KR20180064775A - Driving Support Apparatus Of Vehicle And Driving Method Thereof - Google Patents

Abstract

The present invention relates to a driving support apparatus for a vehicle and a driving method thereof for preventing errors and failures of image detection by pitch motion. A driving support apparatus for a vehicle according to an embodiment of the present invention includes a camera, a radar, a region-of-interest setting unit, an object detecting unit, an image correction unit, and a control unit. The radar detects the distance between one or more objects in front of the vehicle and the vehicle in real time and generates distance information on a frame-by-frame basis. Then, the camera captures a forward image in real time to generate a first image in frame units. Then, the ROI setting unit converts the distance information of the first frame into a second image, and sets the ROI based on the first image and the second image of the first frame. Then, the object detecting unit detects a plurality of objects located in the area of interest. Then, the pitch motion detecting unit detects the pitch motion according to the change of the vehicle speed and altitude. The image correction unit corrects the first image of the second frame based on the reference point difference between the first image and the second image of the first frame when the pitch motion occurs. And controls the speed, steering, and damper of the vehicle based on the first image of the corrected second frame.

Description

Technical Field [0001] The present invention relates to a driving support apparatus for a vehicle,

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a driving support apparatus for a vehicle and a driving method thereof, and more particularly, to a driving support apparatus for a vehicle and a driving method thereof, which prevent errors and failures of image detection by pitch motion.

If an unexpected situation occurs while driving the vehicle, the driver's cognitive ability is significantly lowered, leading to traffic accidents. In order to reduce traffic accidents caused by an unexpected situation, technologies for detecting the situation on the road have been proposed. For example, a technique has been proposed in which a radar apparatus is used to detect an object, and an identifier is assigned and mapped to the detected object as a whole to detect a preceding object.

When the vehicle decelerates or accelerates, or passes over the overspeed preventing jaw, a pitch motion occurs in which the vehicle body of the vehicle moves up and down. When the vehicle is running, the camera and the radar are used to provide the driver with images of the preceding vehicle, object, and pedestrian. However, in the conventional technique, an image due to the pitch motion is generated by detecting the same image without distinguishing the general running situation from the pitch motion situation.

In particular, pitch motion causes errors or failures in lane, vehicle and pedestrian detection, which in turn affects safety. Therefore, there is a demand for a driving support apparatus for a vehicle and a driving method thereof that can prevent an image detection error and failure by correcting an image in consideration of pitch motion.

Korean Patent Publication No. 10-2014-0123270 (Object Detection Device, Method and System Using Radar Device and Image Mapping)

The inventors of the present application detect the aforementioned problems and propose the following technical problems.

SUMMARY OF THE INVENTION It is an object of the present invention to provide a driving support apparatus for a vehicle and a driving method thereof, which prevent errors or failures of image detection by pitch motion.

It is another object of the present invention to provide a driving support apparatus for a vehicle capable of detecting an image by pitch motion using a radar and a camera, and a driving method thereof.

Another object of the present invention is to provide a driving support apparatus for a vehicle and a driving method thereof that can control a speed, a steering, and a damper of a vehicle by correcting an image in which an error occurs due to pitch motion.

Another object of the present invention is to provide a driving support apparatus and a driving method thereof for a vehicle that provides safety to a driver even when pitch motion occurs.

Other features and advantages of the invention will be set forth in the description which follows, or may be obvious to those skilled in the art from the description and the claims.

A driving support apparatus for a vehicle according to an embodiment of the present invention includes a camera, a radar, a region-of-interest setting unit, an object detecting unit, a pitch motion detecting unit, an image correcting unit, and a control unit. The radar detects the distance between one or more objects in front of the vehicle and the vehicle in real time and generates distance information on a frame-by-frame basis. Then, the camera captures a forward image in real time to generate a first image in frame units. Then, the ROI setting unit converts the distance information of the first frame into a second image, and sets the ROI based on the first image and the second image of the first frame. Then, the object detecting unit detects a plurality of objects located in the area of interest. Then, the pitch motion detecting unit detects the pitch motion according to the change of the vehicle speed and altitude. The image correction unit corrects the first image of the second frame based on the reference point difference between the first image and the second image of the first frame when the pitch motion occurs. The control unit then controls the speed, steering, and damper of the vehicle based on the first image of the corrected second frame.

Further, the running support apparatus of a vehicle according to the embodiment of the present invention detects a reference point difference between the first image and the second image of the first frame, and detects the pitch motion based on the reference point difference.

Further, a travel support apparatus for a vehicle according to an embodiment of the present invention calculates a distance between a plurality of objects and a vehicle in the first frame.

In addition, the running support apparatus of a vehicle according to the embodiment of the present invention corrects the first image of the second frame based on an object closest to the child of the plurality of objects.

Further, the running support apparatus of a vehicle according to an embodiment of the present invention calculates a reference point difference between the first image and the second image for each of a plurality of objects in the first frame, Correct the image based on the largest object.

The driving support method of a vehicle according to an embodiment of the present invention includes a step of photographing forward in real time to generate a first image in frame units. And generating distance information on a frame-by-frame basis by detecting a distance between one or more objects ahead of the vehicle and the vehicle in real time. And converting the distance information of the first frame to a second image and setting a region of interest based on the first image and the second image of the first frame. And detecting a plurality of objects located in the area of interest. And detecting pitch motion in accordance with a change in the speed and altitude of the vehicle. And correcting the first image of the second frame based on the reference point difference of the first image and the second image of the first frame when the pitch motion occurs. And controlling the speed, steering and damper of the vehicle based on the first image of the corrected second frame.

According to another aspect of the present invention, there is provided a method of supporting a running of a vehicle, the method comprising the steps of: detecting pitch motion; detecting a reference point difference between a first image and a second image of the first frame; Motion is detected.

In the driving support method of a vehicle according to the embodiment of the present invention, in the step of setting the ROI, a distance between a plurality of objects and a vehicle is calculated in the first frame.

Further, in a method of supporting a running of a vehicle according to an embodiment of the present invention, in the image correcting step, a first image of a second frame is corrected based on an object closest to the vehicle among the plurality of objects.

According to another aspect of the present invention, there is provided a method of supporting a running of a vehicle, the method comprising: calculating a reference point difference between the first image and the second image for each of a plurality of objects in the first frame, An image is corrected on the basis of an object having the largest reference point difference among the plurality of objects.

A driving support apparatus and a driving method of a vehicle according to an embodiment of the present invention detect a distance between an object and a vehicle in front of a first image generated in real time on a frame by frame basis, 2 image, and set the region of interest using the first image and the second image.

In addition, the driving support apparatus and the driving method of the vehicle according to the embodiment of the present invention can detect a plurality of objects located in a region of interest and know the position of the vehicle and the pedestrian in front.

In addition, the driving support apparatus and the driving method of the vehicle according to the embodiment of the present invention calculate the reference point difference between the camera image and the radar image when the pitch motion occurs in the first frame, The camera image of the second frame can be corrected.

In addition, the driving support device and the driving method of the vehicle according to the embodiment of the present invention can control the speed, steering and damper of the vehicle based on the image of the camera in the next frame, and even if pitch motion occurs, Can provide safety to the user.

In addition, the driving support apparatus and the driving method of the vehicle according to the embodiments of the present invention control the speed, steering, and damper of the vehicle based on the closest object among a plurality of objects when detecting an image according to the pitch motion , It is possible to provide the driver with a sense of stability even when the pitch motion occurs.

The driving support device and the driving method of the vehicle according to the embodiment of the present invention may be applied to a driving support device and a driving method of the vehicle according to an embodiment of the present invention in which a speed difference between a first image of a camera and a second image of a radar, So that it is possible to provide the driver with a sense of stability even when the pitch motion occurs.

1 is a view showing a driving support apparatus for a vehicle according to an embodiment of the present invention
2A and 2B are diagrams illustrating a method of detecting a region of interest in front of a vehicle to detect pitch motion.
3A and 3B are diagrams illustrating a method of detecting a pitch motion state according to the running of a vehicle according to an embodiment of the present invention.
4A and 4B are views showing a method of correcting an image of a driving support system for a vehicle according to an embodiment of the present invention.
5 is a diagram illustrating a driving method of a driving support apparatus for a vehicle according to an embodiment of the present invention.

Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings, which will be readily apparent to those skilled in the art to which the present invention pertains. The present invention may be embodied in many different forms and is not limited to the embodiments described herein.

In order to clearly illustrate the present invention, parts not related to the description are omitted, and the same or similar components are denoted by the same reference numerals throughout the specification.

Throughout the specification, when a part is referred to as being "connected" to another part, it includes not only "directly connected" but also "electrically connected" with another part in between . Also, when an element is referred to as "comprising ", it means that it can include other elements as well, without departing from the other elements unless specifically stated otherwise.

If any part is referred to as being "on" another part, it may be directly on the other part or may be accompanied by another part therebetween. In contrast, when a section is referred to as being "directly above" another section, no other section is involved.

The terms first, second and third, etc. are used to describe various portions, components, regions, layers and / or sections, but are not limited thereto. These terms are only used to distinguish any moiety, element, region, layer or section from another moiety, moiety, region, layer or section. Thus, a first portion, component, region, layer or section described below may be referred to as a second portion, component, region, layer or section without departing from the scope of the present invention.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the invention. Here, the singular forms used include plural forms as long as the phrases do not expressly mean the opposite. Means that a particular feature, region, integer, step, operation, element and / or component is specified and that the presence or absence of other features, regions, integers, steps, operations, elements, and / It does not exclude addition.

Terms indicating relative space such as "below "," above ", and the like may be used to more easily describe the relationship to other portions of a portion shown in the figures. These terms are intended to include other meanings or acts of the apparatus in use, as well as intended meanings in the drawings. For example, when inverting a device in the figures, certain parts that are described as being "below" other parts are described as being "above " other parts. Thus, an exemplary term "below" includes both up and down directions. The device can be rotated by 90 degrees or rotated at different angles, and terms indicating relative space are interpreted accordingly.

Unless otherwise defined, all terms including technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Commonly used predefined terms are further interpreted as having a meaning consistent with the relevant technical literature and the present disclosure, and are not to be construed as ideal or very formal meanings unless defined otherwise.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily carry out the present invention. The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein.

1 is a view showing an example of a travel support apparatus for a vehicle according to an embodiment of the present invention.

1, a driving support apparatus 100 for a vehicle according to an embodiment of the present invention includes a radar 110, a camera 120, a velocity sensor 130, a ROI setting unit 140, an object detecting unit 150 A pitch motion detection unit 160, an image correction unit 170, and a control unit 180.

The radar 110 detects the distance between one or more objects ahead of the vehicle and the vehicle in real time and generates distance information on a frame-by-frame basis. The distance information generated by the radar 110 is supplied to the ROI setting unit 140.

The camera 120 takes a forward view in real time and generates a first image in frame units. When shooting a vehicle or pedestrian ahead, the data of one frame is the image. The first image obtained by the camera 120 is supplied to the region-of-interest setting unit 140. [

The speed sensor 130 detects a speed change of the vehicle and generates a speed signal based on the speed change. The velocity signal generated by the velocity sensor 130 is supplied to the pitch motion detector 160.

The region-of-interest setting unit 140 converts the distance information of the first frame into a second image, and sets the region of interest based on the first image and the second image of the first frame.

Here, the image from the camera 120 and the distance information from the radar 110 are converted into an image based on Equation (1) and Equation (2), and the ROI is set based on the converted image. Then, the set object region is supplied to the object detection unit 150.

로 이루어진 좌표계를 하기의 수학식 1에 기초하여 영상 좌표계로 변환한다.Specifically, the radar 110

Is converted into an image coordinate system based on the following expression (1).

[Equation 1]

In Equation (1), "x" is the position in front of the vehicle and "y" is the width of the object in front.

The position of the front position (x), the altitude (z), and the left and right direction (y) is converted into the image coordinate system based on the above equation (1). Then, the converted image coordinate system is converted into image coordinates based on the following equation (2). In this case, it is assumed that the altitude direction z in the following equation (2) is "zero ".

&Quot; (2) "

&Quot; R "is a determinant for converting radar distance information into a determinant, and" T "is a determinant for converting distance information into an image. "P" means a result obtained by converting the images into K, R and T based images.

The image P of the radar is generated by calculating the intrinsic parameter K, the distance R and the stereoscopic transformation T. [ The image coordinates (U) can be generated by converting the image (P) of the radar into the world coordinates (W). The method of generating the image coordinates U will be described with reference to the description of the image corrector 170. [

2A and 2B are diagrams showing a process of detecting a region of interest in front of the vehicle to detect pitch motion.

)에 물체의 높이(H)를 곱하여 얻은 결과 값을 거리(d)로 나누어 자차(210)로부터 일정 거리(d)에 위치하는 차량의 높이(H)를 산출한다. 물체의 높이(H)는 차량 시 대략 1m에서 3m 내외이고, 보행자 시 대략 0.8m에서 2m내외이다. 도 2b를 참조하면, 전방 물체(220)의 너비를 y축으로 두고 상기 수학식 2를 기초로 레이더(110)의 너비(

)에 전방 물체(220)의 너비(W2) 곱한다. 그리고, 거리(d)를 나눈 값을 픽셀로 변환한 너비(W1)를 산출한다. 전방 물체(220)의 너비(W2)는 차량 시 대략 1.5m에서 2.5m내외이고, 보행자 시 대략 0.5m에서 1.5m내외이다.2A, the distance of an object ahead is set as the x-axis, and the length of the radar 110 (

The vehicle height H is calculated by dividing the resultant value obtained by multiplying the vehicle height H by the height H of the object by the distance d. The height (H) of the object is about 3m to about 3m at the time of the vehicle, and about 2m to about 0.8m at the pedestrian. Referring to FIG. 2B, the width of the front object 220 is set to the y-axis, and the width of the radar 110

) By the width W2 of the front object 220. Then, the width W1 obtained by converting the value obtained by dividing the distance d into pixels is calculated. The width W2 of the front object 220 is about 1.5 m to 2.5 m in the vehicle, and about 0.5 m to about 1.5 m in the pedestrian.

The object detecting unit 150 detects a plurality of objects located in the area of interest. Then, the first image and the second image of the first frame for a plurality of objects located in the ROI are supplied to the pitch motion detector 160.

Further, the object detecting unit 150 calculates distances between the plurality of objects and the vehicle in the first frame, and detects the object closest to the first frame. A method of detecting an object closest to the vehicle will be described with reference to the description of the image correcting unit 170. [

Here, the plurality of objects are a plurality of vehicles and pedestrians present in the front. In the actual situation, there is at least one object ahead. At least one of the vehicles and the pedestrian may not move at the same speed.

The pitch motion detecting unit 160 detects a pitch motion according to the vehicle speed and the altitude change based on the first image and the second image of the first frame supplied from the object detecting unit 150. [ Then, the pitch motion result of the first frame is supplied to the image correcting unit 170.

Here, the pitch motion is a case where the top and bottom of the vehicle change. As a kind of pitch motion, there are largely an altitude change due to a change in the speed of the vehicle and an altitude change that occurs when passing the speed limit bust. And detects a pitch motion in which the upper and lower portions of the vehicle body move relative to the overspeed preventing jaw. Further, based on the speed signal detected from the speed sensor 130, it is possible to detect pitch motion in which the vehicle body moves up and down with respect to the speed change of the vehicle.

If the vehicle is moving up and down, the image or image acquired from the camera also flows up and down, but the image from the front acquired from the radar does not flow up and down. Therefore, when the vehicle decelerates, accelerates, or crosses the overspeed prevention threshold, the vehicle is caused to flow up and down to cause a difference between the reference point of the first image obtained in the camera and the reference point of the second image obtained in the radar.

Specifically, the pitch motion detector 160 detects a reference point difference between the first image of the camera 120 and the second image of the radar 110. For example, when pitch motion occurs in which the vehicle is shaken up and down as it passes the speed bump, the second image of the radar 110 in the vehicle is detected regardless of the pitch motion. However, when pitch motion occurs in which the vehicle is shaken up and down as it passes through the speed braking chisl, the first image of the camera changes. When the difference between the first image of the camera and the second image of the radar is generated in all the objects, it is judged as the pitch motion.

On the other hand, when the reference point difference of the first image of the camera and the second image of the radar generates only a specific object and there is no change of the reference point difference of the other objects, a state other than the pitch motion of the vehicle, pitch motion).

Here, when the reference point difference of the first image of the camera and the second image of the radar occurs, the pitch motion detecting unit 160 detects the reference point difference of the first image of the camera and the second image of the radar, It is detected that a motion has occurred. Then, the detection result of the pitch motion is supplied to the image correcting unit 170.

On the other hand, the pitch motion detecting unit 160 detects non-pitch motion when the reference point difference of the first image and the second image does not occur in all of the plurality of objects or occurs in some objects. Then, the detection result of the non-pitch motion is supplied to the image correction unit 170. [

3A and 3B are diagrams illustrating a pitch motion state detection process according to the running of a vehicle according to an embodiment of the present invention.

Referring to FIG. 3A, a first position 310 of the first object included in the first image and a first position 340 of the first object included in the second image are detected. Then, a difference d1 between the first position 310 detected in the first image and the first position 340 detected in the second image is detected. That is, the distance difference d1 between the vehicle and the first object is detected by overlapping the first image and the second image.

It also detects the second position 320 of the second object contained in the first image and the second position 350 of the second object contained in the second image. Then, a difference d2 between the second position 320 detected in the first image and the second position 350 detected in the second image is detected. That is, the first image and the second image are overlapped to detect the distance difference d2 between the vehicle and the second object.

It also detects the third position 330 of the third object contained in the first image and the third position 360 of the third object contained in the second image. Then, a difference d3 between the third position 330 detected in the first image and the third position 360 detected in the second image is detected. That is, the first image and the second image are overlapped to detect the distance difference d3 between the vehicle and the third object. In the present invention, a first distance difference d1, a second distance difference d2, and a third distance difference d3 between the first image and the second image are defined as reference point differences. In this way, when all of the reference point differences occur in a plurality of objects (e.g., the first object, the second object, and the third object), the pitch motion of the vehicle is determined.

Referring to FIG. 3B, when a reference point difference occurs in the first object among the plurality of objects, and a reference point difference does not occur in the second object and the third object, the non-pitch motion of the vehicle is determined.

Referring again to FIG. 1, the image correcting unit 170 corrects the first image of the second frame based on the reference point difference between the first image and the second image of the first frame, when the pitch motion occurs. On the other hand, if it is determined as non-pitch motion, the first image of the second frame is not corrected.

Here, the first image of the second frame corrects the first image of the first frame of the reference point difference due to the pitch motion. That is, the first image of the second frame is corrected based on the reference point difference between the first image of the first frame and the second image when the pitch motion occurs.

Specifically, the first image can be corrected by the following method. (P) of the radar calculated on the basis of Equation (2) into the world coordinate (W) to generate the image coordinate (U). When the pitch motion is detected, the image correcting unit 170 corrects the image coordinates U and converts the image into the first image of the second frame. When the pitch motion detecting unit 160 detects non-pitch motion with reference to the image coordinates U, the image correcting unit 170 does not transform the image coordinates U. That is, the first image of the second frame is not corrected.

As an example, the amount of pixel change due to pitch motion in an image is indicated by coordinates. (Z) with respect to the front object distance (x) with respect to the altitude direction (z) using the following expression (3).

&Quot; (3) "

? Z = x * tan (L)

In Equation (3), L is a tilt angle of the altitude direction (z) with respect to the front object distance (x).

Then, the pitch variation amount? V in the image is detected using the following expression (4). The pitch change amount? V is detected by dividing the resultant value obtained by multiplying the sensor length f by the pixel change amount? Z by the forward object distance x. Then, the first image of the second frame is corrected using the detected pitch variation amount? V.

&Quot; (4) "

? V = f *? Z / x = f * tan (L)

4A and 4B are views showing a method of correcting an image of a driving support apparatus for a vehicle according to an embodiment of the present invention.

Referring to FIG. 4A, when a pitch motion occurs, the vehicle is designated as the origin, and the pixel variation amount? Z is converted into a two-dimensional graph based on the forward object distance x on the basis of the elevation z.

Next, referring to FIG. 4B, the pixel change amount? Z is converted into an image coordinate system and converted into a pitch change amount? V in the image.

When the distance between the car and the object is different, when the pitch motion occurs, the image change of the object closest to the car is the largest. Therefore, in the present invention, the object having the greatest reference point difference can be determined as the object closest to the vehicle.

The image correcting unit 170 corrects the first image of the second frame on the basis of the object closest to the child of the plurality of objects included in the region of interest.

In addition, the image correcting unit 170 may calculate the reference point difference between the first image and the second image for each of the plurality of objects in the first frame, and determine, based on the object having the largest reference point difference among the plurality of objects, The first image of the frame can be corrected. Here, the largest reference point difference means that the altitude difference of the vehicle, the object, or the pedestrian for the preceding vehicle or the change of the distance difference is large.

Then, the control unit 180 controls the speed, steering, and damper of the vehicle based on the first image of the second frame generated by the image correcting unit 170 and copes with the unexpected situation. For example, when a child (pedestrian) moves forward in the pitch motion due to the speed limit of the road around the school, the controller 180 controls the pitch motion Supports driving assistance even in situations and supports safety for young children (pedestrians) and drivers.

In this manner, the speed, steering, and damper of the vehicle can be controlled by coping with an unexpected situation at the pitch motion of the vehicle based on the object closest to the vehicle. This makes it possible to secure the safety of the car, the front vehicle, and the pedestrian. In addition, by correcting the first image of the second frame on the basis of the object with the largest reference point difference, coping with the unexpected situation in the pitch motion of the vehicle can secure safety during traveling.

The apparatus for supporting travel of a vehicle according to an embodiment of the present invention sets a region of interest using a first image of a camera and a second image of a radar, detects a plurality of objects located in a region of interest, The position of the pedestrian can be known.

The apparatus for supporting travel of a vehicle according to an embodiment of the present invention calculates a reference point difference between a camera image and a radar image when a pitch motion occurs in a first frame, It is possible to correct the camera image of two frames.

In addition, when detecting an image according to the pitch motion, the running support apparatus of a vehicle according to an embodiment of the present invention controls the speed, steering, and damper of the vehicle based on the closest object among a plurality of objects, It is possible to provide a sense of stability to the driver even if it occurs.

In addition, the driving support apparatus for a vehicle according to an embodiment of the present invention controls a speed, a steering, and a damper of a vehicle based on an object having a largest reference point difference between a first image of the camera and a second image of the radar, It is possible to provide the driver with a sense of stability even when motion occurs.

5 is a diagram illustrating a driving method of a driving support apparatus for a vehicle according to an embodiment of the present invention. Hereinafter, a driving support method of a vehicle according to an embodiment of the present invention will be described with reference to FIGS. 1 to 5. FIG.

The camera 120 takes a forward view in real time and generates a first image in frame units. Then, the radar 110 detects the distance between one or more objects in front of the vehicle and the vehicle, and generates distance information on a frame-by-frame basis (S1). At this time, the camera 120 generates a first image in units of frames, and the radar 110 also generates distance information in units of frames. The first image generated by the camera 120 and the distance information generated by the radar 110 are supplied to the ROI setting unit 140.

Then, the speed sensor 130 detects a speed change of the vehicle and generates a speed signal based on the change in speed (S2). The velocity signal generated by the velocity sensor 130 is supplied to the pitch motion detector 160.

Then, the region-of-interest setting unit 140 converts the distance information of the first frame into a second image, and sets the region of interest based on the first image and the second image of the first frame (S3). The region of interest set by the region-of-interest setting unit 140 is supplied to the object-detecting unit 150.

로 이루어진 좌표계를 상기 수학식 1에 기초하여 영상 좌표계로 변환한다. 이후, 영상 좌표계를 상기 수학식 2에 이용하여 영상 좌표로 변환한다. 이때, 상기 수학식 2에서 고도 방향(z)은 0(zero)인 것으로 가정한다.A method of setting an area of interest based on Equation (2) will be described in detail. The radar 110 uses an image coordinate system.

Is converted into an image coordinate system based on Equation (1). Then, the image coordinate system is transformed into the image coordinates using Equation (2). In this case, it is assumed that the altitude direction (z) in Equation (2) is zero.

The image P of the radar is generated by calculating the intrinsic parameter K, the distance R and the stereoscopic transformation T. [

)에 물체의 높이(H)를 곱하여 얻은 결과 값을 거리(d)로 나누어 자차(210)로부터 일정 거리(d)에 위치하는 차량의 높이(H)를 산출한다. 한편, 물체의 높이(H)는 차량 시 대략 1m에서 3m 내외이고, 보행자 시 대략 0.8m에서 2m내외이다. 도 2b를 참조하면, 전방 물체(220)의 너비를 y축으로 두고 상기 수학식 2를 기초로 레이더(110)의 너비(

)에 전방 물체(220)의 너비(W2) 곱한다. 그리고, 거리(d)를 나눈 값을 픽셀로 변환한 너비(W1)를 산출한다. 전방 물체(220)의 너비(W2)는 차량 시 대략 1.5m에서 2.5m내외이고, 보행자 시 대략 0.5m에서 1.5m내외이다.2, the distance of the front object is set as the x-axis, and the length of the radar 110 (

The vehicle height H is calculated by dividing the resultant value obtained by multiplying the vehicle height H by the height H of the object by the distance d. On the other hand, the height (H) of the object is about 3m to about 1m at the time of the vehicle, and about 2m to about 0.8m at the time of the pedestrian. Referring to FIG. 2B, the width of the front object 220 is set to the y-axis, and the width of the radar 110

) By the width W2 of the front object 220. Then, the width W1 obtained by converting the value obtained by dividing the distance d into pixels is calculated. The width W2 of the front object 220 is about 1.5 m to 2.5 m in the vehicle, and about 0.5 m to about 1.5 m in the pedestrian.

The object detecting unit 150 detects a plurality of objects located in the ROI based on the ROI detected by the ROI setting unit 140 (S4). The detected first and second images are supplied to the pitch motion detecting unit 160.

Further, the object detecting unit 150 calculates the distance between the plurality of objects and the vehicle, and detects an object closest to the vehicle in the first frame, based on the distance between the vehicle and the plurality of objects.

Here, the plurality of objects are a plurality of vehicles and pedestrians present in the front. In the actual situation, there is at least one object ahead. At least one of the vehicles and the pedestrian may not move at the same speed.

Next, the pitch motion detector 160 detects the pitch motion according to the velocity and altitude of the vehicle based on the first image and the second image supplied from the object detector 150 (S5).

As a kind of pitch motion, there is an altitude change due to a change in the speed of the vehicle and an altitude change that occurs when the speed exceeds the speed limit bust. And detects a pitch motion in which the upper and lower portions of the vehicle body move relative to the overspeed preventing jaw. Further, based on the speed signal detected from the speed sensor 130, it is possible to detect pitch motion in which the vehicle body moves up and down with respect to the speed change of the vehicle.

Specifically, the pitch motion detector 160 detects a reference point difference between the first image of the camera 120 and the second image of the radar 110. For example, when pitch motion occurs in which the vehicle is shaken up and down as it passes the speed bump, the second image of the radar 110 in the vehicle is detected regardless of the pitch motion. However, when pitch motion occurs in which the vehicle is shaken up and down as it passes through the speed braking chisl, the first image of the camera changes. When the difference between the first image of the camera and the second image of the radar is generated in all the objects, it is judged as the pitch motion.

On the other hand, when the reference point difference of the first image of the camera and the second image of the radar generates only a specific object and there is no change of the reference point difference of the other objects, a state other than the pitch motion of the vehicle, pitch motion).

Here, when the reference point difference of the first image of the camera and the second image of the radar occurs, the pitch motion detecting unit 160 detects the reference point difference of the first image of the camera and the second image of the radar, It is detected that a motion has occurred. Then, the detection result of the pitch motion is supplied to the image correcting unit 170.

On the other hand, the pitch motion detecting unit 160 detects non-pitch motion when the reference point difference of the first image and the second image does not occur in all of the plurality of objects or occurs in some objects. Then, the detection result of the non-pitch motion is supplied to the image correction unit 170. [

Referring to FIG. 3A, a first position 310 of the first object included in the first image and a first position 340 of the first object included in the second image are detected. Then, a difference d1 between the first position 310 detected in the first image and the first position 340 detected in the second image is detected. That is, the distance difference d1 between the vehicle and the first object is detected by overlapping the first image and the second image.

It also detects the second position 320 of the second object contained in the first image and the second position 350 of the second object contained in the second image. Then, a difference d2 between the second position 320 detected in the first image and the second position 350 detected in the second image is detected. That is, the first image and the second image are overlapped to detect the distance difference d2 between the vehicle and the second object.

It also detects the third position 330 of the third object contained in the first image and the third position 360 of the third object contained in the second image. Then, a difference d3 between the third position 330 detected in the first image and the third position 360 detected in the second image is detected. That is, the first image and the second image are overlapped to detect the distance difference d3 between the vehicle and the third object. In the present invention, a first distance difference d1, a second distance difference d2, and a third distance difference d3 between the first image and the second image are defined as reference point differences. In this way, when all of the reference point differences occur in a plurality of objects (e.g., the first object, the second object, and the third object), the pitch motion of the vehicle is determined.

Referring to FIG. 3B, when a reference point difference occurs in the first object among the plurality of objects, and a reference point difference does not occur in the second object and the third object, the non-pitch motion of the vehicle is determined.

When the pitch motion is detected in S5, that is, when the difference between the first image and the second image is detected in all of the plurality of objects, it is determined that pitch motion has occurred. The detected pitch motion generation information is supplied to the image correction unit 170.

Next, in the pitch motion detection, the image correcting unit 170 corrects the first image of the second frame based on the reference point difference between the first image and the second image of the first frame (S6).

(P) of the radar calculated on the basis of Equation (2) into the world coordinate (W) to generate the image coordinate (U). When the pitch motion is detected, the image correcting unit 170 corrects the image coordinates U and converts the image into the first image of the second frame. When the pitch motion detecting unit 160 detects non-pitch motion with reference to the image coordinates U, the image correcting unit 170 does not transform the image coordinates U. That is, the first image of the second frame is not corrected.

As an example, the amount of pixel change due to pitch motion in an image is indicated by coordinates. Using the above equation (3), the pixel variation amount? Z with respect to the front object distance (x) is detected based on the altitude direction (z).

Next, the pitch variation amount? V in the image is detected using the equation (4). The pitch change amount? V is detected by dividing the resultant value obtained by multiplying the sensor length f by the pixel change amount? Z by the forward object distance x. . Then, the first image of the second frame is corrected using the detected pitch variation amount? V.

4A, when the pitch motion occurs, the vehicle is designated as the origin, and the pixel variation amount? Z is converted into a two-dimensional graph based on the forward object distance x on the basis of the altitude z .

Next, referring to FIG. 4B, the pixel change amount? Z is converted into an image coordinate system and converted into a pitch change amount? V in the image.

When the distance between the car and the object is different, when the pitch motion occurs, the image change of the object closest to the car is the largest. Therefore, in the present invention, the object having the greatest reference point difference can be determined as the object closest to the vehicle.

On the other hand, if the reference point difference occurs in the first object among the plurality of objects and the reference point difference does not occur in the second and third objects, the non-pitch motion of the vehicle is determined.

Subsequently, the image correcting section 170 converts the first image of the second frame based on the pitch motion detected at S6. On the other hand, if it is determined that the motion is non-pitch motion, the first image of the second frame is not corrected (S7).

The first image can be corrected by the following method. (P) of the radar calculated on the basis of Equation (2) into the world coordinate (W) to generate the image coordinate (U). When the pitch motion is detected, the image correcting unit 170 corrects the image coordinates U and converts the image into the first image of the second frame. When the pitch motion detecting unit 160 detects non-pitch motion with reference to the image coordinates U, the image correcting unit 170 does not transform the image coordinates U. That is, the first image of the second frame is not corrected.

When the distance between the car and the object is different, when the pitch motion occurs, the image change of the object closest to the car is the largest. Therefore, in the present invention, the object having the greatest reference point difference can be determined as the object closest to the vehicle. The image correcting unit 170 corrects the first image of the second frame on the basis of the object closest to the child of the plurality of objects included in the region of interest.

In addition, the image correcting unit 170 may calculate the reference point difference between the first image and the second image for each of the plurality of objects in the first frame, and determine, based on the object having the largest reference point difference among the plurality of objects, The first image of the frame can be corrected. Here, the largest reference point difference means that the altitude difference of the vehicle, the object, or the pedestrian for the preceding vehicle or the change of the distance difference is large.

Then, the control unit 180 controls the speed, steering, and damper of the vehicle based on the first image of the second frame corrected by the image correcting unit 170 (S8). Steering and damper of the vehicle are controlled by the controller 180 supplied with the first image of the second frame at the time of pitch motion detection and a method of controlling the controller 180 supplied with the image at the non- , The way to control the speed, steering and damper of a vehicle can cope with an unexpected situation. For example, when a child (pedestrian) detects an image based on the radar 110 and the camera 120 in front of a child in a pitch motion situation due to a speed limit of the road around the school, Supports driving assistance even in the case of motion and supports safety for young children (pedestrians) and drivers.

In this manner, the speed, steering, and damper of the vehicle can be controlled by coping with an unexpected situation at the pitch motion of the vehicle based on the object closest to the vehicle. This makes it possible to secure safety when driving the vehicle. Further, if the first image of the second frame is corrected based on the object having the largest difference of the reference point, and the unexpected situation occurs during the pitch motion of the vehicle, safety can be secured when driving the vehicle. A driving method of a driving support device for a vehicle according to an embodiment of the present invention sets a region of interest using a first image of a camera and a second image of a radar and detects a plurality of objects located in a region of interest The position of the vehicle and the pedestrian of the vehicle can be known.

According to another aspect of the present invention, there is provided a method of driving a driving support apparatus for a vehicle, the method comprising: calculating a reference point difference between a camera image and a radar image when a pitch motion occurs in a first frame; The camera image of the second frame can be corrected.

In the driving method of a driving support device for a vehicle according to an embodiment of the present invention, when an image according to a pitch motion is detected, speed, steering, and damper of the vehicle are controlled based on the closest object among a plurality of objects It is possible to provide the driver with a sense of stability even when the pitch motion occurs.

In addition, the driving method of a driving support device for a vehicle according to an embodiment of the present invention is a method for driving a driving support device for a vehicle, including a speed, a steering and a damper of a vehicle based on an object having a largest difference between a first image of the camera and a second image of the radar It is possible to provide the driver with a sense of stability even if the pitch motion occurs.

It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the present invention as defined by the following claims and their equivalents. Only. The scope of the present invention is defined by the appended claims rather than the detailed description and all changes or modifications derived from the meaning and scope of the claims and their equivalents are to be construed as being included within the scope of the present invention do.

110: Radar
120: camera
130: Speed sensor
140: Interest area setting section
150: Object detection unit
160: pitch motion detector
170: image correction unit
180:
210: Car
220: forward object
310: first position of the first object
320: second position of the second object
330: Third position of the third object
340: first position of the first object
350: second position of the second object
360: Third position of the third object

Claims (10)

A radar for detecting a distance between at least one object ahead of the vehicle and the vehicle in real time and generating distance information on a frame-by-frame basis;
A camera for capturing a forward image in real time to generate a first image in frame units;
Converts the distance information of the first frame into a second image,
A region of interest setting unit that sets a region of interest based on the first image and the second image of the first frame;
An object detecting unit that detects a plurality of objects located in the ROI;
A pitch motion detector for detecting a pitch motion according to a change in vehicle speed and altitude;
An image correcting unit correcting a first image of a second frame based on a reference point difference between the first image and the second image of the first frame when the pitch motion occurs;
And a controller for controlling a speed, a steering, and a damper of the vehicle based on the first image of the corrected second frame. The apparatus of claim 1, wherein the pitch motion detector comprises:
Detecting a reference point difference between the first image and the second image of the first frame, and detecting the pitch motion based on the reference point difference. The apparatus according to claim 1,
And calculates the distance between the plurality of objects and the vehicle in the first frame. The image processing apparatus according to claim 3,
And corrects the first image of the second frame based on an object closest to the vehicle among the plurality of objects. The image processing apparatus according to claim 1,
Calculating a reference point difference between the first image and the second image for each of a plurality of objects in the first frame,
And corrects the image based on an object having the largest reference point difference among the plurality of objects. Capturing a forward image in real time to generate a first image in frame units;
Detecting distance between at least one object ahead and a vehicle in real time and generating distance information on a frame basis;
Converting the distance information of the first frame to a second image, and setting a region of interest based on the first image and the second image of the first frame;
Detecting a plurality of objects located in the region of interest;
Detecting pitch motion in accordance with a change in vehicle speed and altitude;
Correcting the first image of the second frame based on the reference point difference of the first image and the second image of the first frame when the pitch motion occurs;
And controlling a speed, a steering, and a damper of the vehicle based on the first image of the corrected second frame. 7. The method of claim 6, wherein in the step of detecting pitch motion,
Detecting a reference point difference between the first image and the second image of the first frame and detecting the pitch motion based on the reference point difference. The method according to claim 6, wherein, in the step of detecting the plurality of objects,
And calculates the distance between the plurality of objects and the vehicle in the first frame. 9. The method of claim 8, wherein in the image correction step,
And corrects the first image of the second frame based on an object closest to the child of the plurality of objects. 7. The method of claim 6, wherein in the image correction step,
Wherein the control unit calculates a reference point difference between the first image and the second image for each of a plurality of objects in the first frame and corrects the image based on an object having the largest reference point difference among the plurality of objects, .

Images