KR20150069770A - Image recognizing apparatus and method of car inside - Google Patents

Abstract

A device to recognize an inside image of a vehicle includes an image obtaining part obtaining an image about the inside of a vehicle; a first image processing part obtaining first information on a body shape and position of a passenger of the vehicle from the image; a first communication part providing the first information to an airbag control part controlling an airbag; a second image processing part confirming whether a driver watches forward or not by extracting second information on a head position of the driver from the image; and a second communication part providing a warning signal to a warning control part when the driver is not watching forward for a while. Therefore, the airbag is able to be unfolded according to the body shape and position of the passenger and the driver is prevented from paying no attention to watching forward.

Description

Technical Field [0001] The present invention relates to a vehicle interior image recognition apparatus and method,

The present invention relates to a vehicle interior image recognition apparatus and method, and more particularly, to a vehicle interior image recognition apparatus and method for recognizing an occupant and a driver on a vehicle.

Generally, a recently produced vehicle is equipped with an air bag to minimize the damage of a passenger in the event of a vehicle collision. Further, the present invention is applied to a vehicle having a smart airbag that adjusts the deployment strength of the airbag according to the occupant's position and physical condition.

According to the related art, the position and physical condition of the occupant can be detected by using a seat position sensor or a weight sensor. Specifically, the deployment strength of the airbag with respect to the driver's seat can be adjusted by attaching a position sensor under the driver's seat and confirming information about the position of the driver's seat using the position sensor. In addition, the occupant of the passenger seat or the rear seat can use the weight sensor to determine whether or not the airbag is operated after checking whether or not the airbag is occupied.

In the case of the related art, a position sensor and a weight sensor are mounted on the driver's seat, the front passenger's seat and the rear seat, respectively, to obtain information of the passenger. A large number of the sensors are required, and a large number of wires are required to transmit signals provided from the sensors. Therefore, it is expensive to purchase the sensors and the wires.

Further, since the sensors and the wires are used in large amounts, there is a possibility that the quality of the sensors and the wires may be deteriorated. Therefore, the reliability of the function of the airbag can be reduced.

The present invention provides a vehicle interior image recognition apparatus and method capable of sensing the position and physical condition of a passenger using an image, and detecting whether or not the driver is looking forward.

The apparatus and method for recognizing a vehicle interior image according to the present invention includes an image acquisition unit for acquiring an image of a vehicle interior, a first image processing unit for acquiring first information on a position and a body shape of the vehicle occupant from the image, A first communication unit for providing the first information to the airbag control unit for controlling the airbag, a second communication unit for extracting second information on the head position of the driver among the vehicle occupants from the image, And a second communication unit for providing a warning signal to the warning control unit when the driver and the driver do not perform the forward gazing for a predetermined period of time.

According to one embodiment of the present invention, the image acquiring unit may selectively acquire either the image of the entire passenger of the vehicle or the image of the driver.

According to an embodiment of the present invention, the first image processing unit may obtain the first information when the engine start of the vehicle is sensed or the opening and closing of the vehicle door is detected.

The vehicle interior image recognition method according to the present invention may include a step of monitoring the vehicle occupant and a step of monitoring the driver of the vehicle occupant.

According to an embodiment of the present invention, the step of performing monitoring of the vehicle occupant and the step of monitoring the driver are sequentially performed while the engine start of the vehicle is sensed, and when the door opening / Performing the monitoring for the vehicle occupant, and monitoring the driver may be performed again.

According to one embodiment of the present invention, performing the monitoring for the vehicle occupant includes obtaining position and body information of the vehicle occupant and providing the information to the airbag control unit, The step of monitoring the driver may include checking whether the driver is looking forward or not and transmitting a warning signal to the warning sound controller when the driver does not watch the driver's front.

According to an embodiment of the present invention, the step of transmitting the warning signal to the warning control unit may include the steps of: measuring a first time when the driver does not look ahead; Comparing the first reference time with the first reference time, and transmitting the warning generation signal to the warning control unit when the first time is longer than the first reference time.

According to an embodiment of the present invention, the step of monitoring the driver may include the steps of reconfirming whether or not the driver is looking forward when a warning sound is generated according to the warning signal provided to the warning control unit, And forwarding a warning stop signal to the warning control unit when the user looks ahead.

The apparatus and method for recognizing a vehicle interior image according to the present invention can detect the position and the body shape of a passenger using the image and provide it to the airbag control unit. Accordingly, the deployment of the airbag can be controlled depending on the position and the body shape of the occupant. Therefore, it is possible to prevent the unnecessary deployment of the airbag to reduce the repair cost of the airbag, and to control the deployment speed of the airbag, so that the injury of the occupant due to collision with the airbag can be minimized.

An apparatus and method for recognizing a vehicle interior image according to the present invention can detect whether a driver is looking forward by using the image and provide a warning signal to the warning controller when the driver overlooks the front of the vehicle. It is possible to prevent a vehicle accident caused by the driver's front sight hole by allowing the driver to continuously look ahead using the warning sound.

BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a block diagram illustrating a vehicle interior image recognition apparatus according to an embodiment of the present invention.
2 is a flowchart illustrating a vehicle interior image recognition method according to an embodiment of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, an apparatus and method for recognizing a vehicle interior image according to an embodiment of the present invention will be described in detail with reference to the accompanying drawings. The present invention is capable of various modifications and various forms, and specific embodiments are illustrated in the drawings and described in detail in the text. It should be understood, however, that the invention is not intended to be limited to the particular forms disclosed, but includes all modifications, equivalents, and alternatives falling within the spirit and scope of the invention. Like reference numerals are used for like elements in describing each drawing. In the accompanying drawings, the dimensions of the structures are enlarged to illustrate the present invention in order to clarify the present invention.

The terms first, second, etc. may be used to describe various components, but the components should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, the first component may be referred to as a second component, and similarly, the second component may also be referred to as a first component.

The terminology used in this application is used only to describe a specific embodiment and is not intended to limit the invention. The singular expressions include plural expressions unless the context clearly dictates otherwise. In this application, the terms "comprises", "having", and the like are used to specify that a feature, a number, a step, an operation, an element, a part or a combination thereof is described in the specification, But do not preclude the presence or addition of one or more other features, integers, steps, operations, components, parts, or combinations thereof.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms such as those defined in commonly used dictionaries are to be interpreted as having a meaning consistent with the contextual meaning of the related art and are to be interpreted as either ideal or overly formal in the sense of the present application Do not.

BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 is a block diagram illustrating a vehicle interior image recognition apparatus according to an embodiment of the present invention.

1, the vehicle interior image recognition apparatus 100 includes an image acquisition unit 110, a first image processing unit 120, a first communication unit 130, a second image processing unit 140, and a second communication unit 150 ).

The image acquisition unit 110 is for acquiring an image of a vehicle interior and may be mounted on a room mirror of the vehicle.

More specifically, the image acquisition unit 110 may photograph the driver's seat, the front passenger's seat and the rear seat of the vehicle at one time. Accordingly, the image acquisition unit 110 can photograph the passengers aboard the vehicle.

Also, the image acquisition unit 110 may acquire only the image of the driver by selectively photographing only the driver's seat.

That is, the image acquisition unit 110 may selectively acquire either the image of the entire passenger of the vehicle or the image of the driver.

The image obtaining unit 110 may provide the image of the passenger to the first image processing unit 120 and may provide the image of the driver to the second image processing unit 140. [

The first image processing unit 120 processes the image of the passenger provided from the image obtaining unit 110 to check the first information on the position and the body shape of the vehicle occupant.

Specifically, the first image processing unit 120 can check the position of the passenger by comparing the reference image with the image of the passenger when the vehicle is not occupied. That is, it is possible to confirm where the occupant is located in the driver's seat, the passenger's seat, and the rear seat.

In addition, the first image processing unit 120 can confirm the information on the occupant's body shape using the brightness, the contrast ratio, and the color of the image at the boundary between the driver's seat, the front passenger's seat and the rear seat and the occupant.

When the first information is confirmed in the first image processing unit 120, the first communication unit 130 provides the first information to the airbag control unit 10. For example, the first communication unit 130 may provide the first information to the airbag control unit 10 via the CAN network of the vehicle. The airbag control unit 10 controls the airbag in accordance with the first information when the vehicle collides to selectively deploy the airbag only in the seat occupied by the occupant so that the airbag is not deployed in the remaining seats. Therefore, it is possible to prevent unnecessary deployment of the airbag, thereby reducing the cost of repairing the deployed airbag.

In addition, the airbag control unit 10 can adjust the speed at which the airbag is deployed according to the body shape of the occupant. For example, when the body of the occupant is large, the airbag control unit 10 causes the airbag to deploy relatively quickly. When the body of the occupant is small, the airbag control unit 10 causes the airbag to deploy relatively slowly. Accordingly, when the body of the occupant is small, it is possible to minimize the injury caused by collision of the occupant with the airbag.

The second image processing unit 140 processes the image of the driver provided from the image obtaining unit 110 to extract second information on the head position of the driver and confirm whether or not the driver is looking forward.

Specifically, the first image processing unit 120 extracts second information on the head position of the driver by recognizing the eyes, nose, mouth, and the like using the brightness, contrast, contrast, and color of the image in the image of the driver can do. By checking the position of the eye in the second information, it can be confirmed whether the driver is looking forward or looking elsewhere.

If it is confirmed from the second information that the driver does not look ahead, the second communication unit 150 provides a warning signal to the warning control unit 20. The warning controller 20 generates a warning sound according to the warning signal to warn the driver to watch ahead. It is possible to prevent a vehicle accident caused by the driver's front sight hole by allowing the driver to continuously look ahead using the warning sound.

If it is determined in the second information that the driver is looking forward, the second communication unit 150 provides an alarm stop signal to the alarm controller 20 in a state where the alarm sound is generated. For example, the second communication unit 150 may provide the warning stop unit 20 with the warning stop signal via the CAN network of the vehicle. The warning control unit 20 stops generating the warning sound according to the warning generation stop signal. Therefore, it is possible to prevent unnecessary occurrence of the warning sound.

On the other hand, the first image processing unit 120 can confirm the first information when the engine start of the vehicle or the opening / closing of the vehicle door is detected.

Specifically, when the engine start of the vehicle is sensed, the passengers are boarded on the vehicle, so that the first information on the position and the body shape of the passenger is confirmed. Further, if the opening / closing of the vehicle door is detected, the position or the body shape of the occupant may be changed, so that the first information is confirmed.

Therefore, when the engine start of the vehicle or the opening / closing of the vehicle door is not detected, the first image processing unit 120 does not need to check the first information.

On the other hand, the engine start of the vehicle is maintained, and the second image processor 120 continuously checks the second information when the opening and closing of the vehicle door is not detected.

When the engine start of the vehicle or the opening / closing of the vehicle door is detected, the image obtaining unit 110 obtains an image of the entire occupant of the vehicle and provides the image to the first image processing unit 120.

If the engine start of the vehicle or the opening / closing of the vehicle door is not detected, the image obtaining unit 110 obtains the image of the driver and provides the image to the second image processing unit 140.

2 is a flowchart illustrating a vehicle interior image recognition method according to an embodiment of the present invention.

2, in order to perform the vehicle interior image recognition method, the vehicle occupant is first monitored (S100)

Specifically, in order to monitor the vehicle occupant, the position and the body information of the vehicle occupant are obtained (S110)

The driver's seat, the front passenger's seat and the rear seat of the vehicle are shot at one time and the passengers are photographed. Thereafter, the position of the passenger can be confirmed by comparing the reference image with the image of the passenger when the vehicle is not occupied. That is, it is possible to confirm where the occupant is located in the driver's seat, the passenger's seat, and the rear seat.

Further, the first information on the occupant's body type can be confirmed using the brightness, the contrast ratio and the color of the image at the boundary between the driver's seat, the front passenger's seat, the rear seat and the passenger on the image of the occupant.

When the first information on the position and the body shape of the vehicle occupant is obtained, the first information is provided to the airbag controller (S120)

The airbag control unit controls the airbag in accordance with the information when the vehicle collides to selectively deploy the airbag only in the seat occupied by the occupant so that the airbag is not deployed in the remaining seats. Therefore, it is possible to prevent unnecessary deployment of the airbag, thereby reducing the cost of repairing the deployed airbag.

In addition, the airbag control unit adjusts the speed at which the airbag is deployed according to the body shape of the occupant, thereby minimizing injury caused by the collision of the occupant with the airbag.

When monitoring of the vehicle occupant is completed, monitoring of the driver of the vehicle occupant is performed (S200)

In order to monitor the driver, it is first checked whether the driver is looking forward (S210)

Acquires an image of a driver who operates the vehicle, extracts second information from the driver's head position by recognizing the eyes, nose, mouth, and the like using the brightness, contrast, contrast, and color of the image in the image of the driver do. By checking the position of the eye in the second information, it can be confirmed whether the driver is looking forward or looking elsewhere.

If the driver does not perform the frontward gazing, the warning signal is transmitted to the warning controller (S220)

Specifically, the first time when the driver does not watch the front is measured. For example, when the eyes of the driver are out of the reference eye position, it can be determined that the driver does not look ahead. Therefore, the first time can be confirmed by measuring the time at which the eye deviates from the reference eye position on the head of the driver.

And compares the first time with a predetermined first reference time. The first reference time may vary depending on the setting. For example, the first reference time may be about 2 seconds.

If the first time is longer than the first reference time, the alarm generation unit provides the alarm generation unit with the alarm generation signal. The warning control unit generates a warning sound according to the warning signal to warn the driver to watch ahead. It is possible to prevent a vehicle accident caused by the driver's front sight hole by allowing the driver to continuously look ahead using the warning sound.

If a warning sound is generated in response to the warning signal provided to the warning control unit, the driver is checked to see if the driver is looking forward (S230)

By checking the position of the eye in the second information, it can be confirmed whether the driver is looking forward or looking elsewhere.

And provides a warning stop signal to the warning control unit when the driver watches the front side (S240)

Specifically, the driver measures a second time to look ahead. For example, the second time can be confirmed by measuring the time at which the eye is located at the reference eye position on the head of the driver.

And compares the second time with a predetermined second reference time. The second reference time may vary depending on the setting. For example, the second reference time may be about 0.5 seconds.

And provides the warning generation stop signal to the warning control unit when the second time is longer than the second reference time. The warning control unit stops the warning sound according to the warning generation stop signal.

 If the first reference time is shorter than the second reference time, the warning sound may be generated if the driver does not watch the forward even for a short time. Therefore, the warning sound frequently occurs, which may interfere with the operation of the driver. Therefore, the first reference time may be longer than the second reference time.

The monitoring of the vehicle occupant (S100) and the monitoring of the driver (S200) may be sequentially performed while the engine start of the vehicle is detected. When the engine start of the vehicle is sensed, the passengers are boarded on the vehicle. Therefore, the vehicle occupant needs to be monitored first, and when the monitoring of the passenger is completed, the driver is monitored. Monitoring for the driver is continuously performed while the starting of the vehicle is maintained.

Meanwhile, if door opening and closing of the vehicle is detected while the start of the vehicle is being maintained, the monitoring of the vehicle occupant is performed (S100) and the monitoring of the driver is performed (S200).

When the door of the vehicle is opened and then closed again, there may be a change in the position or body shape of the occupant. Therefore, the execution of the monitoring for the driver (S200) is interrupted and the monitoring of the occupant (S100) is performed again. When the monitoring of the vehicle occupant is completed (S100), the monitoring of the driver is performed again (S200).

Therefore, it is possible to positively cope with the change of the first information on the position and the body shape of the occupant.

As described above, the vehicle interior image recognition apparatus and method according to the present invention detect the position and body shape of a passenger using an image, detect whether or not the driver is looking forward, and provide information to control the deployment and speed of the airbag And may generate a warning sound when the driver neglects the front sight. Therefore, it is possible to prevent an accident of the vehicle caused by the front sight of the driver, and it is possible to reduce the repair cost of the airbag when an accident occurs in the vehicle.

It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the spirit or scope of the present invention as defined by the following claims. It can be understood that it is possible.

100: vehicle interior image recognition device 110:
120: first image processing unit 130: first communication unit
140: second image processing unit 150: second communication unit
10: air bag control unit 20: warning control unit

Claims (8)

An image acquisition unit for acquiring an image of a vehicle interior;
A first image processing unit for obtaining first information on a position and a body shape of the vehicle occupant from the image;
A first communication unit for providing the first information to an airbag control unit for controlling the airbag;
A second image processing unit for extracting second information on a head position of a driver of the vehicle occupant from the image and confirming whether or not the driver is looking forward; And
And a second communication unit for providing a warning signal to the warning control unit when the driver does not watch the forward direction for a predetermined period of time. The vehicle interior image recognizing apparatus as claimed in claim 1, wherein the image acquiring unit selectively acquires either the image of the entire passenger of the vehicle or the image of the driver. The apparatus of claim 1, wherein the first image processing unit obtains the first information when an engine start of the vehicle is detected or when opening and closing of the vehicle door is detected. Performing monitoring on a vehicle occupant; And
And performing monitoring of a driver among the vehicle occupants. 5. The method of claim 4, wherein the step of monitoring the vehicle occupant and the step of monitoring the driver are sequentially performed while detecting an engine start of the vehicle,
Wherein the step of monitoring the vehicle occupant and the step of monitoring the driver are sequentially performed when the door opening and closing of the vehicle is detected. 5. The method of claim 4, wherein performing the monitoring of the vehicle occupant comprises:
Obtaining position and body shape information of the vehicle occupant; And
And providing the information to the airbag control unit,
Wherein the step of monitoring the driver comprises:
Confirming whether or not the driver is looking forward; And
And transmitting a warning signal to the warning sound control unit when the driver does not perform the forward sighting. 7. The method of claim 6, wherein the step of delivering the alert signal to the alert controller comprises:
Measuring a first time when the driver does not look ahead;
Comparing the first time with a predetermined first reference time; And
And if the first time is longer than the first reference time, transmitting the warning generation signal to the warning control unit. 7. The method of claim 6, wherein monitoring the driver comprises:
Reconfirming whether or not the driver is looking forward when a warning sound is generated according to the warning signal provided to the warning control unit; And
And transmitting a warning stop signal to the warning control unit when the driver watches the front side.

Images