CN109624667A - A kind of method and system that the anti-traffic photographic device of automobile intelligent is dazzling - Google Patents

Abstract

The invention discloses a kind of dazzling method and system of the anti-traffic photographic device of automobile intelligent, system of the present invention, there is the facility of the fixation position of the strong light of the sendings such as the camera that tests the speed in vehicle front, the method of the invention is after the fixed bit for getting the strong light of the sendings such as the camera that tests the speed installs the information applied, when automobile will reach this position, automatically turn down the brightness of front windshield corresponding region, the strong light that issues of facility of fixation position of the strong light of the sendings such as camera of making to test the speed filters part by shield glass, it is dazzling to achieve the purpose that the light into driver's eyes not will cause.

Description

A kind of method and system that the anti-traffic photographic device of automobile intelligent is dazzling

Technical field

The present invention relates to a kind of dazzling method and system of the anti-traffic photographic device of automobile intelligent, logical more particularly, to one kind Cross camera identification external environment brightness and the strong light of single-point and the intelligent automobile windshield auxiliary equipment for carrying out predictive adjusting.

Background technique

In very dark environment (when brightness is lower than 10-2cd/m2), such as without the night of light-illuminating, the cone cell of human eye Photosensitization is lost, visual performance is replaced by rhabdocyte, and human eye loses sensibility colored ability, is only capable of distinguishing white and ash Color, if occurring strong light in short-term at this moment, cone cell can directly work, and rod cell is because of internal rhodopsin strong It is decomposed without playing a leading role rapidly under the irradiation of light, if strong light disappears, the rhodopsin in rod cell can be gradually recovered, This time can be long, so cone cell works and is converted to that the time that rhabdocyte works is long, and here it is nights In eyes by the reason of a period of time can not see thing around clearly after the strong optical flare in opposite, it is alert because of the needs of traffic administration Side is mounted with the devices such as camera in most sections, these device majorities have the flash lamp of light filling, nighttime driving automobile Driver's eyes will cause temporary dazzling phenomenon after flash lamp flashing；In view of the above-mentioned problems, application No. is 《201210560307.8》、《201410048552.X》、《201480064155.X》、《201510848696.8》、 " 201720490336.X ", " 201810955087.6 ", " 201710284333.5 " patent of invention provide solution, still There are the following problems for these schemes:

1, application No. is the patent of invention described device of " 201210560307.8 ", driver drives vapour using this device Vehicle, when encountering the flash of light of opposite traffic camera at night, application No. is the patent of invention described devices of " 201210560307.8 " Front windshield can all be become black, driver is made to cannot see that other parts do not issue in addition to the headlight for vehicles of opposite The part of strong light, is easy to appear accident.

2, application No. is the patent of invention described device of " 201410048552.X ", the light that this device compares outside car is strong Degree is adjusted, be not for eyes entering light illumination variation and be adjusted, in night request for utilization number be The patent of invention described device of " 201410048552.X ", when traffic camera flash of light in opposite is opened, according to the light velocity and application number Detection, calculating speed for the patent of invention described device of " 201410048552.X ", it is believed that interior outer brightness simultaneously increases Add, inside and outside light intensity difference is almost without this makes that application No. is the patent of invention described devices of " 201410048552.X " not Have reaction.

3, application No. is the patent of invention described devices of " 201480064155.X ", encounter opposite direction in detection driver's eyes It is just acted after common action when traffic camera glistens dazzling, driver is possible to encounter the sudden strain of a muscle of opposing traffic camera in eyes It does not act, only closes, application No. is the patent of invention described devices of " 201480064155.X " can when light is dazzling It can not work；In addition, driver is also because have occurred and that dazzling situation cannot see front and endanger when working Danger.

It 4, is camera on spectacle frame, at data application No. is the patent of invention described device of " 201510848696.8 " Manage unit etc. because device is arranged on mirror holder, the size of mirror holder because different drivers needs different size, change in size, The glasses that driver inherently wears degree are also possible to, even family-sized car, it is also desirable to while it being adapted to the size of two people, Application No. is the patent of invention described devices of " 201510848696.8 " to be inconvenient to be adapted to；Because application No. is " 201510848696.8 " patent of invention described device can will lead to mirror holder skew on spectacle frame, lead to Shen than heavier Please number for " 201510848696.8 " patent of invention described device detect a position have error, thus impact effect.

5, application No. is the patent of invention described devices of " 201810955087.6 ", detect external light intensity beyond threshold values i.e. It acts, if opposing traffic camera glistens at night application No. is the patent of invention described device of " 201810955087.6 " According to after coming can by front windshield whole blackening, this will lead to the part that should not be seen and does not see, it should be observed that part Also the problem of can't see, so impracticable；Application No. is the patent of invention described device of " 201810955087.6 ", there is also gears The slow problem of wind glass colour change procedure, so the patent of invention described device application No. is " 201810955087.6 " is not firm With.

6, application No. is non-whole screen controls all inside the patent of invention of " 201710284333.5 " and foregoing invention patent Patent of invention, not to opposing traffic camera flash of light predict, cause opposing traffic camera flash glint several times when Any variation can all make eyes by repeatedly it is dazzling, i.e., traffic camera flash of light cause dazzling, device is adjusted to make traffic Camera flash of light photograph restores less than eyes, human eye, the flash of light of opposing traffic camera shines eyes again, dazzling again.

7, application No. is the patents of invention of " 201710284333.5 " and foregoing invention patent described device, do not carry out pre- The property surveyed protection, i.e., when detecting traffic camera, when opposing traffic camera is not turned on flash of light just to the position of its headlight It sets and is preconditioned, above-mentioned apparatus is passively adjusted when opening the flash of light of opposing traffic camera suddenly, and when adjusting drives Member has occurred and that dazzling, anti-effect is not played, only post, so application No. is the hairs of " 201710284333.5 " Bright patent and foregoing invention patent described device are all impracticable, do not play anti-glare effect.

Above-mentioned all devices are all a kind of post measures, i.e., in traffic camera flash irradiation to this vehicle driver Generated on eyes it is dazzling in the case where, then adjust corresponding device, but driver's eyes have occurred and that dazzling feelings at this time Condition, so above-mentioned patent is not very practical.

Summary of the invention

A kind of dazzling method and system of the anti-traffic photographic device of automobile intelligent of the present invention.Be for existing product, Temporary vision Whiteout caused by the flash of light of opposite traffic camera, causes driver or surrounding people to go out when patent is to driving Existing dangerous situation, the present invention are controlled by the light prediction and difference that different directions are entered with driver's eyes, hand over opposite The strong light occurred when logical camera flash of light does not influence the vision of driver.

A kind of dazzling method and system of the anti-traffic photographic device of automobile intelligent of the present invention include dedicated navigation Service End, vehicle-mounted client, vehicle-mounted client include information collection component point, control section, light difference control section, driver head State detection portion can also have communications portion, and each section is specific as follows:

1, the information collection component point may issue the friendship of strong light for collecting, in front of detecting vehicle within the scope of pilot's line of vision Objects, the collection modes such as logical camera can have following one or several kinds:

1) it is collected using the information of shooting, radar detecting, object identification, identifying that camera etc. is tested the speed in front may intense light source Object information, information can have light source type, position, distance, the intensity of light source, and recognition methods can be artificial neural network et al. Work intelligent method, process are:

It extracts clarification of objective (ORB, Hist, HOG, SIFT etc.)；

The corresponding classifier of training；

Sliding window search；

It repeats and wrong report is filtered.

It is also possible to use RCNN, SPP-NET, Fast-RCNN, Faster-RCNN, YOLO, SSD even depth learning algorithm comes Identify target；There are also vehicle direction of advance road surface fluctuating information.

2) using this truck position of the data sources such as CAN, acceleration transducer, gyroscope, GPS, Beidou, speed, turning Angle information；

3) light source information of the fixed capable of emitting strong light in the positions such as camera that tests the speed got from dedicated navigation Service end.

2, the control section, for controlling the other parts in this system, functional module is light source identification module, distance Calculating position prediction module, eye position computing module, light difference control module, specific as follows:

Light source identification module (contains the camera that tests the speed by navigation information according to the information that the information collection component point is collected into The description information of position, flash lamp position), find flash lamp position.

Distance calculates and position prediction module, calculates it in the possibility at next time point to the object that may issue strong light Position, distance, and predict that object may issue the position at part next time point of strong light, distance, object may be sent out The part size of strong light out.

Eye position computing module, the calculated driver of data provided with driver head's state detection portion The position of eyes and the light source identification module, the distance calculate and position prediction in object luminous component size, away from From, position, with a distance from next time point, the position at next time point, next time point object luminous component size Information calculates the point for needing to control on light difference control section.

Light difference control module, according to the eye position calculated result, the information of existing light emitting source, next time Possible light emitting source and the possible position of light emitting source, the light transmission capacity needed in control area is adjusted.

3, light difference control section enters the every of eyes light for controlling under the control of the control module The light transmittance in one region shows image in this region while cover region entering light.

4, driver head's state detection portion, for detect driver head state and two positions, driven The position of human eye under the person's of sailing current head state.

The dedicated navigation Service end provides the facility of the fixation positions of the strong light of sendings such as the camera that tests the speed of designated position Information, information may include testing the speed the position of facility of fixation position of the strong light of the sendings such as camera, luminous component on facility More specific location information.

In order to guarantee effect of the invention, the region that light difference control section covers appropriate can expand, and expand The region that light difference control module needs to control light transmission capacity can be handled with dilation operation greatly, result that treated is for hiding Lid.

Beneficial effects of the present invention are as follows:

1, the opposite fixed position of the camera etc. that tests the speed in driving can be avoided to be likely to occur the light source of strong light to driving to the greatest extent Dazzling situation caused by the person of sailing not only is suitable for day driving, is also suitable for night driving.

Detailed description of the invention

Fig. 1 is 1 flow diagram of the embodiment of the present invention；

Fig. 2 is 1 system comprising modules schematic diagram of the embodiment of the present invention；

Fig. 3 is 2 flow diagram of the embodiment of the present invention；

Fig. 4 is 2 system comprising modules schematic diagram of the embodiment of the present invention.

Specific embodiment

Illustrate specific working mode of the invention below by embodiment.

1 process such as Fig. 1 of the embodiment of the present invention, 1 system comprising modules such as Fig. 2 of the embodiment of the present invention, the embodiment of the present invention 1 are wrapped Containing 207 dedicated navigation Service ends, 201 vehicle-mounted clients, 201 vehicle-mounted clients include 202 information collection components point, 203 control units Divide, 204 light difference control sections, 205 driver head's state detection portions, 206 communications portion, specific each section is such as Under:

1,202 information collection components point, speed, angle of turn, position and automobile direction of advance for detecting automobile test the speed camera shooting The position of the strong light object of sending of the fixed position such as head position, functional module is:

1) CAN link block, for obtaining speed, the angle of turn of automobile.

2) Beidou module, for obtaining the position of automobile.

2,203 control section, using full will T7 chip, for controlling the other parts in this system, functional module have away from It is specific as follows from calculating and position prediction module, eye position computing module, light difference control module:

1) distance calculating and position prediction module, according to the position of this vehicle, speed, angle of turn, vehicle speed measuring camera position Deng the object information of the strong light of sending of fixed position, the position of next this object of time point is predicted.

2) eye position computing module, with the calculated driver's eye of the data of driver head's state detection portion Two eyes of driver of driver head's state detection portion shooting are found using the Haar classifier trained in the position of eyeball The central point of eyes in image is carried out the distance that eyes are calculated apart from detection with two cameras, according to eye by the image of eyeball Position of the distance, eyes of eyeball on picture, calculates the position of eyes.

3) light difference control module calculates according to the eye position and adjusts the light transmission capacity needed in control area, According to the strong light object of sending of the fixed position such as the position of eyes, the position of light difference control section, the camera position that tests the speed Now, the information at next time point, calculates the region that light difference control section needs to control light transmittance, and by this region It is dimmed.

It 3,204 light difference control section can be according to control section to be attached to the liquid crystal film on front windshield Control instruction reduces the light transmittance of certain a part.

4,205 driver head's state detection portion is used for for the binocular camera being mounted in front of driver's cabin driver Detect the position of driver's eyes.

5,206 communications portion is 3G communication module, for communicating with dedicated navigation Service end, obtains advance from server-side Direction test the speed the fixed position such as camera position the strong light of sending object information.

207 dedicated navigation Service ends provide the facilities of the fixation position of the strong light of sendings such as the camera that tests the speed of designated position Information, tool of the position, luminous component of the facility of fixation position of the information comprising the strong light of the sendings such as camera that tests the speed on facility Body position information.

1 workflow of the embodiment of the present invention is as follows:

1.101 obtain location information, the letter of the object of the strong light of sending of the fixed position of the camera position etc. that tests the speed in direction of advance Breath；

2.102 obtain according to the object information and distance, location information of the strong light of sending of the fixed position of the camera position etc. that tests the speed Possible intense light source position in current set distance；

3.103 fix the object of the strong light of sending of position according to current this vehicle speed, angle of turn, the camera position that tests the speed etc. Information prediction go out next time point test the speed the fixed position such as camera position the strong light of sending object position.

4.104 obtain current eye locations information；

5.105 calculate the position that light difference control section needs to reduce light transmittance；

6.106 light difference control sections reduce the light transmittance for needing part according to above-mentioned calculating data.

2 process such as Fig. 3 of the embodiment of the present invention, 2 system comprising modules such as Fig. 4 of the embodiment of the present invention, the embodiment of the present invention 2 are wrapped Containing 402 information collection components point, 403 control sections, 404 light difference control sections, 405 driver head's state detection portions, 406 communications portion, specific each section are as follows:

1,402 information collection components point shine light intensity on shield glass and picture and measure object for detecting Distance, and obtain according to the information of navigation the object space of the strong light of sending of the fixed position of the camera position etc. that tests the speed, information Collection part is an Ouster OS-1-16 line laser radar and computing device NVIDIA GTX 1060, laser radar installation It is shot and is detected outside the front windshield of inside-automobile rear mirror, functional module is:

1) Objective extraction, the purpose of Objective extraction are by the object of the strong light of sending of the fixed position such as the camera position that tests the speed from taking the photograph It is extracted in the picture shot as head, extracts the trained deep learning algorithm of the image of preceding laser radar with depth, when extraction The image with depth information sent with deep learning identification laser radar, the fixed position of the camera position etc. that obtains testing the speed hair The object of strong light out, object extraction algorithm use Fast YOLO, and Fast YOLO structure is as follows:

Construct Fast YOLO network structure；

9 convolutional layers+pond layer finally connect 3 Dense hidden layers；

First layer convolution uses the convolution kernel of 16 3x3x1, step-length 1, and BORDER PROCESSING mode is " SAME ", and activation primitive is (LeakyReLU, is followed by the pond layer of a 2x2, and mode is Max Pooling；

Second layer convolution uses the convolution kernel of 32 3x3x1, step-length 1, and BORDER PROCESSING mode is " SAME ", and activation primitive is LeakyReLU, is followed by the pond layer of a 2x2, and mode is Max Pooling；

Third layer convolution uses the convolution kernel of 64 3x3x1, step-length 1, and BORDER PROCESSING mode is " SAME ", and activation primitive is LeakyReLU, is followed by the pond layer of a 2x2, and mode is Max Pooling；

4th layer of convolution uses the convolution kernel of 128 3x3x1, step-length 1, and BORDER PROCESSING mode is " SAME ", and activation primitive is LeakyReLU, is followed by the pond layer of a 2x2, and mode is Max Pooling；

Layer 5 convolution uses the convolution kernel of 256 3x3x1, step-length 1, and BORDER PROCESSING mode is " SAME ", and activation primitive is LeakyReLU, is followed by the pond layer of a 2x2, and mode is Max Pooling；

Layer 6 convolution uses the convolution kernel of 512 3x3x1, step-length 1, and BORDER PROCESSING mode is " SAME ", and activation primitive is LeakyReLU, is followed by the pond layer of a 2x2, and mode is Max Pooling；

Multi-layer data is become into one-dimensional data

Dense layers of first layer: using parameter 256；

Dense layers of the second layer: use parameter 4096, activation primitive be ReLU；

Dense layers of third layer: using parameter 1470.

2) target range is detected, according to the target identified, the distance number of target is obtained from the data of laser radar According to.

2,403 control section, using full will T7 chip, for controlling the other parts in this system, the function of completion is Position prediction, eye position calculate, light difference controls, specific as follows:

1) distance calculates and position prediction, the object of the strong light of sending of position fixed for the camera position that tests the speed etc., according to working as Preceding vehicle speed, angle of turn predict the position of next this object of time point on the basis of this vehicle；

2) eye position calculates, with the position of the calculated driver's eyes of data of driver head's state detection portion It sets, using the Haar classifier trained, finds the figure of two eyes of driver of driver head's state detection portion shooting The central point of image is carried out the distance that eyes are calculated apart from detection with two cameras, according to the distance of eyes, eye by picture Position of the eyeball on picture, calculates the position of eyes.

3) light difference controls, and is calculated according to the eye position and adjusts the light transmission capacity needed in control area, according to The position of eyes, the position of light difference control, the position of information collection component shunt excitation optical radar, distance calculates and position prediction obtains The position of light source prediction out, calculates the region that light difference control section needs to control light transmittance, and this region is dimmed.

It 3,404 light difference control section can be according to control section to be attached to the liquid crystal film on front windshield Control instruction reduces the light transmittance of certain a part.

4,405 driver head's state detection portion is used for for the binocular camera being mounted in front of driver's cabin driver Detect the position of driver's eyes.

5,406 communications portion is CAN interface, Beidou module, is used for and vehicle communication, obtains speed, the turning angle of vehicle Spend information, Beidou positioning information.

2 workflow of the embodiment of the present invention is as follows:

The outer picture of 1.301 collecting vehicles, opens laser radar and camera, shooting picture, obtains the distance letter of picture and every bit Breath, identifies picture, range information, the object source of the strong light of sending of the fixed position such as discrimination speed-testing camera position；

2.302, according to target information, obtain target range；

3.303 obtain according to the object information and distance, location information of the strong light of sending of the fixed position of the camera position etc. that tests the speed Current possible intense light source position；

4.304 fix the object of the strong light of sending of position according to current this vehicle speed, angle of turn, the camera position that tests the speed etc. Information prediction go out next time point test the speed the fixed position such as camera position the strong light of sending object position.

5.305 obtain current eye locations information；

6.306 calculate the position that light difference control section needs to reduce light transmittance；

7.307 light difference control sections reduce the light transmittance for needing part according to above-mentioned calculating data.

Although the present invention has been described by way of example and in terms of the preferred embodiments, embodiment and attached drawing are not for limiting the present invention 's.Without departing from the spirit and scope of the invention, any equivalent change or retouch done, also belongs to the protection of the present invention Range.Therefore protection scope of the present invention should be based on the content defined in the claims of this application.

Claims (6)

1. a kind of method and system that the anti-traffic photographic device of automobile intelligent is dazzling, the method includes information collection components point, control System part, light difference control section, driver head's state detection portion, each section are specific as follows:

The information collection component point may issue the object of strong light for obtaining, in front of detecting vehicle within the scope of pilot's line of vision, And the position of object, range information are obtained, also obtain the speed, angle of turn information of this vehicle；

The control section, for controlling the other parts in this system, the function of completion is light source distance, position calculates, pre- It surveys, eye position calculates, the control of light difference；

Light difference control section, for control enter eyes light each region light transmittance or cover region Image is shown in this region while entering light；

Driver head's state detection portion, the state of driver head obtains two positions for identification；

The function that the invention patent is completed is:

Divide light source information of acquirement vehicle external environment and the camera that tests the speed identified etc. strong according to the information collection component Light source information, the control section predict the location information at this time point, the intense light source that next time point is likely to occur, and lead to The driver eye positions' information obtained from driver head's state detection portion is crossed, the light difference control is calculated Part needs that the position of light light transmittance reduction is controlled light difference control section and reduced corresponding portion light transmittance, The strong illumination for issuing intense light source in the position that next time point is likely to occur is controllable into the light intensity of driver's eyes.

2. a kind of dazzling method and system of the anti-traffic photographic device of automobile intelligent according to claim 1, it is characterised in that: institute Information collection component point is stated, the mode for collecting the object of the fixed capable of emitting intense light source in position such as camera may is that

The data being collected into from camera, radar identify that the information of the possible intense light source in front, information may include position It sets, distance, the intensity of light source；

The strong optical information of sending of the fixed position such as camera position that tests the speed based on navigation information；

This vehicle relevant information collection mode is:

From CAN, acceleration transducer, gyroscope, GPS, one or several kinds of this truck position taken out of Beidou, speed, turning Information；

The function of the control section, completion is as follows:

Distance calculate and position prediction, to the object that may issue strong light calculate its this time point position, distance；And it calculates The possible position at next time point, distance out；

Eye position calculates, according to the calculated driver's eyes of data of driver head's state detection portion offer Position and the distance calculate and position prediction in the size of object luminous component, distance, position, next time point away from Size from, the position at next time point, next time point object luminous component calculates the light difference control unit The point for needing to control on point；

The control of light difference, according to the eye position calculated result, the light transmission capacity needed in control area is adjusted.

3. a kind of dazzling method and system of the anti-traffic photographic device of automobile intelligent according to claim 2, it is characterised in that: light Dilation operation is used when line difference controls, operation result subtracts corresponding portion light transmittance for light difference control section It is small.

4. a kind of dazzling method and system of the anti-traffic photographic device of automobile intelligent according to claim 2, it is characterised in that also Have dedicated navigation Service end, communications portion complete function also:

Communications portion is 3G communication module, is tested the speed the fixed position such as camera position for obtaining direction of advance from server-side Issue the information of the object of strong light；

Dedicated navigation Service end provides the information of the facilities of the fixation position of the strong light of sendings such as the camera that tests the speed of designated position, letter Specific location letter of the position, luminous component of the facility of fixation position of the breath comprising the strong light of the sendings such as camera that tests the speed on facility Breath；

Information collection component is divided into:

CAN link block, for obtaining speed, the angle of turn of automobile；

Beidou module, for obtaining the position of automobile；

Control section, functional module are specific as follows:

Distance calculates and position prediction module, according to the position of this vehicle, speed, angle of turn, vehicle speed measuring camera position etc. The object information of the strong light of sending of fixed position, predicts the position of next this object of time point；

Eye position computing module, with the position of the calculated driver's eyes of data of driver head's state detection portion It sets；

Light difference control module calculates according to the eye position and adjusts the light transmission capacity needed in control area, according to eye The strong light object of sending of the fixed position such as the position of eyeball, the position of light difference control section, the camera position that tests the speed now, under The information at one time point calculates the region that light difference control section needs to control light transmittance, and this region is dimmed；

It light difference control section can be according to the control instruction of control section to be attached to the liquid crystal film on front windshield The light transmittance of certain a part is reduced；

Driver head's state detection portion drives for the binocular camera being mounted in front of driver's cabin driver for detecting The position of member's eyes.

5. a kind of dazzling method and system of the anti-traffic photographic device of automobile intelligent according to claim 2, it is characterised in that also There is communications portion, be used for and vehicle communication, obtains speed, the angle of turn information of vehicle；Vehicle location information can also be obtained； Other parts are realized, function is as follows:

Information collection component point, information collection component is divided into a laser radar and computing device, function are:

Objective extraction, the purpose of Objective extraction be will test the speed the fixed position such as camera position the strong light of sending object from camera shooting It is extracted in the picture of head shooting, extracts the trained deep learning algorithm of the image of preceding laser radar with depth, when extraction is used The sending of the image with depth information, the fixed position of the camera position etc. that obtains testing the speed that deep learning identification laser radar is sent The object of strong light

Target range is detected, according to the target identified, the range data of target is obtained from the data of laser radar；

Automobile direction of advance information of road surface；

Control section, for controlling the other parts in this system, the function of completion is position prediction, eye position calculating, light The control of line difference, specific as follows:

Distance calculates and position prediction, the object of the strong light of sending of position fixed for the camera position that tests the speed etc., according to current This vehicle speed, angle of turn, information of road surface predict the position of next this object of time point on the basis of this vehicle；

Eye position calculates, with the position of the calculated driver's eyes of data of driver head's state detection portion；

The control of light difference, calculates according to the eye position and adjusts the light transmission capacity needed in control area, according to eyes Position, the position of light difference control, the position of information collection component shunt excitation optical radar, distance calculates and position prediction obtains light source The position of prediction calculates the region that light difference control section needs to control light transmittance, and this region is dimmed；

It light difference control section can be according to the control instruction of control section to be attached to the liquid crystal film on front windshield The light transmittance of certain a part is reduced；

Driver head's state detection portion drives for the binocular camera being mounted in front of driver's cabin driver for detecting The position of member's eyes.

6. according to a kind of dazzling method and system of the anti-traffic photographic device of automobile intelligent of claim 4,5, it is characterised in that: Eye position calculates, and using the Haar classifier trained, finds the driver two of driver head's state detection portion shooting The image of eyes, carries out the distance that eyes are calculated apart from detection with two cameras for the central point of image, according to eyes Position on picture of distance, eyes, calculate the position of eyes.