KR20140109011A - Apparatus and method for controlling vehicle by detection of tunnel - Google Patents

Abstract

The present invention relates to a method for controlling a vehicle by the detection of a tunnel, configured to comprise the steps of generating at least one image by which at least one camera photographs the front of the vehicle; determining whether the vehicle enters the tunnel by recognizing a shape of the tunnel based on the image; and performing a tunnel driving mode if the vehicle is determined to enter the tunnel.

Description

[0001] DESCRIPTION [0002] APPARATUS AND METHOD FOR CONTROLLING VEHICLE BY DETECTION OF TUNNEL [

The present invention relates to a vehicle control apparatus and method for automatically recognizing a tunnel and automatically controlling a vehicle when the vehicle approaches a tunnel.

In a typical road environment, a situation in which a tail light and an in-and-out-of-road conversion are required frequently occurs during driving. Especially, in the mountainous terrain like Korea, the tunnel is frequently encountered. In such a case, not only inconvenience such that the driver changes the inside / outside mode or the taillight at the time of entry of the tunnel occurs, and also it can affect the safety when driving the vehicle.

Therefore, in order to solve the inconvenience, a technology for detecting whether or not the tunnel enters the tunnel is controlled and the vehicle is controlled accordingly. However, the conventional tunnel entry detection and automatic control system has a problem that it can not effectively distinguish between a night driving mode and a tunnel entrance time, for example, and thus can not effectively or accurately detect entry of a tunnel, thereby causing an operation error.

The background art of the present invention is disclosed in Korean Patent Laid-Open Publication No. 2009-0059981 (published on June 11, 2009).

SUMMARY OF THE INVENTION Accordingly, it is an object of the present invention to provide a method and apparatus for automatically recognizing entry of a vehicle into a tunnel through an image obtained through a plurality of cameras mounted on the vehicle, And to provide a vehicle control device and a control method by tunnel recognition that can automatically execute vehicle control.

According to an aspect of the present invention, there is provided a method for controlling a vehicle, comprising: at least one camera photographing a front of a vehicle to generate at least one image; Recognizing a shape of a tunnel based on the at least one image and determining entrance of a tunnel of the vehicle; And executing the tunnel driving mode when it is determined that the vehicle enters the tunnel.

In the present invention, the at least one camera includes a first camera and a second camera, the at least one image includes first and second images, and recognizing a shape of the tunnel to determine a tunnel entrance of the vehicle Generating a parallax map based on the first and second images; And determining a tunnel entry of the vehicle based on the parallax map.

In the present invention, the parallax map includes a plurality of pixels, a distance between each forward point projected on the first and second images and the vehicle is mapped to the plurality of pixels, And the distance is calculated based on the parallax of the first and second images.

In the present invention, the distance between each of the vehicle front points and the vehicle is calculated based on the camera focal distance, the distance between the first and second cameras, and the distance from the center of the image of the corresponding forward point input to the first and second cameras, Is calculated on the basis of the following equation.

In the present invention, the step of determining entry of a vehicle into a tunnel based on the parallax map may include generating a contour line image using differential values differentiated in the first image direction from a distance mapped to each pixel in the parallax map; And comparing the outline image with a reference image related to a previously stored tunnel shape to determine entry of the vehicle into a tunnel.

In the present invention, at the time of generating the contour image, the contour image is generated by reflecting only the differential values exceeding a preset threshold value.

In the present invention, it may be determined whether or not the vehicle is in a tunnel based on the at least one image. And releasing the tunnel traveling mode if it is determined that the tunnel is to be advanced.

In the present invention, it is determined whether or not the vehicle enters the tunnel by comparing the brightness intensity calculated from the at least one image with a threshold range when determining whether or not the vehicle is entering the tunnel.

In the present invention, the threshold range is set by a difference between an average value of the brightness intensity obtained before entering the tunnel and a preset reference error value, and when the brightness intensity is out of the threshold range, it is determined that the vehicle advances the tunnel .

In the present invention, the at least one camera includes first and second cameras, and the at least one image includes first and second images, and the step of determining whether or not the vehicle enters the tunnel includes: And generating a parallax map based on the second image; And a step of judging the entry of the vehicle into a tunnel based on the parallax map.

In the present invention, the tunnel running mode includes at least one of a sunroof control, an air conditioner control, a headlight lighting control, a tail lamp lighting control, and a vehicle window shutoff control.

According to another aspect of the present invention, there is provided a method of driving a vehicle, comprising: capturing a front side of a vehicle by a first camera and a second camera to generate first and second images, respectively; And recognizing a shape of the tunnel based on the first and second images to determine entry of the tunnel into the vehicle.

In the present invention, the step of recognizing the shape of the tunnel and judging the entrance of the tunnel of the vehicle may include: generating a parallax map based on the first and second images; And determining a tunnel entry of the vehicle based on the parallax map.

In the present invention, the parallax map includes a plurality of pixels, a distance between each forward point projected on the first and second images and the vehicle is mapped to the plurality of pixels, And the distance is calculated based on the parallax of the first and second images.

According to another aspect of the present invention, there is provided a method of controlling a vehicle, comprising: capturing a front side of a vehicle by a first camera and a second camera to generate first and second images, respectively; And recognizing the shape of the tunnel based on the first and second images to determine the entry of the tunnel into the vehicle.

In the present invention, the step of recognizing the shape of the tunnel and judging the advancement of the tunnel of the vehicle may include: generating a parallax map based on the first and second images; And a step of judging the entry of the vehicle into a tunnel based on the parallax map.

In the present invention, the parallax map includes a plurality of pixels, a distance between each forward point projected on the first and second images and the vehicle is mapped to the plurality of pixels, And the distance is calculated based on the parallax of the first and second images.

According to another aspect of the present invention, there is provided an image processing apparatus comprising: an image unit including a first camera and a second camera for photographing the front of a vehicle and generating first and second images, respectively; A parallax map generation unit for generating a parallax map based on the first and second images provided from the image unit; And a controller for determining entrance of a tunnel of the vehicle based on the parallax map provided by the parallax map generator.

In the present invention, when it is determined that the vehicle enters the tunnel, the control unit executes the tunnel running mode.

The present invention further includes a brightness intensity calculating unit for calculating a brightness intensity based on at least one of the first and second images, wherein the controller compares the brightness intensity with a threshold range during execution of the tunnel running mode, And the tunnel driving mode is canceled when it is determined that the tunnel is advanced.

A vehicle control apparatus and a control method according to the present invention automatically recognize a vehicle entering a tunnel through an image obtained through a camera mounted on the vehicle when the vehicle is approaching a tunnel and perform vehicle control suitable for the driving environment in the tunnel By automatically executing, it is possible to provide convenience to the driver of the vehicle and allow the driver to concentrate only on driving the vehicle, thereby realizing a high-value image of the vehicle.

FIG. 1 is a block diagram showing the configuration of a vehicle control apparatus by tunnel recognition according to an embodiment of the present invention.
2 is a flowchart for explaining a vehicle control method by tunnel recognition according to the present embodiment.
3 is a conceptual diagram for explaining calculation of the distance from the vehicle to a forward object using an image photographed by two cameras in this embodiment.
Fig. 4 shows a three-dimensional positional relationship between an image photographed by a camera and an object in front of the vehicle in this embodiment.
Fig. 5 shows an example in which the distance to a corresponding forward object is mapped to one pixel in an image photographed by the camera in this embodiment.
Fig. 6 shows a parallax map generated by mapping the distance to the corresponding forward object to each pixel in the image photographed by the camera in this embodiment.
7 shows the distribution of the differential values in the vertical direction with respect to the area A in the parallax map of Fig.
FIG. 8 shows an outline image generated by using differential values obtained by differentiating the distance mapped to each pixel in the parallax map of FIG. 6 in the vertical direction.
Fig. 9 shows a change in brightness intensity according to the vehicle traveling position at the time of entering the vehicle.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily carry out the present invention. The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. In order to clearly illustrate the present invention, parts not related to the description are omitted, and similar parts are denoted by like reference characters throughout the specification.

Throughout the specification, when an element is referred to as "comprising ", it means that it can include other elements as well, without excluding other elements unless specifically stated otherwise.

FIG. 1 is a block diagram showing a configuration of a vehicle control apparatus by tunnel recognition according to an embodiment of the present invention, FIG. 2 is a flowchart for explaining a vehicle control method by tunnel recognition according to the present embodiment, 3 is a conceptual diagram for explaining calculation of the distance from the vehicle to a forward object using an image photographed by two cameras in this embodiment. 4 to 9 are reference views for explaining tunnel recognition and vehicle control according to the present embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, the present invention will be described with reference to FIGS.

As shown in FIG. 1, the vehicle control apparatus based on the tunnel recognition according to the present embodiment includes first and second cameras 111 and 112 for photographing the front of the vehicle and generating the first and second images 10 and 20, respectively. 112); A parallax map generation unit 130 for generating a parallax map 50 based on the first and second images 10 and 20 provided from the video unit 110; A control unit 120 for determining entrance of a tunnel of a vehicle based on the parallax map 50 provided from the parallax map generation unit 130; And a brightness intensity calculator 140 for calculating a brightness intensity based on at least one of the first and second images 10 and 20.

The control unit 120 executes the tunnel running mode when it is determined that the vehicle enters the tunnel. In addition, the controller 120 compares the brightness intensity I during execution of the tunnel running mode with a threshold range to determine whether or not the vehicle has entered the tunnel, and releases the tunnel running mode if it is determined to advance the tunnel. The threshold range is set by a difference between an average value of the brightness intensity I obtained before entering the tunnel and a preset reference error value I, and the control unit 120 determines that the brightness intensity I is out of the threshold range It is judged that the tunnel is advanced.

A time difference map (50) includes a plurality of pixels, and a distance between each vehicle front point and a vehicle projected on the first and second images (10, 20) is mapped to the plurality of pixels, The distance between the points and the vehicle is calculated based on the parallax of the first and second images 10 and 20, and detailed calculation methods will be described later.

The control unit 120 generates a contour line image 55 by using the differential values obtained by differentiating the distance mapped to each pixel in the disparity map 50 through the disparity map generating unit 130 in the first image direction (y direction) The control unit 120 compares the outline image 55 with the reference image related to the tunnel shape previously stored in the memory unit 150 to determine whether the vehicle enters the tunnel. The parallax map generation unit 130 generates the contour line image 55 by reflecting only the differential values exceeding the predetermined threshold value at the time of generating the contour line image 50, and a detailed description thereof will be described later.

The operation and operation of the present embodiment thus configured will be described in detail with reference to Figs. 1 to 9. Fig.

First, the video unit 110 photographs the front of the vehicle through the first camera 111 and the second camera 112 and generates a stereo image, that is, the first and second images 10 and 20 as shown in FIG. 3, Respectively (S201). The first camera 111 and the second camera 112 are respectively installed on the front left and right sides of the vehicle and photograph the front of the vehicle respectively. As shown in FIG. 3, 1 image 10 and a second image 20 are generated. The image capturing for the front of the vehicle through the video unit 110 is continuously performed during the running of the vehicle.

Next, the parallax map generator 130 generates a disparity map 50 as shown in FIG. 6 based on the first and second images 10 and 20 (S202). As shown in FIG. 4, the first and second images 10 and 20 generated by the image unit 110 are divided into a two-dimensional image having a horizontal axis x and a vertical axis y, to be. And z represents the distance from the vehicle, more specifically the image portion 110, to an object in front of the vehicle. 3 is a conceptual diagram for explaining calculation of the distance from the vehicle to the forward object using the images taken by the two cameras. The first and second cameras 111 The first and second images 10 and 20 as shown in FIG. 3 are generated by the cameras 112 and 112, respectively, and the distance z from the vehicle to the object is calculated by the following equations (1) and Can be calculated.

(Where, f is the camera focal length, b: the first and second camera distance, d _l is the x-axis direction distance from the center of the image of the object entered in the first camera, d _r is input to the second camera Axis distance from the image center of the object, d is the sum of d _l and d _r )

The parallax map generation unit 130 generates a parallax map 50 as shown in FIG. 6 by mapping the distance to the vehicle ahead object obtained through Equations 1 and 2 to the two-dimensional image. The parallax map 50 includes a plurality of pixels. The parallax map generation unit 130 generates a parallax map of a certain object in front of the vehicle projected on the first and second images 10 and 20, as shown in FIG. 5, Maps the distance z ₁ to the corresponding position ₁ in the two-dimensional image, and performs this operation on the entire vehicle front image to generate the parallax map 50 as shown in Fig. Fig. 6 shows a parallax map generated by mapping the distance to the corresponding forward object to each pixel in the image photographed by the camera in this embodiment. In particular, Fig. 6 shows the parallax map when a tunnel appears in front of the vehicle . The distance from the vehicle to the corresponding forward point is mapped to each pixel on the generated parallax map 50. If it is displayed as an image, it can be converted into luminance and RGB values and displayed.

Next, the control unit 120 judges entry of the vehicle into the tunnel based on the time difference map 50 (S203). First, the controller 120 controls the parallax map generator 130 to calculate a distance z mapped to each pixel in the parallax map 50 as a derivative value obtained by differentiating the distance z in the vertical axis direction (y direction) To generate a contour line image 55 (S203a). 7 shows distribution of differential values in the vertical direction (vertical axis direction) with respect to the area A in the parallax map 50 of FIG. 6. As shown in FIG. 7, in the boundary of the tunnel, that is, at the tunnel edge, The variation of the distance to the corresponding point is abruptly generated, so that the differential value (dz / dy) thereof increases sharply. Therefore, the parallax map generation unit 130 extracts only the portion of the pixels in the parallax map 50 whose differential value (dz / dy) exceeds a preset threshold value and projects the extracted portion on the two-dimensional image, An outline image 55 such as a bar can be generated. Of course, depending on the embodiment, it is also possible to generate a contour image by extracting the distribution of differential values in the horizontal direction (horizontal axis direction) or other one direction in the parallax map 50.

Next, the control unit 120 compares the outline image 55 with the reference image related to the tunnel shape stored in advance in the memory unit 150, and determines whether the vehicle enters the tunnel (S203b). Specifically, the controller 120 compares the contour line image 55 with the reference image using known or unknown various shape recognition techniques including a shape recognition technique based on a Haar-like-feature method to identify a tunnel shape can do. When the distance D between the lowest point of the outline in the generated outline image 55 and the lower end of the outline image 55 is less than a predetermined reference value, the control unit 120 enters the tunnel . At this time, if it is determined that the vehicle enters the tunnel as a result of the determination, the process proceeds to the following step, but if it is not determined that the vehicle enters the tunnel, the process returns to step S201.

If it is determined that the vehicle enters the tunnel, the control unit 120 executes the tunnel running mode (S204). Here, the tunnel running mode means a vehicle running mode preset to automatically control the various additional devices 160 installed in the vehicle when the vehicle enters a tunnel. For example, the tunnel running mode automatically blocks the sunroof , The air conditioner control that controls the air conditioner driving automatically, the headlight lighting control that automatically lights the headlights, the tail lamp which lights up the tail lamp automatically, the vehicle window that automatically blocks the window of the open vehicle Shut-off control, and the like. In addition, various traveling modes can be set.

Next, the control unit 120 determines whether or not the vehicle enters the tunnel by comparing the brightness intensity I calculated based on at least one of the first and second images 10 and 20 with the threshold range (S205). Specifically, when the first image 10 is used as an example, the image generally includes RGB information. The RGB (Red, Green, and Blue) information typically has values of 0 to 255, respectively. As the image becomes brighter, it has a value close to 255, and has a value closer to 0 as the image becomes darker. In this embodiment, the average R, G, and B values of the image are extracted, and the values are averaged as shown in Equation (3) to calculate the brightness intensity (I).

As shown in FIG. 9, the brightness intensity I has a relatively high value before entry into the tunnel, and begins to descend when entering the tunnel, and becomes low when it completely enters the tunnel. When it comes out, it goes up again to recover the value before entering the tunnel. The brightness intensity calculating section 140 calculates the brightness intensity I using the first image 10 or the second image 20 and provides the brightness intensity I to the control section 120. The control section 120 controls the brightness The calculated brightness intensity I during running mode is compared with a threshold range to determine whether or not the vehicle is entering the tunnel. In particular, as shown in Equation (4), when the control unit 120 exceeds the threshold intensity set by the difference between the average value of the brightness intensity acquired a plurality of times before entering the tunnel and the preset reference error value I, If the brightness value is multiplied by a negative value, it can be determined that the tunnel is advanced if the brightness value is less than the negative threshold strength. That is, the controller 120 determines that the vehicle enters the tunnel when the brightness intensity I is out of a certain threshold range, for example, at point P in FIG.

In addition, although it has been described in the step S205 that the advance of the tunnel is determined using the brightness intensity I, according to the embodiment, when determining whether or not the vehicle is entering the tunnel, the parallax map generated by the parallax map generator 130 The control unit 120 may determine whether or not the tunnel is advanced. That is, the parallax map generated by the parallax map generator 130 and the corresponding contour image 55 are compared with a reference image related to the tunnel shape stored in advance in the memory unit 150, And its concrete implementation method is the same as the tunnel shape recognition in the above-mentioned tunnel entry method, and thus a detailed description thereof will be omitted.

As a result of the determination in step S205, if it is determined to advance the tunnel, the process proceeds to the next step. However, if it is determined that the tunnel has not yet been advanced, the process returns to step S204.

In the above description, the brightness intensity I is calculated using the R, G, and B information of the image. However, the present invention is not limited thereto. Any method can be employed as long as it can reflect the brightness around the vehicle.

If it is determined in step S205 that the tunnel will advance, the control unit 120 cancels the tunnel running mode (S206).

As described above, the vehicle control apparatus and the control method according to the present invention automatically recognize the entry of a vehicle into a tunnel through a video obtained through a plurality of cameras mounted on the vehicle when the vehicle approaches the tunnel, So as to provide convenience to the driver of the vehicle and enable the driver to focus on driving the vehicle, thereby realizing a high-value image of the vehicle.

While the present invention has been particularly shown and described with reference to exemplary embodiments thereof, it is to be understood that the invention is not limited to the disclosed exemplary embodiments, It belongs to the scope of right.

110:
111: first camera 112: second camera
120: control unit 130: parallax map generating unit
140: brightness intensity calculation unit 150: memory unit
160: In-vehicle additional devices
10: first image 20: second image
50: Time difference map 55: Outline image

Claims (33)

At least one camera photographing the front of the vehicle to generate at least one image;
Recognizing a shape of a tunnel based on the at least one image and determining entrance of a tunnel of the vehicle; And
And executing a tunnel running mode when it is determined that the vehicle enters the tunnel.
The method according to claim 1,
Wherein the at least one camera comprises a first and a second camera, the at least one image comprises a first and a second image,
The step of recognizing the shape of the tunnel and judging the entrance of the tunnel of the vehicle,
Generating a parallax map based on the first and second images; And
And judging entry of a vehicle into a tunnel based on the time difference map.
3. The method of claim 2,
Wherein the parallax map includes a plurality of pixels, a distance between each forward point projected on the first and second images and the vehicle is mapped to the plurality of pixels,
Wherein the distance between the vehicle front points and the vehicle is calculated based on the parallax of the first and second images.
The method of claim 3,
The distance between each of the vehicle front points and the vehicle is calculated based on the camera focal distance, the distance between the first and second cameras, and the distance from the image center of the corresponding forward point input to the first and second cameras, respectively Wherein the vehicle is a tunnel.
The method of claim 3,
Wherein the step of judging entry of a vehicle into a tunnel based on the parallax map comprises:
Generating a contour image using differential values obtained by differentiating a distance mapped to each pixel in the parallax map to a first image direction; And
And comparing the outline image with a reference image related to a previously stored tunnel shape to determine entry of a vehicle into a tunnel.
6. The method of claim 5,
Wherein the contour line image is generated by reflecting only differential values exceeding a preset threshold value at the time of generating the contour line image.
The method according to claim 1,
Determining whether or not the vehicle is in a tunnel based on the at least one image; And
Further comprising the step of releasing the tunnel running mode when it is determined that the tunnel is to be advanced.
8. The method of claim 7,
Upon determining whether or not the vehicle is in the tunnel,
And comparing the brightness intensity calculated from the at least one image with a threshold range to determine whether or not the vehicle has advanced into a tunnel.
9. The method of claim 8,
The threshold range is set by a difference between an average value of the brightness intensity acquired before entering the tunnel and a preset reference error value,
And when the brightness intensity is out of the threshold range, it is determined that the vehicle advances the tunnel.
8. The method of claim 7,
Wherein the at least one camera comprises a first and a second camera, the at least one image comprises a first and a second image,
The step of judging whether or not the vehicle enters the tunnel includes:
Generating a parallax map based on the first and second images; And
And determining that the vehicle is in a tunnel based on the parallax map.
The method according to claim 1,
Wherein the tunnel running mode includes at least one of a sunroof control, an air conditioner control, a headlight lighting control, a tail lamp lighting control, and a vehicle window shutoff control.
The first and second cameras photographing the front of the vehicle to generate first and second images, respectively; And
And recognizing the shape of the tunnel based on the first and second images to determine entry of the tunnel into the vehicle.
13. The method of claim 12,
The step of recognizing the shape of the tunnel and judging the entrance of the tunnel of the vehicle,
Generating a parallax map based on the first and second images; And
And determining a tunnel entrance of the vehicle based on the parallax map.
14. The method of claim 13,
Wherein the parallax map includes a plurality of pixels, a distance between each forward point projected on the first and second images and the vehicle is mapped to the plurality of pixels,
Wherein the distance between each of the vehicle front points and the vehicle is calculated based on the parallax of the first and second images.
15. The method of claim 14,
The distance between each of the vehicle front points and the vehicle is calculated based on the camera focal distance, the distance between the first and second cameras, and the distance from the image center of the corresponding forward point input to the first and second cameras, respectively Wherein the tunnel entry recognition method comprises the steps of:
15. The method of claim 14,
Wherein the step of judging entry of a vehicle into a tunnel based on the parallax map comprises:
Generating a contour image using differential values obtained by differentiating a distance mapped to each pixel in the parallax map to a first image direction; And
And comparing the contour image with a reference image related to a previously stored tunnel shape to judge entrance of a tunnel of a vehicle.
17. The method of claim 16,
Wherein the contour line image is generated by reflecting only differential values exceeding a preset threshold value at the time of generating the contour line image.
The first and second cameras photographing the front of the vehicle to generate first and second images, respectively; And
And recognizing the shape of the tunnel based on the first and second images to judge the entry of the vehicle into the tunnel.
19. The method of claim 18,
The step of recognizing the shape of the tunnel and judging the advancement of the tunnel of the vehicle includes:
Generating a parallax map based on the first and second images; And
And determining a tunnel entry of the vehicle based on the parallax map.
20. The method of claim 19,
Wherein the parallax map includes a plurality of pixels, a distance between each forward point projected on the first and second images and the vehicle is mapped to the plurality of pixels,
Wherein the distance between each of the vehicle front points and the vehicle is calculated based on a parallax of the first and second images.
21. The method of claim 20,
The distance between each of the vehicle front points and the vehicle is calculated based on the camera focal distance, the distance between the first and second cameras, and the distance from the image center of the corresponding forward point input to the first and second cameras, respectively Wherein the tunnel entry recognition method comprises the steps of:
21. The method of claim 20,
Wherein the step of determining the entry of the vehicle into the tunnel based on the parallax map comprises:
Generating a contour image using differential values obtained by differentiating a distance mapped to each pixel in the parallax map to a first image direction; And
And comparing the outline image with a reference image related to a previously stored tunnel shape to determine whether the vehicle is entering the tunnel.
23. The method of claim 22,
Wherein when generating the contour image, the contour image is generated by reflecting only a differential value exceeding a preset threshold value.
1. An image display apparatus comprising: an image unit including a first camera and a second camera for photographing a front side of a vehicle and generating first and second images, respectively;
A parallax map generation unit for generating a parallax map based on the first and second images provided from the image unit; And
And a control unit for determining a tunnel entry of the vehicle based on the parallax map provided by the parallax map generation unit.
25. The method of claim 24,
Wherein the control unit executes a tunnel running mode when it is determined that the vehicle enters the tunnel.
26. The method of claim 25,
And a brightness intensity calculating unit for calculating a brightness intensity based on at least one of the first and second images,
Wherein the controller determines whether or not the vehicle is in a tunnel by comparing the brightness intensity with a threshold range during execution of the tunnel running mode, and releases the tunnel running mode when it is determined to advance the tunnel. The vehicle control apparatus comprising:
27. The method of claim 26,
The threshold range is set by a difference between an average value of the brightness intensity acquired before entering the tunnel and a preset reference error value,
Wherein the control unit determines that the vehicle advances the tunnel if the brightness intensity is out of the threshold range.
26. The method of claim 25,
Wherein the control unit judges whether or not the vehicle enters the tunnel based on the time difference map provided from the time difference map generating unit, and releases the tunnel running mode when it is determined to advance the tunnel. Device.
26. The method of claim 25,
Wherein the tunnel driving mode includes at least one of a sunroof control, an air conditioner control, a headlight lighting control, a tail lamp lighting control, and a vehicle window shutoff control.
25. The method of claim 24,
Wherein the parallax map includes a plurality of pixels, a distance between each vehicle front point projected on the first and second images and the vehicle is mapped to the plurality of pixels,
Wherein the distance between each of the vehicle front points and the vehicle is calculated based on the parallax of the first and second images.
31. The method of claim 30,
The distance between each of the vehicle front points and the vehicle is calculated based on the camera focal distance, the distance between the first and second cameras, and the distance from the image center of the corresponding forward point input to the first and second cameras, respectively Wherein the vehicle is a tunnel.
32. The method of claim 31,
Wherein the parallax map generator generates an outline image using differential values obtained by differentiating a distance mapped to each pixel in the parallax map to a first image direction,
Wherein the control unit compares the contour image with a reference image related to a tunnel shape previously stored in the memory unit to determine entry of the vehicle into the tunnel when the tunnel entrance of the vehicle is determined.
33. The method of claim 32,
Wherein the parallax map generator generates the contour image by reflecting only differential values exceeding a predetermined threshold value at the time of generating the contour line image.

Images