KR102633257B1 - A Distance Measuring Method Using Images And Vehicle Controlling Method Thereof - Google Patents

Abstract

The present invention consists of a control unit 110, a photographing unit 120 connected to the control unit 110, a display unit 140 connected to the control unit 110, and a storage unit 130 connected to the control unit 110. The operation program for executing the present invention is stored in the storage unit 130 and is executed in the measurement system 100; A first photographing step (ST-110) in which a mark is photographed multiple times by the photographing unit 120 at different distances and the photographed images are stored in the storage unit 130, and the first photographing step (ST-110) A DB storage step (ST-120) in which a pixel information-distance DB is created from the pixel information and shooting distance of the image captured and stored in the storage unit 130 and stored in the storage unit 130, and the capturing unit 120 A second photographing step (ST-130) in which a mark attached to the target object is photographed, and pixel information of the mark image of the target object photographed in the second photographing step (ST-130) and stored in the storage unit 130. A distance measurement method using an image consisting of a calculation step (ST-140) in which the distance from the pixel information-distance DB to the target object is calculated, and a display step (ST-150) in which the calculated distance to the target object is displayed on the display. and a vehicle control method using the same.

Description

Distance Measuring Method Using Images And Vehicle Controlling Method Thereof}

The present invention relates to a distance measurement method and a vehicle control method using images. The distance and angle to the target are measured by calculating the captured image, and the measured results are provided to the vehicle control unit (ECU) to enable automatic driving. This relates to a method of controlling a car using a distance measurement method.

The demand for measuring distances to external objects is increasing. In particular, when watching video, there is an increasing demand to watch 3D video, that is, stereoscopic video, in addition to 2D video. To detect the depth of a 3D video, the distance to an external object can be detected. As such, various methods are being attempted as methods for detecting distances to external objects.

However, no method was proposed to measure the rotation angle of the Mokpo object along with the distance to the target object, so there was a problem in that such information could not be used.

Republic of Korea Publication No. 10-2014-0107986 Open Patent Publication

The present invention was proposed to solve the problems of the prior art as described above. The distance to the target object can be quickly measured by simple calculation, and the rotation angle of the target object is also calculated, so that the distance to the target object can be quickly measured by simple calculation. The purpose is to provide a distance measurement method and vehicle control method using images that can calculate rotation and use it as vehicle operation information.

For the above purpose, the present invention consists of a control unit, a photographing unit connected to the control unit, a display unit connected to the control unit, and a storage unit connected to the control unit, and the storage unit is executed in a measurement system in which an operation program is stored; A mark is photographed multiple times by the photographing unit at different distances, and the photographed image is stored in the storage portion. A pixel is obtained from the pixel information and the photographing distance of the image captured in the first photographing step and stored in the storage portion. A DB storage step in which an information-distance DB is created and stored in the storage unit, a second photographing step in which a mark attached to the target object is photographed in the photographing unit, and a mark image of the target object photographed in the second photographing step. Provides a distance measurement method using an image consisting of a calculation step in which the distance to the target object is calculated from the pixel information and the pixel information-distance DB stored in the storage unit, and a display step in which the calculated distance to the target object is displayed on the display unit. .

In the above, the pixel information-distance DB is characterized in that the number of pixels between both ends in the horizontal or vertical direction of the mark image photographed multiple times is derived, paired with the photographed distance, and stored in the storage unit.

In the above, the calculation step is characterized in that the distance to the target object is calculated using the pixel information of the mark image of the target object and the pixel information-distance DB and interpolation operation.

In the above, the pixel information-distance DB includes the pixel ratio, which is the width-to-height ratio calculated from pixel information in the horizontal direction and pixel information in the vertical direction; In the calculation step, the rotation angle of the mark image of the target object is calculated from the horizontal pixel information and the vertical pixel information of the mark image of the target object captured in the second photographing step and stored in the storage unit.

Meanwhile, in the present invention, in the above, the control unit is a control unit that controls the driving unit of the engine and steering device of the vehicle, the target object is a preceding vehicle, and the mark is a license plate attached to the preceding vehicle; The rotation angle of the mark image is the turning angle of the preceding vehicle, and the distance to the target object is the distance to the preceding vehicle, which becomes the input value of the control command transmitted from the control unit to the driving unit of the vehicle's engine and steering system. Provides a vehicle control method in which a device is controlled.

According to the present invention, it is possible to accurately and quickly extract and measure the distance (change) to the target object from the image, and it is also possible to measure the rotation information of the target object, so when the target object is a preceding vehicle, the distance to the preceding vehicle is possible. It is possible to control the vehicle by keeping it constant and using it as information to drive along the driving trajectory of the preceding vehicle.

1 is a schematic configuration diagram showing a measurement system in which the distance measurement method and vehicle control method using images according to the present invention are implemented;
Figure 2 is a schematic configuration diagram illustrating the storage unit of the measurement system in which the present invention is implemented;
Figure 3 is a schematic configuration diagram illustrating the display unit of the measurement system in which the present invention is implemented;
Figure 4 is a schematic flowchart of the distance measurement method using images according to the present invention;
Figure 5 is an exemplary diagram illustrating a method of measuring distance using an image according to the present invention.
Figure 6 is an example diagram of a license plate shown to explain the angle measurement method using an image according to the present invention.

Hereinafter, the distance measurement method and vehicle control method using images according to the present invention will be described in detail with reference to the drawings.

Figure 1 is a schematic configuration diagram showing a measurement system in which a distance measurement method and a vehicle control method using an image according to the present invention are implemented, and Figure 2 is a schematic diagram showing the storage unit of the measurement system in which the present invention is implemented. Figure 3 is a schematic diagram showing the display unit of the measurement system in which the present invention is implemented, Figure 4 is a schematic flowchart of the distance measurement method using an image according to the present invention, and Figure 5 is an exemplary diagram shown to explain the distance measuring method using an image according to the present invention, and Figure 6 is an exemplary diagram of a license plate shown to explain the angle measuring method using an image according to the present invention.

As shown in Figure 1, the measurement system in which the distance measurement method and vehicle control method using images according to the present invention are implemented includes a control unit 110, a photographing unit 120 connected to the control unit 110, and the control unit ( It consists of a display unit 140 connected to the display unit 110 and a storage unit 130 connected to the control unit 110, and an operation program for executing the present invention is stored in the storage unit 130.

In the vehicle control method according to the present invention, the control unit 110 is a control unit (ECU) provided in the vehicle, and the control unit 110 controls the operation of a driving unit (e.g., a motor) that drives the steering of the steering device and the engine. Controls the opening and closing of the throttle valve.

The distance measurement method using an image according to the present invention includes a first photographing step (ST-110), a DB storage step (ST-120), a second photographing step (ST-130), and a calculation step (ST-140). It consists of a display step (ST-150).

In the first photographing step (ST-110), the photographed image is photographed multiple times by varying the distance between the photographing unit 120 and the mark, and the photographed image (pixel information of the image) is stored in the storage unit 130. In the case of a vehicle control method, the mark may be a license plate attached to the vehicle.

In the DB storage step (ST-120), the pixel information (pixel color (RGB) information and location information) of the image captured in the first photographing step (ST-110) and stored in the storage unit 130 and the distance to the mark A pixel information-distance DB is created from and stored in the storage unit 130.

As shown in Figure 5, when the mark is a license plate, the number of pixels between pixels in which a change in pixel color information occurs in the horizontal direction (x-axis) where a change in pixel color information occurs, and a change in pixel color information occur. The number of pixels between pixels where a change in pixel color information in the vertical direction (y-axis) occurs is stored in the storage unit 130 as a pixel information-distance DB together with the distance taken as pixel information. In addition, the pixel ratio (number of pixels in the vertical direction/number of pixels in the horizontal direction), which is the ratio of the number of pixels in the horizontal direction and the number of pixels in the vertical direction, is also stored.

In the first photographing step (ST-110), the vehicle is photographed with a sign (license plate), and the sign (license plate) can be extracted from the photographed image and stored in the storage unit 130 as a pixel information-distance DB. The method of extracting a mark (license plate) from a photographed vehicle image is a conventionally known technique, so a detailed description thereof will be omitted (e.g., Republic of Korea Patent Publication No. 10-2015-0053073).

The pixel information-distance DB is stored as a combination of (distance between pixels in the horizontal direction, distance between pixels in the vertical direction, and distance to the mark) for each distance, and the pixel ratio is also converted into a pixel information-distance DB in the storage unit (130). ) is stored in

In the second photographing step (ST-130), the target object whose distance is to be checked is photographed, and the photographed image is stored in the storage unit 130. The target object may be a vehicle, and the mark may be a license plate attached to the vehicle. Pixel information about the mark of the target object captured in the second photographing step (ST-130) and stored in the storage unit 130 (number of pixels between pixels where pixel color information in the horizontal direction (x-axis) changes occurs (between pixels) distance), the number of pixels (distance between pixels) in the vertical direction (y-axis) where changes in pixel color information occur, and the pixel ratio are derived.

If the pixel ratio of the target object image captured in the second photographing step (ST-130) is the same as the pixel ratio of the pixel information-distance DB, the target object image is determined to have been photographed from the front, and the number of pixels in the horizontal direction (x-axis) or One of the number of pixels in the vertical direction (y-axis) is selected and calculated using the number of pixels and distance information in the pixel information-distance DB and interpolation to calculate the distance to the captured target object.

An exemplary explanation of the distance calculation from the horizontal direction (x-axis) pixel number-distance data included in the pixel information-distance DB and the horizontal pixel number of the target object image to the target object is as follows.

Let the (horizontal direction (x-axis) pixel number, distance) data included in the pixel information-distance DB be (500, 4m), (600, 7m), and the number of horizontal pixels of the image taken in the second shooting step is If it is 530,

The distance (D) to the target object is calculated as 4+(530-500)/(600-500)×(7-4), and the distance to the target object is calculated as 4.9m and displayed on the display through the control unit. In the first photographing stage (ST-110), marks are photographed at distance intervals according to the user's needs, such as 1m intervals or 2m intervals, and are stored in the storage. Pixel information (number of pixels) and pixels of the image for each stored distance are recorded. It is stored in the storage unit 130 along with the rain. In the first shooting stage (ST-110), since the image is taken from the front, the pixel ratio at each distance has a constant value.

The pixel information (number of pixels) of the mark image of the target object captured in the second shooting step (ST-130) is compared with the data of the pixel information-distance DB, and the pixel information of the mark image of the target object becomes the between value. Data from the information-distance DB is selected and calculated as above.

In the above, the pixel information-distance DB includes the horizontal (x-axis) pixel count-distance data and the horizontal pixel count of the target object image, but the calculation for the vertical direction (y-axis) is also performed in the same way. . One of the vertical or horizontal directions is selected and the distance to the target object is calculated.

The target object is a preceding vehicle and the mark is a license plate attached to the preceding vehicle, and when the target object, the preceding vehicle, turns, the license plate photographed and derived in the second photographing step (ST-130) is as shown in FIG. 6, The horizontal length of the captured image (T(θ)) is shorter than the horizontal length of the image (T(0)) captured from the front (straight ahead). This is because the mark of the target object rotates to one side. Therefore, the pixel ratio of the marking image T(θ) of the turning preceding vehicle becomes smaller than the pixel ratio of the marking image of the preceding vehicle moving straight. In the calculation step, the pixel ratio of the pixel information-distance DB and the pixel ratio of the mark image are calculated to calculate the turning angle (α) of the preceding vehicle.

The turning angle (α) is calculated as cos ^-1 [(pixel ratio of mark image)/(pixel ratio of pixel information-distance DB)]. The number of pixels between pixels in which pixel color information changes in the vertical direction (y-axis) at the left end of the marking image (T(θ)) of the preceding vehicle shown in FIG. 6, and the vertical direction (y-axis) at the right end The number of pixels between pixels in which a change in pixel color information occurs is derived, and these average values become the number of pixels in the vertical direction (y-axis), so that the pixel ratio to the number of pixels in the horizontal direction (x-axis) can be calculated.

Pixel color information in the vertical direction (y-axis) at the left end of the marking image (T(θ)) of the preceding vehicle. Number of pixels between pixels where changes occur and pixel color information in the vertical direction (y-axis) at the right end. The number of pixels between pixels where a change occurs is contrasted, and the number of pixels between pixels where a change occurs is the number of pixels in the vertical direction (y-axis) at the left end of the marking image (T(θ)) of the preceding vehicle. If the change in pixel color information in the vertical direction (y-axis) is greater than the number of pixels between pixels, the preceding vehicle is judged to be turning left. If the opposite is true, the preceding vehicle is judged to be turning right, and the driving unit that drives the steering device is judged to be turning right. The driving direction is controlled, and a control command is transmitted from the control unit 110 to the engine or steering device drive unit so that the vehicle speed and the turning direction of the vehicle are controlled based on the distance to the preceding vehicle and the turning angle.

Therefore, by controlling the degree of opening and closing of the vehicle engine's throttle valve and controlling the operation of the driving unit (motor) of the steering device, it is possible to drive along the driving trajectory of the preceding vehicle while maintaining a constant distance from the preceding vehicle. do.

The display unit 140 may display the speed of the driving vehicle as well as the speed of the preceding vehicle calculated from changes in distance over time.

100: measurement system 110: control unit
120: recording unit 130: storage unit
140: display unit

Claims (5)

It consists of a control unit, an imaging unit connected to the control unit, a display unit connected to the control unit, and a storage unit connected to the control unit, and the storage unit is executed by a measurement system storing an operating program;
A mark is photographed multiple times by the photographing unit at different distances, and the photographed image is stored in the storage portion. A pixel is obtained from the pixel information and the photographing distance of the image captured in the first photographing step and stored in the storage portion. A DB storage step in which an information-distance DB is created and stored in the storage unit, a second photographing step in which a mark attached to the target object is photographed in the photographing unit, and a mark image of the target object photographed in the second photographing step. It consists of a calculation step in which the distance to the target object is calculated from the pixel information and the pixel information-distance DB stored in the storage unit, and a display step in which the calculated distance to the target object is displayed on the display unit;
The pixel information-distance DB is derived from the number of pixels between both ends in the horizontal or vertical direction of the mark image photographed multiple times, paired with the photographed distance, and stored in the storage unit;
The pixel information-distance DB includes an aspect ratio calculated from pixel information in the horizontal direction and pixel information in the vertical direction; In the calculation step, the rotation angle of the mark image of the target object is calculated from the horizontal pixel information and the vertical pixel information of the mark image of the target object captured in the second shooting step and stored in the storage. How to measure distance. delete The method of claim 1, wherein in the calculation step, the distance to the target object is calculated by using pixel information of the mark image of the target object and interpolation calculation with the pixel information-distance DB. delete It consists of a control unit, an imaging unit connected to the control unit, a display unit connected to the control unit, and a storage unit connected to the control unit, and the storage unit is executed by a measurement system storing an operating program;
A mark is photographed multiple times by the photographing unit at different distances, and the photographed image is stored in the storage portion. A pixel is obtained from the pixel information and the photographing distance of the image captured in the first photographing step and stored in the storage portion. A DB storage step in which an information-distance DB is created and stored in the storage unit, a second photographing step in which a mark attached to the target object is photographed in the photographing unit, and a mark image of the target object photographed in the second photographing step. It consists of a calculation step in which the distance to the target object is calculated from the pixel information and the pixel information-distance DB stored in the storage unit, and a display step in which the calculated distance to the target object is displayed on the display unit;
The pixel information-distance DB is derived from the number of pixels between both ends in the horizontal or vertical direction of the mark image photographed multiple times, paired with the photographed distance, and stored in the storage unit;
The pixel information-distance DB includes an aspect ratio calculated from pixel information in the horizontal direction and pixel information in the vertical direction; In the calculation step, the rotation angle of the mark image of the target object is calculated from the horizontal pixel information and the vertical pixel information of the mark image of the target object captured in the second photographing step and stored in the storage unit;
The control unit is a control unit that controls the driving unit of the engine and steering device of the vehicle, the target object is a preceding vehicle, and the mark is a license plate attached to the preceding vehicle; The rotation angle of the mark image is the turning angle of the preceding vehicle, and the distance to the target object is the distance to the preceding vehicle, which becomes the input value of the control command transmitted from the control unit to the driving unit of the vehicle's engine and steering system. A vehicle control method, characterized in that the device is controlled.

Images