JPH041844B2 - - Google Patents

Description

[Detailed Description of the Invention] [Technical Field] The present invention relates to a vehicle driver position recognition device that recognizes the position of a vehicle driver, and in particular recognizes the three-dimensional position of the driver in a vehicle interior from one two-dimensional image. The present invention relates to a vehicle driving position recognition device.

[Prior Art] Conventionally, devices have been developed that serve as an auxiliary eye for passengers and ensure safe driving by recognizing objects outside the vehicle, such as inter-vehicle distance detection devices or back sonar that detects obstacles behind the vehicle. It's here.

However, in recent years, there has been a strong demand for improvements in the operability and comfort of vehicles such as automobiles from the perspective of ensuring safe driving. , adjust the angle of the back mirror, adjust the direction of the air conditioner outlet, adjust the height of the tilt handle,
Alternatively, it has become desirable to have a vehicle that automatically adjusts the height of the headrest to suit each driver.

For this purpose, it is necessary to know the position of the vehicle driver, but conventionally, the driver's position could only be estimated by detecting the front and back position and height of the driver's seat, or the reclining state. However, there was a problem in that it was not possible to accurately recognize the position of the driver, taking into account the height and posture of each driver.

[Objective of the Invention] Therefore, the present invention realizes good vehicle operability and improves safety based on an unprecedented idea of looking inside the vehicle interior and recognizing the position of the vehicle driver as a three-dimensional position using images. It is an object of the present invention to provide a vehicle driver position recognition device that facilitates driving.

[Configuration of the invention] The configuration of the present invention to achieve the above object is as follows:
As shown in the basic configuration diagram of FIG. 1, there is a light-emitting means a that irradiates light to a vehicle driver, and a light-emitting means a that is disposed diagonally in front of the driver's seat to image the light reflected from the vehicle driver due to the irradiation of the light-emitting means. an image detection means b for detecting information;
and a recognition means (a) for recognizing the three-dimensional position of the driver in the vehicle interior based on the two-dimensional image detected by the image detection means by assuming that the driver moves only in the vertical direction. The main subject is a vehicle driver position recognition device.

[Example] The present invention will be described below by giving examples and referring to the drawings. This example is an example in which the present invention is applied to an automobile. FIGS. 2 and 3 are views of how the optical system 1 of this embodiment is installed in the vehicle interior. The optical system 1 of this embodiment corresponds to a light emitting means and an image detecting means. In the figure, the optical system 1 is provided at a position where the light emitted from the optical system 1 can irradiate a range where the head of the driver 2 is highly likely to be present.

In this embodiment, the optical system 1 is mounted in a position where it is easy to install, for example, in a corner of the vehicle interior, to the upper left of the passenger seat, using bolts, nuts, etc., so that the light irradiated to the passenger seat (not shown) is not obstructed. Fixed. 3 is a steering wheel, 4 is a driver's seat, 5 is a vehicle body, and 6 is a center line passing through the center of the steering wheel 3 and the center of the driver's seat 4. Here, the front-rear direction of the vehicle, that is, the direction of the center line 6, is the x direction, the left-right direction is the y-direction, and the up-down direction is the z-direction.

Next, FIGS. 4 and 5 are configuration diagrams of the optical system 1 described above. FIG. 4 is a plan view of the optical system 1, and FIG. 5 is a sectional view taken along line XX of the optical system. In the figure, the lens 11 is aligned with the central axis of the cylindrical holder 10.
is fixed to the holder 10 with adhesive or the like, and the lens 11
Similarly, a two-dimensional solid-state image sensor 12 as an image detection means is fixed to the lower part of the lens 11 with adhesive or the like. In this embodiment, the two-dimensional solid-state image sensor 12 employs a two-dimensional charge-coupled device (two-dimensional CCD). The holder 10 is fixed to the case 13 with adhesive, screws, or the like. The light emitting elements 14a to 14h for auxiliary illumination as light emitting means are formed in a substantially cylindrical shape, and are attached to the case 13 at a predetermined distance from the holder 10 and the two-dimensional solid-state image sensor 12, parallel to the central axis of the holder 10. On the other hand, they are fixed with adhesive or screws, and eight of them are provided around the circumference. This is to uniformly irradiate the driver 2 with light.

As the light emitting elements 14a to 14h, high brightness infrared light emitting diodes are used. The light emitting elements 14a to 14h are connected to an optical system control circuit 16 via a plurality of lead wires 15, and the two-dimensional solid-state image sensor 12 is connected to the optical system control circuit 16 via a lead wire 17. This optical system control circuit 16 inputs an image readout synchronization signal from an arithmetic control circuit to be described later, and inputs an image readout synchronization signal to the two-dimensional solid-state image sensor 12.
image data is output to the arithmetic control circuit. Also,
A drive control signal that controls the magnitude of the drive current for driving the light emitting elements 14a to 14h is output to the light emitting elements 14a to 14h via the lead wire 15.

Next, FIG. 6 is a block diagram of an arithmetic and control circuit 100 that recognizes the position of the driver as a recognition means. 101 is an input port equipped with an A/D converter, a multiplexer, etc., 102 is a central processing unit (hereinafter referred to as CPU), and 103 is a CPU 102
At predetermined intervals according to the data written by
A timer that generates a timer interrupt for the CPU 102; 104 is a read-only memory (hereinafter simply referred to as ROM) that stores image recognition calculations for the driver 2 and processing programs that operate the actuator; 105 is data for image recognition processing; Random access memory (hereinafter referred to as
It is simply called RAM. ), 106 are output ports that output control signals to the optical system 1 and the drive circuit 107.

Further, 107 is an actuator drive circuit that drives an actuator, and 108 is an actuator that adjusts the arrangement of vehicle equipment based on a signal from the actuator drive circuit 107. This actuator includes, for example, a fender mirror adjustment device,
Examples include dampers for air conditioner outlets, safety pillow adjustment devices, roadside detection devices, tilt steering wheel adjustment devices, and automatic seat height adjustment devices.

109 is a bus line that interconnects the input port 101, CPU 102, timer 103, ROM 104, RAM 105, and output port 106;
0 represents a power supply circuit that supplies power from the battery 111 to the arithmetic control circuit 100 via the key switch 112. Additionally, these have an interface circuit.

The image recognition process executed by the arithmetic control circuit 100 described above will be described. FIG. 7 shows a flowchart of a control program for this process.
When the engine key is placed in the accessory state (ACC) or ignition state (IG), the key switch 112 is closed, the necessary power is supplied from the power supply circuit 111, and processing is started. Before entering into a detailed explanation of the processing, an outline of the processing will first be explained. Image recognition processing is generally divided into observation, quantization, preprocessing, feature extraction, identification, and postprocessing. Steps 201 to 203 are observation, steps 204 and 205 are quantization, steps 206 to 208 are image conversion, preprocessing such as processing, steps 209 and 210 are feature extraction such as boundary line extraction, and steps 211 to 205 are Step 214 represents post-processing. By performing these processes, image recognition processing is performed.

Next, a detailed explanation of this process will be given. step
In 201, it is determined whether there is a separately provided processing request signal. This processing request signal input means may be considered to be ACC or IG, but it may also be a request switch (not shown), for example, a dedicated switch attached to the steering wheel, which can be operated without taking your hands off the steering wheel. Incidentally, in the case of an actuator that must be constantly operated during driving, such as a back mirror adjustment device, it is preferable to use a key switch, and in the case of a seat height adjustment device or a special actuator, it is preferable to provide a dedicated switch. This is because it is easy to operate.

If there is no request for this processing, it remains on standby. On the other hand, when a processing request is input to the input port 101, the CPU 102 starts image recognition processing.
First, in step 202, the CPU 102
Clears internal registers and sets parameters. For example, the coordinates P(x,
Initialization of y, z) changes the coordinates to P(0, 0, 0)
Set to .

In the next step 203, output port 10
A control signal for causing the light emitting elements 14a to 14h to emit light is outputted to the optical system control circuit 16 via the optical system control circuit 16, thereby driving the optical system 1. The light emitting elements 14a to 14h immediately emit light upon receiving the control signal, and the driver 2 is irradiated with infrared light. The irradiated infrared light hits the driver 2 and is reflected, and the reflected light passes through the lens 11 to the driver 2.
The image is taken into the dimensional solid-state image sensor 12. Therefore,
An image of the driver is focused on a two-dimensional solid-state image sensor 12 through a lens 11 . The two-dimensional solid-state image sensor 12 is composed of a charge-coupled device that divides the image into 512 x 400 pixels, that is, a photoelectric conversion/charge storage device. So-called quantization is performed to make discontinuous values set for each pixel, and the two-dimensional solid-state image sensor 12
After photoelectric conversion is performed according to the amount of reflected light incident on the light, it is accumulated as a charge.

In the following step 204, the accumulated charge is
The image is sequentially scanned and read out from the upper left corner by the image readout synchronization signal, but the amount of charge changes from one readout to the next readout on the two-dimensional solid-state image sensor 1.
2 is accumulated according to the amount of light received, so it corresponds to the amount of light received by the two-dimensional solid-state image sensor 12 during the readout interval, and is sent to the optical system as a time-series analog signal in the order of readout. It is output to the input port 101 of the arithmetic control circuit 100 via the control circuit 16.

Then, at the input port 101, the A/D converter performs A/D conversion at high speed, converts it into a digital signal, and stores it in a predetermined area of the RAM 105, that is, the image memory, as 6-bit or 8-bit image information. Ru. Information on the image including the upper body of the driver 2 at the time it was captured using infrared light is left in the image memory. This operation is called "freezing" in the sense that the image is fixed, and after freezing, image information as shown in FIG. 8A is stored in the image memory of the RAM 105.

In the following step 205, a stop signal is output from the input port 101 to the optical system 1.
is stopped to avoid unnecessary power consumption, and the process moves to step 206.

In step 206, among the so-called pre-processing of the image information obtained in step 204, the image is first corrected and enhanced. Image correction is a process of removing noise caused by external disturbances. Image enhancement is a process also called edge enhancement, and an example of this process is shown in FIG. Regarding the pixels of 3 vertically x 3 horizontally, the value Pi,j of the center pixel and the neighboring 4
pixel values Pi _-1 , j, Pi, j _-1 , Pi, j ₊₁ , Pi ₊₁ ,
Add j, subtract 4 times the center pixel value Pi, j, divide the value by 4, and use the value as the new center pixel value Pi, j. This calculation is performed for all pixels except peripheral pixels. As a result, bright and dark areas are emphasized, and an image as shown in FIG. 8A is obtained, and the process proceeds to step 207.

In step 207, the image obtained in step 206 is binarized using set values. Here, the binarization process involves setting a predetermined level (threshold level) for the gradation information of the image, that is, 6-bit or 8-bit gradation information, and comparing the above level. This is a process that clearly separates areas darker than the above level into black, ie, level "0," and areas lighter than the above level, into white, ie, level ``1.'' The dark portions are portions in which little charge was accumulated in the two-dimensional solid-state image sensor 12, and the light portions are portions where charge was sufficiently accumulated. In this way, the image is divided into 1 and 0 levels, and an image as shown in FIG. 8C is obtained.

Note that the image after being binarized changes depending on the determination level of the binarization, but for example, if a liquid crystal aperture element is provided on the two-dimensional solid-state image sensor 12,
It is easy to adjust the amount of incident light and set a determination level such that the driver's face is at a white level and the background is at a black level.

In the following step 208, the above-mentioned step 207 is performed.
The boundary line of the binarized image is made thinner. This process is easily realized by finding the center of the black part in FIG. 8C, and an image as shown in FIG.

In step 209, the image obtained in step 208 is scanned in the horizontal direction from the upper left corner of the image, and the point where X is minimum and the slope of the tangent line is vertical as shown in the upper part of the image Perform detection. Scanning may also be performed from the vertical direction. In addition, since the infrared light is irradiated diagonally from above, the position of the nose is the best for localization, and detection accuracy is high. In addition, in this embodiment, there is no time to identify the so-called form of pattern recognition, and a complicated algorithm is not adopted due to the processing time. Therefore, for example, under conditions such as wearing glasses or having long hair, a complex feature extraction process may be followed by an identification process. In this way, a part (in this case, the nose) that has different characteristics from the surrounding area is detected as a singular point from the driver's image.

In the following step 210, the values of the two-dimensional coordinates X and Z of the singular point on the image memory are determined. From these coordinates, the coordinates of the three-dimensional position of the eye within the vehicle interior are determined. That is, since the position of the optical system 1 is fixed, the coordinates of the eye position are calculated based on the average value of the distance from the Japanese person's nose stored in advance in the ROM 104.

FIG. 10 shows the three-dimensional position of the driver's car in the passenger compartment. 302a represents the origin, 302b
represents the three-dimensional position of the eye after movement. 1st
Figure 1 is an image 300 of the image memory after calculation processing.
represents. 302c is the origin on the image memory, and 302d is the position of the eye after movement on the image memory. Therefore, 302a and 302c, and 302b and 302d have a one-to-one correspondence, respectively.

Here, the driver 2 uses the steering wheel 3 and the driver's seat 4.
Because of this, the movement in the lateral direction, that is, in the y-axis direction, is restricted, that is, the movement in the y-axis direction is considered to be small. It can be assumed that the eyes of the driver 2 are located on the (x-z plane), that is, that the eyes of the driver 2 move only in the front, back, and up and down directions of the driver's seat 4. Therefore, the position 302d of the eyes of the driver 2 according to the image 300 in the image memory after calculation processing is determined by the coordinates (x ₁ , z ₁ ) from the origin 302c of the memory. Position P
(x, O, z) can be found.

In the following step 211, the above-mentioned step 210 is performed.
The three-dimensional position P(x, O,
z) and the coordinates of the three-dimensional position obtained from the previous processing
Distance from P′(x′, O, z′) |P−P′|, that is, √(
−x′) ² + (z−z′) ² is calculated. In other words, driver 2
Compute the movement of on the xz plane.

In step 212, it is determined whether the value of |P-P'| is greater than or equal to the set value, and if it is determined that |P-P'| is greater than or equal to the set value, the process proceeds to step 213, where |
If it is determined that P-P'| is smaller than the set value, the process moves to step 214. This step is
This is provided to prevent the driving feeling from worsening due to the actuator and vehicle equipment moving gradually as the position of the eye moves little by little.

Then, in step 213, which is processed when it is determined that |P-P'| is greater than or equal to the set value, the drive amount of the actuator 108 is calculated based on the value of P, and the Output port 106 to actuator 108
A drive signal is output to the actuator 108, and the process moves to step 214.

If it is determined in step 212 that |P-P'| is smaller than the set value and there is no need to drive the actuator 108, or in step 214 where the process is performed after the actuator drive process in step 213, As in step 201, it is determined again whether there is a final processing request, and if it is determined that there is a processing request, the process returns to step 203 and the image recognition loop processing is performed again. . In one loop process, one piece of three-dimensional position data of the driver is calculated, the movement of the eye position of the driver 2 is detected based on the calculated value, and the actuator is activated according to the change in the eye position. Driven. In this way, as long as there is a processing request, loop processing is performed repeatedly. Furthermore, if it is determined that there is no processing request, the processing of this routine is ended.

FIG. 12 shows a back mirror and its driving mechanism applied to this embodiment. The back mirror is equipped with a single motor actuator. This actuator is equipped with a small DC motor 321 and a mechanism section 322 having a reduction gear and a clutch, and is capable of adjusting the angle of a mirror case 324 attached to the back surface of the mirror 320 in the horizontal and vertical directions. Further, the position sensor 325, 326 is configured to detect the position of the mechanism section 322 and perform feedback control.

Other control methods include an open loop control method using a step motor and a feedback control method using a DC servo motor. If such a rearview mirror is used and its actuator is controlled according to the position of the driver's eyes, the rearview mirror will be driven and the trouble of moving the mirror will be eliminated. Also, when adjusting the seat height, for example, turn on the dedicated switch, move your eyes upwards to raise the seat, and then turn off the dedicated switch to avoid the hassle associated with adjusting the seat height. disappears.

As described in detail above, due to the configuration of this embodiment, the driver 2 has little movement in the y-axis direction due to the steering wheel 3 and the driver's seat 4 while driving.
It can be assumed that the eyes of the driver 2 are located on the x-z plane, that is, they move only in the front-rear and up-down directions of the driver's seat, and one two-dimensional solid-state image sensor 12 and a plurality of light emitting elements 14a to 14 are arranged on the x-z plane. 14h, the driver's position can be recognized three-dimensionally.

That is, the light emitting elements 14a to 14h irradiate infrared light onto an area where the upper body of the driver 2 is likely to be present, and the reflected light is converted into an image by one two-dimensional solid-state image sensor (two-dimensional CCD) 12. detect,
The two-dimensional position of the driver's eyes is recognized from external image information, and from this the three-dimensional position of the driver's eyes is recognized. In this way, the driver's actual three-dimensional position can be known with high precision.

Therefore, the actual three-dimensional position of the driver 2 can be accurately grasped, regardless of the height of the driver 2, which varies from person to person, or the movement of the driver 2 on the x-z plane. The actuator can be driven according to the two three-dimensional positions.

For example, the fender mirror and rearview mirror can be automatically adjusted, freeing you from the hassle of adjusting them. By adjusting the damper of the air conditioner and directing the air outlet of the air conditioner toward the position of the driver 2, the heating and cooling effect can be promoted. It detects periodic movements of the driver 2, determines that the driver is dozing off, and issues a warning using light, sound stimulation, etc., thereby preventing drowsy driving. Distracted driving can be prevented by detecting the position of the nose. Using light to display a scale from the top of the dash board to the bottom of the windshield, roadside detection can be performed in accordance with individual differences. The tilt handle can be automatically adjusted and set to the optimal position according to individual differences between drivers.

In this way, it is possible to achieve good vehicle operability and comfort depending on the individual driver. Therefore, the driver is freed from the trouble of operating these actuators. Also,
From the perspective of monitoring the driver's driving, it is possible to promote safe driving.

Since it uses a two-dimensional solid-state image sensor, the detection unit can be made smaller compared to conventional image pickup tubes, and since there are no moving parts, it has excellent vibration resistance and is highly reliable for use in vehicles. You can realize your sexuality.

Incidentally, regardless of this embodiment, in the flowchart of FIG. 7, the request signal for image recognition processing is
It may be generated at every set time using a software timer or a hardware timer. In other words, a timer interrupt process may be performed, which allows the actuator to be driven at every set time, making it possible to correct the actuator according to the movement of the eye position.

Furthermore, when an image including the upper body of the driver 2 is frozen by irradiating infrared light from the infrared light emitting elements 14a to 14h, it may be necessary to freeze the image including the upper body of the driver 2 for some reason, such as when the driver looks to the side when the vehicle is temporarily stopped, or when driving. If the position of the eyes cannot be detected, such as when the user looks behind them due to a need for the camera, a step may be provided to suspend the image recognition process.

The processing request in step 201 may be started when the vehicle speed pulse exceeds a predetermined value or when the neutral switch is turned off. This is because the driver may move his or her face during a temporary stop due to a stop signal or the like.

Furthermore, the light emitting time of the infrared light emitting diode may be continuous, and there is no need to time the light emission and light reception. Also, visible light may be used within a range where the driver does not feel glare.

Next, another example of the optical system will be explained. This example has almost the same configuration as the optical system of the example, but has a configuration in which the amount of light from the light emitting element can be controlled. In the embodiment, all the light emitting elements were configured to be driven at the same time, but in a bright environment, there is a sufficient amount of light, so this is not necessary. Furthermore, because the amount of light is large, so-called blooming phenomenon occurs.
Therefore, the driving current of the light emitting element is controlled according to the amount of incident light. Therefore, in this example, the light emitting element 14a shown in FIGS.
and 14e only, or 14a, 14c,
The brightness of the light emitting elements is controlled by a method of driving four light emitting elements 14e and 14g or a method of controlling the driving current of all the light emitting elements 14a to 14h.

As described above, according to this example, a clear image can be obtained, the algorithm for detecting the driver's position can be simplified, calculation speed can be increased, and detection accuracy can be improved.

Next, other examples with different optical systems as shown in FIGS. 13A and 13B will be explained. 13A represents a plan view of this example, and FIG. 13B represents a YY cross-sectional view. This example has almost the same configuration as the example, but a slightly longer cylindrical long holder 510 is used as the holder 10, and the lens 51
1, a mechanical optical aperture mechanism or an electric aperture mechanism 520 using liquid crystal, or infrared light emitting elements 514a to 514h are used as light emitting means. Further, a visible light cut filter may be used as a mechanism for controlling the amount of light. This is to optimally control the amount of light incident on the two-dimensional solid-state image sensor 12.

According to this example, a clear two-dimensional image can be obtained, and the same effect as that of the previous example can be obtained.

The liquid crystal aperture element 520 controls the amount of light collected on the two-dimensional solid-state image sensor within a certain range, which is effective in preventing the blooming phenomenon generally seen in solid-state image sensors.

Furthermore, as the light amount diaphragm mechanism, a transparent ceramic diaphragm that utilizes the birefringent electric field property of ceramic may be used instead of a liquid crystal diaphragm element or a normal mechanical light amount diaphragm. Transparent ceramic has excellent durability and does not change much over time, so it can increase the reliability of the device.

Next, another example of the light emitting means using an infrared strobe as the light emitting means will be explained.

FIG. 14A is a side view of the infrared strobe 605, where 650 is an infrared emitter, 651 is a lens for irradiating a wide range of infrared light to the driver 2, and 653 is a lens that transmits infrared light and visible light. Infrared filter that does not pass through, 65
5 is a case, 657 is a lens 651 and a filter 6
53 to the case. The infrared strobe 605 is fixed approximately at the center of the instrument panel 604a with a bolt 658a and a nut 658b.

The emission spectrum of the infrared light emitter 650 is shown in FIG.
It is configured to cut out light of 800 nm or less and irradiate only infrared light to the upper body of the driver 2. According to this example, the driver does not feel dazzled even when the infrared strobe 605 emits light, and the image is not affected by external disturbances.

Note that other configurations may be used as described below without changing the gist of the present invention.

That is, the light emitting means and the image detecting means may be installed at a position other than the upper left of the driver, or may be installed at a position close to the driver's upper body, for example, at the upper right of the vehicle.

In addition, the light emitting means includes a light emitting element equipped with a lens and a light beam with a set irradiation range (for example, the irradiation range is
A small lens may be installed on a light-emitting element with a light beam of 60°) or a light-emitting element with a normal wide-angle light beam to create a slightly parallel beam (irradiation range of 10°) to increase the sensitivity of the image. Note that the angle of the irradiation range may be corrected as appropriate.

A charge-coupled device (CCD) was used as a solid-state image sensor as part of the image detection means.
Instead, the output of the photodiode array,
A MOS type solid-state image sensor that reads out data by switching MOS transistors may also be used. Since the MOS type solid-state image sensor has a simple image readout circuit, the image signal control circuit can be simplified and miniaturized.

Further, as the pattern recognition processing performed by the recognition means, instead of the binarization processing, differentiation processing may be performed to obtain the contour line of the face, and the position of the eyes may be determined from this contour line. Alternatively, the two-dimensional image of the face may be divided into white and black open and closed parts, and the positions of the eyes may be determined from these parts. In other words, the image may be scanned horizontally, two places where first white and then black are present are detected, and the detected positions may be identified as the positions of the eyes.

Furthermore, when recognizing the position of the eyes, instead of expressing them using the coordinates of the eye positions, the driver's mouth or shoulder area may be detected and expressed using these coordinates. Furthermore, as a form of coordinate expression, optical system 1
For example, the position may be recognized by expressing it in the form of polar coordinates with the origin at the position of the rearview mirror, instead of the coordinate position as seen from the rear view mirror. In cases such as adjusting the angle of the rearview mirror, calculations are simplified and
This is because it is particularly effective.

[Effects of the Invention] The vehicle driver position recognition device according to the present invention includes a light emitting means for emitting light to a vehicle driver, and a light emitting means disposed diagonally in front of the driver's seat, and the vehicle driver's position recognition device emits light from the vehicle driver by the light emitting means. an image detection means for detecting reflected light as image information; and an image detection means for detecting reflected light as image information;
and recognition means that recognizes the three-dimensional position of the driver in the vehicle interior based on the two-dimensional image detected by the image detection means by assuming that the driver moves only in the vertical direction.

Therefore, the actual three-dimensional position of the driver can be recognized with high accuracy depending on individual differences between drivers or the movement of the driver on the surface. From this, it is possible to move the vehicle equipment to a suitable position, that is, it is possible to realize good vehicle operability and comfort. Therefore, the driver can ensure even safer driving. Another side effect is that the device is simple and has fewer failures.

[Brief explanation of drawings]

Fig. 1 is a basic configuration diagram of the present invention, Fig. 2 is a plan view of the mounting position showing the mounting position of the embodiment on an automobile;
Fig. 3 is a front view of the mounting position, Fig. 4 is a front view of the optical system of the embodiment, Fig. 5 is its XX cross-sectional view,
FIG. 6 is a schematic system diagram of the embodiment, FIG. 7 is a flowchart of the control program, FIG. FIG. 10 and FIG. 11 are explanatory diagrams showing an example of the movement of the driver's eye position in the image memory, and FIG. 12 is an explanatory diagram showing an example of the movement of the driver's eye position in the image memory. 13A is a plan view of another example of the optical system, FIG. Graphs showing the emission spectra of the light emitters are respectively shown. 1...Optical system, 2...Driver, 3...Steering, 4...Driver's seat, 5...Center line, 12...2
Dimensional solid-state image sensor, 14a to 14h...Light emitting element, 100...Arithmetic control circuit, 104...
ROM, 105...RAM.

Claims (1)

[Scope of Claims] 1. A light emitting device that irradiates light to a vehicle driver; and an image detection device that is disposed diagonally in front of the driver's seat and that detects light reflected from the vehicle driver due to the irradiation of the light emitting device as image information. means, and the position of the vehicle driver is in front of or behind the driver's seat.
A vehicle characterized by comprising: recognition means that recognizes the three-dimensional position of the driver in the vehicle interior based on the two-dimensional image detected by the image detection means by assuming that the driver moves only in the vertical direction. Driver position recognition device. 2. The vehicle driver position recognition device according to claim 1, wherein the image detection means includes one two-dimensional solid-state image sensor. 3. The vehicle driver position recognition device according to claim 2, wherein the light emitting means is an infrared light emitting element disposed close to the two-dimensional solid-state image sensor.