JP2008305190A - Drowsiness warning device and automobile - Google Patents

Abstract

To provide a dozing alarm device capable of reliably detecting dozing and alerting a driver.
An image capturing means for continuously capturing at least a head including a driver's face and image data obtained by image capturing by the image capturing means are acquired. Storage means for storing operation pattern data to be compared with change mode data acquisition means, change mode data acquired by change mode data acquisition means, change mode data acquired by change mode data acquisition means, and storage means On the basis of the operation pattern data stored in the operation means, and determining means for determining whether or not the change mode data satisfies a predetermined condition, and driving when the determination means determines that the predetermined condition is satisfied A drowsiness warning device, comprising: warning means for performing processing for warning a person.
[Selection] Figure 1

Description

The present invention relates to a drowsiness warning device and an automobile.

Conventionally, in order to prevent a drowsy driving, it is necessary for each driver to take a prior approach such as recovering fatigue before driving. Such an approach is carried out before the actual occurrence of sleepiness and depends on the driver. In addition, even if efforts are made in advance, sleepiness may occur.

In order to prevent drowsy driving when sleepiness actually occurs, conventionally, there is a device that determines whether or not it is drowsy driving based on blinking or eyeball movement and warns the driver. (For example, see Patent Documents 1 to 4).

JP-A-7-93700 JP-A-8-147484 JP-A-11-304428 JP 2006-193057 A

However, since the amount of movement of blinking and eyeball movement is relatively small, the devices of Patent Documents 1 to 4 have a problem that the amount of movement may not be detected. Further, when the driver is wearing glasses, erroneous detection may occur frequently due to reflection of light from the outside. In addition, when the interior of the vehicle is dark, there is a problem that the position of the eye itself cannot be detected. For this reason, there is a problem that it is impossible to reliably recognize the drowsy driving and warn the driver.

The present invention has been made in view of the above-described problems, and an object of the present invention is to provide a drowsiness warning device and an automobile capable of reliably detecting a drowsiness and warning a driver.

In order to solve the above-described problems, the present invention provides the following.
(1) imaging means for continuously imaging at least the head including the driver's face;
Change mode data acquisition means for acquiring change mode data indicating a video change mode from video data obtained by imaging by the imaging unit;
Storage means for storing operation pattern data to be compared with change aspect data acquired by the change aspect data acquisition means;
A determination unit that determines whether or not the change mode data satisfies a predetermined condition based on the change mode data acquired by the change mode data acquisition unit and the operation pattern data stored in the storage unit;
A drowsiness warning device comprising: warning means for performing processing for giving a warning to a driver when the determination means determines that a predetermined condition is satisfied.

According to the invention of (1), the change mode data indicating the change mode of the video is acquired from the video data obtained by photographing at least the head including the driver's face by the imaging means (for example, monitor camera). Change mode data. Then, this change mode data and pre-stored motion pattern data to be compared with the change mode data (for example, data indicating a motion pattern including blinking, eye movement, and head vertical movement). Based on this, it is determined whether or not the change mode data satisfies a predetermined condition. When it is determined that the predetermined condition is satisfied, a process for warning the driver is performed. In order to warn the driver not only based on blinking and eye movement but also based on at least the movement of the head including these, for example, when the eyes do not fall asleep like garbage However, it is possible to reduce warnings despite the fact that the warning can be performed accurately only when the driver is asleep.
In addition, when blinking or eye movement cannot be detected (for example, when the driver is wearing glasses or the inside of the vehicle is extremely dark), for example, the head is moved up and down without using blinking or eye movement. By detecting this, it can be determined whether or not the patient is dozing. Therefore, it is possible to reduce the possibility that the warning cannot be performed due to the influence of the driver or the external situation.

Furthermore, the present invention provides the following.
(2) The dozing alarm device according to (1) above,
A release input means for inputting a warning release;
And a warning canceling means for canceling the warning when there is a warning canceling input from the canceling input means.

According to the invention of (2), since the warning is canceled when the warning cancellation input is received, the driver can strongly recognize that he / she was in a dozing state by the operation of the cancellation input. In addition, when a warning canceling input is received, the warning is stopped, so that it is possible to prevent the operation from being hindered by giving more warnings than necessary.

Furthermore, the present invention provides the following.
(3) The dozing warning device according to the above (1) or (2) provided on a vehicle provided with braking means,
And a brake signal output means for outputting a signal for decelerating or stopping the vehicle to the braking means when no warning cancellation input is received from the release input means within a predetermined period after the start of warning. To do.

According to the invention of (3), when the warning is not input within a predetermined period after the warning is started, a signal for decelerating or stopping the vehicle is output. The probability that an accident will occur can be reduced.

Furthermore, the present invention provides the following.
(4) The dozing alarm device of (3) above,
And a notification means for performing processing for notifying the vehicle that the vehicle decelerates or stops when there is no warning cancellation input from the cancellation input means within a predetermined period after the start of the warning. .

According to the invention of (4), when there is no warning cancellation input within a predetermined period after the start of the warning, a process of notifying the vehicle that the vehicle is decelerating or stopping is performed (for example, an automobile hazard) To prevent secondary accidents such as rear-end collisions, so that outsiders (for example, the driver of the following vehicle) can pay attention to the movement of the vehicle. It becomes possible.

Furthermore, the present invention provides the following.
(5) The dozing alarm device according to any one of (1) to (4) above,
The warning means performs a process for giving a warning according to a dozing period.

According to the invention of (5), a process for giving a warning according to the period of dozing (for example, when a 10-second doze is made, a larger warning sound than when a doze is taken for 5 seconds) is performed. In general, the longer the dozing period, the higher the level of consciousness loss. Therefore, by performing the process for giving a warning according to the period of dozing, it is possible to warn the driver more reliably according to the level of consciousness reduction.

Furthermore, the present invention provides the following.
(6) An automobile comprising the drowsiness warning device according to any one of (1) to (5) above.

According to the invention of (6), it is possible to warn the driver who drives the car that he is dozing.

According to the present invention, it is possible to reliably detect dozing and warn the driver.

Embodiments of the present invention will be described with reference to the drawings.
FIG. 1 is a side view schematically showing an automobile according to an embodiment of the present invention.
FIG. 2 is a top view of the automobile shown in FIG. In FIG. 2, the roof is omitted so that the inside of the vehicle can be grasped.
The automobile 50 is provided with a dozing alarm device 10. The dozing alarm device 10 includes a control unit 12, a monitor camera 22, and a confirmation button 24. As shown in FIG. 2, the monitor camera 22 is provided on an upper part of a steering wheel 52 provided in front of the dashboard 56 and images the head including the driver's face. Video data obtained by imaging with the monitor camera 22 is transmitted to the control unit 12. The video data is converted into optical flow data, and the optical flow data is analyzed to determine whether or not the driver is asleep. Specifically, it is determined whether or not the driver is asleep by determining whether or not the optical flow data converted from the video data matches the operation pattern data for doze determination (see FIG. 4) described later. To be judged. The optical flow will be described in detail later. If it is determined that the driver is asleep, a warning sound is output from the speaker (see FIG. 3). The confirmation button 24 is provided below the steering wheel 52. When the driver operates the confirmation button 24, the output of the warning sound is stopped. The confirmation button 24 corresponds to the cancel input means of the present invention.

FIG. 3 is a block diagram schematically showing the internal configuration of the dozing alarm device shown in FIG.
The dozing warning device 10 includes a CPU 14, a ROM 16, and a RAM 18.
The ROM 16 is a non-volatile memory and stores programs executed by the CPU 14, data used when the CPU 14 performs processing, and the like. In addition, the ROM 16 stores doze determination operation pattern data (see FIG. 4). The ROM 16 corresponds to storage means of the present invention. The RAM 18 is a volatile memory, and temporarily stores data corresponding to the processing result of the CPU 14.

A speaker 20, a monitor camera 22, and a confirmation button 24 are connected to the CPU 14.
The monitor camera 22 images the driver and transmits video data obtained by the imaging to the CPU 14. The monitor camera 22 functions as an imaging unit. The CPU 14 calculates an optical flow, which will be described later, based on the video data received from the monitor camera 22, and acquires the optical flow data. The optical flow data corresponds to the change mode data in the present invention.

The speaker 20 is for outputting a warning sound and a warning message. Based on the optical flow data, the CPU 14 determines whether or not the driver is asleep. If the CPU 14 determines that the driver is asleep, the CPU 14 outputs a warning sound or a warning message to the speaker 20. At this time, if it is determined that the driver is asleep for more than 5 seconds, a level 1 warning is given, and if it is determined that the driver is asleep for more than 5 seconds, the level is Warning 2 is performed. Then, if it is determined that the driver is asleep for more than 5 seconds, a level 3 warning is given. In the present embodiment, the level 1 warning is to output a warning sound of a predetermined volume (for example, “pi, pi, pi, pi ...”) from the speaker 20, and the level 2 warning is , Outputting a warning sound having a louder volume than that at the level 1 warning from the speaker 20, and the warning at the level 3 is accompanied by a warning message (for example, “dangerous” Is output from the speaker. In the present invention, the warning is not limited to this example as long as the warning is performed according to the period determined to be asleep, and a weak current may be supplied to the seat or the steering wheel. It is good also as sending a wind (for example, cold wind) from an air conditioner.

The confirmation button 24 outputs a warning stop request signal when operated by the driver. When the CPU 14 receives the warning stop request signal, the CPU 14 stops outputting the warning sound and the warning message from the speaker 20.

A brake device 70 and a lamp lighting control device 80 are connected to the CPU 14 via the communication interface 26. CPU14 transmits the stop signal for stopping the motor vehicle 50 with respect to the brake device 70, when it is judged that the driver is dozing for 15 seconds or more. When the CPU 14 determines that the driver is asleep for 15 seconds or more, the CPU 14 transmits a hazard lamp lighting instruction signal for lighting the hazard lamp to the lamp lighting control device 80.

FIG. 4 is a diagram illustrating an example of operation pattern data for dozing determination.
The doze determination operation pattern data is data indicating an operation pattern for determining that the driver is dozing, and includes eye movement pattern data and head movement pattern data as shown in FIG. It is. The eye movement pattern data is data indicating the left and right movements of the driver's eyeball, and the movement of the eyeball when the driver checks the left and right is optical flow data. The head movement pattern data is data indicating the vertical movement of the driver's head, and is an optical flow data that is a head shake that may occur when the driver falls asleep. The eye movement pattern data and the head movement pattern data are movement pattern data to be compared with the optical flow data in the present invention.
Hereinafter, the optical flow related to the eye movement pattern data A will be described with reference to FIG. 5, and the optical flow related to the head movement pattern data A will be described using FIG.

FIG. 5 is a diagram for explaining an optical flow related to eye movement.
An optical flow is a velocity vector between pixels in an image. As a method of calculating the optical flow, first, a pixel block composed of a plurality of pixels is set in advance in the first image. Next, this pixel block is detected in the second image following the first image. Then, the movement of each pixel block in the two images is detected. Thereby, the optical flow of the object in the imaging region of the monitor camera 22 can be calculated.

The diagram on the left side of FIG. 5A is a diagram showing the state of the driver imaged by the monitor camera 22.
As shown in the diagram on the left side of FIG. 5A, the image obtained by the monitor camera 22 shows a state in which the head of the driver 60 is imaged from the front.
The diagram on the right side of FIG. 5A is a diagram showing the optical flow in the state of the diagram on the left side of FIG.
The monitor camera 22 transmits video data to the processing terminal 10 every 0.2 seconds. Then, the processing terminal 10 calculates an optical flow every 0.2 seconds from each transmitted video data. In the diagram on the right side of FIG. 5A, an optical flow is not obtained. This indicates that the image has not changed from 0.2 seconds ago to the present time.

The diagram on the left side of FIG. 5 (b) is a diagram showing a state 0.2 seconds after the state of the diagram on the right side of FIG. 5 (a), and the diagram on the right side of FIG. It is a figure which shows an optical flow in the state of the figure on the left side of b).
The left diagram in FIG. 5B is the same as the left diagram in FIG. 5A except that the eyeball of the person 60 moves to the right from the state in the left diagram in FIG. .
In the diagram on the right side of FIG. 5B, an optical flow indicating that each pixel block P (P1, P2) of the eyeball portion of the person 60 has moved to the right side is obtained. This is because each pixel block P has moved to the right between 0.2 seconds ago (the state in the left diagram in FIG. 5A) and the present (the state in the left diagram in FIG. 5B). It is shown that. Data indicating this optical flow corresponds to eyeball movement pattern data A.

FIG. 6 is a diagram for explaining an optical flow related to head movement.
6A is a diagram showing the state of the driver imaged by the monitor camera 22, and the diagram on the right side of FIG. 6A is the state of the diagram on the left side of FIG. 6A. It is a figure which shows the optical flow when it is.
As shown in the diagram on the left side of FIG. 6A, the image obtained by the monitor camera 22 shows a state in which the head of the driver 60 is imaged from the front. Further, in the diagram on the right side of FIG. 6A, an optical flow is not obtained. This indicates that the image has not changed from 0.2 seconds ago to the present time.

The diagram on the left side of FIG. 6B is a diagram showing a state 0.2 seconds after the state of the diagram on the right side of FIG. 6A, and the diagram on the right side of FIG. It is a figure which shows an optical flow in the state of the figure on the left side of b).
6B, the left side view of FIG. 6A, except that the head of the person 60 has moved from the state of the left side of FIG. 6A to the lower front side. Is the same.
The right side of FIG. 6B shows a vector in which each pixel block P (P10 to P14) near the top of the person spreads downward and outward. Data indicating this optical flow corresponds to head movement pattern data A.

FIG. 7 is a block diagram schematically showing the internal configuration of the brake device provided in the automobile shown in FIG.
In the brake device 70, a brake pedal 72 is connected to a wheel cylinder 73, and a brake 75 is connected to the wheel cylinder 73. In the wheel cylinder 73, brake fluid pressure is generated in response to the driver 60 depressing the brake pedal 72. The brake 75 generates a braking force according to the brake fluid pressure.

The brake device 70 includes a brake control device 74 and a brake actuator 78 connected to the brake control device 74, and the brake actuator 78 is connected to the wheel cylinder 73. The brake control device 74 is connected to the dozing warning device 10 via the communication interface 76. When receiving a stop signal from the dozing warning device 10, the brake control device 74 operates the brake actuator 78 to generate the brake hydraulic pressure in the wheel cylinder 73. Let The brake device 70 corresponds to the braking means in the present invention.

FIG. 8 is a flowchart showing a subroutine of dozing determination processing executed in the dozing warning device.
First, the CPU 14 starts motion capture when the engine is started (step S10). In this process, the CPU 14 starts imaging with the monitor camera 22 and acquires optical flow data from the obtained video data. Note that motion capture is repeatedly executed until the engine is stopped. The CPU 14 functions as a change mode data acquisition unit that acquires optical flow data from video data obtained by imaging with the monitor camera 22.

Next, in step S12, the CPU 14 sets an elapsed time t = 0 and starts measuring the elapsed time t. When executing the process of step S12, the CPU 14 functions as a measuring unit.
Next, in step S14, the CPU 14 executes a warning process to be described later, and ends this subroutine.

FIG. 9 is a flowchart showing a subroutine of warning processing executed in the dozing alarm device.
First, the CPU 14 determines whether or not the obtained optical flow data (see step S10) matches any of the eye movement pattern data (see FIG. 4) stored in the ROM 16 (step S20). When it is determined that the optical flow data does not match any of the eye movement pattern data, the CPU 14 determines whether or not the elapsed time t is 5 seconds or more (step S22). When determining that the elapsed time t is 5 seconds or more, the CPU 14 determines whether or not the acquired optical flow data matches any of the head movement pattern data (see FIG. 4) stored in the ROM 16. (Step S24). In this specification, the optical flow data and the movement pattern data (eye movement pattern data, head movement pattern data) coincide with each other when the values of the optical flow data and the movement pattern data quantified by a predetermined process are calculated. This includes the case where it is within a predetermined range (high similarity). When executing the processing of step S20 and step S24, the CPU 14 functions as a determination unit.

If it is determined that the optical flow data acquired in step S24 matches any of the head movement pattern data, the CPU 14 determines whether or not the elapsed time t is 10 seconds or more (step S26). When determining that the elapsed time t is not 10 seconds or more, the CPU 14 issues a level 1 warning (outputs a warning sound from the speaker 20) (step S30). On the other hand, when determining that the elapsed time t is 10 seconds or longer, the CPU 14 determines whether or not the elapsed time t is 15 seconds or longer (step S28). When determining that the elapsed time t is not 15 seconds or more, the CPU 14 issues a level 2 warning (output of a warning sound from the speaker 20 at a volume higher than level 1) (step S32). When determining that the elapsed time t is 15 seconds or more, the CPU 14 performs a level 3 warning (output of a warning sound having a volume larger than level 2 and a predetermined warning message from the speaker 20) (step S34). . When executing the process of step S30, step S32 or step S34, the CPU 14 functions as a warning means.

After the process of step S30, step S32, or step S34, the CPU 14 determines whether or not there is a confirmation input. In this process, the CPU 14 determines whether or not a warning stop request signal output by operating the confirmation button 24 has been received. When determining that there is a confirmation input, the CPU 14 stops outputting the warning sound (and warning message) from the speaker 20 (step S46), and moves the process to step S48. When executing the process of step S46, the CPU 14 functions as a warning stopping unit.

If it is determined in step S20 that the optical flow data matches any of the eye movement pattern data, if it is determined in step S24 that the optical flow data does not match any of the head movement pattern data, or the process of step S46 After that, the CPU 14 sets the elapsed time t to t = 0 (step S48), and ends this subroutine.

If it is determined in step S36 that there is no confirmation input, the CPU 14 determines whether or not a level 3 warning is in progress (step S38). If the level 3 warning is not in progress, this subroutine is terminated. On the other hand, if it is determined that the warning of level 3 is being performed, the CPU 14 transmits a stop signal for stopping the automobile 50 to the brake device 70 (step S40). When executing the process of step S40, the CPU 14 functions as a braking signal output means. In the brake device 70 that has received the stop signal, the brake actuator 78 is operated to generate a brake fluid pressure in the wheel cylinder 73 to generate a braking force. Thereby, the automobile 50 starts to decelerate and finally stops. Therefore, it is possible to reduce the probability that an accident will occur if a warning does not wake up from sleep.

Next, in step S42, the CPU 14 transmits a hazard lamp lighting instruction signal for lighting the hazard lamp to the lamp lighting control device 80. When executing the process of step S42, the CPU 14 functions as a notifying means for performing a process of notifying the outside that the automobile 50 is decelerated or stopped. In the lamp lighting control device 80 that has received the hazard lamp lighting instruction signal, the hazard lamp is turned on. Accordingly, the driver of the succeeding vehicle can pay attention to the movement of the automobile 50 and can prevent a secondary disaster such as a rear-end collision.

Next, in step S44, the CPU 14 performs post-emergency stop processing. In this process, the CPU 12 outputs a message for notifying that an emergency stop has occurred from the speaker 20. Then, it waits until there is an input signal from the confirmation button 24, and on the condition that there is an input signal, a signal for releasing the brake is transmitted to the brake device 70 and a hazard is given to the lamp lighting control device 80. Send a signal to stop the lamp lighting. After the process of step S44, this subroutine is terminated.

As described above, according to the snoozing warning device 10 and the automobile 50, the optical flow data is acquired from the video data obtained by photographing at least the head including the driver's face by the monitor camera 22. And based on this optical flow data and pre-stored motion pattern data (eyeball motion pattern data, head motion pattern data), whether or not the optical flow data matches any of the motion pattern data, When it is determined whether or not the driver is asleep, and it is determined that the driver is asleep, a process for warning the driver (output of a warning sound or the like) is performed. In order to warn the driver not only based on the movement of the eyeball but also based on the movement of the eyeball and the movement of the head, for example, even when the eyes are dusty, Regardless of this, it is possible to reduce the number of warnings, and it is possible to give a warning accurately only when the driver is asleep.
In addition, when the movement of the eyeball cannot be detected (for example, when the driver is wearing spectacles or when the interior of the vehicle is extremely dark), for example, the vertical movement of the head is detected without using the movement of the eyeball. Thus, it can be determined whether or not the patient is dozing. Therefore, it is possible to reduce the possibility that the warning cannot be performed due to the influence of the driver or the external situation.

In addition, since the warning is canceled when the warning cancellation input is received, the driver 60 can strongly recognize that he / she was in a dozing state by the operation of the cancellation input. In addition, when a warning canceling input is received, the warning is stopped, so that it is possible to prevent the operation from being hindered by giving more warnings than necessary.

Moreover, according to the dozing warning device 10 and the automobile 50, a process for giving a warning corresponding to the period of dozing is performed. In general, the longer the dozing period, the higher the level of consciousness loss. Therefore, by performing the process for giving a warning according to the period of dozing, it is possible to warn the driver more reliably according to the level of consciousness reduction.

In the present embodiment, the case where the driver is warned when the acquired optical flow data matches any of the eye movement pattern data and does not match any of the head movement pattern data has been described. That is, in the present embodiment, a case has been described in which the predetermined condition according to the present invention matches any of the eyeball movement pattern data and does not match any of the head movement pattern data. However, the predetermined condition in the present invention is not particularly limited as long as it is a condition for determining whether the driver is asleep or not, and the change mode data (optical flow data) indicates the movement pattern of the eyelid. The optical flow data includes data that matches both the eyeball movement pattern data and the eyelid movement pattern data, and the head movement pattern. It may be that none of the data is included.

Further, in the present embodiment, the case of imaging the driver's head has been described. However, in the present invention, the driver may be imaged, for example, the driver's hands and feet may be imaged. When taking an image of the driver's hand, when the driver travels on a straight road, the operation of the hand that corrects the course by manipulating a small amount of the steering wheel is stored in the storage means as operation pattern data to be compared. You just have to. In addition, when imaging the driver's foot, when the driver travels at a constant speed, the operation of the foot that corrects the speed by operating the accelerator in a small amount is stored in the storage means as operation pattern data to be compared. Just remember.

In the present embodiment, the case in which the vehicle in the present invention is an automobile has been described. However, the vehicle in the present invention is not limited to this example as long as driving is performed, and examples thereof include trains, ships, submarines, and aircraft. May be.

The embodiment of the present invention has been described above, but only specific examples are illustrated, and the present invention is not particularly limited. The specific configuration of each unit and the like can be appropriately changed. The effects described in the embodiments of the present invention are only the most preferable effects resulting from the present invention, and the effects of the present invention are limited to those described in the embodiments of the present invention. is not.

1 is a side view schematically showing an automobile according to an embodiment of the present invention. It is a top view of the motor vehicle shown in FIG. It is a block diagram which shows typically the internal structure of the dozing warning apparatus shown in FIG. It is a figure which shows an example of the operation pattern data for dozing determination. It is a figure for demonstrating the optical flow which concerns on an eyeball operation | movement. It is a figure for demonstrating the optical flow which concerns on head movement. It is a block diagram which shows typically the internal structure of the brake device with which the motor vehicle shown in FIG. 1 is provided. It is a flowchart which shows the subroutine of the dozing determination process performed in the dozing alarm device. It is a flowchart which shows the subroutine of the warning process performed in the dozing warning device.

Explanation of symbols

10 dozing alarm device 12 control unit 14 CPU
16 ROM
18 RAM
20 Speaker 22 Monitor Camera 24 Confirmation Button 26 Communication Interface 50 Car 52 Steering Wheel 56 Dashboard 60 Driver 70 Brake Device 72 Brake Pedal 73 Wheel Cylinder 74 Brake Control Device 75 Brake 76 Communication Interface 78 Brake Actuator 80 Lamp Lighting Control Device

Claims (6)

Imaging means for continuously imaging at least the head including the face of the driver;
Change mode data acquisition means for acquiring change mode data indicating a video change mode from video data obtained by imaging by the imaging unit;
Storage means for storing operation pattern data to be compared with change mode data acquired by the change mode data acquisition unit;
A determination unit that determines whether or not the change mode data satisfies a predetermined condition based on the change mode data acquired by the change mode data acquisition unit and the operation pattern data stored in the storage unit;
A drowsiness warning device comprising: warning means for performing processing for warning the driver when the judgment means judges that a predetermined condition is satisfied. A release input means for inputting a warning release;
The dozing warning device according to claim 1, further comprising warning canceling means for canceling a warning when a warning canceling input is received from the canceling input means. The dozing warning device according to claim 1 or 2, which is provided on a vehicle provided with braking means,
A brake signal output means is provided for outputting a signal for decelerating or stopping the vehicle to the braking means when there is no warning release input from the release input means within a predetermined period after the start of warning. A doze alarm device. And a notification means for performing a process of notifying the vehicle that the vehicle decelerates or stops when there is no warning cancellation input from the cancellation input means within a predetermined period after the start of the warning. The dozing alarm device according to claim 3. Measuring means for measuring a period determined by the determining means when the predetermined condition is satisfied,
The doze warning device according to any one of claims 1 to 4, wherein the warning means performs a process for giving a warning according to a period measured by the measurement means. An automobile comprising the drowsiness warning device according to any one of claims 1 to 5.

Images