KR102647407B1 - Device and method for preventing car accident caused by obstacle - Google Patents

Abstract

A method for preventing vehicle accidents is disclosed. This method includes adjusting the camera angle of the camera using the result of comparing a first input image input from a camera installed in the vehicle and a first high-precision map image input from a navigation system; Compare the second input image input from the camera with the adjusted camera angle and the second high-precision map image input from the navigation, detect pixels with different pixel values from the input image, and detect the detected pixels as obstacles. steps; and displaying the detected obstacle on a head-up display.

Description

Vehicle accident prevention system and method {DEVICE AND METHOD FOR PREVENTING CAR ACCIDENT CAUSED BY OBSTACLE}

The present invention relates to a vehicle accident prevention system and method, and particularly to a vehicle accident prevention system and method due to road obstacles.

Recently released vehicles are equipped with various obstacle detection systems to prevent accidents caused by road obstacles. Among the conventional obstacle detection systems, there is an obstacle detection system using radar.

This conventional obstacle detection system detects road obstacles or falling objects using radar, and allows drivers to check the detection results through navigation, thereby enabling safe driving to avoid road obstacles. However, because conventional obstacle detection systems use expensive radar equipment, their design costs are high.

The problem to be solved by the present invention is to provide an obstacle accident prevention system and method that can prevent accidents caused by obstacles without using expensive radar equipment.

The problems to be solved by the present invention are not limited to those mentioned above, and other problems not mentioned can be clearly understood by those skilled in the art from the description below.

A vehicle accident prevention method according to one aspect of the present invention includes the steps of adjusting the camera angle of the camera using the result of comparing a first input image input from a camera installed in the vehicle and a first high-precision map image input from a navigation system; , Compare the second input image input from the camera with the camera angle adjusted and the second high-precision map image input from the navigation, detect pixels with different pixel values from the input image, and treat the detected pixels as obstacles. It includes detecting and displaying the detected obstacle on a head-up display.

A vehicle accident prevention system according to another aspect of the present invention includes a camera that adjusts the camera angle of the camera using the result of comparing the first input image input from the camera installed in the vehicle and the first high-precision map image input from the navigation. An adjustment unit compares a second input image input from the camera with the camera angle adjusted and a second high-precision map image input from the navigation, detects pixels with different pixel values from the input image, and detects the detected pixels. An image processing unit that detects obstacles; and a head-up display that displays the detected obstacle.

According to the present invention, without using expensive radar equipment, road obstacles are detected using the result of comparing the input image input from the camera mounted on the vehicle and the high-precision map image input from the navigation, and By providing warnings through the Head-Up-Display, it is possible to drive to avoid road obstacles. Additionally, the rear vehicle receives information about road obstacles detected by the front vehicle, enabling avoidance driving against road obstacles detected by the front vehicle through the received information.

The effects of the present invention are not limited to those mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description below.

1 is a functional block diagram of a vehicle accident prevention system according to an embodiment of the present invention.
FIG. 2 is a functional block diagram of the camera control unit shown in FIG. 1.
FIG. 3 is a diagram schematically showing an example of an area set in the area setting unit shown in FIG. 2.
FIG. 4 is a functional block diagram of the image processing unit shown in FIG. 2.
FIG. 5 is a diagram schematically showing an example of an area set in the area setting unit shown in FIG. 4.
6 to 9 are flowcharts of a vehicle accident prevention method according to an embodiment of the present invention.

It should be noted that the technical terms used in this specification are only used to describe specific embodiments and are not intended to limit the present invention. In addition, the technical terms used in this specification, unless specifically defined in a different way in this specification, should be interpreted as meanings commonly understood by those skilled in the art in the technical field to which the present invention pertains, and are not overly comprehensive. It should not be interpreted in a literal or excessively reduced sense. Additionally, if the technical terms used in this specification are incorrect technical terms that do not accurately express the spirit of the present invention, they should be replaced with technical terms that can be correctly understood by those skilled in the art. In addition, general terms used in the present invention should be interpreted according to the definition in the dictionary or the context, and should not be interpreted in an excessively reduced sense. Additionally, as used herein, singular expressions include plural expressions, unless the context clearly dictates otherwise. In this application, terms such as “consists of” or “comprises” should not be construed as necessarily including all of the various components or steps described in the specification, and some of the components or steps may include It may not be included, or it should be interpreted as including additional components or steps.

The present invention relates to a system and method that identifies obstacles and provides warnings about them to vehicle drivers, thereby helping drivers identify and avoid obstacles in advance.

Hereinafter, an embodiment of the present invention will be described in detail with reference to the attached drawings.

1 is a functional block diagram of a falling object accident prevention system according to an embodiment of the present invention.

Referring to Figure 1, the vehicle accident prevention system according to an embodiment of the present invention includes a sensor unit 110, a storage unit 120, a camera control unit 130, a camera driver 140, an image processing unit 150, and a display unit. (160) and a communication unit (170).

sensor part (110)

The sensor unit 110 includes a camera sensor 112 that captures an image of an obstacle on the road ahead (hereinafter referred to as an input image) by photographing the front of the vehicle, and a distance sensor that measures the distance from the vehicle to the obstacle. Includes (114).

The camera sensor 112 may be installed on the front of the vehicle to photograph the front of the vehicle. The camera sensor 112 includes a general camera and a special camera suitable for night photography. A general camera may be, for example, a CCD camera or a CMOS camera. The special camera may be, for example, an infrared camera. The input image may be obtained from a general camera during the day and from the special camera at night, depending on the driver's selection.

The distance sensor 114 may be, for example, a low-cost ultrasonic sensor.

Storage unit (120)

The storage unit 120 stores the input image captured by the camera sensor and the distance value measured by the distance sensor. The input image may be stored in the storage unit 120 in units of frames. The storage unit 120 may be a non-volatile memory.

Camera control unit (130)

The camera control unit 130 outputs an initial input image (hereinafter referred to as first input image) input from the camera sensor 112 and an initial high-precision map image (hereinafter referred to as first high-precision map image) input from the navigation unit 10. The camera angle of the camera sensor 112 is adjusted using the compared result.

Since the first input image is an image used to adjust the camera angle, it does not need to be an image in which the obstacle exists. Of course, it is okay if the video contains obstacles. The high-precision map image is a three-dimensional graphic image depicting the surrounding environment (buildings, roads, guardrails, etc.) at the current location of the vehicle, is produced in advance, and is stored in the navigation unit 10.

In order to adjust the camera angle of the camera sensor 112, the camera adjustment unit 130 includes an image conversion unit 131, an area setting unit 133, an edge detection unit 135, as shown in FIG. 2. It includes a difference value calculation unit 137 and an angle calculation unit 139.

The image conversion unit 131 converts the first input image and the first high-precision map image into gray scale, respectively. Hereinafter, the first input image converted to gray scale will be referred to as the 1-1 gray scale image (G _1-1 ), and the first high-precision map image converted to gray scale will be referred to as the 1-2 gray scale image (G _1-2 ). ).

When the conversion to gray scale for the first input image and the first high-precision map image is completed, the image conversion unit 131 upscales the 1-1 grayscale image (G _1-1 ), The resolution of the 1-1st grayscale image ( _G1-1 ) is converted to the resolution of the 1-2nd grayscale image ( _G1-2 ).

The area setting unit 133 sets a first area (R 1-1 ) within the resolution-converted 1-1 gray-scale image (G _1-1 ), and sets the first area (R _1-1 ) within the 1-2 gray-scale image (G 1-1 ) of which the resolution has been converted. _1-2 ), a second area (R _1-2 ) compared to the first area (R _1-1 ) is set.

Specifically, as shown in FIG. 3, the area setting unit 133 divides the entire area of the first grayscale image A into thirds in the X-axis direction, and selects the bottom area among the three divided areas. Set as the first area (R _1-1 ), the entire area of the second grayscale image is divided into three in the X-axis direction, and the lowest area among the three divided areas is divided into the second area (R _1-2) . ).

When comparing the entire area of the resolution-converted 1-1st grayscale image ( _G1-1 ) with the entire area of the 1-2nd grayscale image ( _G1-2 ), processing time and system load increase. , in order to reduce this, the set first area (R _1-1 ) and the second area (R _1-2 ) are defined as areas in which they are compared.

The resolution of the first area (R _1-1 ) and the second area (R _1-2 ) can be expressed as the number of horizontal pixels × (the number of vertical pixels × 0.3). That is, the first area (R _1-1 ) and the second area (R _1-2 ) are areas corresponding to 30% of the total area of each image (G _1-1 , G _1-2 ), and each The areas R _1-1 and R _{1- 2} provide a sufficient number of pixel data for comparative analysis of the first gray level image G _1-1 and the second gray level image G _1-2 .

Meanwhile, the reason for setting the bottom area of each image (G _1-1 , G _1-2 ) as the comparison area is that within each image (G _1-1 , G _1-2 ), objects such as parking lines and road curbs are included. This is because the outline appears more clearly in the lower area than in the upper area.

When the areas (R _1-1 , R _1-2 ) are set, the edge detection unit 135 detects the first object (building, road sign, parking line, and road) within the first area (R _1-1 ). An edge (E ₁ ) of a curb, etc.) is detected, and an edge (E ₂ ) of a second object corresponding to the first object is detected within the second area (R _1-2 ). Methods for detecting the edge of an object include an edge detection technique using the brightness change rate (first derivative), a Sobel edge detection technique, a prewitt edge detection technique, a Roberts edge detection technique, and a compass. ) Examples include various algorithms such as edge detection technique, edge detection technique using second order differentiation and Laplacian, canny edge detection technique, and line edge detection technique.

When the detection of the edges (E ₁ and E ₂ ) is completed, the difference calculation unit 137 calculates the grayscale value of the pixel constituting the edge (E ₁ ) of the first object and the edge (E 2 ) of the second object. A first difference value between grayscale values of pixels constituting E ₂ ) is calculated, and a second difference value between the first difference value and a reference value is calculated. Here, when the entire gray scale is divided into intervals of 256 gray levels, the reference value may be a gray level difference corresponding to 10% of the total 256 gray levels (approximately 26 gray levels = 256 × 0.1).

The angle calculation unit 139 calculates a camera angle corresponding to the second difference value. For example, the camera angle may be calculated by referring to a table in which pre-learned camera angles are stored according to the second difference value calculated by the difference value calculation unit 137. Here, the camera angle includes an angle in the pitch direction, an angle in the yaw direction, and an angle in the roll direction.

Camera driving unit (140)

The camera driving unit 140 is configured to generate a driving force corresponding to the camera angle calculated by the angle calculating unit 139, and the driving force includes a first driving force corresponding to the angle in the pitch direction, the yaw It includes a second driving force corresponding to an angle in the (yaw) direction and a third driving force corresponding to the angle in the roll direction. The driving force may be, for example, a motor driving force. Accordingly, the camera driving unit 140 may be implemented with an electric motor or the like to physically adjust the camera angle of the camera sensor 112 rotatably installed in the vehicle.

Image processing unit (150)

When the adjustment of the camera angle is completed by the camera adjuster 130 and the camera driver 140, the image processor 150 processes the input image (hereinafter referred to as 2 input image) and a high-precision map image input from the navigation unit 10 (hereinafter referred to as a second high-precision map image) to detect obstacles.

Specifically, in order to detect the obstacle, the image processing unit 150 includes an image conversion unit 151, a background area removal unit 152, an area setting unit 155, and an area comparison unit, as shown in FIG. 4. It includes a unit 154, a comparison time calculation unit 155, and a data generation unit 156.

The image conversion unit 151 converts the second input image input from the camera sensor 112 with the camera angle adjusted and the second high-precision map image input from the navigation unit 10 into a 2-1 grayscale image ( Converted to G _2-1 ) and 2-2nd grayscale image (G _2-2 ), respectively.

The background area removal unit 153 removes the background area of the 2-1st grayscale image ( _G2-1 ) and the 2-2nd grayscale image ( _G2-2 ) based on an algorithm for separating the object and the background. Remove background area.

The area setting unit 153 sets a 2-1 area (R _2-1 ) within the 2-1 grayscale image (G' _2-1 ) from which the background area has been removed. A 2-2 region (R _2-2 ) is set within the 2-2 gray scale image (G' _{2 -2} ). As shown in FIG. 5, the 2-1 area (R _2-1 ) and the 2-2 area (R _2-2 ) divide the entire area of each image into an upper area and a lower area, It is the upper area, and the upper area may be, for example, an area that occupies 70% of the entire area. Objects that are close to the vehicle are viewed at the bottom of the video screen, and objects that are relatively far away from the vehicle are viewed at the top of the video screen. Therefore, when an obstacle is detected by comparing the lower area of the 2-1st grayscale image (G' _{2 - 1} ) with the lower area of the 2-2 grayscale image (G' _{2 - 2} ), the detected obstacle Because it exists at a short distance from the vehicle, there is not enough time to avoid obstacles. Therefore, it is desirable to detect an obstacle by comparing the upper area of the 2-1st grayscale image (G' _{2 - 1} ) with the upper area of the 2-2 grayscale image (G' _{2 - 2} ).

The area comparison unit 154 calculates the pixel values (gradation values) of the 2-1st area (R _2-1 ) and the pixel values (grayscale values) of the 2-2 area (R _2-2 ) for each corresponding position coordinate. By comparing the gray level values, pixels with different pixel values (or gray level values) are detected from the 2-1 area (R _2-1 ), and the detected pixels are detected as pixels representing obstacles.

The comparison time calculation unit 155 calculates the image comparison time performed by the area comparison unit 154 according to the current speed of the vehicle. The calculated comparison time is provided to the area setting unit 153, so that the area comparing unit 154 compares the 2-1 area (R 2-1 ) and the 2-2 area (R _2-1 ) within the calculated comparison time. The areas of each of the 2-1 region (R _2-1 ) and the 2-2 region (R _2-2 ) are reset to compare R _2-2 ).

In a situation where the current speed of the vehicle is very high, obstacles must be detected quickly, so in this case, the areas of each of the 2-1 area (R _2-1 ) and the 2-2 area (R _2-2 ) are reduced. It is necessary to accelerate the obstacle detection time by reducing the comparison time. The reduction in area may be appropriately selected, for example, 10% of the total area of each region (R _2-1 , R _2-2 ). At this time, since the obstacle moves from the top to the bottom within the screen over time, if you decrease from the top of each area (R _2-1 , R _2-2 ), there are cases where the obstacle cannot be detected quickly. It can happen. Therefore, it is desirable to reduce the area in the direction from the bottom to the top (D1, shown in FIG. 5) within the screen.

The comparison time may be calculated using the vehicle's current speed and the safety distance of the vehicle's current driving road included in GPS information. This can be expressed as a formula as shown in Equation 1 below.

The current speed of the vehicle may be obtained from a vehicle speed sensor (not shown), and the safety distance may be included in GPS information provided from the navigation unit 10.

The data generator 156 generates image data including coordinate data of pixels detected by the area comparison unit 154 and distance data to an obstacle measured by the distance sensor 114.

Display unit (160)

Referring again to FIG. 2, the display unit 160 displays obstacles detected by the image processing unit 150 and warns the driver that an obstacle exists ahead. The display unit 160 includes, for example, a cover glass, a mirror, an LED, a TFT projection display, a windshield, etc. It may be a display device.

When the display unit 160 is a head-up-display device, obstacles detected by the image processing unit 150 may be displayed on a transparent display screen installed on the windshield of the vehicle.

The obstacle may be highlighted with a specific color to stand out on the transparent display screen. Additionally, the obstacle may be highlighted on the transparent display screen by a circular or square-shaped guide line surrounding the obstacle, and the presence of the obstacle may be further highlighted by highlighting the guide line. The distance from the vehicle to the obstacle measured by the distance sensor 114 may be displayed around the obstacle or the guide line. Additionally, the obstacle may be displayed on a sub-screen of the transparent display screen.

Communications Department (170)

The communication unit 170 may be configured to wirelessly transmit image data about obstacles detected by the image processing unit 150 to surrounding vehicles, and conversely, wirelessly receive image data about obstacles detected by the surrounding vehicles. there is. Accordingly, the communication unit 170 may include a transmitter and a receiver.

Specifically, the communication unit 170 encodes image data about the obstacle detected by the image processing unit 150 into wireless communication data, and transmits the encoded wireless communication data to the surrounding vehicle through an antenna (not shown). Send. Examples of wireless communication methods include DLNA or WI-DI communication methods.

Conversely, the communication unit 170 receives wireless communication data about the obstacle from the surrounding vehicle, decodes the received wireless communication data into the image data, and heads up the obstacle corresponding to the decoded image data. It can be displayed on the display.

Meanwhile, when the communication unit 170 receives the wireless communication data from the surrounding vehicle, that is, when it receives a warning message indicating the presence of an obstacle ahead from the surrounding vehicle, the comparison time calculation unit 155 assigns a weight (W) to the currently calculated comparison time in response to the warning message, thereby reducing the currently calculated comparison time by the weight (W) to enable faster recognition of the obstacle. For example, the comparison time calculated in Equation 1 above is reduced by about 10%, allowing information about obstacles to be confirmed in advance. In this case, the weight (W) may be 0.1 (10%). If this is expressed as a formula, it is as equation 2 below.

Figures 6 to 9 are flowcharts of a vehicle accident prevention method according to an embodiment of the present invention. In explaining each step, content that overlaps with the content described with reference to Figures 1 to 5 will be briefly described or omitted. do.

First, referring to FIG. 6, first, in step S610, the first input image input from the camera 112 installed in the vehicle is compared with the first high-precision map image input from the navigation, and the comparison result is used to The process of adjusting the camera angle of 112 is performed. A detailed description of step S610 is provided with reference to FIGS. 7 and 8. First, referring to FIG. 7, first, in step S612, the first input image is converted into a 1-1 grayscale image (G _1-1 ), and the first high-precision map image is converted into a 1-2 grayscale image (G 1-1 ). Convert to G _1-2 ). Next, in step S614, the resolution of the 1-1st grayscale image ( _G1-1 ) is converted to the resolution of the 1-2nd grayscale image ( _G1-2 ). Then, in step S616, the 1-2nd grayscale image ( _G1-1 ) and the 1-1st grayscale image ( _G1-1 ) converted to the resolution of the 1-2nd grayscale image ( _G1-2 ) ) is used to adjust the camera angle of the camera 112. Referring to FIG. 8, if step S616 is described in detail, first, in step S616A, the 1-1 grayscale image (G _1- ) converted to the resolution of the 1-2 grayscale image (G _1-2 ) ₁ ), a first area (R _1-1 ) is set within the 1-2 grayscale image (G _1-2 ), and a second area (R) is compared with the first area (R _1-1 ) within the 1-2 grayscale image (G 1-2). _1-2 ). Then, in step S616B, an edge (E ₁ ) of the first object is detected within the first region (R _1-1 ), and an edge (E 1 ) corresponding to the first object is detected within the second region (R _1-2 ). The edge (E ₂ ) of the second object is detected. Then, in step S616C, a first difference value between the pixel value (gradation value) constituting the edge (E ₁ ) of the first object and the pixel value (gradation value) constituting the edge (E ₂ ) of the second object. After calculating, a second difference value between the first difference value and a preset value is calculated. Then, in step S616D, the camera angle of the camera is adjusted with an adjustment value corresponding to the second difference value. Here, the adjusted camera angle includes an angle in the pitch direction, an angle in the roll direction, and an angle in the yaw direction. Meanwhile, in FIG. 8, step S616A may be omitted depending on system performance. In this case, the camera angle is adjusted using the result of comparing the entire area of the 1-1st grayscale image converted to the resolution of the 1-2nd grayscale image with the entire area of the 1-2nd grayscale image.

Referring again to FIG. 6, in step S620, the second input image input from the camera with the camera angle adjusted is compared with the second high-precision map image input from the navigation, and pixels with different pixel values (gradation values) are compared. After detecting pixels from the input image, a process of detecting the detected pixels as obstacles is performed.

A detailed description of step S620 will be described with reference to FIG. 9. Referring to FIG. 9, first, in step S621, the second input image is converted into a 2-1 grayscale image ( _G2-1 ), and the second high-precision map image is converted into a 2-2 grayscale image ( _G2-1) . Convert to _-2 ). Next, in step S623, the background area of the 2-1st grayscale image ( _G2-1 ) and the background area of the 2-2nd grayscale image ( _G2-2 ) are removed. Next, in step S625, the 2-1 region (R _2-1 ) existing at the upper part of the 2-1 grayscale image (G' _{2 -1} ) from which the background region has been removed is set, and the background region is The 2-2 region (R _2-2 ) existing at the upper part of the removed 2-2 grayscale image (G' _{2 -2} ) image is set. Then, in step S627, the pixel values (grayscale values) of the 2-1 region (R _2-1 ) and the pixel values (grayscale values) of the 2-2 region (R _2-2 ) are By comparison, pixels with different pixel values (gradation values) are detected from the 2-1 area (R _2-1 ), and the detected pixels are detected as the obstacles. Here, step S627 may be performed during a comparison time calculated based on the current speed of the vehicle and the safety distance set at the current location of the vehicle. This comparison time can be calculated from Equation 2 described above.

Referring again to FIG. 6, in step S630, a process of displaying the detected obstacle on the head-up display is performed. Specifically, the obstacle may be highlighted with a specific color to stand out on the transparent display screen of the head-up display. Additionally, the obstacle may be highlighted on the transparent display screen by a circular or square-shaped guide line surrounding the obstacle, and the presence of the obstacle may be further highlighted by highlighting the guide line. Additionally, the distance from the vehicle to the obstacle measured by the distance sensor 114 may be displayed around the obstacle or the guide line. Additionally, the obstacle may be displayed on a sub-screen of the transparent display screen.

Next, in step S640, a process of transmitting data about the detected obstacle to a surrounding vehicle or receiving the data from the surrounding vehicle is performed. Here, as a method of transmitting or receiving the data to or from the surrounding vehicles, DLNA or WI-DI communication method may be used.

As described above, the present invention does not use expensive radar equipment, but uses the result of comparing the input image input from the camera mounted on the vehicle and the high-precision map image input from the navigation to detect road obstacles (or road obstacles from surrounding vehicles). It detects fallen objects) and provides warnings about detected road obstacles through a head-up display, enabling avoidance driving against road obstacles. Additionally, surrounding vehicles receive information about road obstacles detected by the vehicle ahead, enabling avoidance driving regarding road obstacles detected by the vehicle ahead through the received information.

Meanwhile, the block diagrams of FIGS. 1, 2, and 4 showing a vehicle accident prevention system for detecting road obstacles should be understood as embodying the principles of the invention from a functional perspective. Similarly, the flow diagrams of FIGS. 6-9 may be substantially represented on a computer-readable medium and should be understood as representing various processes performed by a computer or processor whether or not the computer or processor is explicitly shown.

The blocks of Figures 1, 2, and 4, which are represented by processors or similar concepts, can be provided using dedicated hardware as well as hardware capable of executing software.

When the blocks of Figures 1, 2, and 4 are implemented by a processor, the functionality of the blocks shown in Figures 1, 2, and 4 may be provided by a single dedicated processor, a single shared processor, or multiple individual processors, any of which Some may be shared.

In addition, the clear use of terms such as processor, control, or similar concepts should not be construed as exclusively referring to hardware capable of executing software, and should not be interpreted as referring exclusively to hardware capable of executing software, including without limitation digital signal processor (DSP) hardware and ROM for storing software. It should be understood as implicitly including ROM, RAM, and non-volatile memory. Of course, other hardware for general use may also be included.

The above description is merely an illustrative explanation of the technical idea of the present invention, and various modifications, changes, and substitutions can be made by those skilled in the art without departing from the essential characteristics of the present invention. will be. Accordingly, the embodiments disclosed in the present invention and the attached drawings are not intended to limit the technical idea of the present invention, but are for illustrative purposes, and the scope of the technical idea of the present invention is not limited by these embodiments and the attached drawings. . The scope of protection of the present invention should be interpreted in accordance with the claims below, and all technical ideas within the equivalent scope should be construed as being included in the scope of rights of the present invention.

Claims (15)

adjusting the camera angle of the camera using a result of comparing a first input image input from a camera installed in the vehicle and a first high-precision map image input from a navigation system;
Compare the second input image input from the camera with the camera angle adjusted and the second high-precision map image input from the navigation, detect pixels with different pixel values from the input image, and detect the detected pixels as obstacles. steps; and
displaying the detected obstacle on a head-up display;
Vehicle accident prevention method including.
In claim 1, the adjusting step includes:
Converting the first input image into a 1-1 grayscale image and converting the first high-precision map image into a 1-2 grayscale image;
converting the resolution of the 1-1 grayscale image to the resolution of the 1-2 grayscale image; and
and adjusting the camera angle of the camera using a result of comparing the 1-2nd grayscale image with the 1-1st grayscale image converted to the resolution of the 1-2nd grayscale image. How to prevent car accidents.
In claim 2, the step of adjusting the camera angle includes:
Detecting the edge of the first object in the 1-1 gray-scale image converted to the resolution of the 1-2 gray-scale image, and detecting the edge of the second object corresponding to the first object in the 1-2 gray-scale image detecting an edge;
calculating a first difference value between pixel values constituting an edge of the first object and pixel values constituting an edge of the second object;
calculating a second difference between the first difference and a preset value; and
adjusting the camera angle of the camera with an adjustment value corresponding to the second difference value.
A vehicle accident prevention method comprising:
In claim 2, the step of adjusting the camera angle includes:
Setting a first area in the 1-1 gray-scale image converted to the resolution of the 1-2 gray-scale image, and setting a second area compared to the first area in the 1-2 gray-scale image step;
Detecting an edge of a first object within the first area and detecting an edge of a second object corresponding to the first object within the second area;
calculating a first difference value between pixel values constituting an edge of the first object and pixel values constituting an edge of the second object;
calculating a second difference between the first difference and a preset value; and
adjusting a camera angle of the camera with an adjustment value corresponding to the second difference value;
A vehicle accident prevention method comprising:
In claim 4, the first area is the lowest area among areas divided by dividing the entire area of the 1-1 grayscale image into thirds in the X-axis direction,
The second area is a vehicle accident prevention method, wherein the entire area of the 1-2 grayscale image is divided into three areas in the x-axis direction.
In claim 1, the detecting step includes:
converting the second input image into a 2-1 grayscale image and converting the second high-precision map image into a 2-2 grayscale image;
removing a background area of the 2-1st grayscale image and a background area of the 2-2nd grayscale image;
Set a 2-1 area existing at the upper part of the 2-1 grayscale image from which the background area has been removed, and set a 2-2 area existing at the upper part of the 2-2 grayscale image from which the background area has been removed. Setting up; and
Comparing the pixel values of the 2-1 area with the pixel values of the 2-2 area, detecting pixels with different pixel values from the 2-1 area, and detecting the detected pixels as the obstacle step
A vehicle accident prevention method comprising:
In claim 6, the step of detecting the detected pixels as the obstacle comprises:
A vehicle accident prevention method, characterized in that it is performed for a comparison time calculated based on the current speed of the vehicle and a safety distance set at the current location of the vehicle.
In clause 7, the comparison time is calculated by the formula below,
The above formula is,

A vehicle accident prevention method characterized by:
In claim 1, after detecting the detected pixels as obstacles,
Encoding image data corresponding to the detected obstacle into wireless communication data; and
Further comprising: transmitting the encoded wireless communication data to surrounding vehicles,
The surrounding vehicle decodes the wireless communication data into the image data, and displays an obstacle corresponding to the decoded image data on a head-up display installed in the rear vehicle.
a camera adjustment unit that adjusts the camera angle of the camera using a result of comparing a first input image input from a camera installed in the vehicle and a first high-precision map image input from a navigation system;
Compare the second input image input from the camera with the adjusted camera angle and the second high-precision map image input from the navigation, detect pixels with different pixel values from the input image, and detect the detected pixels as obstacles. an image processing unit that does; and
Head-up display that displays the detected obstacles
A vehicle accident prevention system that includes.
In claim 10, the camera control unit,
The first input image and the first high-precision map image are converted into a 1-1 gray-scale image and a 1-2 gray-scale image, respectively, and the resolution of the 1-1 gray-scale image is changed to the resolution of the 1-2 gray-scale image. A video conversion unit that converts to;
Setting a first area in the 1-1 gray-scale image converted to the resolution of the 1-2 gray-scale image, and setting a second area compared to the first area in the 1-2 gray-scale image Area setting unit;
an edge detection unit detecting an edge of a first object within the first area and detecting an edge of a second object corresponding to the first object within the second area;
Calculating a first difference value between a pixel value constituting an edge of the first object and a pixel value constituting an edge of the second object, and then calculating a second difference value between the first difference value and a preset value. Difference value calculation unit; and
An angle calculation unit that calculates the camera angle of the camera with an adjustment value corresponding to the second difference value.
A vehicle accident prevention system comprising:

In claim 11, the first area is the lowermost area among areas divided by dividing the entire area of the 1-1 grayscale image into thirds in the X-axis direction, and the second area is the entire area of the 1-2 grayscale image. A vehicle accident prevention system characterized in that the area is at the bottom of the three areas divided in the x-axis direction.
In claim 10, the image processing unit,
an image converter converting the second input image into a 2-1 grayscale image and converting the second high-precision map image into a 2-2 grayscale image;
a background area removal unit that removes a background area of the 2-1st grayscale image and a background area of the 2-2nd grayscale image;
an area setting unit that sets a 2-1 area existing in the upper part of the 2-1 gray scale image and sets a 2-2 area existing in the upper part of the 2-2 gray scale image; and
Comparing the pixel values of the 2-1 area with the pixel values of the 2-2 area, detecting pixels with different pixel values from the 2-1 area, and detecting the detected pixels as the obstacle Area comparison unit
A vehicle accident prevention system comprising:
In claim 13, further comprising a comparison time calculation unit that calculates a comparison time calculated based on the current speed of the vehicle and a safety distance set at the current location of the vehicle,
The area setting unit,
A vehicle accident prevention system, characterized in that the 2-1 area and the 2-2 area are reset according to the comparison time.
In claim 14, the comparison time is calculated by the formula below,
The above formula is,

A vehicle accident prevention system characterized by:

Images