pixels, 1280*720 pixel, 1920*1080 pixel.
Here, camera can use common camera or the infrared visible image capturing head of monocular, to reinforce in decreased light
Or the clarity of the Image Acquisition under the conditions of night running.
Then, in step S102, Face datection is carried out to the driver activity image of acquisition.
Face datection is the face in order to identify driver in whole picture (frame) driver's image, for further positioning eye
Eyeball and mouth do basis.Face datection can use existing various detection identification technologies, for example, such as skin color segmentation, shape inspection
Survey etc..Preferably, Face datection can be carried out using multi-stage cascade sorting algorithm.
Then, in step S103, eyes and mouth are further positioned in the facial image of detection.Side according to the present invention
Method can be carried out, according to positioning in the step of further positioning eyes and nose based on the method for deep neural network
Eyes, to identify human eye state in which.
Finally, the variation of eye state in multiframe facial image is continuously tracked, whether determines driver in step S104
Fatigue and degree of fatigue.
Preferably, the human eye and/or mouth that detect are positioned, identification human eye state in which includes: to human eye
Carry out coarse localization and accurate positioning.Carrying out coarse localization to human eye includes: that facial image input human face characteristic point is returned volume
Product neural network model, regression forecasting boundary position of human eye and/or mouth in a down-sampled low-resolution image, into
And identify the state of human eye.For example, human eye and/or mouth can be resolution ratio as 72* in down-sampled low-resolution image
72 image block.In one embodiment, facial image is input to convolutional neural networks, so that obtaining includes two eyes of characterization
Two pairs of data of the two-dimensional coordinate of eyeball position.In another embodiment, facial image is input to convolutional neural networks, thus
Obtaining includes three pairs of data for characterizing the two-dimensional coordinate of two eyes and mouth position.Conventional images analysis side can also be used
Method, for example, Pupil Segmentation, SHAPE DETECTION etc., orient the boundary position of human eye, and then determine the state of human eye.Determine human eye
State include the area of pupil of human, human eye opening and closing size and its variation.For example, normalized human eye area area, pupil
The relative motion in region.
Preferably, further human eye can be accurately positioned on the basis of carrying out coarse localization to human eye.To inspection
The human eye measured carries out the human eye positioning result being accurately positioned to include: according to coarse localization, from down-sampled low resolution
Eyes area image is cut out in rate image, input eye areas is divided deep neural network model, predicted another down-sampled
Low-resolution image on belong to the probability graph of human eye area, be partitioned into the image pixel that human eye area is included, and sentence accordingly
The opening and closing state of disconnected human eye.For example, cutting out driver's eyes on the image that another down-sampled low resolution is 64*64
Image, more accurately to judge the variation of human eye state.
Preferably, during above-mentioned accurate positioning human eye, according to the mouth zone location when carrying out coarse localization to human eye
As a result, cutting out mouth region image, input mouth region segmentation deep neural network model carries out classification and judges mouth opening and closing shape
State.Mouth opening and closing state is combined into analysis with above-mentioned human eye opening and closing state, obtains more accurate fatigue state testing result.
It preferably, further include the shape for tracking human eye in multiple image in the method for above-mentioned detection driver tired driving
The variation of state, so that the variation of the human eye opening and closing frequency is analyzed, the degree of fatigue variation of auxiliary detection driver.
In above-mentioned detection, optionally, including positioning multiple human face characteristic points such as nose, mouth in the face detected,
And the accuracy positioned to eye detection is improved based on deep neural network model.This is to promote to accelerate according to nerve net
The eyes of the method positioning people of network model.In the case, facial image is input to the deep neural network model, output packet
Include four pairs of data of the two-dimensional coordinate of two eyes of characterization, mouth and nose shape.
In above-mentioned method for detecting fatigue driving, it can also include that mouth states is combined to analyze, judge whether fatigue.Example
Such as, it by analyzing the variation of eye state in comparison continuous multiple frames image, and combines the variation of mouth opening and closing size or beats Kazakhstan
Whether the deficient frequency, auxiliary judgment driver are tired.
The degree of fatigue of driver is judged according to the degree and the frequency of eyes and/or mouth opening and closing, extracts damage parameters, it can
To be carried out according to prior art standard.
It, can be only after carrying out human eye coarse localization i.e. to the opening and closing shape of human eye during above-mentioned judgement human eye state
State judges, and is conducive to rapidly obtain the judging result for judging driver tired driving in this way.
In addition, in above-mentioned neural network model, the Face datection of front and back multiframe or human eye detection result is interrelated,
Error detection can be reduced, the accuracy of detection is improved.
The method for detecting fatigue driving further includes being arranged above-mentioned tired according to the different situations of the fatigue of the driver of detection
Please the susceptibility for sailing detection makes different grades of early warning.For example, the too small i.e. human eye closure of human eye area reaches 10
Second or pupil were set as " slight fatigue ", and started the alarm of voice prompting primary without relative motion 10 seconds;Human eye is closed 20 seconds,
It is set as " moderate fatigue ", initially enters intermediate alarm;Human eye is closed 30 seconds, is set as " severe fatigue ", is started max volume
Lasting alarm, etc..
In above-mentioned driver tired driving detection method, when establishing convolutional neural networks model, for Multidimensional numerical number
According to, such as the image data of RGB multichannel, progress multitiered network Nonlinear Processing, such as convolutional layer, pond layer (Pooling),
Full articulamentum obtains the semantic meaning representation feature of image different phase, for the detection to image, classification and identification.For example, instructing
Practice the stage, collect a large amount of human face datas, and carries out eyes and mouth region mark, it is excellent using supervised learning and reverse conduction algorithm
Change model parameter, extracts robust and accurate neural network model.
By driver tired driving detection method according to the present invention, it is inexpensive quick, accurate, robust to can be realized
Driver fatigue state detection device based on image can obtain in real time so that embedded device does not need any human-computer interaction
It takes driver whether in a state of fatigue, provides safety protective prompting or early warning for driver.
The present invention also provides a kind of driver fatigue detection devices 1, as shown in Fig. 2, comprising: human face detection device 12,
Human eye positioning device 13, and tired judgment means 14.It may include Image Acquisition in the outside of driver fatigue detection device 1
Device 11, for acquiring the live image of driver.The human face detection device 12 is used in received driver activity image
The face of middle detection driver, the human eye positioning device 13, for positioning the eyes of driver in the face, thus
Determine the state of driver's eyes, the fatigue judgment means 14, for the state according to the driver's eyes, described in judgement
Whether driver is tired;Wherein, human eye positioning device 13 is based on deep neural network model, to the human eye and/or mouth detected
Ba Jinhang positioning, identifies the state of human eye;Tired judgment means 14 track the variation of the state of human eye in multiple image, and judgement is driven
Whether the person of sailing is tired.
Preferably, in above-mentioned driver tired driving detection device, human eye positioning device includes: human eye coarse localization dress
It sets.The human eye coarse localization device is returned for facial image input human face characteristic point to be returned convolutional neural networks model
Prediction boundary position of human eye and/or mouth in a down-sampled low-resolution image, and then identify the state of human eye.
Preferably, above-mentioned driver tired driving detection device, human eye positioning device further comprise that human eye is accurately positioned
Device.The human eye accurate positioning device is inputted for cutting out eyes area image from down-sampled low-resolution image
Eye areas divides deep neural network model, and prediction belongs to the general of human eye area on another down-sampled low-resolution image
Rate figure is partitioned into the image pixel that human eye area is included, and judges the opening and closing state of human eye accordingly.
Preferably, above-mentioned driver tired driving detection device further includes mouth accurate positioning device.The mouth is accurate
Positioning device cuts out mouth region image, inputs mouth for positioning mouth region from down-sampled low-resolution image
Region segmentation convolution deep neural network model, classification judge mouth opening and closing state.
Preferably, above-mentioned driver tired driving detection device further comprises fatigue driving warning device, the fatigue
It drives the fatigue driving degree that warning device is used to judge according to driver tired driving detection device and issues alarm to driver
Information.Warning message includes sound and/or optics alarm.For example, warning device includes loudspeaker and warning lamp, appropriate journey is being determined
After the fatigue driving of degree, loudspeaker sending pipes and/or warning lamp issues the light flashed.
Optionally, above-mentioned image collecting device is also desirably integrated into driver tired driving detection device.
Above-mentioned image collecting device, human face detection device, human eye positioning device and tired judgment means can use electronics
Hardware circuit realizes that human face detection device, human eye positioning device and tired judgment means can also be used can be embedded hard
The software realization run on part platform.For example, human face detection device, human eye positioning device and tired judgment means can be used
It, can also be respectively with operating in ARM platform, on X86 platform respectively with one or more ASIC and/or FPGA and combinations thereof realization
Software function module realize.Each functional module, the convenience that can also be divided according to hardware or software function, reconfigure or
Integration is realized.
Driver tired driving detection device according to the present invention can adopt a split structure, wherein image collecting device
It is preferably mounted on windshield, on the left anterior-superior part of position of driver or the roof of front upper right.It can also use
Integral structure, it is integrated to be embedded into different location, such as rearview mirror, instrument panel center of vehicle etc..Fig. 3 and Fig. 4 shows installation
The position view of driver tired driving detection device according to the present invention.Driver tired driving detection device is pacified in Fig. 3
The positive appropriate location of driver can be captured through steering wheel loaded on instrument panel center, driver tired driving detects in Fig. 4
Device is installed on the left of rearview mirror towards the position of driver.Driver can be according to actual application scenarios, from main regulation early warning
Susceptibility and alarm volume.
It, can be real-time, quickly to driver fatigue by driver tired driving detection method according to the present invention and device
State is determined that embedded software hardware appliance device is desirably integrated into the various equipment for monitoring driver, such as
Car, public transport, high-speed rail, aircraft etc..
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations;Although
Present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: it still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features;
And these are modified or replaceed, technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (11)
1. a kind of method for detecting fatigue driving, comprising:
Receive the direct picture of the driver of acquisition;
Face datection is carried out in the image of acquisition;
Human eye is further positioned in the face detected;
It is characterized in that, the method also includes:
Based on deep neural network model, the human eye detected is positioned, identifies the state of human eye;And
The variation for tracking the state of human eye in multiple image, judges whether driver is tired;
Described to be based on deep neural network model, carrying out positioning to the human eye detected includes:
Facial image input human face characteristic point is returned into convolutional neural networks model, regression forecasting is in a down-sampled low resolution
The boundary position of human eye in rate image;And
The eyes region as another down-sampled low-resolution image is cut out from the down-sampled low-resolution image
Image, input eye areas divide deep neural network model, and prediction belongs on another down-sampled low-resolution image
In the probability graph of human eye area, it is partitioned into the image pixel that human eye area is included, and judges the opening and closing state of human eye accordingly.
2. method for detecting fatigue driving according to claim 1, which is characterized in that the variation of the state of the human eye includes
The variation of human eye opening and closing size.
3. method for detecting fatigue driving according to claim 1, which is characterized in that the variation of the state of the human eye includes
The variation of the human eye opening and closing frequency.
4. method for detecting fatigue driving according to claim 1, which is characterized in that the method for detecting fatigue driving also wraps
It includes and further positions nose in the face detected, and be based on deep neural network model, the nose detected is carried out
Positioning.
5. method for detecting fatigue driving according to claim 1, which is characterized in that the method for detecting fatigue driving also wraps
It includes and carries out Image Acquisition using monocular infrared camera.
6. method for detecting fatigue driving according to claim 1, which is characterized in that the method for detecting fatigue driving also wraps
It includes and positions mouth region from the down-sampled low-resolution image, cut out mouth region image, input mouth region segmentation
Deep neural network model, classification judge mouth opening and closing state.
7. method for detecting fatigue driving according to claim 1, which is characterized in that the method for detecting fatigue driving also wraps
The different situations for including the fatigue according to detection, make different grades of early warning.
8. a kind of driver tired driving detection device, including human face detection device, human eye positioning device and fatigue judgement dress
It sets, the human face detection device in received driver activity image for detecting the face of driver, the human eye positioning
Device, for positioning the eyes of driver in the face, so that it is determined that the state of driver's eyes, the fatigue judgement
Device judges whether the driver is tired for the state according to the driver's eyes;It is characterized in that,
The human eye positioning device is based on deep neural network model, positions to the human eye detected, identifies the shape of human eye
State;
The variation of the state of human eye, judges whether driver is tired in the fatigue judgment means tracking multiple image;
The human eye positioning device includes human eye coarse localization device, and the human eye coarse localization device is used for facial image is defeated
Enter human face characteristic point and returns convolutional neural networks model, the side of regression forecasting human eye in a down-sampled low-resolution image
Boundary position, and then identify the state of human eye;
The human eye positioning device further comprises human eye accurate positioning device, and the human eye accurate positioning device from drop for adopting
The eyes area image as another down-sampled low-resolution image is cut out in the low-resolution image of sample, inputs eyes area
Regional partition deep neural network model, prediction belong to the probability of human eye area on another down-sampled low-resolution image
Figure, is partitioned into the image pixel that human eye area is included, and judge the opening and closing state of human eye accordingly.
9. driver tired driving detection device according to claim 8, which is characterized in that the driver tired driving
Detection device further includes mouth accurate positioning device, and the mouth accurate positioning device is used for from down-sampled low-resolution image
Middle positioning mouth region, cuts out mouth region image, input mouth region segmentation deep neural network model, and classification judges mouth
Opening and closing state.
10. driver tired driving detection device according to claim 8, which is characterized in that the driver fatigue is driven
Sailing detection device further comprises fatigue driving warning device, and the fatigue driving warning device according to driver fatigue for driving
The fatigue driving degree of detection device judgement is sailed to driver's alert.
11. driver tired driving detection device according to claim 8, which is characterized in that the driver fatigue is driven
Sailing detection device further comprises image collecting device, and described image acquisition device is used to acquire the direct picture of driver.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610056984.4A CN105769120B (en) | 2016-01-27 | 2016-01-27 | Method for detecting fatigue driving and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610056984.4A CN105769120B (en) | 2016-01-27 | 2016-01-27 | Method for detecting fatigue driving and device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105769120A CN105769120A (en) | 2016-07-20 |
CN105769120B true CN105769120B (en) | 2019-01-22 |
Family
ID=56402500
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610056984.4A Active CN105769120B (en) | 2016-01-27 | 2016-01-27 | Method for detecting fatigue driving and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105769120B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109770925A (en) * | 2019-02-03 | 2019-05-21 | 闽江学院 | A kind of fatigue detection method based on depth time-space network |
Families Citing this family (33)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106446811A (en) * | 2016-09-12 | 2017-02-22 | 北京智芯原动科技有限公司 | Deep-learning-based driver's fatigue detection method and apparatus |
CN106599821A (en) * | 2016-12-07 | 2017-04-26 | 中国民用航空总局第二研究所 | Controller fatigue detection method and system based on BP neural network |
CN107038422B (en) * | 2017-04-20 | 2020-06-23 | 杭州电子科技大学 | Fatigue state identification method based on space geometric constraint deep learning |
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 |
WO2019028798A1 (en) * | 2017-08-10 | 2019-02-14 | 北京市商汤科技开发有限公司 | Method and device for monitoring driving condition, and electronic device |
CN107657236A (en) * | 2017-09-29 | 2018-02-02 | 厦门知晓物联技术服务有限公司 | Vehicle security drive method for early warning and vehicle-mounted early warning system |
CN107977605B (en) * | 2017-11-08 | 2020-04-24 | 清华大学 | Eye region boundary feature extraction method and device based on deep learning |
CN107832721B (en) * | 2017-11-16 | 2021-12-07 | 百度在线网络技术(北京)有限公司 | Method and apparatus for outputting information |
CN107958573A (en) * | 2017-12-25 | 2018-04-24 | 芜湖皖江知识产权运营中心有限公司 | A kind of traffic control method being applied in intelligent vehicle |
CN108162893A (en) * | 2017-12-25 | 2018-06-15 | 芜湖皖江知识产权运营中心有限公司 | A kind of running control system applied in intelligent vehicle |
CN108128161A (en) * | 2017-12-25 | 2018-06-08 | 芜湖皖江知识产权运营中心有限公司 | A kind of fatigue driving identification control method applied in intelligent vehicle |
CN108491858A (en) * | 2018-02-11 | 2018-09-04 | 南京邮电大学 | Method for detecting fatigue driving based on convolutional neural networks and system |
CN108657185A (en) * | 2018-03-28 | 2018-10-16 | 贵州大学 | A kind of fatigue detecting and control method of vehicle ACC system active safety |
CN108888294B (en) * | 2018-03-30 | 2021-02-23 | 杭州依图医疗技术有限公司 | Method and device for detecting width of neck transparent belt |
CN109308445B (en) * | 2018-07-25 | 2019-06-25 | 南京莱斯电子设备有限公司 | A kind of fixation post personnel fatigue detection method based on information fusion |
CN110855934A (en) * | 2018-08-21 | 2020-02-28 | 北京嘀嘀无限科技发展有限公司 | Fatigue driving identification method, device and system, vehicle-mounted terminal and server |
CN109460704B (en) * | 2018-09-18 | 2020-09-15 | 厦门瑞为信息技术有限公司 | Fatigue detection method and system based on deep learning and computer equipment |
CN110956061B (en) * | 2018-09-27 | 2024-04-16 | 北京市商汤科技开发有限公司 | Action recognition method and device, and driver state analysis method and device |
CN109376649A (en) * | 2018-10-20 | 2019-02-22 | 张彦龙 | A method of likelihood figure, which is reduced, from eye gray level image calculates the upper lower eyelid of identification |
CN109614892A (en) * | 2018-11-26 | 2019-04-12 | 青岛小鸟看看科技有限公司 | A kind of method for detecting fatigue driving, device and electronic equipment |
CN109598237A (en) * | 2018-12-04 | 2019-04-09 | 青岛小鸟看看科技有限公司 | A kind of fatigue state detection method and device |
CN109711309B (en) * | 2018-12-20 | 2020-11-27 | 北京邮电大学 | Method for automatically identifying whether portrait picture is eye-closed |
US10713948B1 (en) * | 2019-01-31 | 2020-07-14 | StradVision, Inc. | Method and device for alerting abnormal driver situation detected by using humans' status recognition via V2V connection |
CN110263641A (en) * | 2019-05-17 | 2019-09-20 | 成都旷视金智科技有限公司 | Fatigue detection method, device and readable storage medium storing program for executing |
CN110674701A (en) * | 2019-09-02 | 2020-01-10 | 东南大学 | Driver fatigue state rapid detection method based on deep learning |
CN110654314A (en) * | 2019-09-30 | 2020-01-07 | 浙江鸿泉车联网有限公司 | Deep learning-based automatic rearview mirror adjusting method and device |
CN110826521A (en) * | 2019-11-15 | 2020-02-21 | 爱驰汽车有限公司 | Driver fatigue state recognition method, system, electronic device, and storage medium |
CN111428680B (en) * | 2020-04-07 | 2023-10-20 | 深圳华付技术股份有限公司 | Pupil positioning method based on deep learning |
CN111521270A (en) * | 2020-04-23 | 2020-08-11 | 烟台艾睿光电科技有限公司 | Body temperature screening alarm system and working method thereof |
CN111626221A (en) * | 2020-05-28 | 2020-09-04 | 四川大学 | Driver gazing area estimation method based on human eye information enhancement |
CN111724408B (en) * | 2020-06-05 | 2021-09-03 | 广东海洋大学 | Verification experiment method of abnormal driving behavior algorithm model based on 5G communication |
CN112036352B (en) * | 2020-09-08 | 2021-09-14 | 北京嘀嘀无限科技发展有限公司 | Training method of fatigue detection model, and fatigue driving detection method and device |
CN112966664A (en) * | 2021-04-01 | 2021-06-15 | 科世达(上海)机电有限公司 | Fatigue driving detection method, system and device and readable storage medium |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102254151A (en) * | 2011-06-16 | 2011-11-23 | 清华大学 | Driver fatigue detection method based on face video analysis |
CN103400471A (en) * | 2013-08-12 | 2013-11-20 | 电子科技大学 | Detecting system and detecting method for fatigue driving of driver |
CN103824049A (en) * | 2014-02-17 | 2014-05-28 | 北京旷视科技有限公司 | Cascaded neural network-based face key point detection method |
CN103839379A (en) * | 2014-02-27 | 2014-06-04 | 长城汽车股份有限公司 | Automobile and driver fatigue early warning detecting method and system for automobile |
CN104688251A (en) * | 2015-03-02 | 2015-06-10 | 西安邦威电子科技有限公司 | Method for detecting fatigue driving and driving in abnormal posture under multiple postures |
CN105096528A (en) * | 2015-08-05 | 2015-11-25 | 广州云从信息科技有限公司 | Fatigue driving detection method and system |
CN105139070A (en) * | 2015-08-27 | 2015-12-09 | 南京信息工程大学 | Fatigue driving evaluation method based on artificial nerve network and evidence theory |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9129505B2 (en) * | 1995-06-07 | 2015-09-08 | American Vehicular Sciences Llc | Driver fatigue monitoring system and method |
JP2007122362A (en) * | 2005-10-27 | 2007-05-17 | Toyota Motor Corp | State estimation method using neural network and state estimation apparatus using neural network |
-
2016
- 2016-01-27 CN CN201610056984.4A patent/CN105769120B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102254151A (en) * | 2011-06-16 | 2011-11-23 | 清华大学 | Driver fatigue detection method based on face video analysis |
CN103400471A (en) * | 2013-08-12 | 2013-11-20 | 电子科技大学 | Detecting system and detecting method for fatigue driving of driver |
CN103824049A (en) * | 2014-02-17 | 2014-05-28 | 北京旷视科技有限公司 | Cascaded neural network-based face key point detection method |
CN103839379A (en) * | 2014-02-27 | 2014-06-04 | 长城汽车股份有限公司 | Automobile and driver fatigue early warning detecting method and system for automobile |
CN104688251A (en) * | 2015-03-02 | 2015-06-10 | 西安邦威电子科技有限公司 | Method for detecting fatigue driving and driving in abnormal posture under multiple postures |
CN105096528A (en) * | 2015-08-05 | 2015-11-25 | 广州云从信息科技有限公司 | Fatigue driving detection method and system |
CN105139070A (en) * | 2015-08-27 | 2015-12-09 | 南京信息工程大学 | Fatigue driving evaluation method based on artificial nerve network and evidence theory |
Non-Patent Citations (1)
Title |
---|
Extensive Facial Landmark Localization with Coarse-to-fine Convolutional Network Cascade;Erjin Zhou等;《2013 IEEE International Conference on Computer Vision Workshops》;20131208;正文第387页右栏第8行到第389页右栏第14行及图2 |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109770925A (en) * | 2019-02-03 | 2019-05-21 | 闽江学院 | A kind of fatigue detection method based on depth time-space network |
Also Published As
Publication number | Publication date |
---|---|
CN105769120A (en) | 2016-07-20 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105769120B (en) | Method for detecting fatigue driving and device | |
CN108960065B (en) | Driving behavior detection method based on vision | |
CN101593425B (en) | Machine vision based fatigue driving monitoring method and system | |
CN104013414B (en) | A kind of Study in Driver Fatigue State Surveillance System based on intelligent movable mobile phone | |
Rongben et al. | Monitoring mouth movement for driver fatigue or distraction with one camera | |
US6927694B1 (en) | Algorithm for monitoring head/eye motion for driver alertness with one camera | |
Horng et al. | Driver fatigue detection based on eye tracking and dynamic template matching | |
CN104637246B (en) | Driver multi-behavior early warning system and danger evaluation method | |
CN102054163B (en) | Method for testing driver fatigue based on monocular vision | |
CN110119676A (en) | A kind of Driver Fatigue Detection neural network based | |
CN109460780A (en) | Safe driving of vehicle detection method, device and the storage medium of artificial neural network | |
CN108309311A (en) | A kind of real-time doze of train driver sleeps detection device and detection algorithm | |
WO2021016873A1 (en) | Cascaded neural network-based attention detection method, computer device, and computer-readable storage medium | |
Vitabile et al. | Bright pupil detection in an embedded, real-time drowsiness monitoring system | |
CN109584507A (en) | Driver behavior modeling method, apparatus, system, the vehicles and storage medium | |
CN112016457A (en) | Driver distraction and dangerous driving behavior recognition method, device and storage medium | |
CN103714659B (en) | Fatigue driving identification system based on double-spectrum fusion | |
CN109389806A (en) | Fatigue driving detection method for early warning, system and medium based on multi-information fusion | |
CN105844245A (en) | Fake face detecting method and system for realizing same | |
Tang et al. | Real-time image-based driver fatigue detection and monitoring system for monitoring driver vigilance | |
CN109977930A (en) | Method for detecting fatigue driving and device | |
CN107844783A (en) | A kind of commerial vehicle abnormal driving behavioral value method and system | |
Yao et al. | Real-time vision-based driver drowsiness/fatigue detection system | |
CN106295474A (en) | The fatigue detection method of deck officer, system and server | |
CN107909012A (en) | A kind of real-time vehicle tracking detection method and device based on disparity map |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |