CN106327801B - Method for detecting fatigue driving and device - Google Patents
Method for detecting fatigue driving and device Download PDFInfo
- Publication number
- CN106327801B CN106327801B CN201510393702.5A CN201510393702A CN106327801B CN 106327801 B CN106327801 B CN 106327801B CN 201510393702 A CN201510393702 A CN 201510393702A CN 106327801 B CN106327801 B CN 106327801B
- Authority
- CN
- China
- Prior art keywords
- key point
- facial image
- face
- human eye
- human
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/06—Alarms for ensuring the safety of persons indicating a condition of sleep, e.g. anti-dozing alarms
Landscapes
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the invention provides method for detecting fatigue driving and device, wherein the described method includes: the facial image of acquisition driver, therefrom detects human face region, determines the face key point in human face region, the face key point as present frame facial image；After determining human eye area according to face key point, it is located at the human eye key point in human eye area from selection in face key point；According to the angle information between the human eye key point line in human eye area, judge driver whether fatigue driving.With the application of the invention, the accuracy of fatigue driving state detection can be improved.
Description
Technical field
The present invention relates to the technical fields of terminal device, specifically, the present invention relates to method for detecting fatigue driving and dress
It sets.
Background technique
In recent years, with the development of economy and society, the quantity of motor vehicles increases significantly, thus, since fatigue driving is led
The traffic accident of cause is also more and more.In view of the above-mentioned problems, the detection method of existing fatigue driving mainly has following three kinds of sides
Method:
In recent years, with the development of economy and society, the quantity of motor vehicles increases significantly, thus, since fatigue driving is led
The traffic accident of cause is also more and more.In view of the above-mentioned problems, the detection method of existing fatigue driving mainly has following three kinds of sides
Method:
(1) based on the detection method of physiological signal.
Detection method based on physiological signal, needs to acquire the blood pressure of driver and the physiological signal of brain wave, and according to
Judge whether driver is in fatigue driving state according to above-mentioned physiological signal.Such detection method needs high-precision detector
Device, therefore corresponding cost is also relatively high.
(2) based on the fatigue detection method of running information.
When running information shows that left and right vehicle wheel rocks that amplitude is excessive or speed wobble, then is judged as current driving
Member is in fatigue driving state.Since different drivers has the driving shape on different driving habits, and different roads
Condition, thus, the fatigue detection method based on running information is difficult to efficiently perform, and the accuracy of result obtained is not high.
(3) based on the fatigue detection method of physiological characteristic.
In order to improve the treatment effeciency of image processing techniques, the search range of eyes is reduced, face is positioned.It is based on
The fatigue detection method of physiological characteristic divides by image processing techniques, first locating human face region, then in current face region
The state for analysing eyes, judges whether driver is in a state of fatigue according to the state of eyes obtained.Due to calculating speed
Fastly, and it is illuminated by the light the small advantage of influence, the method for classifier is applied in Face detection technology.It is driven if testing result is shown
The person of sailing shows to bow and close one's eyes again and again, then judges that driver is in the state of fatigue driving.
But it was found by the inventors of the present invention that this method has biggish limitation to the validity for improving fatigue detecting algorithm
Property: for example, the face image of acquisition occurs inclined when the head back torsion of driver or head side are to the left or when right side
Turn, be easy to appear erroneous judgement situation at this time, reduction judges whether driver is in the accuracy of fatigue driving state.
Summary of the invention
In view of the above-mentioned drawbacks of the prior art, the present invention provides a kind of method for detecting fatigue driving and device, energy
Enough location informations for obtaining more high accuracy, the human eye key point of precision, mobile device can more precisely know driver
Whether the information of fatigue driving reminds driver when fatigue driving occurs in driver, so that driver is in safety
The state of driving improves safety when driver's long-duration driving.
The embodiment of the present invention provides a kind of method for detecting fatigue driving according on one side, comprising:
The facial image for acquiring driver, therefrom detects human face region, determines that the face in the human face region is crucial
Point, the face key point as present frame facial image；
After determining human eye area according to the face key point, is chosen from the face key point and be located at the human eye
Human eye key point in region；
According to the angle information between the human eye key point line in the human eye area, judge whether the driver is tired
Please it sails.
The embodiment of the present invention additionally provides a kind of fatigue driving detection device according on the other hand, comprising:
Human face region detection module therefrom detects human face region for acquiring the facial image of driver；
Face key point determining module, for from the human face region detected by the human face region detection module
Determine face key point, the face key point as present frame facial image；
Human eye key point determining module is used for the present frame face figure according to determined by the face key point determining module
The face key point of picture after determining human eye area, is located at the people in the human eye area from selection in the face key point
Eye key point；
Fatigue driving judgment module, in the human eye area according to determined by the human eye key point determining module
Human eye key point line between angle information, judge the driver whether fatigue driving.
In technical solution of the present invention, the facial image of driver is acquired, therefrom detects human face region, from human face region
In determine the face key point of present frame facial image, and then determine human eye key point, according to human eye key point line it
Between angle information judge the fatigue driving state of driver；Rule is laid out by human face compared to existing, or is passed through
The method of pupil detection obtains position of human eye, the influence of human face posture, illumination variation is less susceptible to, to improve fatigue driving
State-detection accuracy.
Further, in technical solution of the present invention, based on more high accuracy, the position of human eye information of precision, to human eye
The angle information between human eye key point line in region is read out, judge driver whether fatigue driving；Compared to existing
Human eye state detection method, the present invention is based on more high accuracies, the closure degree for judging human eye of precision, thus more precisely
Know driver whether remind driver when fatigue driving occurs in driver by the information of fatigue driving, so that driving
Member is in the state of safe driving, improves safety when driver's long-duration driving.
It further, can in the method for carrying out fatigue driving detection according to adjacent two frames facial image of the embodiment of the present invention
The human face region that next frame facial image is initially dissolved with the face key point using present frame facial image, and from each frame people
Detect that human face region is compared in face image, computation amount improves the speed of fatigue driving detection on the whole, can be with
The fatigue driving state of driver is detected in time and is reminded, and traffic safety is improved.
The additional aspect of the present invention and advantage will be set forth in part in the description, these will become from the following description
Obviously, or practice through the invention is recognized.
Detailed description of the invention
Above-mentioned and/or additional aspect and advantage of the invention will become from the following description of the accompanying drawings of embodiments
Obviously and it is readily appreciated that, in which:
Fig. 1 a, 1b are the flow diagram of the method for detecting fatigue driving of the embodiment of the present invention；
Fig. 2 a is the human face region schematic diagram of the embodiment of the present invention；
Fig. 2 b is the face key point schematic diagram of the embodiment of the present invention；
Fig. 3 is the structural schematic diagram of the fatigue driving detection device of the embodiment of the present invention；
Fig. 4 is the schematic diagram of internal structure of the fatigue driving judgment module of the embodiment of the present invention.
Specific embodiment
The embodiment of the present invention is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, and for explaining only the invention, and is not construed as limiting the claims.
Those skilled in the art of the present technique are appreciated that unless expressly stated, singular " one " used herein, " one
It is a ", " described " and "the" may also comprise plural form.It is to be further understood that being arranged used in specification of the invention
Diction " comprising " refer to that there are the feature, integer, step, operation, element and/or component, but it is not excluded that in the presence of or addition
Other one or more features, integer, step, operation, element, component and/or their group.It should be understood that when we claim member
Part is " connected " or when " coupled " to another element, it can be directly connected or coupled to other elements, or there may also be
Intermediary element.In addition, " connection " used herein or " coupling " may include being wirelessly connected or wirelessly coupling.It is used herein to arrange
Diction "and/or" includes one or more associated wholes for listing item or any cell and all combinations.
Those skilled in the art of the present technique are appreciated that unless otherwise defined, all terms used herein (including technology art
Language and scientific term), there is meaning identical with the general understanding of those of ordinary skill in fields of the present invention.Should also
Understand, those terms such as defined in the general dictionary, it should be understood that have in the context of the prior art
The consistent meaning of meaning, and unless idealization or meaning too formal otherwise will not be used by specific definitions as here
To explain.
Those skilled in the art of the present technique are appreciated that " terminal " used herein above, " terminal device " both include wireless communication
The equipment of number receiver, only has the equipment of the wireless signal receiver of non-emissive ability, and including receiving and emitting hardware
Equipment, have on bidirectional communication link, can carry out two-way communication reception and emit hardware equipment.This equipment
It may include: honeycomb or other communication equipments, shown with single line display or multi-line display or without multi-line
The honeycomb of device or other communication equipments；PCS (Personal Communications Service, PCS Personal Communications System), can
With combine voice, information processing, fax and/or info-communication ability；PDA (Personal Digital Assistant, it is personal
Digital assistants), it may include radio frequency receiver, pager, the Internet/intranet access, web browser, notepad, day
It goes through and/or GPS (Global Positioning System, global positioning system) receiver；Conventional laptop and/or palm
Type computer or other equipment, have and/or the conventional laptop including radio frequency receiver and/or palmtop computer or its
His equipment." terminal " used herein above, " terminal device " can be it is portable, can transport, be mounted on the vehicles (aviation,
Sea-freight and/or land) in, or be suitable for and/or be configured in local runtime, and/or with distribution form, operate in the earth
And/or any other position operation in space." terminal " used herein above, " terminal device " can also be communication terminal, on
Network termination, music/video playback terminal, such as can be PDA, MID (Mobile Internet Device, mobile Internet
Equipment) and/or mobile phone with music/video playing function, it is also possible to the equipment such as smart television, set-top box.
It was found by the inventors of the present invention that the pass of the testing result inaccuracy of the existing fatigue detection method based on physiological characteristic
Key reason is: fatigue detecting algorithm is the image bowed again and again that is shown based on collected current driver's to carry out
Operation.When driver head deflects situation, for example, the head back torsion for working as driver or head side are to the left
Or when right side, the face image of acquisition is deflected.Since the face image of acquisition deflects, current driving can not be collected
The image bowed again and again that is shown of member, based on the image bowed again and again that collected current driver's are shown come into
The fatigue detecting algorithm of row operation also just fails, can not know driver whether the information of fatigue driving, cause to be easy to appear
Judge situation by accident, reduction judges whether driver is in the accuracy of fatigue driving state.
Therefore, it is necessary to provide a kind of the tired of the location information that can obtain more high accuracy, the human eye key point of precision
Please the detection method sailed, thus between the location information of the human eye key point based on acquisition and human eye key point line
Angle information, mobile device can more precisely know driver whether the information of fatigue driving, when driver occur fatigue
When driving, driver is reminded, so that driver is in the state of safe driving, when improving driver's long-duration driving
Safety.
The present inventor is it is considered that the camera that can use mobile device shoots the face of active user
Afterwards, human face region is detected from the facial image of shooting, face key point is determined from human face region, according to face key
Point determines human eye area, and then determines the human eye key point in human eye area, and then according between human eye key point line
Angle information, can more precisely judge driver whether fatigue driving.
Moreover, being laid out rule by human face compared to existing, or judge to drive by the method for pupil detection
Member whether fatigue driving, technical solution of the present invention is not easily susceptible to the influence of human face posture, illumination variation；In fact, working as face
Posture changes, and when face deflects, the angle of human eye key point line can't change, therefore, of the invention
Judgment method of the technical solution in human face posture, illumination variation compared with the prior art has more high accuracy.So that
When fatigue driving occurs in driver, it is reminded in time, improves the safety of long-duration driving.
The technical solution that the invention will now be described in detail with reference to the accompanying drawings.
In the embodiment of the present invention, mobile device can use the facial image of batch before carrying out fatigue driving detection
Human-face detector is trained；The specific method that human-face detector is trained is well known to those skilled in the art, this
Place repeats no more.
In the embodiment of the present invention, mobile device carries out the specific method stream of fatigue driving detection according to present frame facial image
Journey includes the following steps: as shown in Figure 1a
S101: the facial image of driver is acquired, therefrom detects human face region.
In view of current mobile device, especially mobile phone, tablet computer etc. are commonly provided with camera (for example, preposition camera shooting
Head).Therefore, in this step, mobile device can use its front camera and shoot to the face of user, to collect
The facial image of driver.
After mobile device collects the first frame facial image of driver, it is fixed to can use human-face detector trained in advance
Position goes out human face region.For example, indicating the human face region detected from the facial image positioned at the box of personnel face in Fig. 2 a.
S102: determining the face key point in human face region, the face key point as present frame facial image.
Specifically, mobile device utilizes face Keypoint detector trained in advance from the human face region oriented, really
Determine the face key point in human face region, the face key point as present frame facial image；This present frame facial image can be with
It is first frame facial image.That is, can determine present frame face using face Keypoint detector trained in advance
The location information of the face key point of image.Face key point may include: that human eye key point, people's nose key point and mouth are crucial
Point.The location information of face key point specifically can be the coordinate information of face key point plane where facial image.Face
The training method of Keypoint detector is well known to those skilled in the art, and details are not described herein again.
Preferably, mobile device can use Supervised Descent Method (supervision descent method) from face area
Face key point is determined in domain.
Such as multiple points of the quartile at personnel's eyes, nose and mouth in the box of Fig. 2 b, all indicate present frame face
The face key point of image.
S103: after the human eye area for determining present frame facial image according to the face key point of present frame facial image,
It is located at the human eye key point in human eye area from selection in face key point.
In order to improve detection efficiency and the accuracy of human eye area, mobile device can be according to the people of present frame facial image
Face key point determines the human eye area of present frame facial image, and then is located in human eye area from choosing in face key point
Human eye key point, the human eye key point as present frame facial image.Human eye key point may include: canthus key point, upper eye
Eyelid key point and palpebra inferior key point.
S104: according to the angle information between the human eye key point line in the human eye area of present frame facial image, sentence
Disconnected driver whether fatigue driving.
In this step, mobile device can be according to the human eye key point line in the human eye area of present frame facial image
Between angle information, judge driver whether fatigue driving.
In practical application, mobile device can according in the human eye key point of present frame facial image canthus key point with
Angle information between the line and canthus key point and the line of palpebra inferior key point of upper eyelid key point, can be accurate
Ground judge driver whether fatigue driving.
Specifically, if the company of canthus key point and upper eyelid key point in the human eye key point of present frame facial image
When angle between line and canthus key point and the line of palpebra inferior key point is less than preset threshold, driver fatigue is judged
It drives.In this way, mobile device can accurately know that driver is in fatigue driving state, and driver is reminded, is made
Obtain the state that driver is in safe driving.
Conversely, if judging that driver is in non-fatigue and drives when the angle between key point line is greater than preset threshold
State is sailed, and records the parameter information of current location calibration point.In this way, mobile device can accurately know that driver is in non-
Fatigue driving state, and record the parameter information of current location calibration point.
More preferably, above-mentioned threshold value, can also be by largely acquiring the face of the driver either fixed setting in advance
Image, and learnt according to the angle information between the human eye key point line in the human eye area in a large amount of facial images,
Training, obtains the threshold value for being suitable for the driver.Its specific training method can apply some model trainings of the prior art
Method, details are not described herein again.In fact, its human eye area feature of image of each different driver is different；Therefore, according to
Threshold value is arranged in the human eye area feature of image of each driver itself, helps to improve the judgment accuracy of fatigue driving.
More preferably, mobile device is closed according to upper eyelid key point in the human eye key point of present frame facial image and palpebra inferior
The location information of key point determines the percentage of the eyes closed time of driver using PERCLOS (eyelid closure) algorithm
Rate；When the percentage for the eyes closed time determined is not less than the percentage threshold value of preset eyes closed time, judgement
Driver is in fatigue driving state out；When the percentage for the eyes closed time determined is less than the preset eyes closed time
Percentage threshold value when, judge that driver is in non-fatigue driving state.
More preferably, to improve the speed for judging fatigue driving state, to find the fatigue driving state of driver in time
Carry out alarm prompting, in technical solution of the present invention, mobile device be can use after continuing to acquire next frame facial image preceding
The face key point of frame accelerates fatigue driving detection, specific method process, as shown in Figure 1 b, in above-mentioned steps S101-S104
Later further include following steps:
S105: continue after acquiring next frame facial image, at the beginning of the position using the face key point of previous frame facial image
Beginningization next frame facial image obtains the initialization human face region of next frame facial image.
Specifically, mobile device continues after acquiring next frame facial image, using current described in above-mentioned steps S102
The face key point of frame facial image, i.e., using the location information of the face key point of previous frame facial image, from next frame people
One rough human face region of Primary Location is in face image to get the initialization human face region and its position for arriving next frame facial image
Confidence breath.
The face in next frame facial image can be quickly positioned due to the face key point using previous frame facial image
Region can greatly save the time from next frame facial image locating human face region compared to using human-face detector, thus whole
The time for reducing fatigue driving detection on body, detection efficiency is improved, accelerates detection speed.
S106: finally differentiate that initialization human face region is the face in next frame facial image really using recognition of face device
Behind region, from the human face region in next frame facial image, the face key point of next frame facial image is determined.
Specifically, recognition of face device can be two classification device, can be trained in advance by multiple positive samples and negative sample
It obtains；Wherein, positive exemplar uses facial image, and negative sample can be using other images other than facial image.Specifically
Training method can use conventional process well-known to those skilled in the art, and details are not described herein again.
Mobile device differentiates whether initialization human face region is next frame people using the recognition of face device that training obtains in advance
Human face region in face image: if so, from the human face region in next frame facial image, next frame facial image is determined
Face key point；Otherwise ignore the next frame facial image that shooting obtains, and return to step S105.From next frame facial image
In human face region in, determine the specific method of the face key point of next frame facial image, in above-mentioned steps S102 determine
The specific method of the face key point of present frame facial image is identical, and details are not described herein again.
S107: determining the human eye area in next frame facial image according to the face key point of next frame facial image,
It is crucial from the human eye chosen in the face key point of next frame facial image in the human eye area being located in next frame facial image
Point, the human eye key point as next frame facial image.
Specifically, mobile device is determined in next frame facial image according to the face key point of next frame facial image
Human eye area.
Later, mobile device is chosen in next frame facial image from the face key point of next frame facial image
Human eye key point in human eye area, as next frame facial image.
S108: according to the angle information between the human eye key point line of next frame facial image, whether judge driver
Fatigue driving.
Specifically, mobile device is according to the angle information between the human eye key point line of next frame facial image, judgement
Driver whether fatigue driving, according to the people in the human eye area of present frame facial image in specific method and above-mentioned steps S104
Eye key point line between angle information, judge driver whether fatigue driving method it is consistent, details are not described herein again.
The method for detecting fatigue driving of above-mentioned steps S101 to step S108 is not needed to acquisition compared with prior art
Every frame image does Face datection, and mobile device only needs to directly read the face key point of stored previous frame facial image
Location information, and calculated with this information, to obtain the location information of the human face region of next frame facial image, Jin Ercong
The human eye key point of next frame facial image is obtained in the human face region of next frame facial image, and carries out fatigue driving judgement.
This will greatly improve and determines the human eye key point of next frame facial image and its speed of location information, improve user experience
Degree.
Based on the detection method of above-mentioned fatigue driving, it can be applied the embodiment of the invention provides one kind and be set to movement
Fatigue driving detection device in equipment, as shown in figure 3, can specifically include: human face region detection module 301, face are crucial
Point determining module 302, human eye key point determining module 303 and fatigue driving judgment module 304.
Wherein, human face region detection module 301 is used to acquire the facial image of driver, therefrom detects human face region.
Face key point determining module 302 is used for from human face region detected by human face region detection module 301 really
Face key point is made, the face key point as present frame facial image.
Human eye key point determining module 303 is used for the present frame face according to determined by face key point determining module 302
The face key point of image after determining human eye area, is chosen from the face key point of present frame facial image and is located at human eye
Human eye key point in region, the human eye key point as frame facial image.
Fatigue driving judgment module 304 is in the human eye area according to determined by human eye key point determining module 303
Angle information between human eye key point line, judge driver whether fatigue driving.
Preferably, human face region detection module 301 is also used to continue camera the next frame facial image of acquisition, benefit
With the position initialization next frame facial image of the face key point of previous frame facial image, the first of next frame facial image is obtained
Beginningization human face region.
Face key point determining module 302 also finally differentiates 301 gained of human face region detection module using recognition of face device
To initialization human face region be really human face region in next frame facial image after, face from next frame facial image
In region, the face key point of next frame facial image is determined.
Human eye key point determining module 303 is also used to the next frame people according to determined by face key point determining module 302
The face key point of face image determines the human eye area in next frame facial image, crucial from the face of next frame facial image
The human eye key point in the human eye area being located in next frame facial image, the human eye as next frame facial image are chosen in point
Key point.
Fatigue driving judgment module 304 is also used to the next frame face according to determined by human eye key point determining module 303
Angle information between the human eye key point line of image, judge driver whether fatigue driving.
More preferably, the schematic diagram of internal structure of fatigue driving judgment module 304 is as shown in figure 4, specifically include: human eye is crucial
Point line unit 401 and judging unit 402.
Wherein, human eye key point line unit 401 is for determining that human eye determined by human eye key point determining module 303 closes
The line of canthus key point and upper eyelid key point in key point；And the line of the canthus key point and palpebra inferior key point.
Canthus of the judging unit 402 in the human eye key point determined by human eye key point line unit 401 is crucial
Point and the angle between the line and the canthus key point and the line of palpebra inferior key point of upper eyelid key point are less than default
When threshold value, driver tired driving is judged, otherwise, judge that driver is in non-fatigue driving state.
Specifically, the canthus key point in the human eye key point determined by human eye key point line unit 401 and upper eye
When angle between the line of eyelid key point and the canthus key point and the line of palpebra inferior key point is less than preset threshold,
The judging unit 402 of fatigue driving judgment module 303 is for judging driver tired driving.Thus, driver is reminded,
So that driver is in the state of safe driving, safety when driver's long-duration driving is improved.
Conversely, canthus key point and upper eyelid in the human eye key point determined by human eye key point line unit 401
It is tired when angle between the line of key point and the canthus key point and the line of palpebra inferior key point is greater than preset threshold
Please the judging unit 402 for sailing judgment module 303 judges that driver is in non-fatigue driving state.
Further, the detection device of the fatigue driving of the embodiment of the present invention, further includes: logging modle (is not marked) in figure.
After the judging unit 402 of fatigue driving judgment module 304 judges that driver is in non-fatigue driving state,
In order to further improve the data-handling efficiency of facial image, start the function of the recording parameters information of logging modle.Record
The location information of each face key point of the module for further recording previous frame (or present frame) facial image.
In order to further improve the data processing speed of facial image, the detection device of fatigue driving further includes storage mould
Block (is not marked) in figure, wherein memory module is used for the position of each face key point of previous frame (or present frame) facial image
Information is stored.In this way, the face key point that mobile device can use previous frame facial image can quickly position it is next
Human face region in frame facial image, can be big from next frame facial image locating human face region compared to using human-face detector
It is big to save the time, so that the time of reduction fatigue driving detection on the whole, improves detection efficiency, accelerate detection speed.
Above-mentioned human face region detection module 301, face key point determining module 302, human eye key point determining module 303,
The concrete methods of realizing of fatigue driving judgment module 304 and its human eye key point line unit 401 and 402 function of judging unit,
The particular content of above-mentioned method flow step as illustrated in figs. 1A and ib can be referred to, details are not described herein again.
In technical solution of the present invention, due to acquiring the facial image of driver, human face region is therefrom detected, from face
The face key point of present frame facial image is determined in region, and then determines human eye key point, is connected according to human eye key point
Angle information between line judges the fatigue driving state of driver；Rule is laid out by human face compared to existing, or
Position of human eye is obtained by the method for pupil detection, the influence of human face posture, illumination variation is less susceptible to, to improve fatigue
Driving condition accuracy in detection.
Moreover, in the embodiment of the present invention, based on more high accuracy, the position of human eye information of precision, in human eye area
Angle information between human eye key point line is read out, judge driver whether fatigue driving；Compared to existing human eye state
Detection method, the present invention is based on more high accuracies, the closure degree for judging human eye of precision, to more precisely know driving
Member whether remind driver, when fatigue driving occurs in driver so that at driver in time by the information of fatigue driving
In the state of safe driving, safety when driver's long-duration driving is improved.
It further, can in the method for carrying out fatigue driving detection according to adjacent two frames facial image of the embodiment of the present invention
The human face region that next frame facial image is initially dissolved with the face key point using present frame facial image, and from each frame people
Detect that human face region is compared in face image, computation amount improves the speed of fatigue driving detection on the whole, can be with
The fatigue driving state of driver is detected in time and is reminded, and traffic safety is improved.
Those skilled in the art of the present technique are appreciated that the present invention includes being related to for executing in operation described herein
One or more equipment.These equipment can specially design and manufacture for required purpose, or also may include general
Known device in computer.These equipment have the computer program being stored in it, these computer programs are selectively
Activation or reconstruct.Such computer program can be stored in equipment (for example, computer) readable medium or be stored in
It e-command and is coupled in any kind of medium of bus respectively suitable for storage, the computer-readable medium includes but not
Be limited to any kind of disk (including floppy disk, hard disk, CD, CD-ROM and magneto-optic disk), ROM (Read-Only Memory, only
Read memory), RAM (Random Access Memory, immediately memory), EPROM (Erasable Programmable
Read-Only Memory, Erarable Programmable Read only Memory), EEPROM (Electrically Erasable
Programmable Read-Only Memory, Electrically Erasable Programmable Read-Only Memory), flash memory, magnetic card or light card
Piece.It is, readable medium includes by equipment (for example, computer) with any Jie for the form storage or transmission information that can be read
Matter.
Those skilled in the art of the present technique be appreciated that can be realized with computer program instructions these structure charts and/or
The combination of each frame and these structure charts and/or the frame in block diagram and/or flow graph in block diagram and/or flow graph.This technology neck
Field technique personnel be appreciated that these computer program instructions can be supplied to general purpose computer, special purpose computer or other
The processor of programmable information processing method is realized, to pass through the processing of computer or other programmable information processing methods
The scheme specified in frame or multiple frames of the device to execute structure chart and/or block diagram and/or flow graph disclosed by the invention.
Those skilled in the art of the present technique have been appreciated that in the present invention the various operations crossed by discussion, method, in process
Steps, measures, and schemes can be replaced, changed, combined or be deleted.Further, each with having been crossed by discussion in the present invention
Kind of operation, method, other steps, measures, and schemes in process may also be alternated, changed, rearranged, decomposed, combined or deleted.
Further, in the prior art to have and the step in various operations, method disclosed in the present invention, process, measure, scheme
It may also be alternated, changed, rearranged, decomposed, combined or deleted.
The above is only some embodiments of the invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (9)
1. a kind of method for detecting fatigue driving characterized by comprising
The facial image for acquiring driver, therefrom detects human face region, determines the face key point in the human face region, makees
For the face key point of present frame facial image；
After determining human eye area according to the face key point, is chosen from the face key point and be located at the human eye area
In human eye key point；
According to the angle information between the human eye key point line in the human eye area, judging the driver, whether fatigue is driven
It sails；
Further include:
Continue acquire next frame facial image after, described in the position initialization using the face key point of previous frame facial image under
One frame facial image obtains the initialization human face region of the next frame facial image；
Finally differentiate that the initialization human face region is the face in the next frame facial image really using recognition of face device
Behind region, from the human face region in the next frame facial image, the face key point of next frame facial image is determined；
The human eye area in next frame facial image is determined according to the face key point of the next frame facial image, from described
The human eye key point in the human eye area being located in next frame facial image is chosen in the face key point of next frame facial image,
Human eye key point as next frame facial image；
According to the angle information between the human eye key point line of next frame facial image, judging the driver, whether fatigue is driven
It sails.
2. the method as described in claim 1, which is characterized in that the recognition of face implement body is two classification device, Yi Jishi
It is obtained by the training in advance of multiple positive and negative samples；
Wherein, the positive sample is specially facial image, and the negative sample is other images.
3. the method according to claim 1, which is characterized in that the facial image of the acquisition driver, therefrom
It detects human face region, specifically includes:
After the facial image for acquiring driver, using human-face detector trained in advance, human face region is oriented.
4. the method according to claim 1, which is characterized in that the face in the determination human face region closes
Key point, specifically includes:
Using facial feature points detection device trained in advance from the human face region oriented, the people in the human face region is determined
Face key point, the face key point as present frame facial image.
5. the method according to claim 1, which is characterized in that the key point of human eye connects in the human eye area
Line, comprising:
The line of canthus key point and upper eyelid key point in the human eye key point；
The line of the canthus key point and palpebra inferior key point.
6. method as claimed in claim 5, which is characterized in that the human eye key point line according in the human eye area
Between angle information, judge the driver whether fatigue driving, specifically include:
When angle between the key point line is less than preset threshold, the driver tired driving is judged.
7. method as claimed in claim 5, which is characterized in that the method also includes:
When angle between the key point line is greater than preset threshold, judge that the driver is in non-fatigue driving shape
State.
8. a kind of fatigue driving detection device characterized by comprising
Human face region detection module therefrom detects human face region for acquiring the facial image of driver；
Face key point determining module, for being determined from the human face region detected by the human face region detection module
Face key point out, the face key point as present frame facial image；
Human eye key point determining module, for the present frame facial image according to determined by the face key point determining module
Face key point after determining human eye area, is closed from the human eye being located in the human eye area is chosen in the face key point
Key point；
Fatigue driving judgment module, for the people in the human eye area according to determined by the human eye key point determining module
Eye key point line between angle information, judge the driver whether fatigue driving；
The human face region detection module is also used to continue camera the next frame facial image of acquisition, utilizes previous frame people
Next frame facial image described in the position initialization of the face key point of face image obtains the initial of the next frame facial image
Change human face region；
The face key point determining module also utilizes recognition of face device finally to differentiate that the initialization human face region is institute really
After stating the human face region in next frame facial image, from the human face region in the next frame facial image, next frame is determined
The face key point of facial image；
The human eye key point determining module is also used to be determined according to the face key point of the next frame facial image next
Human eye area in frame facial image is chosen from the face key point of the next frame facial image and is located at next frame face figure
The human eye key point in human eye area as in, the human eye key point as next frame facial image；
The fatigue driving judgment module is also used to the letter of the angle between the human eye key point line according to next frame facial image
Breath, judge the driver whether fatigue driving.
9. device as claimed in claim 8, which is characterized in that the fatigue driving judgment module specifically includes:
Human eye key point line unit, for determining in the human eye key point determined by the human eye key point determining module
Canthus key point and the line of upper eyelid key point and the line of the canthus key point and palpebra inferior key point；
Judging unit, for the canthus key point in the human eye key point determined by the human eye key point line unit
Angle between the line and the canthus key point and the line of palpebra inferior key point of upper eyelid key point is less than default
When threshold value, the driver tired driving is judged, otherwise, judge that the driver is in non-fatigue driving state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510393702.5A CN106327801B (en) | 2015-07-07 | 2015-07-07 | Method for detecting fatigue driving and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510393702.5A CN106327801B (en) | 2015-07-07 | 2015-07-07 | Method for detecting fatigue driving and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106327801A CN106327801A (en) | 2017-01-11 |
| CN106327801B true CN106327801B (en) | 2019-07-26 |
Family
ID=57727488
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510393702.5A Active CN106327801B (en) | 2015-07-07 | 2015-07-07 | Method for detecting fatigue driving and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106327801B (en) |
Families Citing this family (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109803583A (en) * | 2017-08-10 | 2019-05-24 | 北京市商汤科技开发有限公司 | Driver monitoring method, apparatus and electronic equipment |
| CN107818310B (en) * | 2017-11-03 | 2021-08-06 | 电子科技大学 | Driver attention detection method based on sight |
| CN108062526B (en) * | 2017-12-15 | 2021-05-04 | 厦门美图之家科技有限公司 | Human body posture estimation method and mobile terminal |
| CN108021911B (en) * | 2018-01-04 | 2018-09-11 | 重庆公共运输职业学院 | A kind of driver tired driving monitoring method |
| CN110278367B (en) * | 2018-03-14 | 2021-11-19 | 厦门歌乐电子企业有限公司 | Human eye detection method, system, device and medium based on shooting device |
| CN108545080A (en) * | 2018-03-20 | 2018-09-18 | 北京理工大学 | Driver Fatigue Detection and system |
| CN109086719A (en) * | 2018-08-03 | 2018-12-25 | 北京字节跳动网络技术有限公司 | Method and apparatus for output data |
| CN110826372B (en) * | 2018-08-10 | 2024-04-09 | 浙江宇视科技有限公司 | Face feature point detection method and device |
| CN109522863B (en) * | 2018-11-28 | 2020-11-27 | 北京达佳互联信息技术有限公司 | Ear key point detection method and device and storage medium |
| CN109948590B (en) * | 2019-04-01 | 2020-11-06 | 启霖世纪（北京）教育科技有限公司 | Attitude problem detection method and device |
| CN109977930B (en) * | 2019-04-29 | 2021-04-02 | 中国电子信息产业集团有限公司第六研究所 | Fatigue driving detection method and device |
| CN111563435A (en) * | 2020-04-28 | 2020-08-21 | 深圳市优必选科技股份有限公司 | Sleep state detection method and device for user |
| CN111645695B (en) * | 2020-06-28 | 2022-08-09 | 北京百度网讯科技有限公司 | Fatigue driving detection method and device, computer equipment and storage medium |
| CN112818838A (en) * | 2021-01-29 | 2021-05-18 | 北京嘀嘀无限科技发展有限公司 | Expression recognition method and device and electronic equipment |
| CN113887302A (en) * | 2021-08-31 | 2022-01-04 | 际络科技(上海)有限公司 | Fatigue driving detection method, device, storage medium and computer program product |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101059836A (en) * | 2007-06-01 | 2007-10-24 | 华南理工大学 | Human eye positioning and human eye state recognition method |
| CN101916496A (en) * | 2010-08-11 | 2010-12-15 | 无锡中星微电子有限公司 | System and method for detecting driving posture of driver |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6130617A (en) * | 1999-06-09 | 2000-10-10 | Hyundai Motor Company | Driver's eye detection method of drowsy driving warning system |
| CN101030316B (en) * | 2007-04-17 | 2010-04-21 | 北京中星微电子有限公司 | Safety driving monitoring system and method for vehicle |
| CN101593425B (en) * | 2009-05-06 | 2011-01-12 | 深圳市汉华安道科技有限责任公司 | Machine vision based fatigue driving monitoring method and system |
| CN102043943B (en) * | 2009-10-23 | 2012-11-07 | 华为技术有限公司 | Method and device for obtaining human face pose parameter |
| CN202472863U (en) * | 2010-12-31 | 2012-10-03 | 北京星河易达科技有限公司 | Driver fatigue monitoring network system based on image information comprehensive evaluation |
| CN102647582B (en) * | 2012-04-27 | 2015-06-03 | 浙江晨鹰科技有限公司 | Video monitoring method and system |
| CN104361716A (en) * | 2014-10-31 | 2015-02-18 | 新疆宏开电子系统集成有限公司 | Method for detecting and reminding fatigue in real time |
-
2015
- 2015-07-07 CN CN201510393702.5A patent/CN106327801B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101059836A (en) * | 2007-06-01 | 2007-10-24 | 华南理工大学 | Human eye positioning and human eye state recognition method |
| CN101916496A (en) * | 2010-08-11 | 2010-12-15 | 无锡中星微电子有限公司 | System and method for detecting driving posture of driver |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106327801A (en) | 2017-01-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106327801B (en) | Method for detecting fatigue driving and device | |
| US11375338B2 (en) | Method for smartphone-based accident detection | |
| US10867195B2 (en) | Systems and methods for monitoring driver state | |
| CN103824420B (en) | Fatigue driving identification system based on heart rate variability non-contact measurement | |
| US9694680B2 (en) | System and method for determining drowsy state of driver | |
| CN102310771B (en) | Motor vehicle safety control method and system based on driver face identification | |
| CN105354988B (en) | A kind of driver tired driving detecting system and detection method based on machine vision | |
| US10152642B2 (en) | Method for detecting driving behavior and system using the same | |
| US10078099B2 (en) | Methods and systems for aligning a mobile device to a vehicle | |
| CN202142160U (en) | Fatigue driving early warning system | |
| CN105564436A (en) | Advanced driver assistance system | |
| CN109934199A (en) | A kind of Driver Fatigue Detection based on computer vision and system | |
| CN208498370U (en) | Fatigue driving based on steering wheel detects prior-warning device | |
| CN104680714A (en) | Method and system for sending prompts to user | |
| CN111179552A (en) | Driver state monitoring method and system based on multi-sensor fusion | |
| CN109151204A (en) | A kind of air navigation aid based on mobile terminal, device and mobile terminal | |
| CN103700220A (en) | Fatigue driving monitoring device | |
| CN103714659A (en) | Fatigue driving identification system based on double-spectrum fusion | |
| CN107315997B (en) | Sight orientation judgment method and system based on rapid feature point positioning | |
| CN109308467A (en) | Traffic accident prior-warning device and method for early warning based on machine learning | |
| CN110803170B (en) | Driving assistance system with intelligent user interface | |
| CN104224205B (en) | A kind of based on simple electrocardiogram acquisition with the fatigue detection method of coupling | |
| CN116798189A (en) | State detection method, device and storage medium | |
| Bhuvaneswari et al. | Internet of vehicle based accident detection and management techniques by using vanet: An empirical study | |
| Yu et al. | Sensing Vehicle Conditions for Detecting Driving Behaviors |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |