CN108985245A - Determination method, apparatus, computer equipment and the storage medium of eye locations - Google Patents
Determination method, apparatus, computer equipment and the storage medium of eye locations Download PDFInfo
- Publication number
- CN108985245A CN108985245A CN201810826192.XA CN201810826192A CN108985245A CN 108985245 A CN108985245 A CN 108985245A CN 201810826192 A CN201810826192 A CN 201810826192A CN 108985245 A CN108985245 A CN 108985245A
- Authority
- CN
- China
- Prior art keywords
- driver
- location information
- eye
- bianry image
- ocular
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/19—Sensors therefor
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/59—Context or environment of the image inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
- G06V20/597—Recognising the driver's state or behaviour, e.g. attention or drowsiness
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
- B60W2040/0818—Inactivity or incapacity of driver
- B60W2040/0827—Inactivity or incapacity of driver due to sleepiness
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Ophthalmology & Optometry (AREA)
- Human Computer Interaction (AREA)
- Automation & Control Theory (AREA)
- Mathematical Physics (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses determination method, apparatus, computer equipment and the storage mediums of a kind of eye locations.This method comprises: when locomotive is in driving status, the bianry image that obtains driver's face, driver eye region are in the second location information of first location information and driver targeted object region in the bianry image in the bianry image;Relative positional relationship based on the targeted object region Yu the ocular is modified the first location information using the second location information, obtains identification position of the ocular in the bianry image.The embodiment of the present invention is modified the position of ocular using the position of targeted object region by using above-mentioned technical proposal, and the accuracy of eye locations definitive result can be improved, and reduces monitoring device and the probability misidentified occurs.
Description
Technical field
The present invention relates to technical field of image processing more particularly to a kind of determination method, apparatus of eye locations, computer
Equipment and storage medium.
Background technique
In recent years, long routing, single-operator on duty operating mode be increasingly becoming China Railway (including subway fortune
It is defeated) operating mode carried out extensively.
The use of long routing, single-operator on duty operating mode is effectively reduced the outfit quantity of driver, still,
Since the operator region of trainman (i.e. engineer) under the operating mode is usually long, trainman is at work
The probability that fatigue occurs also increases with it, and in recent years, the fatigue driving of trainman has become important in train operating safety
Risk factors.Currently, bad, tired, even drowsiness etc. is pacified for driver and conductor's working condition for being likely to occur in locomotive operation
Full hidden danger detects the method progress performance review of guidance or nobody is arranged and is vigilant relative to traditional administrative staff's follow the bus taken
The regulation model that the means of button are managed driver and conductor is monitored to determine machine trainman by monitoring system
Vehicle driver regulation model whether in a state of fatigue has obtained people with its efficient monitoring efficiency and has more and more paid close attention to.Prison
Examining system is when being monitored trainman, it usually needs determines position of the trainman in acquired picture first, so
The eye state of trainman is determined based on the texture information of picture at this location afterwards, and then determines whether trainman is in
Fatigue state.
But inventor has found in the implementation of the present invention, the prior art is when determining trainman's eye locations
Often there is a problem of that accuracy rate is lower, causes the accuracy rate of trainman's fatigue state definitive result lower, it can not be effective
Improve the safety in train travelling process.
Summary of the invention
In view of this, the embodiment of the present invention provides determination method, apparatus, computer equipment and the storage of a kind of eye locations
Medium, the lower technical problem of accuracy rate to solve trainman's eye locations definitive result in the prior art.
In a first aspect, the embodiment of the invention provides a kind of determination methods of eye locations, comprising:
When locomotive is in driving status, the bianry image of driver's face, driver eye region are obtained described two
It is worth second location information of the first location information and driver targeted object region in image in the bianry image;
Relative positional relationship based on the targeted object region Yu the ocular, using the second location information
The first location information is modified, identification position of the ocular in the bianry image is obtained.
Second aspect, the embodiment of the invention provides a kind of determining devices of eye locations, comprising:
Data obtaining module, for when locomotive is in driving status, obtaining bianry image, the driver of driver's face
Ocular in the bianry image first location information and driver targeted object region in the bianry image
Second location information;
First position determining module is closed for the relative position based on the targeted object region and the ocular
System, is modified the first location information using the second location information, obtains the ocular in the two-value
Identification position in image.
The third aspect, the embodiment of the invention provides a kind of computer equipments, comprising:
One or more processors;
Memory, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processing
Device realizes the determination method of eye locations as described in the embodiments of the present invention.
Fourth aspect, the embodiment of the invention also provides a kind of computer readable storage mediums, are stored thereon with computer
Program, the program realize the determination method of eye locations as described in the embodiments of the present invention when being executed by processor.
In the technical solution of above-mentioned determining eye locations, when locomotive is in driving status, driver's face is obtained
Bianry image, and determine first location information and driver targeted object region of the driver eye region in the bianry image
Second location information in bianry image, according to the relative positional relationship of targeted object region and ocular, using this
Two location informations are modified the first location information, obtain identification position of the driver eye region in bianry image.
The technical solution of above-mentioned determining eye locations is modified the position of ocular using the position of targeted object region, can
To improve the accuracy of eye locations definitive result, reduces monitoring device and the probability misidentified occur.
Detailed description of the invention
By reading a detailed description of non-restrictive embodiments in the light of the attached drawings below, of the invention other
Feature, objects and advantages will become more apparent upon:
Fig. 1 is a kind of flow diagram of the determination method for eye locations that the embodiment of the present invention one provides;
Fig. 2 is a kind of flow diagram of the determination method of eye locations provided by Embodiment 2 of the present invention;
Fig. 3 is a kind of structural block diagram of the determining device for eye locations that the embodiment of the present invention three provides;
Fig. 4 is a kind of structural schematic diagram for computer equipment that the embodiment of the present invention four provides.
Specific embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention rather than limiting the invention.It also should be noted that in order to just
In description, only some but not all contents related to the present invention are shown in the drawings.
Embodiment one
The embodiment of the present invention one provides a kind of determination method of eye locations.This method can be filled by determining for eye locations
Set execution, wherein the device can generally be integrated in the calculating with fatigue warning function by software and or hardware realization
In machine equipment.Fig. 1 is a kind of flow diagram of the determination method for eye locations that the embodiment of the present invention one provides, such as Fig. 1 institute
Show, this method comprises:
S110, when locomotive is in driving status, obtain the bianry image of driver's face, driver eye region in institute
State the second location information of first location information and driver targeted object region in the bianry image in bianry image.
Wherein, targeted object region can be understood as other energy in the bianry image of driver's face in addition to ocular
The block of pixels for enough characterizing face feature, such as forehead region, brow region, nasal area, chin area, cheekbone area or cheek area
Domain etc. specifically can according to need and be configured, and the present embodiment is limited not to this.In view of targeted object region
Second location information error that may be present, the target area preferably may include brow region, nasal area, maxillary area
At least two in domain, cheekbone area and cheek region, to further increase the identification position of subsequent determined ocular
Accuracy.
In the present embodiment, it can determine whether locomotive is in driving status based on the present speed of locomotive, i.e., if locomotive
Present speed be 0, then determine that locomotive is not in driving status, if the present speed of locomotive is not 0, can be determined that locomotive
In driving status.Here, the determination method of locomotive present speed can according to need setting, can such as be sensed by angular speed
Device detects the angular speed of locomotive wheel or detects the speed of locomotive by linear velocity trans;Alternatively, passing through acceleration sensing
Device detects the acceleration of locomotive, at this point, can be determined that locomotive is in driving status if the acceleration of locomotive is not 0, if
The acceleration of locomotive is 0, then can be based further on locomotive by original stationary state (or speed of service by last moment)
The variation for becoming current state brief acceleration calculates the present speed of locomotive, and then determines whether locomotive is in driving status;?
Can be clicked by driver or crew when locomotive starts running configured in locomotive start running button and locomotive stop
Afterwards click locomotive in configure locomotive stop button, at this point, correspondingly, if detect driver and conductor clicked bring into operation by
Button but not yet click locomotive stop button, then can be determined that locomotive is in driving status;Alternatively, from the machine for establishing connection with locomotive
Vehicle on-vehicle safety guard system (such as TAX machine or 6A system) obtains the running condition information, etc. of locomotive, does not limit herein
System.
In the present embodiment, after determining that locomotive is in driving status, the bianry image of available driver, and determination is driven
The targeted object region of first location information and driver of the person's of sailing ocular in the bianry image is in bianry image
Second location information, so that subsequent can determine driver eye's based on the first location information and the second location information
Accurate location.Here, bianry image can carry out processing acquisition by the color image or infrared image of driver's face.
Influence in view of extraneous factor (such as light etc.) to acquisition image definition, it is preferred that can be based on driving
The infrared image of member's face determines its bianry image.Specifically, can control target after determining that locomotive is in driving status and take the photograph
Camera acquires infrared image, and removes the background information in the infrared image, to obtain the grayscale image of driver's face;Using
Dynamic edge analytic approach handles the grayscale image, obtains the bianry image of driver's face.Wherein, target video camera can
It is indoor for acquiring the thermal camera of driver's facial image to be interpreted as being located at service on buses or trains.
It should be noted that i.e. locomotive is merely able to along locomotive if locomotive is only configured with attendant room at headstock position
Tail, then can be when determining that locomotive is in driving status to the direction running of headstock, and the target directly controlled in locomotive head is taken the photograph
The infrared image of camera acquisition driver's face;If being each equipped with attendant room at the headstock and the tailstock of locomotive, which is taken the photograph
Camera is preferably located at the indoor video camera of locomotive head service on buses or trains under the driving direction, at this point, in the control target video camera
It preferably can also include: to obtain the driving direction of locomotive, and by the traveling side before setting period acquisition infrared image
The downward indoor video camera of locomotive head service on buses or trains is determined as target video camera.
It illustratively, can be first when determining the location information of ocular and targeted object region in bianry image
The texture information of driver eye and the texture information of target object are first obtained, then according to acquired texture information two
It is worth ocular and the targeted object region that driver is identified in image, so that it is determined that driver eye region and target object area
Location information of the domain in bianry image.Wherein, the texture information of driver's each position can acquire in advance, and be stored in locomotive
The computer equipment local of interior configuration is stored in the server being connected with the equipment or other systems, equipment.
S120, the relative positional relationship based on the targeted object region Yu the ocular, using the second
Confidence breath is modified the first location information, obtains identification position of the ocular in the bianry image.
Illustratively, the relative positional relationship that targeted object region and ocular can be obtained first, it is opposite according to this
The third place in driver eye region in positional relationship and the second location information of targeted object region prediction bianry image
Information is modified the first location information of acquired driver eye using the third place information, is driven with determining
Position of member's ocular in bianry image, i.e. identification position.It, such as can be with here, correcting mode can according to need setting
The average value or weighted average of first location information and the third place information are determined as ocular in bianry image
Identify position.Wherein, the weighted value of first location information and the third place information can according to need when calculating weighted average
Setting, such as the weighted value of first location information can be set to 0.6, set 0.4 for the weighted value of the third place information
Deng;The relative positional relationship of targeted object region and ocular can first pass through the multiple samples of acquisition and in advance to sample collected
Originally it is trained acquisition, it can be for certain universality, the relative position pass that can be used in determining different people eye locations
System, or only can be suitably used for the relative positional relationship of the driver, herein with no restriction.
The determination method for the eye locations that the embodiment of the present invention one provides is obtained and is driven when locomotive is in driving status
The bianry image of member's face, and determine first location information and driver target of the driver eye region in the bianry image
Second location information of the subject area in bianry image, according to the relative positional relationship of targeted object region and ocular,
The first location information is modified using the second location information, obtains knowledge of the driver eye region in bianry image
Other position.The present embodiment by using above-mentioned technical proposal, using targeted object region position to the position of ocular into
Row amendment, can be improved the accuracy of eye locations definitive result, reduces monitoring device and the probability misidentified occurs.
Embodiment two
Fig. 2 is a kind of flow diagram of the determination method of eye locations provided by Embodiment 2 of the present invention.The present embodiment
It optimizes on the basis of the above embodiments, further, obtains the ocular in the bianry image described
Identification position after, further includes: according to the subgraph of ocular described in the identification position acquisition bianry image, and base
Determine that the eye status information of driver, the eye status information are closed state or non-occluded state in the subgraph;
The current fatigue exponent of driver is determined according to the original fatigue exponent of the eye status information and driver, it is described original
Fatigue exponent is the fatigue exponent determined based on a upper bianry image;If the current fatigue exponent reaches the index of setting
Threshold value then carries out tired prompting to driver.
Further, after the tired prompting to driver's progress, further includes: propose the fatigue that the fatigue is reminded
Awake information, locomotive information and driver information are reported to control centre.
Correspondingly, as shown in Fig. 2, the determination method of eye locations provided in this embodiment includes:
S210, when locomotive is in driving status, obtain the bianry image of driver's face, driver eye region in institute
State the second location information of first location information and driver targeted object region in the bianry image in bianry image.
S220, the relative positional relationship based on the targeted object region Yu the ocular, using the second
Confidence breath is modified the first location information, obtains identification position of the ocular in the bianry image.
The subgraph of S230, the ocular according to the identification position acquisition bianry image, and it is based on the son
Image determines that the eye status information of driver, the eye status information are closed state or non-occluded state.
In the present embodiment, identification position can be the center of ocular, or the position of ocular profile
It sets.Correspondingly, if the identification position is the center of ocular, it can the phase based on ocular with facial image
The size of ocular is determined to size, and centered on determining identification position, is intercepted in bianry image according to the size
The subgraph of ocular;If the identification position is the outline position of eye, identification position interception can be directly based upon
The subgraph of ocular alternatively, the identification position, which is expanded setting pixel, obtains interception position, and is based on the interception position
Ocular subgraph is intercepted, to ensure available complete eyes image.Wherein, the shape of intercepted subgraph can root
According to needing to be arranged, such as it can be set to the shape of rectangle, ellipse or eye profile.
It, can be according to the color in subgraph at eyeball position after getting the subgraph of ocular in this step
(or texture) determines the eye status information of driver.Illustratively, the location information of eyeball in subgraph can be determined first,
Such as the central area of subgraph can be determined as eyeball;Then identify whether the color (or texture) at the position meets
Standard color (or texture) information when eyes are opened, if so, the eye state of driver can be determined as non-closed shape
State determines that driver's eyes are in and opens state, if it is not, then the eye state of driver can be determined as closed state.
S240, the current fatigue that driver is determined according to the original fatigue exponent of the eye status information and driver
Index, the original fatigue exponent are the fatigue exponent determined based on a upper bianry image.
It, can be according to the eye status information and driver specifically, after determining the eye status information of driver
Original fatigue exponent calculates the current fatigue exponent of driver using pre-set fatigue exponent computation rule.Wherein, tired
The computation rule of index can according to need flexible setting, such as it is contemplated that or not considering a upper bianry image collected
The eye status information (i.e. upper eye status information) of middle driver considers or does not consider the current eye status information of driver
Duration (i.e. driver eye be continuously in closure or non-occluded state time span), and/or, consider or do not consider
Opening degree (or closure degree) of driver eye etc..
Upper eye status information, the feelings of duration and eye opening degree are not considered for fatigue exponent computation rule
Condition illustratively can preset eye and be in fractional value corresponding to closed state and non-occluded state, and drive in determination
Increase corresponding fractional value after the eye state for the person of sailing on the basis of original fatigue exponent to obtain the current fatigue of driver
Index.Wherein, it is preferably positive number that eye, which is in the first fractional value corresponding to closed state, and it is right that eye is in non-occluded state institute
The second fractional value answered is preferably negative.For example, it is assumed that original fatigue exponent is 60, and the first fractional value is 7, the second score
Value is -8, then if the eye status information of driver is closed state, current fatigue exponent is 60+7=67;If driven
The eye status information for the person of sailing is non-occluded state, then its current fatigue exponent is 60-8=52.
The case where considering upper eye status information for fatigue exponent rule, illustratively, can preset one
When eye status information is closed state, current eye is in the first fractional value of closed state and current eye is in non-closed
Second fractional value of state, and, when upper eye status information is non-occluded state, current eye is in the of closed state
Three fractional values and current eye are in the 4th fractional value of non-occluded state, and original after the eye state for determining driver
Increase corresponding fractional value on the basis of fatigue exponent to obtain the current fatigue exponent of driver.Wherein, the first fractional value and
4th fractional value is preferably positive number, and the second fractional value and the 4th fractional value are preferably negative, and the first fractional value is preferably greater than second
Fractional value, the second fractional value are preferably greater than the 4th fractional value.For example, it is assumed that original fatigue exponent is 60, the first fractional value
It is 10, the second fractional value is -2, and third fractional value is 5, and the 4th fractional value is -14, then if upper eye status information is to close
Conjunction state, current eye information are closed state, then the fatigue exponent of driver is 60+10=70;If upper eye state
Information is closed state, and current eye information is non-occluded state, then the fatigue exponent of driver is 60-2=58;If upper one
Eye status information is non-occluded state, and current eye information is closed state, then the fatigue exponent of driver is 60+5=65;
If upper eye status information is non-occluded state, current eye information is non-occluded state, then the fatigue exponent of driver
For 60-14=46.
If S250, the current fatigue exponent reach the index threshold of setting, tired prompting is carried out to driver.
In the present embodiment, index threshold can according to need setting, such as can be set to 62,70,76 or other numerical value.With
For index threshold is 70, at this point, correspondingly, if the current fatigue exponent of driver is greater than or equal to 70, it can be to driving
The person of sailing carries out tired prompting.Wherein, fatigue remind mode can according to need setting, can such as carry out vibrating alert and/or
Sound prompting etc., this implementation is limited not to this.
S260, tired prompting message, locomotive information and driver information that the fatigue is reminded are reported to control centre.
In the present embodiment, after triggering fatigue is reminded, tired prompting message, the locomotive information that this fatigue can be reminded
It is reported to motive power control center with driver information, so that control centre staff timely takes measures to ensure that locomotive
Safety.Here, tired prompting message can be obtained by recording this tired reminder process, the machine of the driven locomotive of driver
Vehicle information and the relevant information (i.e. driver information) of driver can be stored in advance in locally and when being reported to control centre
It obtains, can also be stored in advance in locomotive vehicle-mounted security protection system from local, correspondingly, being mentioned in this triggering fatigue
After waking up, this fatigue can be obtained from locomotive on-vehicle safety guard system and reminds corresponding locomotive information and driver's letter
Breath.Wherein, tired prompting message can be understood as the relevant information that this fatigue is reminded, at the beginning of reminding such as this fatigue
Between, reminder time length, this fatigue remind fatigue exponent, (such as driver is tired at this for the generating process of the fatigue exponent
Labor remind for the previous period in eye status information definitive result) and/or this fatigue remind front and back driver video
Video recording etc.;Locomotive information may include the information such as the locomotive depot of the identity ID of locomotive, the speed of locomotive and locomotive;Driver
Information may include the driver number of driver.
The determination method of eye locations provided by Embodiment 2 of the present invention is obtained and is driven when locomotive is in driving status
The bianry image of member's face, and determine first location information and driver target of the driver eye region in the bianry image
Second location information of the subject area in bianry image, according to the relative positional relationship of targeted object region and ocular,
The first location information is modified using the second location information, obtains knowledge of the driver eye region in bianry image
Other position determines the eye of driver based on the subgraph according to the subgraph in identification position acquisition driver eye region
Status information determines the current fatigue exponent of driver according to the eye state, reaches the index of setting in current fatigue exponent
When threshold value, fatigue is carried out to driver and reminds simultaneously reporting scheduling center.The present embodiment not only may be used by using above-mentioned technical proposal
To improve the accuracy of eye locations definitive result, reduces monitoring device and the probability misidentified occur, fatigue can also be improved and mentioned
The safety of awake accuracy and locomotive in the process of moving.
On the basis of the above embodiments, it is closed described based on the targeted object region and the relative position of ocular
System, before being modified using the second location information to the first location information, can also comprise determining that described first
Location information and the second location information obtain success.In the present embodiment, can only it believe in the first position of ocular
When the second location information of breath and target area is obtained successfully, believed using first position of the second location information to ocular
Breath is modified, to avoid when there are large errors for first location information or second location information the case where to determined eye area
The accuracy rate of the identification position in domain impacts.At this point, correspondingly, if the first location information obtains failure and described the
Two location informations obtain successfully, then the opposite position based on the second location information and the targeted object region and ocular
Set identification position of the Relationship Prediction ocular in the bianry image;If the first location information obtains successfully and institute
It states second location information and obtains failure, then knowledge of the ocular in the bianry image is determined based on the first location information
Other position;If the first location information and the second location information obtain failure, alarm.Here, position
The determination method of acquisition of information success or failure can flexibly try, and such as can not get a certain location information (first
Location information or second location information) and/or some region of texture definition lower than setting clarity threshold when, determine the position
Confidence ceases (and/or the corresponding location information in the region) and obtains failure;Type of alarm can according to need setting, such as can be set
For audible alarm and/or vibration alarm.
Embodiment three
The embodiment of the present invention three provides a kind of determining device of eye locations.The device can be by software and/or hardware reality
It is existing, it can generally be integrated in the computer equipment with fatigue warning function, the determination method of execution eye locations can be passed through
Determine the position of driver eye.Fig. 3 is a kind of structural frames of the determining device for eye locations that the embodiment of the present invention three provides
Figure, as shown in figure 3, the device includes:
Data obtaining module 301, for when locomotive is in driving status, obtaining the bianry image of driver's face, driving
First location information and driver targeted object region of the person's of sailing ocular in the bianry image are in the bianry image
In second location information;
First position determining module 302, for the relative position based on the targeted object region Yu the ocular
Relationship is modified the first location information using the second location information, obtains the ocular described two
It is worth the identification position in image.
The determining device for the eye locations that the embodiment of the present invention three provides is in traveling in locomotive by data obtaining module
When state, the first position letter of the bianry image and driver eye region of driver's face in the bianry image is obtained
Breath and second location information of the driver targeted object region in bianry image, by first position determining module according to target
The relative positional relationship of subject area and ocular is modified the first location information using the second location information,
Obtain identification position of the driver eye region in bianry image.The technical solution of above-mentioned determining eye locations, using target
The position of subject area is modified the position of ocular, and the accuracy of eye locations definitive result can be improved, and reduces
There is the probability misidentified in monitoring device.
Further, the determining device of eye locations provided in this embodiment can also include: eye information determination module,
For obtaining the ocular after the identification position in the bianry image described, according to the identification position acquisition
The subgraph of ocular described in bianry image, and determine based on the subgraph eye status information of driver, it is described
Eye status information is closed state or non-occluded state;Fatigue exponent determining module, for according to the eye status information
And the original fatigue exponent of driver determines that the current fatigue exponent of driver, the original fatigue exponent are based on upper one
The fatigue exponent that bianry image determines;Tired reminding module, for reaching the index of setting in response to the current fatigue exponent
The event of threshold value carries out tired prompting to driver.
Further, the determining device of eye locations provided in this embodiment can also include: information reporting module, be used for
After the tired prompting to driver's progress, tired prompting message, locomotive information and driver that the fatigue is reminded
Information reporting is to control centre.
Further, the determining device of eye locations provided in this embodiment can also include: information determination module, be used for
In the relative positional relationship based on the targeted object region and ocular, using the second location information to described
Before first location information is modified, determine that the first location information and the second location information obtain success.
Further, the determining device of eye locations provided in this embodiment can also include: second position determining module,
For obtaining failure in response to the first location information and the second location information obtains successful event, based on described the
The relative positional relationship of two location informations and the targeted object region and ocular predicts ocular in the binary map
Identification position as in;Alarm module, for obtaining mistake in response to the first location information and the second location information
The event lost, alarms.
In the above scheme, the data obtaining module 301 may include: grayscale image generation module, at locomotive
When driving status, control target video camera acquires infrared image, and removes the background information in the infrared image, to obtain
The grayscale image of driver's face;Bianry image generation module, for using dynamic edge analytic approach to the grayscale image at
Reason, obtains the bianry image of driver's face;Location information acquiring unit, for obtaining driver eye region in the two-value
The second location information of first location information and driver targeted object region in the bianry image in image.
In the above scheme, the data obtaining module 301 can also include: video camera determination unit, for described
Before target video camera is controlled according to setting period acquisition infrared image, the driving direction of locomotive is obtained, and by the traveling side
The downward indoor video camera of locomotive head service on buses or trains is determined as target video camera.
The eye that any embodiment of that present invention provides can be performed in the determining device for the eye locations that the embodiment of the present invention three provides
Portion's method for determining position has the corresponding functional module of determination method and beneficial effect for executing eye locations.Not in this reality
The technical detail of detailed description in example is applied, reference can be made to the determination method of eye locations provided by any embodiment of the invention.
Example IV
Fig. 4 is a kind of structural schematic diagram for computer equipment that the embodiment of the present invention four provides, as shown in figure 4, the calculating
Machine equipment includes processor 40 and memory 41;The quantity of processor 40 can be one or more in computer equipment, in Fig. 4
By taking a processor 40 as an example;Processor 40 and memory 41 in computer equipment can be connected by bus or other modes
It connects, in Fig. 4 for being connected by bus.
Memory 41 is used as a kind of computer readable storage medium, can be used for storing software program, journey can be performed in computer
Sequence and module, if the corresponding program instruction/module of the determination method of the eye locations in the embodiment of the present invention is (for example, eye
Data obtaining module 301 and first position determining module 302 in the determining device of position.Processor 40 is stored in by operation
Software program, instruction and module in memory 41, at the various function application and data of computer equipment
Reason, that is, realize the determination method of above-mentioned eye locations.
Memory 41 can mainly include storing program area and storage data area, wherein storing program area can store operation system
Application program needed for system, at least one function;Storage data area, which can be stored, uses created data etc. according to terminal.This
Outside, memory 41 may include high-speed random access memory, can also include nonvolatile memory, for example, at least a magnetic
Disk storage device, flush memory device or other non-volatile solid state memory parts.In some instances, memory 41 can be further
Including the memory remotely located relative to processor 40, these remote memories can be set by network connection to computer
It is standby.The example of above-mentioned network includes but is not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.This hair
Bright example IV also provides a kind of storage medium comprising computer executable instructions, and the computer executable instructions are by counting
For executing a kind of determination method of eye locations when calculation machine processor executes, this method comprises:
When locomotive is in driving status, the bianry image of driver's face, driver eye region are obtained described two
It is worth second location information of the first location information and driver targeted object region in image in the bianry image;
Relative positional relationship based on the targeted object region Yu the ocular, using the second location information
The first location information is modified, identification position of the ocular in the bianry image is obtained.
Certainly, a kind of storage medium comprising computer executable instructions, computer provided by the embodiment of the present invention
The method operation that executable instruction is not limited to the described above, can also be performed eye locations provided by any embodiment of the invention
Determination method in relevant operation.
By the description above with respect to embodiment, it is apparent to those skilled in the art that, the present invention
It can be realized by software and required common hardware, naturally it is also possible to which by hardware realization, but in many cases, the former is more
Good embodiment.Based on this understanding, technical solution of the present invention substantially in other words contributes to the prior art
Part can be embodied in the form of software products, which can store in computer readable storage medium
In, floppy disk, read-only memory (Read-Only Memory, ROM), random access memory (Random such as computer
Access Memory, RAM), flash memory (FLASH), hard disk or CD etc., including some instructions are with so that a computer is set
Standby (can be personal computer, server or the network equipment etc.) executes method described in each embodiment of the present invention.
It is worth noting that, in the embodiment of the determining device of above-mentioned eye locations, included each unit and module
It is only divided according to the functional logic, but is not limited to the above division, as long as corresponding functions can be realized;
In addition, the specific name of each functional unit is also only for convenience of distinguishing each other, the protection scope being not intended to restrict the invention.
Note that the above is only a better embodiment of the present invention and the applied technical principle.It will be appreciated by those skilled in the art that
The invention is not limited to the specific embodiments described herein, be able to carry out for a person skilled in the art it is various it is apparent variation,
It readjusts and substitutes without departing from protection scope of the present invention.Therefore, although being carried out by above embodiments to the present invention
It is described in further detail, but the present invention is not limited to the above embodiments only, without departing from the inventive concept, also
It may include more other equivalent embodiments, and the scope of the invention is determined by the scope of the appended claims.
Claims (10)
1. a kind of determination method of eye locations characterized by comprising
When locomotive is in driving status, the bianry image of driver's face, driver eye region are obtained in the binary map
The second location information of first location information and driver targeted object region in the bianry image as in;
Relative positional relationship based on the targeted object region Yu the ocular, using the second location information to institute
It states first location information to be modified, obtains identification position of the ocular in the bianry image.
2. the method according to claim 1, wherein obtaining the ocular in the bianry image described
In identification position after, further includes:
It is driven according to the subgraph of ocular described in the identification position acquisition bianry image, and based on subgraph determination
The eye status information for the person of sailing, the eye status information are closed state or non-occluded state;
The current fatigue exponent of driver is determined according to the original fatigue exponent of the eye status information and driver, it is described
Original fatigue exponent is the fatigue exponent determined based on a upper bianry image;
If the current fatigue exponent reaches the index threshold of setting, tired prompting is carried out to driver.
3. according to the method described in claim 2, it is characterized in that, also being wrapped after the tired prompting to driver's progress
It includes:
Tired prompting message, locomotive information and driver information that the fatigue is reminded are reported to control centre.
4. the method according to claim 1, wherein being based on the targeted object region and ocular described
Relative positional relationship, before being modified using the second location information to the first location information, further includes:
Determine that the first location information and the second location information obtain success.
5. according to the method described in claim 4, it is characterized by further comprising:
If the first location information obtains failure and the second location information obtains successfully, it is based on the second position
The relative positional relationship of information and the targeted object region and ocular predicts ocular in the bianry image
Identify position;
If the first location information and the second location information obtain failure, alarm.
6. the method according to claim 1, wherein the bianry image for obtaining driver's face, comprising:
It controls target video camera and acquires infrared image, and remove the background information in the infrared image, to obtain driver people
The grayscale image of face;
The grayscale image is handled using dynamic edge analytic approach, obtains the bianry image of driver's face.
7. according to the method described in claim 6, it is characterized in that, in the control target video camera according to the acquisition of setting period
Before infrared image, further includes:
The driving direction of locomotive is obtained, and the indoor video camera of locomotive head service on buses or trains under the driving direction is determined as target and is taken the photograph
Camera.
8. a kind of determining device of eye locations characterized by comprising
Data obtaining module, for when locomotive is in driving status, obtaining bianry image, the driver eye of driver's face
Region the first location information and driver targeted object region in the bianry image in the bianry image second
Location information;
First position determining module is adopted for the relative positional relationship based on the targeted object region Yu the ocular
The first location information is modified with the second location information, obtains the ocular in the bianry image
Identification position.
9. a kind of computer equipment, which is characterized in that the computer equipment includes:
One or more processors;
Memory, for storing one or more programs,
When one or more of programs are executed by one or more of processors, so that one or more of processors are real
The now determination method of the eye locations as described in any in claim 1-7.
10. a kind of computer readable storage medium, is stored thereon with computer program, which is characterized in that the program is by processor
The determination method of the eye locations as described in any in claim 1-7 is realized when execution.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810826192.XA CN108985245A (en) | 2018-07-25 | 2018-07-25 | Determination method, apparatus, computer equipment and the storage medium of eye locations |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810826192.XA CN108985245A (en) | 2018-07-25 | 2018-07-25 | Determination method, apparatus, computer equipment and the storage medium of eye locations |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108985245A true CN108985245A (en) | 2018-12-11 |
Family
ID=64550617
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810826192.XA Pending CN108985245A (en) | 2018-07-25 | 2018-07-25 | Determination method, apparatus, computer equipment and the storage medium of eye locations |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108985245A (en) |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030169907A1 (en) * | 2000-07-24 | 2003-09-11 | Timothy Edwards | Facial image processing system |
CN101090482A (en) * | 2006-06-13 | 2007-12-19 | 唐琎 | Driver fatigue monitoring system and method based on image process and information mixing technology |
CN101472067A (en) * | 2007-12-28 | 2009-07-01 | 华晶科技股份有限公司 | Method for correcting red eye |
CN101732055A (en) * | 2009-02-11 | 2010-06-16 | 北京智安邦科技有限公司 | Method and system for testing fatigue of driver |
CN102314589A (en) * | 2010-06-29 | 2012-01-11 | 比亚迪股份有限公司 | Fast human-eye positioning method and device |
CN104574321A (en) * | 2015-01-29 | 2015-04-29 | 京东方科技集团股份有限公司 | Image correction method and device and video system |
CN104616438A (en) * | 2015-03-02 | 2015-05-13 | 重庆市科学技术研究院 | Yawning action detection method for detecting fatigue driving |
CN104809445A (en) * | 2015-05-07 | 2015-07-29 | 吉林大学 | Fatigue driving detection method based on eye and mouth states |
CN107481222A (en) * | 2017-07-21 | 2017-12-15 | 深圳市梦网百科信息技术有限公司 | A kind of quick eye lip video locating method and system based on Face Detection |
-
2018
- 2018-07-25 CN CN201810826192.XA patent/CN108985245A/en active Pending
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030169907A1 (en) * | 2000-07-24 | 2003-09-11 | Timothy Edwards | Facial image processing system |
CN101090482A (en) * | 2006-06-13 | 2007-12-19 | 唐琎 | Driver fatigue monitoring system and method based on image process and information mixing technology |
CN101472067A (en) * | 2007-12-28 | 2009-07-01 | 华晶科技股份有限公司 | Method for correcting red eye |
CN101732055A (en) * | 2009-02-11 | 2010-06-16 | 北京智安邦科技有限公司 | Method and system for testing fatigue of driver |
CN102314589A (en) * | 2010-06-29 | 2012-01-11 | 比亚迪股份有限公司 | Fast human-eye positioning method and device |
CN104574321A (en) * | 2015-01-29 | 2015-04-29 | 京东方科技集团股份有限公司 | Image correction method and device and video system |
CN104616438A (en) * | 2015-03-02 | 2015-05-13 | 重庆市科学技术研究院 | Yawning action detection method for detecting fatigue driving |
CN104809445A (en) * | 2015-05-07 | 2015-07-29 | 吉林大学 | Fatigue driving detection method based on eye and mouth states |
CN107481222A (en) * | 2017-07-21 | 2017-12-15 | 深圳市梦网百科信息技术有限公司 | A kind of quick eye lip video locating method and system based on Face Detection |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Kashevnik et al. | Methodology and mobile application for driver behavior analysis and accident prevention | |
US12032730B2 (en) | Methods and systems for using artificial intelligence to evaluate, correct, and monitor user attentiveness | |
Zhang et al. | SOVCAN: Safety-oriented vehicular controller area network | |
CN111989729B (en) | Information processing apparatus, mobile apparatus, information processing system, method, and program | |
US10559196B2 (en) | Method and system for vehicular-related communications | |
EP3564086B1 (en) | Managing drive modes of a vehicle | |
JP7324716B2 (en) | Information processing device, mobile device, method, and program | |
WO2019097944A1 (en) | Information processing device and information processing method | |
KR20210134634A (en) | autonomous vehicle system | |
CN104408878B (en) | Vehicle fleet fatigue driving early warning monitoring system and method | |
US7792328B2 (en) | Warning a vehicle operator of unsafe operation behavior based on a 3D captured image stream | |
CN107657236A (en) | Vehicle security drive method for early warning and vehicle-mounted early warning system | |
CN104730949A (en) | Affective user interface in an autonomous vehicle | |
CN105956548A (en) | Driver fatigue state detection method and device | |
EP4030326A1 (en) | Information processing device, mobile device, information processing system, method, and program | |
CN109523652A (en) | Processing method, device, equipment and the storage medium of insurance based on driving behavior | |
CN109471439A (en) | Control method for vehicle, device, equipment, storage medium and automobile | |
CN103700220A (en) | Fatigue driving monitoring device | |
CN107585026A (en) | A kind of anti-fatigue-driving system | |
CN109606376A (en) | A kind of safe driving Activity recognition system based on vehicle intelligent terminal | |
WO2021067380A1 (en) | Methods and systems for using artificial intelligence to evaluate, correct, and monitor user attentiveness | |
CN106985818A (en) | A kind of motor vehicle intelligent drive assist system based on cloud computing | |
CN108985245A (en) | Determination method, apparatus, computer equipment and the storage medium of eye locations | |
CN110059650A (en) | Information processing method, device, computer storage medium and electronic equipment | |
CN206039557U (en) | Driving situation monitoring system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
AD01 | Patent right deemed abandoned | ||
AD01 | Patent right deemed abandoned |
Effective date of abandoning: 20221018 |