KR20230067242A - Performance evaluation apparatus and method for autonomous emergency braking system - Google Patents

Abstract

The performance evaluation device of the emergency braking system of the present invention includes a dual camera-mounted positioning device for measuring the distance to an object based on the dual camera; and a performance evaluation unit that evaluates the performance of the AEB system to be evaluated by comparing the distance detected through the dual-camera-equipped positioning device with the distance measured by the AEB system to be evaluated.

Description

Performance evaluation apparatus and method of emergency braking system {PERFORMANCE EVALUATION APPARATUS AND METHOD FOR AUTONOMOUS EMERGENCY BRAKING SYSTEM}

The present invention relates to an emergency braking system performance evaluation apparatus and method for evaluating the performance of an AEB system performing emergency braking.

Recently, research and development of autonomous vehicles is increasing.

The self-driving vehicle refers to a vehicle that autonomously determines a driving route by recognizing the surrounding environment through an external information sensing and processing function while driving, and independently drives using its own power. These self-driving vehicles prevent collisions with obstacles on the driving path and drive to the destination by themselves while adjusting the vehicle speed and driving direction according to the shape of the road, even if the driver does not manipulate the steering wheel, accelerator pedal, or brake. aim for

Therefore, as a process to achieve the above goal, at least one driver assistance system (ADAS: Advanced Driver Assistance System) is applied to current vehicles to assist the driver's driving, and among the driver assistance systems (ADAS) are automatic emergency There is an Autonomous Emergency Braking (AEB) system.

At this time, the driver assistance system (ADAS), especially the automatic emergency braking (AEB) system, has a problem of causing human accidents due to collisions with nearby vehicles or pedestrians when malfunctioning, so precise test evaluation on operation and braking performance is essential. is being demanded However, at present, development of specific devices and methods for testing and performance evaluation of the automatic emergency braking (AEB) system is insufficient.

The background art of the present invention is disclosed in Korean Patent Registration No. 10-0405569 (2003.11.03) 'Braking performance evaluation test device'.

The present invention has been devised to improve the above problems, and an object according to an aspect of the present invention is to provide an apparatus and method for evaluating the performance of an emergency braking system for evaluating the performance of an AEB system.

An apparatus for evaluating the performance of an emergency braking system according to an aspect of the present invention includes a dual camera mounting positioning device for measuring a distance to an object based on a dual camera; and a performance evaluation unit that evaluates the performance of the AEB system to be evaluated by comparing the distance detected through the dual-camera-equipped positioning device with the distance measured by the AEB system to be evaluated.

The performance evaluation unit of the present invention evaluates the performance of the AEB system to be evaluated by using an error between the distance detected through the dual camera mounting positioning device for each preset scenario and the distance measured by the AEB system to be evaluated. to be characterized

The performance evaluation unit of the present invention uses at least one of the maximum value, the minimum value, and the average value of the error between the distance detected through the dual-camera-equipped positioning device and the distance measured by the evaluation target AEB system for each scenario. Characterized in evaluating the performance of the AEB system.

The present invention is characterized in that it further comprises an evaluation result output unit outputting an evaluation result of the performance evaluation unit.

An apparatus for evaluating performance of an emergency braking system according to another aspect of the present invention includes a distance measuring unit for measuring a distance between a vehicle and an object using an initial relative distance of an object, a vehicle speed, and an object speed; and a performance evaluation unit that evaluates performance of the AEB system to be evaluated by comparing the distance measured through the distance measurement unit with the distance measured by the AEB system to be evaluated.

이며, 여기서,

는 상대거리,

는 초기 상대거리,

는 선행차량 속도,

는 대상차량 속도, 0.2, 2.9, 및 36.1은 보정 파라미터인 것을 특징으로 한다.The distance measurement unit of the present invention measures the distance between the vehicle and the object using the following equation, the equation is

is, where

is the relative distance,

is the initial relative distance,

is the speed of the preceding vehicle,

is the target vehicle speed, and 0.2, 2.9, and 36.1 are correction parameters.

The performance evaluation unit of the present invention may evaluate the performance of the AEB system to be evaluated by using an error between the distance measured through the distance measurement unit and the distance measured by the AEB system to be evaluated for each preset scenario.

The performance evaluation unit of the present invention uses at least one of the maximum value, the minimum value, and the average value of the error between the distance measured through the distance measurer and the distance measured by the AEB system to be evaluated for each scenario, and uses at least one of the performance of the AEB system to be evaluated. It is characterized by evaluating.

The present invention is characterized in that it further comprises an evaluation result output unit outputting an evaluation result of the performance evaluation unit.

A performance evaluation method of an emergency braking system according to an aspect of the present invention includes the steps of measuring a distance to an object based on a dual camera by a dual camera mounting positioning device; and evaluating the performance of the AEB system to be evaluated by a performance evaluation unit by comparing the distance detected through the dual-camera mounting positioning device with the distance measured by the AEB system to be evaluated.

In the step of evaluating the performance of the AEB system to be evaluated according to the present invention, the performance evaluation unit calculates an error between the distance detected through the dual camera mounting positioning device and the distance measured by the AEB system to be evaluated for each preset scenario. It is characterized in that the performance of the AEB system to be evaluated is evaluated by using.

In the step of evaluating the performance of the AEB system to be evaluated according to the present invention, the performance evaluation unit is the maximum value of the error between the distance detected through the dual camera mounted positioning device for each scenario and the distance measured by the AEB system to be evaluated. It is characterized in that the performance of the AEB system to be evaluated is evaluated using at least one of the minimum value and the average value.

According to another aspect of the present invention, a performance evaluation method of an emergency braking system includes measuring a distance between a vehicle and an object by a distance measurer using an initial relative distance of an object, a vehicle speed, and an object speed; and comparing the distance measured by the distance measurer with the distance measured by the AEB system to be evaluated by the performance evaluation unit to evaluate the performance of the AEB system to be evaluated.

이며, 여기서,

는 상대거리,

는 초기 상대거리,

는 선행차량 속도,

는 대상차량 속도, 0.2, 2.9, 및 36.1은 보정 파라미터인 것을 특징으로 한다.In the step of measuring the distance between the vehicle and the object by the distance measurement unit using the initial relative distance of the object, the speed of the vehicle and the speed of the object, the distance measurement unit calculates the distance between the vehicle and the object using the following equation. measured, and the above equation is

is, where

is the relative distance,

is the initial relative distance,

is the speed of the preceding vehicle,

is the target vehicle speed, and 0.2, 2.9, and 36.1 are correction parameters.

The performance evaluation unit of the present invention may evaluate the performance of the AEB system to be evaluated by using an error between the distance measured through the distance measurement unit and the distance measured by the AEB system to be evaluated for each preset scenario.

The performance evaluation unit of the present invention uses at least one of the maximum value, the minimum value, and the average value of the error between the distance measured through the distance measurer and the distance measured by the AEB system to be evaluated for each scenario, and uses at least one of the performance of the AEB system to be evaluated. It is characterized by evaluating.

The apparatus and method for evaluating the performance of an emergency braking system of the present invention enable the performance of an AEB system to be evaluated based on a distance calculated using a dual camera.

The apparatus and method for evaluating the performance of an emergency braking system of the present invention use a relative distance, an initial relative distance, an object speed, a target vehicle speed, a target relative distance, a time difference, a time difference between a target vehicle and an object, and a time difference between a target vehicle and an object. The distance to the object is measured, and based on this, the performance of the AEB system to be evaluated can be evaluated.

The apparatus and method for evaluating the performance of an emergency braking system according to the present invention can drastically reduce the time, expense, and expensive equipment and professional manpower required for a vehicle test in evaluating the safety of a finished vehicle.

The apparatus and method for evaluating the performance of an emergency braking system according to the present invention can provide a theoretical basis for the development freedom and safety verification of a component developer or an automobile company.

1 is a block diagram of a performance evaluation device for an emergency braking system according to an embodiment of the present invention.
2 is a block diagram of a dual camera mounted positioning device according to an embodiment of the present invention.
3 is a block diagram of an image correction unit according to an embodiment of the present invention.
4 is a diagram showing a checkerboard image for image distortion correction according to an embodiment of the present invention.
5 is a diagram showing a corrected image according to an embodiment of the present invention.
6 is a diagram illustrating a horizontal stereo camera model according to an embodiment of the present invention.
7 is a block configuration diagram of a lane detection unit according to an embodiment of the present invention.
8 is a flowchart illustrating a lane detection process according to an embodiment of the present invention.
9 is an image of a lane detection process according to an embodiment of the present invention.
10 is a block configuration diagram of a mounting position determining unit according to an embodiment of the present invention.
11 is a view conceptually showing a mounting position according to an embodiment of the present invention.
12 to 14 are diagrams showing images according to the position of a camera according to an embodiment of the present invention.
15 to 17 are diagrams showing average error rates according to location selection according to an embodiment of the present invention.
18 is a diagram showing a distance to a forward object on a straight road according to an embodiment of the present invention.
19 is a diagram showing a distance to a forward object on a curved road according to an embodiment of the present invention.
20 is an exemplary view of a scenario for distance measurement according to an embodiment of the present invention.
21 is a flowchart of a performance evaluation method of an emergency braking system according to an embodiment of the present invention.
22 is a flowchart of a performance evaluation method of an emergency braking system according to an embodiment of the present invention.

Hereinafter, an apparatus and method for evaluating performance of an emergency braking system according to an embodiment of the present invention will be described in detail with reference to the accompanying drawings. In this process, the thickness of lines or the size of components shown in the drawings may be exaggerated for clarity and convenience of explanation. In addition, terms to be described later are terms defined in consideration of functions in the present invention, which may vary according to the intention or custom of a user or operator. Therefore, definitions of these terms will have to be made based on the content throughout this specification.

1 is a block diagram of a performance evaluation device for an emergency braking system according to an embodiment of the present invention.

Referring to FIG. 1 , the performance evaluation device of an emergency braking system according to an embodiment of the present invention includes a dual camera mounting positioning device 100, a distance measurement unit 200, a performance evaluation unit 300, and an evaluation result output. Includes section 400.

In FIG. 1 , an evaluation target AEB system 500 is an AEB system that is mounted or can be installed in a vehicle, and is an AEB system to be evaluated.

The dual camera mounting position determining apparatus 100 determines an optimal dual camera mounting position in a vehicle and measures a distance to an object based on the determined mounting position.

2 is a block diagram of a dual camera mounted positioning device according to an embodiment of the present invention.

Referring to FIG. 2 , the dual camera mounting position determining device 100 according to an embodiment of the present invention includes two cameras 10, a lane detection unit 30, an image correcting unit 40, and a mounting position determining unit ( 50) included.

Cameras 10 are installed on the left and right sides of the vehicle, respectively, to capture images of the front of the vehicle.

3 is a block diagram of an image correction unit according to an embodiment of the present invention, FIG. 4 is a diagram showing a checkerboard image for image distortion correction according to an embodiment of the present invention, and FIG. It is a diagram showing a corrected image according to an embodiment. 6 is a diagram illustrating a parallel stereo camera model according to an embodiment of the present invention.

The image correction unit 40 corrects the image captured by the camera 10 .

Referring to FIG. 3 , the image correction unit 40 includes an image distortion removal unit 41 , an image rectification unit 42 , and a focal length detection unit 43 .

The image distortion removal unit 41 removes image distortion.

Typically, images acquired by the camera 10 have radial distortion caused by the refractive index of a convex lens and tangential distortion caused by horizontal problems of the lens and image sensor during the camera manufacturing process. do. Accordingly, the image distortion removing unit 41 corrects circular distortion due to radial distortion and elliptical distortion due to tangential distortion at the edge of the image.

To this end, when the image distortion remover 41 distorts the coordinates corresponding to each pixel in the image, the value of the corresponding pixel in the distorted image is used as the value of each pixel in the corrected image.

In this embodiment, OpenCV's built-in checkerboard pattern search function, corner point search function, and camera calibration function are used for image processing. In order to obtain a corrected image, a 6x4 checkerboard is photographed by the camera 10 to find corner points in the checkerboard, and a camera matrix and distortion coefficient are calculated from the obtained points. 5(a) is an image in which corner points are found in an original image, and (b) is an image in which distortion is removed.

The image rectifying unit 42 rectifies and corrects vertical parallax that may occur due to the installation process of the camera 10 or internal parameters of the camera.

In general, the parallel stereo camera configuration uses two cameras 10 in which the optical axes of the cameras 10 and lenses are parallel, so that there is no vertical parallax, which is advantageous for image processing.

Image rectification is to find an epipolar line for matching pixel rows in an image of a dual camera, and then to have an arbitrary object in the image have the same horizontal coordinates.

In this embodiment, OpenCV's built-in stereo calibration function and stereo rectification function are used for image processing, and the checkerboard image used in the image distortion removal step can be used for the checkerboard pattern search, corner point search, and calibration of the dual camera. there is. As shown in (a) of FIG. 5 , internal parameters, rotation matrices of the two cameras 10 , projection matrices in the rectified coordinate system, and the like can be obtained from a pair of images obtained by photographing a checkerboard with a dual camera. Using this, a corrected image as shown in (b) of FIG. 5 can be obtained.

The focal length detector 43 detects a focal length for distance measurement. For distance measurement, the optical axes of the two cameras 10 are parallel to each other, the lenses are located at the same height from the ground and are on the same line, and the geometry of the cameras 10 and triangulation as shown in FIG. 6 are used. By doing so, the 3D coordinates from the position of the camera 10 to the object can be calculated as in Equation 1.

Here, X, Y, Z are the coordinates of the object in the world coordinate system, f is the focal length, b is the distance between the left and right cameras, d is the parallax, xl is the x-coordinate of the left image, xr is the x-coordinate of the right image, yl is the left The y-coordinate of the image, yr is the y-coordinate of the right image.

On the other hand, the focal length is one of the parameters required to calculate the Z-axis coordinate, but in the case of inexpensive webcams compared to expensive cameras, the manufacturer may not provide the focal length or there may be an error with the provided value. In addition, since an error may occur during image correction, it is necessary to correct the value.

For focal length correction, curve fitting may be performed based on actual data. In Equation 1, Equation 2 can be obtained by using the fact that the Z-axis coordinate Z and the parallax d are inversely proportional.

Z _actual is the actual distance, α, β are the coefficients obtained through focal length correction, and d is the parallax.

For example, if an object installed at 0.5m intervals from 1m to 5m is photographed, the parallax of the object at each point is calculated, and curve fitting using the least squares method is performed using the parallax data for each distance and Equation 2. α and β can be obtained.

Based on the focal length and parallax, the distance to the object may be detected by a distance detector 51 to be described later.

The lane detecting unit 30 detects lanes in images captured by the two cameras 10 .

7 is a block diagram of a lane detection unit according to an embodiment of the present invention, FIG. 8 is a flowchart illustrating a lane detection process according to an embodiment of the present invention, and FIG. 9 is a block diagram according to an embodiment of the present invention. This is a video of the lane detection process.

7 to 9, the lane detection unit 30 includes a region of interest setting unit 31, a straight line detection image extraction unit 32, a color detection image extraction unit 33, and an image perspective. It includes a converting unit 34, a lane generating unit 35, and a lane applying unit 36.

When an image is input, the region of interest setting unit 31 sets a region of interest in which a lane can be positioned within the image (S10 and S20). The region of interest is a region containing necessary information in an image acquired by a camera. When the camera is fixed to the car, the area covered by the road does not change, so extraneous areas can be removed to obtain only the necessary areas.

(a) of FIG. 9 is an image input from a fixed left camera, and can be obtained as shown in (b) of FIG.

The straight line detection image extraction unit 32 extracts the straight line detection image through image processing for the region of interest set by the region of interest setting unit 31, such as grayscale conversion, edge detection, Hough conversion, and filtering.

First, the straight line detection image extractor 32 performs gray scale conversion on the region of interest (S30). That is, the straight line detection image extraction unit 32 converts the RGB format, which is the region of interest, into a black and white image having only a single channel.

Grayscale conversion converts an RGB (Red, Green, Blue) format image composed of three channels into a single color image composed of one channel. Since the converted image has only brightness information, the amount of data to be processed is reduced to a level of 1/3, thereby increasing the processing speed.

9(c) is an image obtained by grayscale conversion, and is a single-channel image generated by adding and averaging pixel values of R, G, and B channels.

The straight line detection image extractor 32 detects an edge in the region of interest using a canny edge detector composed of steps of noise removal, gradient calculation, non-maximum suppression, and hysteresis thresholding (S40).

The Canny Edge Detector is one of the edge detection algorithms. Through steps such as noise removal, gradient magnitude and direction calculation, non-maximum suppression, and hysteresis threshold, the image is detected. Detect edges within As a multi-step algorithm, it has better performance than a method using only a differential operator such as a Sobel mask.

9(d) is an image in which an edge is detected. In addition, noise was removed using a Gaussian filter, and an image in which edges were detected was generated using a Canny edge detector.

Finally, the straight line detection image extractor 32 extracts a straight line component from the edge detection image through a Hough transform, calculates a slope, removes horizontal and vertical lines, and extracts an image in which the straight line is detected (S50). ).

The Hough transform is a method of expressing components of the x-y coordinate system by transforming them into components of the r-θ parameter space. A straight line and a point in the x-y coordinate system are expressed as a point and a straight line, respectively, in the parameter space, and a straight line in the x-y coordinate system can be searched using the point where the straight lines in the parameter space intersect.

9(e) is an image of a straight line corresponding to a lane. In the edge-detected image, linear components were detected using Hough transform. In addition, after calculating the slope of the obtained straight line to remove the horizontal and vertical lines that are unlikely to be lanes, straight lines with an absolute value of slope of 5° or less were removed.

The color detection image extraction unit 33 extracts a color detection image through Hue, Saturation, Value (HSV) format conversion and color detection for the region of interest.

That is, the color detection image extraction unit 33 converts the RGB format, which is an input image, into an HSV format image having hue, saturation, and brightness channels (S60).

The HSV (Hue, Saturation, Value) format is a color model that expresses an image in hue, saturation, and brightness. Since it is a model that applies the method of human color recognition, it is easier to express the desired color.

Subsequently, the color detection image extraction unit 33 designates range values for hue, saturation, and brightness of a range corresponding to yellow, and extracts a color detection image in which pixels within the range are detected (S70).

FIG. 9(f) is an image obtained by extracting yellow pixels from FIG. 9(b). After converting the image from RGB format to HSV format, the yellow range was set. When the ranges of hue, saturation, and brightness are normalized to a value between 0 and 1, the range of hue corresponds to 0 to 0.1 and 0.9 to 1, and the range of saturation corresponds to 0.12 to 1. As for the value of brightness, 1/3 of the average brightness of the image was used. In addition, pixels with a value corresponding to the range in the image have a value of 255, and otherwise have a value of 0.

The image perspective conversion unit 34 combines the image in which the straight line detected by the straight line detection image extractor 32 and the color detected by the color detection image extractor 33 are combined, and the perspective is removed. Acquire an image with an effect.

That is, the image perspective conversion unit 34 converts the straight line detected image extracted by the straight line detection image extractor 32 and the color detected image extracted by the color detection image extractor 33 into a predetermined ratio Example For example, they are combined with a weight of 8:2 (S80).

9(g) is an image obtained by combining an image obtained by extracting a straight line and an image obtained by extracting a color in order to obtain a pixel corresponding to a lane candidate. It is an image obtained by combining the image of FIG. 9 (c) with a weight of 0.8 and the image of FIG. 9 (d) by giving a weight of 0.2.

Subsequently, the image perspective conversion unit 34 applies the transformation matrix calculated with the 4 coordinates for the combined image and the 4 coordinates for the transformed image to the input image as described above to obtain an image having the effect of removing the perspective. Obtain (S90).

Perspective transformation is a transformation that can be modeled by homography using a 3x3 transformation matrix. It is possible to obtain an image from which perspective is removed through a geometric processing technique that moves the location of pixels in an image.

The lane generation unit 35 searches for lane candidates in the entire area of the image converted by the image perspective converter 34 or in the lane curve area, depending on whether the lane line has been detected in the previous frame.

That is, when a lane generation unit 35 detects a lane line in the previous frame, the left and right lanes are divided based on the center of the image converted by the image perspective conversion unit 34, and a sliding window is displayed in the area adjacent to the obtained lane curve. A next-best candidate is searched through the technique (S110).

On the other hand, if no lane is detected in the previous frame, the lane generation unit 35 divides the left and right lanes based on the center of the image converted by the image perspective conversion unit 34, and uses the sliding window technique in the entire area. Next best candidates are searched (S120).

(h) of FIG. 9 is an image obtained by removing perspective from the image of (g) of FIG. 9 and then obtaining lane candidates using a sliding window. The four points on the lane set in the region of interest were moved to the points of (300, 648), (300, 0), (780, 0), and (780, 648) in the warped image to make a straight line. . Then, a 54-pixel square window with a width of 1/20 and a height of 1/6 of the video was set, and the window with the largest sum of pixels was found through the sliding window method.

The sliding window technique is a method of reducing the amount of computation by using a sub-array of a specific size, called a window, and reusing redundant elements instead of discarding them whenever elements within each window are calculated in the entire array.

9(i) is an image in which lane curves are generated through quadratic curve fitting from lane candidate pixels. In (h) of FIG. 9 , a lane curve can be generated by fitting a quadratic curve using the position of the lane candidate pixels obtained from each of the six windows of the left and right lanes and the least squares method.

The lane generator 35 obtains coordinates of pixels of lane candidates in each window, and generates lane curves by fitting the coordinates to a quadratic curve (S130).

Subsequently, the lane generator 35 obtains an image in which the lane is detected by applying the generated lane curve to the input image through perspective transformation (S140).

(j) of FIG. 9 is an image obtained by detecting lanes in an input image. If the obtained lane curve is applied to the input image through perspective transformation, an image in which the lane is detected can be obtained.

10 is a block configuration diagram of a mounting position determining unit according to an embodiment of the present invention, FIG. 11 is a view conceptually showing a mounting position according to an embodiment of the present invention, and FIGS. 12 to 14 are one part of the present invention 15 to 17 are diagrams showing an average error rate according to position selection according to an embodiment of the present invention.

The mounting position determiner 50 uses the curvature of the straight or curved road of the lane through the lane detected by the lane detection unit 30 and the parallax obtained through the image compensator 40 to reach a forward object. The distance is measured, and the mounting position of the camera is determined based on the error rate between the measured distance and the actual distance.

The mounting position determination unit 50 includes a distance detection unit 51, a position determination unit 52, and a variable adjustment unit 53.

The mounting position of the camera 10 is the front side of the vehicle as shown in FIG. 11 . The mounting position of the camera 10 may be defined by the height, spacing, and angle (inclination angle) of the camera 10, and an optimal mounting position may be determined by correcting these variables.

Accordingly, a height setting range, an interval setting range, and an angle setting range are set according to the height, interval, and angle of the camera 10 according to the vehicle, and the mounting position of the camera 10 can be determined within each of these setting ranges.

In this embodiment, the distance is measured based on the ground. As the mounting height of the camera 10 decreases, the area of the ground captured in the image increases. Therefore, the mounting height of the camera 10 also has a significant effect on determining the area of the acquired image.

For example, it will be described as an example that the height is selected as 30 cm, 40 cm, and 50 cm within the height setting range.

In the case of a general passenger car, since the bumper is at least 30 cm away from the ground, the minimum value of the height may be selected as 30 cm. In addition, if the height is greater than 50 cm, since it is difficult to photograph the ground within 1 m, the maximum value of the height may be selected as 50 cm. 12(a) is an input image when the installation distance of the camera 10 is 30 cm and the angle is 13° and the height is 30 cm, 40 cm, and 50 cm, respectively.

Equation 1 is an equation based on the geometry of the camera 10 and the triangulation method. Therefore, the distance between the cameras 10 has a great effect on distance measurement.

The interval will be explained as an example in which 10cm, 20cm, and 30cm are selected within the interval setting range. When arranging the camera 10, since the minimum distance physically possible is 10 cm, the minimum value may be selected as 10 cm. In addition, three values up to 30 cm at intervals of 10 cm may be selected in order to confirm the tendency of the height. 13 is an input image when the installation height of the camera 10 is 40 cm and the angle is 13°, and the intervals are 10 cm, 20 cm, and 30 cm, respectively.

When the camera 10 is installed horizontally with the ground, the camera 10 having a small vertical angle of view may not be able to photograph the ground at a short distance. Therefore, when the camera 10 is tilted by an inclination angle θ, the installation angle of the camera 10 is important because it is possible to photograph the ground at a short distance.

The angle will be explained as an example in which 3°, 7°, and 12° are selected within the angle setting range. When the height is 50 cm, if the angle is less than 4°, it is difficult to photograph the ground within 1 m, so the minimum angle value may be selected as 3°. As the angle increases, the area of the road in the image increases. If there is a vehicle shaking or a slope, there is a possibility that the top of the road may not be captured. When the angle is 12°, since 20% to 80% of the image height is the road area, the maximum value of the angle may be set to 12°. 14 shows input images when the angles are 3°, 7°, and 12°, respectively, when the installation height of the camera 10 is 40 cm and the spacing is 30 cm.

The distance detection unit 51 measures the distance from the vehicle to the object multiple times for each of the above variables, that is, the height, interval, and angle.

The position determination unit 52 compares the distance measured by the distance detection unit 51 for each height, interval, and angle with the actual distance to detect an error rate, compares the detected error rate with a preset reference error rate, and optimizes the optimum according to the comparison result. determine the mounting location of

In this case, the position determination unit 52 determines the current height, interval, and angle as the optimal mounting position according to whether the error rate is less than the preset standard error rate. The position determining unit 52 determines the current position of the dual camera as the final position when the error rate is less than the reference error rate. On the other hand, if the error rate is equal to or greater than the reference error rate, the variable is adjusted by the variable adjusting unit 53 .

The variable adjusting unit 53 adjusts at least one of the height, interval, and angle when the error rate detected by the position determination unit 52 is equal to or greater than the reference error rate. The variable adjusting unit 53 outputs the adjusted height, interval, and angle of the dual camera through a separate display device. Accordingly, the user refers to the adjusted parameters and changes the mounting position of the dual camera. At this time, the distance detection unit 51 detects the distance to the object based on the adjusted variable.

For example, each camera 10 is mounted on a car, objects are installed at intervals of 0.5 m from 1 m to 5 m on a real road, and results of measurement through the distance detector 51 are shown in FIGS. 15 to 17 .

15 is a test result when the height is 30 cm, and (a), (b), and (c) of FIG.

In (a), (b), and (c) of FIG. 15 , the smallest average error rates are 13.28% for 3°, 4.14% for 12°, and 8.34% for 12°, respectively.

16 is a test result when the height is 40 cm. 16 (a), (b), and (c) show the result of comparing the accuracy according to the angle when the intervals are 10 cm, 20 cm, and 30 cm, respectively.

In (a), (b), and (c) of FIG. 16, the smallest average error rates are 5.55% for 3°, 5.49% for 7°, and 0.86% for 12°, respectively.

17 is a test result when the height is 50 cm. 17 (a), (b), and (c) show the results of comparing the accuracy according to the angle when the intervals are 10 cm, 20 cm, and 30 cm, respectively.

In (a), (b) and (c) of FIG. 17 , the smallest average error rates are 3.77% at 7°, 2.45% at 7°, and 1.32% at 12°, respectively.

15 to 17, the error rate decreases as the angle increases, the error rate decreases as the interval increases, the error rate decreases when the height increases from 30 cm to 40 cm, and the error rate decreases again when the height increases to 50 cm. It increases.

Accordingly, the variable adjusting unit 53 selectively adjusts at least one of the angle, interval, and height based on the change in the error rate.

As a result of the above analysis, the mounting position of the camera 10 is the best at a height of 40 cm, an interval of 30 cm, and an angle of 13°.

Meanwhile, the distance detection unit 51 may detect distances to a front object on a straight road and a curved road, respectively.

18 is a diagram showing a distance to a forward object on a straight road according to an embodiment of the present invention, and FIG. 19 is a diagram showing a distance to a forward object on a curved road according to an embodiment of the present invention.

The distance detector 51 may obtain the Z-axis coordinate of the object by substituting the coefficient α acquired through the focal length correction into Equation 1 as the focal length f. However, in the test, when the camera 10 is mounted in order to photograph the ground at a close distance, the inclination angle θ is required. That is, the optical axis of the camera 10 and the ground are not parallel.

In order to calculate the Z-axis coordinate from the camera position on the ground to the object, it can be calculated as in Equation 3 by considering the inclination angle θ in Equation 1.

Here, X _g , Y _g , and Z _g are X, Y, and Z coordinates of the object on the ground, θ is the angle of the camera 10, and h is the height of the camera 10.

를 전방 물체까지의 거리로 사용할 수 있다.18, since the distance from the camera 10 to the object in front requires only the vertical distance

can be used as the distance to the forward object.

In the curved road as shown in FIG. 19, the radius of curvature of the road should be considered in order to measure the distance to the object in front.

Therefore, the distance detection unit 51 obtains the vertical distance using the X-axis coordinate and the Z-axis coordinate of the object, and then calculates the distance to the front object in consideration of the radius of curvature.

The vertical distance between the camera position and the front object is calculated as in Equation 4.

Here, chord is the vertical distance between the car and the object, X _g1 and Y _g1 are the x and y coordinates of the car on the ground, and X _g2 and Y _g2 are the x and y coordinates of the object on the ground.

The central angle φ of a sector having the center of curvature as a center and the vertical distance from the position of the camera 10 to the front object as a chord is calculated as in Equation 5.

Here, φ is the angle between the car and the object (the central angle of the sector), and R is the radius of curvature of the road.

The length of the arc of the circle calculated using the central angle φ and the radius of curvature R of the sector is calculated as in Equation 6.

Here, arc is the distance between the car and the object considering the radius of curvature.

The distance from the vehicle to the front object on the curved road can be calculated by considering the center of curvature and the 3D position of the object, and the arc can be determined as the distance from the camera position to the front object.

Depending on the presence or absence of the radius of curvature, different equations were proposed depending on the straight road and the curved road. In the proposed equation, as the curvature radius increases, the difference between the straight line distance measurement equation and the curved road distance measurement equation decreases. Therefore, if the radius of curvature is more than a certain value, it is determined as a straight path, and if not, it is determined as a curved path and then the formula is applied. When the radius of curvature is 1293 m, the error rate is less than 0.1%. Therefore, the proposed equation uses 1293m as a reference point and is expressed as in Equation 7.

Here, Z _t is the theoretical distance from the camera 10 to the object in front.

The vehicle test was conducted after installing the dual camera at the selected optimal location (height 40cm, interval 30cm, angle 13°) to verify the forward distance measurement formula.

It is a straight road and a curved road that have been tested. In the case of a curved road, the radius of curvature was 69m, and the study was conducted on a curved road with a radius of curvature of 80m or less. In the case of a straight road, obstacles installed at 10m intervals from 10m to 40m in front of the vehicle were classified into stationary and driving conditions. In the case of a curved road, obstacles were installed in the center of the road and in the left and right lanes, and for the obstacles installed at 5m intervals from 6m to 21m, tests were conducted on a total of 4 cases by dividing the stationary state and the running state.

For objective data acquisition, the same equipment was used and repeated three times.

In the case of a stationary state on a straight line, objects could be identified from the 10m point to the 40m point, and the maximum error was 2.29% at the 30m point.

In the case of driving on a straight road, an object could be identified from the 10m point to the 20m point, but the object could not be identified from the 30m point or more. This was judged by the influence of shaking of the car, lighting change, vibration of the camera 10, etc., which occurred during driving, and the maximum error was found to be 5.35% at the 20m point.

In the case of a stop state on a curved road, objects could be identified from the 5m point to the 20m point, and the maximum error was 1.65% at the 20m point.

In the case of driving on a curved road, the object could be identified from the 5m point to the 15m point, but the object could not be identified from the 20m point. This was judged by the influence of shaking of the car, lighting change, and vibration of the camera 10 occurring during driving, and the maximum error was found to be 9.40% at the 6m point.

As a result of the test, the error in measuring the distance to the object tends to increase when the forward object is incorrectly detected due to shaking of the vehicle, lighting change, vibration of the camera 10, and the like. In addition, in the case of driving on a curved road, the error tends to be relatively large compared to that on a straight road, which is judged to be influenced by the fixed radius of curvature used in the calculation process.

For reference, as an optimal mounting position according to precision and error rate, the height of the camera 10 is 40 cm, the interval of the camera 10 is 30 cm, and the angle may be 12 °, based on the position of the camera 10 Explain.

The distance measurement unit 200 detects the distance between the vehicle and the object using the initial relative distance of the object, the speed of the vehicle, and the speed of the object.

In this embodiment, an object detected by the distance measurement unit 200 is described as an example of a preceding vehicle. However, the object may be a pedestrian or the like other than the preceding vehicle, and the type of object is not particularly limited.

The distance measurer 200 calculates the distance between the vehicle and the preceding vehicle through Equation 8 below using the initial relative distance between the vehicle (target vehicle) and the preceding vehicle, the speed of the vehicle, and the speed of the preceding vehicle. Here, the speed of the preceding vehicle may be detected based on a radar sensor or the like.

Here, d is the distance between the vehicle and the preceding vehicle, v _TV is the speed of the preceding vehicle, and v _SV is the speed of the subject vehicle.

), 차량과 선행차량 간의 시간차(

), 및 차량과 선행차량 간의 속도차(

)를 토대로 유도될 수 있다.The distance between the vehicle and the preceding vehicle is the target relative distance (

), the time difference between the vehicle and the preceding vehicle (

), and the speed difference between the vehicle and the preceding vehicle (

) can be derived based on

The target acceleration for controlling the vehicle speed and distance can be calculated through the optimal control theory using the vehicle speed and distance information measured using the radar sensor, and the target relative distance, which is related distance information, is as follows.

이다. First, the target relative distance

am.

The speed and distance of the preceding vehicle may be measured through various sensors installed in the vehicle. As such a sensor, a radar sensor, lidar sensor, or ultrasonic sensor may be employed, and is not particularly limited.

Here, d _des is the target relative distance, d ₀ is the initial relative distance between the vehicle and the preceding vehicle, τ is the time difference, and t _ront is the time difference between the vehicle and the preceding vehicle.

이며, 여기서 차량과 선행차량 간의 시간차 계산식에서의 V는 차량과 선행차량 간의 속도차이다.The time difference between the vehicle and the preceding vehicle is

Here, V in the formula for calculating the time difference between the vehicle and the preceding vehicle is the speed difference between the vehicle and the preceding vehicle.

이다.On the other hand, the speed difference between the vehicle and the preceding vehicle is

am.

Here, v _TV is the speed of the preceding vehicle, and v _SV is the speed of the subject vehicle.

As the time difference τ and t _ront play the same role, the distance between the vehicle and the preceding vehicle can be derived as in Equation 3 above.

를 통해 차량과 선행차량의 상대속도만으로도 시간차 오차가 감소될 수 있다. Typically, as the relative speed of the vehicle and the preceding vehicle increases, the time difference also increases, and thus an error may occur. thus,

Through this, the time difference error can be reduced only with the relative speed of the vehicle and the preceding vehicle.

Meanwhile, the result of measuring the distance between the vehicle and the preceding vehicle when the height of the camera 10 is 40 cm, the interval is 30 cm, and the angle is 12 ° will be described with reference to Tables 1 and 2 below.

Table 1 is a result of comparing the distance measured by the dual camera mounting positioning device 100 with the actual DGPS measurement value.

Referring to Table 1, the minimum deviation between the distance measured by the dual-camera mounting positioning device 100 and the actual DGPS value was 2.57cm in the third test of the Vehicle to Vehicle 30km/h scenario, and the minimum error rate It can be seen that is represented by 1.80%.

The maximum deviation was 16.20cm in the third test of the Vehicle to Pedestrian 30km/h scenario, and the maximum error rate was 8.89%.

Based on this, it can be seen that the error between the camera and the DGPS measurement value is relatively small.

Table 2 is a result of comparing the calculated value of Equation 8 above, that is, the distance measured by the distance measurement unit 200 and the DGPS measurement value.

Referring to Table 2, the minimum deviation between the distance measured by the distance measuring unit 200 and the actual value showed a deviation of 0.17cm in the second test of the Vehicle to Vehicle 30km/h scenario, and the minimum error rate was 0.11% can know

The maximum deviation was 6.31cm in the first test of the Vehicle to Pedestrian 40km/h scenario, and the maximum error rate was 4.45%.

Based on this, it can be seen that the error between the theoretical value of Equation 8 and the DGPS measured value is relatively small.

The performance evaluation unit 300 compares the distance measured by the evaluation target AEB system 500 with the distance measured through the dual camera mounting positioning device 100 or the distance measurement unit 200, respectively, and compares the corresponding evaluation target AEB system Evaluate the performance of (500).

20 is an exemplary view of a scenario for distance measurement according to an embodiment of the present invention. A plurality of scenarios may be prepared.

When the vehicle drives according to a preset scenario as shown in FIG. 20 , the dual-camera positioning device detects a distance to an object and inputs the detected distance to the performance evaluation unit 300 .

In addition, the evaluation target AEB system 500 inputs the distance to the object measured according to the scenario to the performance evaluation unit 300 . Here, the distance to the object measured by the AEB system 500 to be evaluated may be previously stored in a database or mounted on a vehicle and measured.

The performance evaluation unit 300 detects an error by comparing distances input from the dual camera mounting positioning device 100 and the AEB system 500 to be evaluated.

Subsequently, the performance evaluation unit 300 may evaluate the performance of the corresponding evaluation target AEB system 500 based on the detected error.

Meanwhile, when the vehicle drives according to a preset scenario, the distance measurement unit 200 detects a distance to an object and inputs the detected distance to the performance evaluation unit 300 .

In addition, the evaluation target AEB system 500 inputs the distance to the object measured according to the scenario to the performance evaluation unit 300 . Here, the distance to the object measured by the AEB system 500 to be evaluated may be previously stored in a database or mounted on a vehicle and measured.

The performance evaluation unit 300 detects an error by comparing distances respectively input from the distance measurement unit 200 and the AEB system 500 to be evaluated.

Subsequently, the performance evaluation unit 300 may evaluate the performance of the corresponding evaluation target AEB system 500 based on the detected error.

At this time, the performance evaluation unit 300 may detect the maximum value, minimum value, and average value of the error for each scenario.

The evaluation result output unit 400 outputs the evaluation result of the performance evaluation unit 300 .

In this case, the evaluation result output unit 400 may output the maximum value, minimum value, and average value of error for each scenario.

Hereinafter, a performance evaluation method of an emergency braking system according to an embodiment of the present invention will be described in detail with reference to FIGS. 21 and 22 .

21 is a flowchart of a performance evaluation method of an emergency braking system according to an embodiment of the present invention.

Referring to FIG. 21 , first, the vehicle drives according to a preset scenario (S210).

At this time, the dual camera mounting positioning device 100 detects the distance to the object (S220), and the evaluation target AEB system 500 detects the distance to the object measured according to the scenario (S230).

The distance to the object measured by the dual camera-equipped positioning device 100 and the distance to the object detected by the AEB system 500 to be evaluated are input to the performance evaluation unit 300 .

The performance evaluation unit 300 compares the distances inputted from the dual camera mounting location determining device 100 and the evaluation target AEB system 500 (S240).

The performance evaluation unit 300 detects an error according to the comparison result, evaluates the performance of the AEB system 500 to be evaluated based on the error, and the evaluation result output unit 400 outputs the corresponding evaluation result (S250). ).

At this time, the performance evaluation unit 300 may detect the maximum value, minimum value, and average value of errors for each scenario, and evaluate the performance of the AEB system 500 to be evaluated based on them.

22 is a flowchart of a performance evaluation method of an emergency braking system according to an embodiment of the present invention.

Referring to FIG. 22 , first, the vehicle drives according to a preset scenario (S310).

At this time, the distance measuring unit 200 measures the distance to the object (S320), and the AEB system 500 to be evaluated detects the distance to the measured object according to the scenario (S330).

The distance to the object measured by the distance measurement unit 200 and the distance to the object detected by the AEB system 500 to be evaluated are input to the performance evaluation unit 300 .

The performance evaluation unit 300 compares the distance input from the distance measuring unit 200 and the AEB system 500 to be evaluated (S340).

The performance evaluation unit 300 detects an error according to the comparison result, evaluates the performance of the AEB system 500 to be evaluated based on the error, and the evaluation result output unit 400 outputs the evaluation result (S350). .

At this time, the performance evaluation unit 300 may detect the maximum value, minimum value, and average value of errors for each scenario, and evaluate the performance of the AEB system 500 to be evaluated based on them.

As described above, the performance evaluation apparatus and method of an emergency braking system according to an embodiment of the present invention enables performance evaluation of the AEB system 500 to be evaluated based on the distance calculated using the dual camera.

In addition, an apparatus and method for evaluating the performance of an emergency braking system according to an embodiment of the present invention provide a relative distance, an initial relative distance, an object speed, a target vehicle speed, a target relative distance, a time difference, a time difference between a target vehicle and an object, and a target vehicle. The distance to the object is measured using the time difference between and the object, and based on this, the performance of the AEB system 500 to be evaluated can be evaluated.

In addition, the apparatus and method for evaluating the performance of an emergency braking system according to an embodiment of the present invention can dramatically reduce the time, expenses, and expensive equipment and professional manpower required for a vehicle test in evaluating the safety of a finished vehicle.

In addition, the apparatus and method for evaluating the performance of the emergency braking system of the present invention can provide a theoretical basis for the degree of freedom of development and safety verification of parts developing companies or finished car companies.

Implementations described herein may be embodied in, for example, a method or process, an apparatus, a software program, a data stream, or a signal. Even if discussed only in the context of a single form of implementation (eg, discussed only as a method), the implementation of features discussed may also be implemented in other forms (eg, an apparatus or program). The device may be implemented in suitable hardware, software and firmware. The method may be implemented in an apparatus such as a processor, which is generally referred to as a processing device including, for example, a computer, microprocessor, integrated circuit or programmable logic device or the like. Processors also include communication devices such as computers, cell phones, personal digital assistants ("PDAs") and other devices that facilitate communication of information between end-users.

Although the present invention has been described with reference to the embodiments shown in the drawings, it should be noted that this is only exemplary and various modifications and equivalent other embodiments are possible from those skilled in the art to which the technology pertains. will understand Therefore, the true technical scope of protection of the present invention will be defined by the claims below.

10: camera 30: lane detection unit
31: region of interest setting unit 32: gray scale conversion unit
33: HSV format conversion unit 34: edge detection unit
35: filtering unit 36: lane recognition unit
40: image correction unit 41: image distortion removal unit
42: image rectification unit 43: focal length detection unit
50: mounting position determination unit 51: distance detection unit
52: error rate detection unit 53: variable adjustment unit
100: dual camera mounting positioning device
200: distance measurement unit 300: performance evaluation unit
400: evaluation result output unit 500: evaluation target AEB system

Claims (16)

A dual-camera-equipped positioning device that measures the distance to an object based on the dual-camera; and
A performance evaluation device for an emergency braking system comprising a performance evaluation unit that evaluates the performance of the AEB system to be evaluated by comparing the distance detected through the dual camera-equipped positioning device with the distance measured by the AEB system to be evaluated. The method of claim 1, wherein the performance evaluation unit
Evaluating the performance of the AEB system to be evaluated using an error between the distance detected through the dual camera-equipped positioning device and the distance measured by the AEB system to be evaluated for each preset scenario. performance evaluation device. The method of claim 2, wherein the performance evaluation unit
Evaluating the performance of the AEB system to be evaluated using at least one of the maximum value, the minimum value, and the average value of the error between the distance detected through the dual-camera mounting positioning device and the distance measured by the AEB system to be evaluated for each scenario Performance evaluation device of an emergency braking system, characterized in that. The apparatus for evaluating performance of an emergency braking system according to claim 1, further comprising an evaluation result output unit outputting an evaluation result of the performance evaluation unit. a distance measuring unit that measures the distance between the vehicle and the object using the initial relative distance of the object, the speed of the vehicle, and the speed of the object; and
A performance evaluation device for an emergency braking system comprising a performance evaluation unit that evaluates performance of the AEB system to be evaluated by comparing the distance measured through the distance measuring unit with the distance measured by the AEB system to be evaluated. The method of claim 5, wherein the distance measuring unit
Measure the distance between the vehicle and the object using the equation below,
The above formula is

is, where

is the relative distance,

is the initial relative distance,

is the speed of the preceding vehicle,

is the target vehicle speed, 0.2, 2.9, and 36.1 are correction parameters. The method of claim 5, wherein the performance evaluation unit
The performance evaluation device of the emergency braking system, characterized in that for each preset scenario, the performance of the AEB system to be evaluated is evaluated using an error between the distance measured through the distance measuring unit and the distance measured by the AEB system to be evaluated. The method of claim 7, wherein the performance evaluation unit
Characterized in that for each scenario, the performance of the AEB system to be evaluated is evaluated using at least one of a maximum value, a minimum value, and an average value of errors between the distance measured through the distance measurement unit and the distance measured by the AEB system to be evaluated. Performance evaluation device of emergency braking system. 6. The apparatus for evaluating performance of an emergency braking system according to claim 5, further comprising an evaluation result output unit outputting an evaluation result of the performance evaluation unit. Measuring a distance to an object based on the dual camera by the dual camera mounting positioning device; and
Evaluating the performance of the AEB system to be evaluated by a performance evaluation unit by comparing the distance detected through the dual camera-equipped positioning device with the distance measured by the AEB system to be evaluated. Performance evaluation method of the emergency braking system. The method of claim 10, wherein in the step of evaluating the performance of the AEB system to be evaluated,
The performance evaluation unit evaluates the performance of the AEB system to be evaluated by using an error between the distance detected through the dual-camera mounting positioning device for each preset scenario and the distance measured by the AEB system to be evaluated. Performance evaluation method of emergency braking system. The method of claim 11, wherein in the step of evaluating the performance of the AEB system to be evaluated,
The performance evaluation unit determines the AEB system to be evaluated by using at least one of the maximum value, the minimum value, and the average value of the error between the distance detected through the dual-camera mounting positioning device and the distance measured by the AEB system to be evaluated for each scenario. A performance evaluation method of an emergency braking system, characterized in that the performance is evaluated. measuring the distance between the vehicle and the object by a distance measurement unit using the initial relative distance of the object, the speed of the vehicle, and the speed of the object; and
Evaluating the performance of the AEB system to be evaluated by a performance evaluation unit by comparing the distance measured through the distance measuring unit with the distance measured by the AEB system to be evaluated. 14. The method of claim 13, wherein in the step of measuring the distance between the vehicle and the object by using the initial relative distance of the object, the speed of the vehicle, and the speed of the object by the distance measurer,
The distance measurement unit measures the distance between the vehicle and the object using the following equation,
The above formula is

is, where

is the relative distance,

is the initial relative distance,

is the speed of the preceding vehicle,

is the speed of the target vehicle, and 0.2, 2.9, and 36.1 are correction parameters. 14. The method of claim 13, wherein the performance evaluation unit
Evaluating the performance of the AEB system to be evaluated using an error between the distance measured through the distance measurement unit and the distance measured by the AEB system to be evaluated for each preset scenario. 15. The method of claim 14, wherein the performance evaluation unit
Characterized in that for each scenario, the performance of the AEB system to be evaluated is evaluated using at least one of a maximum value, a minimum value, and an average value of errors between the distance measured through the distance measurement unit and the distance measured by the AEB system to be evaluated. Performance evaluation method of emergency braking system.

Images