KR20040001793A - Method of signaling deviation from lane for vehicles - Google Patents

Method of signaling deviation from lane for vehicles Download PDF

Info

Publication number
KR20040001793A
KR20040001793A KR1020020037115A KR20020037115A KR20040001793A KR 20040001793 A KR20040001793 A KR 20040001793A KR 1020020037115 A KR1020020037115 A KR 1020020037115A KR 20020037115 A KR20020037115 A KR 20020037115A KR 20040001793 A KR20040001793 A KR 20040001793A
Authority
KR
South Korea
Prior art keywords
lane
vehicle
gradient
slope
lane departure
Prior art date
Application number
KR1020020037115A
Other languages
Korean (ko)
Other versions
KR100488694B1 (en
Inventor
류남규
이준용
Original Assignee
현대자동차주식회사
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 현대자동차주식회사 filed Critical 현대자동차주식회사
Priority to KR10-2002-0037115A priority Critical patent/KR100488694B1/en
Publication of KR20040001793A publication Critical patent/KR20040001793A/en
Application granted granted Critical
Publication of KR100488694B1 publication Critical patent/KR100488694B1/en

Links

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60Q—ARRANGEMENT OF SIGNALLING OR LIGHTING DEVICES, THE MOUNTING OR SUPPORTING THEREOF OR CIRCUITS THEREFOR, FOR VEHICLES IN GENERAL
    • B60Q9/00—Arrangement or adaptation of signal devices not provided for in one of main groups B60Q1/00 - B60Q7/00, e.g. haptic signalling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/42—Global feature extraction by analysis of the whole pattern, e.g. using frequency domain transformations or autocorrelation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
    • G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road

Abstract

PURPOSE: A method for alarming the lane separation of a vehicle is provided to decide the lane separation of the vehicle by putting together gradients of line segments corresponding to a lane and using an edge distribution function and accordingly to prevent a wrong alarm for lane separation. CONSTITUTION: A method for alarming the lane separation of a vehicle is composed of steps of detecting the gradient of a line segment decided to a lane by using hough transformation on a road formed with lanes(110); removing noise by using average and standard deviations for each region(120); computing gradient(130); comparing the computed gradient with a threshold value and deciding if the threshold value is bigger than the gradient(140); and alarming the lane separation of the vehicle if the threshold value is bigger than the gradient(150).

Description

차량의 차선 이탈 경보방법{METHOD OF SIGNALING DEVIATION FROM LANE FOR VEHICLES}Lane departure warning method of vehicle {METHOD OF SIGNALING DEVIATION FROM LANE FOR VEHICLES}

본 발명은 차량의 차선 이탈 경보방법에 관한 것으로서, 보다 상세하게는 차선이라고 판단되는 선분의 기울기 분포를 이용한 차량의 차선 이탈 경보방법에 관한 것이다.The present invention relates to a lane departure warning method for a vehicle, and more particularly, to a lane departure warning method for a vehicle using a slope distribution of a line segment determined to be a lane.

일반적인 차선 이탈 경보방법은 추출된 이미지에서 차선이라고 판단되는 선분이 이미지의 양단으로부터 멀어진 거리를 이용한다.In general, the lane departure warning method uses a distance away from both ends of a line segment determined to be a lane in the extracted image.

도 1 및 도 2에는 도로의 차선이 도시되어 있다.1 and 2 show lanes of the road.

도 1에서 참조부호 a는 이미지의 양단에서 차선까지의 거리이고(일반적으로카메라나, 카메라의 위치가 정해지면 고정값), b는 차선이라고 판단한 선분이다.In FIG. 1, reference numeral a denotes a distance from both ends of an image to a lane (generally a fixed value when a camera or a camera is located), and b denotes a line segment determined to be a lane.

도면을 참조하면, 종래의 기술에 따른 차선 이탈 판단방법은, 도 1에 도시된 바와 같이, a의 거리를 계산하여 기준값(threshold)과의 비교를 통해 알 수 있었다. 그러나 도 2의 경우에는 왼쪽 차선의 a의 거리를 구할 수가 없으므로 오경보의 원인이 된다.Referring to the drawings, the lane departure determination method according to the prior art, as shown in Figure 1, it can be seen through the comparison with the reference value (threshold) by calculating the distance of a. However, in FIG. 2, the distance of a in the left lane cannot be obtained, which causes a false alarm.

본 발명은 상기와 같은 문제점을 해결하기 위하여 창출된 것으로서, 차선의 기울기를 구하여 분포 함수를 통하여 통해 차선 이탈을 판단토록 하여 차선 이탈의 오경보를 줄이도록 한 차량의 차선 이탈 경보방법을 제공하는데 그 목적이 있다.The present invention has been made to solve the above problems, to provide a lane departure warning method for a vehicle to reduce the false alarm of lane departure by determining the lane deviation through the distribution function to obtain the slope of the lane. There is this.

도 1 및 도 2는 종래의 기술에 따른 차량의 차선 이탈을 판단을 설명하기 위한 도면. 경보방법의 구성을 개략적으로 나타내 보인 도면.1 and 2 are views for explaining determination of lane departure of a vehicle according to the related art. Figure schematically showing the configuration of the alarm method.

도 3은 본 발명에 따른 차량의 차선 이탈 경보방법을 순차적으로 나타내 보인 개략적인 플로차트.3 is a schematic flowchart sequentially showing a lane departure warning method of a vehicle according to the present invention;

도 4 및 도 5는 본 발명을 설명하기 위한 도면.4 and 5 are views for explaining the present invention.

상기와 같은 목적을 달성하기 위한 본 발명의 차량의 차선 이탈 경보방법은, (a) 차선이 형성된 도로에서, 상기 차선이라고 판단된 선분의 기울기를 허프 변환을 이용하여 검출하는 단계와; (b) 각 영역별 평균 및 표준편차를 이용하여 노이즈를 제거하는 단계와; (c) 상기 기울기를 계산하는 단계와; (d) 상기 단계 (c)에서 구한 상기 기울기와 기준값을 비교하여, 상기 기준값이 큰지 판단하는 단계와; (e) 상기 단계 (d)에서의 조건을 만족하는 경우, 차선의 이탈을 경보하는 단계;를 포함하는 것을 그 특징으로 한다.The lane departure warning method of the vehicle of the present invention for achieving the above object comprises the steps of: (a) detecting the slope of the line segment determined as the lane on the road is formed by the Hough transform; (b) removing noise using the mean and standard deviation of each region; (c) calculating the slope; (d) comparing the slope obtained from the step (c) with a reference value to determine whether the reference value is large; (e) if the condition in step (d) is satisfied, warning the departure of the lane; and characterized in that it comprises a.

이하, 첨부된 도면을 참조하여 본 발명에 따른 바람직한 실시예를 상세히 설명하기로 한다.Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings.

도 3에는 본 발명에 따른 차량의 차선 이탈 경보방법을 순차적으로 나타내보인 개략적인 플로차트가 도시되어 있다. .3 is a schematic flowchart sequentially illustrating a lane departure warning method of a vehicle according to the present invention. .

도면을 참조하면, 본 발명에 따른 차량의 차선 이탈 경보방법은, 우선, 차선이 형성된 도로에서, 차선이라고 판단된 선분의 기울기를 허프 변환(hough transformation)을 이용하여 검출한다.(단계 110)Referring to the drawings, the lane departure warning method of a vehicle according to the present invention first detects the slope of a line segment determined as a lane on a road on which a lane is formed by using a hough transformation (step 110).

이어서, 각 영역별 평균 및 표준편차를 이용하여 노이즈(noise)를 제거한다 .(단계 120)Subsequently, noise is removed using the mean and standard deviation of each region (step 120).

그리고 상기한 기울기를 계산한다.(단계 130)Then, the slope is calculated (step 130).

상기 단계 130에서 구한 기울기와 기준값(threshold)을 비교하여, 상기 기준값이 큰지 판단한다.(단계 140)The slope obtained in step 130 and the threshold are compared to determine whether the reference value is large (step 140).

상기 단계 140에서의 조건을 만족하는 경우, 차선의 이탈을 경보한다.(단계 150)If the condition in step 140 is satisfied, the lane departure is alerted (step 150).

상기 단계 150에서 차선의 이탈 경보는, 차량에 장착되어 차선을 감지하는 카메라의 광축이 차선 경계의 중앙을 벗어날 경우 하도록 한다.The lane departure warning in step 150 may be performed when the optical axis of the camera mounted on the vehicle and detecting the lane is out of the center of the lane boundary.

한편, 상기 단계 140에서의 조건을 만족하지 못하는 경우에는 본 제어를 처음부터 다시 재 시작한다.On the other hand, if the condition in step 140 is not satisfied, the control is restarted from the beginning.

상기한 바와 같이 본 발명에 따른 차량의 차선 이탈 경보방법은, 종래의 문제점인 오경보를 줄이기 위해 차선의 기울기를 구하여 분포함수를 통하여 차선 이탈을 판단하도록 하는 것이다.As described above, the lane departure warning method for a vehicle according to the present invention is to determine a lane departure through a distribution function by obtaining a slope of a lane in order to reduce a false alarm, which is a conventional problem.

이를 보다 구체적으로 설명하면, 차선 이탈을 판단할 경우 한쪽 차선이나 차선의 일부분만 검출되더라도 차선이나 변화의 연속성을 감안하면 차선 이탈을 판단할 수 있다.In more detail, when the lane departure is determined, even if only one lane or a part of the lane is detected, the lane departure may be determined in consideration of the continuity of the lane or the change.

도 4 및 도 5에 도시된 바와 같이, 차선이라고 판단된 선분의 기울기 분포(Edge Distribution Function)('C')를 계산하면 차선 이탈을 판단한다.As shown in FIG. 4 and FIG. 5, the lane departure is determined by calculating an edge distribution function ('C') of the line segment determined as the lane.

직선 주행시는 θ1과 θ2가 45˚, 135˚ 주위에 집중적으로 분포되어 있으나(카메라나 장착각도에 따라 다름) 옆 차선으로 이동할 경우에는 이탈되는 차선쪽의 각도가 90˚를 이루게 된다.When driving in a straight line, θ1 and θ2 are concentrated around 45 ° and 135 ° (depending on the camera or mounting angle), but when moving to the next lane, the angle of the lane to be separated is 90 °.

이러한 현상을 이용하여 차선 이탈을 판단할 경우에는 불연속적인 차선이라 하더라도 차선 이탈을 판단할 수 있다.If the lane departure is determined using this phenomenon, the lane departure may be determined even if the lane is discontinuous.

즉, 도 4에 도시된 바와 같이, 카메라 광축이 차선 경계의 접선 방향과 일치할 경우, θ1 = θ2와, ρ1 = ρ2가 성립한다. 그리고 카메라 광축이 좌우 차선 경계의 중앙을 벗어날 경우(이탈 발생), θ1 ≠ θ2와, ρ1 ≠ ρ2가 성립한다.That is, as shown in FIG. 4, when the camera optical axis coincides with the tangential direction of the lane boundary, θ1 = θ2 and ρ1 = ρ2 hold. When the camera optical axis is out of the center of the left and right lane boundaries (deviation occurs), θ1 ≠ θ2 and ρ1 ≠ ρ 2 are established.

이에 따라 차선 이탈을 경보한다.This warns of lane departure.

상술한 바와 같이 본 발명에 따른 차량의 차선 이탈 경보방법은 다음과 같은 효과를 갖는다.As described above, the lane departure warning method of the vehicle according to the present invention has the following effects.

차선이라고 판단되는 선분의 기울기를 종합하여 기울기의 분포를 이용하여 차선 이탈을 판단할 수 있어 차선 이탈에 대한 오경보를 방지할 수 있다. 이에 따라 차량의 신뢰성을 향상시킬 수 있다.By integrating the slopes of the line segments determined to be lanes, the lane departure can be determined using the distribution of the slopes, thereby preventing false alarms for lane departures. This can improve the reliability of the vehicle.

본 발명은 도면에 도시된 일 실시예를 참고로 설명되었으나 이는 예시적인 것에 불과하며, 당해 기술 분야에서 통상의 지식을 가진 자라면 이로부터 다양한변형 및 균등한 실시예가 가능하다는 점을 이해할 것이다. 따라서 본 발명의 진정한 보호 범위는 첨부된 특허청구범위에 의해서만 정해져야 할 것이다.Although the present invention has been described with reference to one embodiment illustrated in the drawings, this is merely exemplary, and it will be understood by those skilled in the art that various modifications and equivalent embodiments are possible. Therefore, the true scope of protection of the present invention should be defined only by the appended claims.

Claims (2)

(a) 차선이 형성된 도로에서, 상기 차선이라고 판단된 선분의 기울기를 허프 변환을 이용하여 검출하는 단계와;(a) detecting a slope of a line segment determined as the lane on the road on which the lane is formed by using a Hough transform; (b) 각 영역별 평균 및 표준편차를 이용하여 노이즈를 제거하는 단계와;(b) removing noise using the mean and standard deviation of each region; (c) 상기 기울기를 계산하는 단계와;(c) calculating the slope; (d) 상기 단계 (c)에서 구한 상기 기울기와 기준값을 비교하여, 상기 기준값이 큰지 판단하는 단계와;(d) comparing the slope obtained from the step (c) with a reference value to determine whether the reference value is large; (e) 상기 단계 (d)에서의 조건을 만족하는 경우, 차선의 이탈을 경보하는 단계;를 포함하는 것을 특징으로 하는 차량의 차선 이탈 경보방법.and (e) alerting the departure of the lane when the condition in the step (d) is satisfied. 제1항에 있어서,The method of claim 1, 상기 단계 (e)에서 상기 차선의 이탈 경보는, 차량에 장착되어 차선을 감지하는 카메라의 광축이 차선 경계의 중앙을 벗어날 경우 하도록 하는 것을 특징으로 하는 차량의 차선 이탈 경보방법.The lane departure warning in the step (e) is a lane departure warning method for a vehicle, characterized in that when the optical axis of the camera mounted on the vehicle detecting the lane is out of the center of the lane boundary.
KR10-2002-0037115A 2002-06-28 2002-06-28 Method of signaling deviation from lane for vehicles KR100488694B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR10-2002-0037115A KR100488694B1 (en) 2002-06-28 2002-06-28 Method of signaling deviation from lane for vehicles

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR10-2002-0037115A KR100488694B1 (en) 2002-06-28 2002-06-28 Method of signaling deviation from lane for vehicles

Publications (2)

Publication Number Publication Date
KR20040001793A true KR20040001793A (en) 2004-01-07
KR100488694B1 KR100488694B1 (en) 2005-05-11

Family

ID=37313526

Family Applications (1)

Application Number Title Priority Date Filing Date
KR10-2002-0037115A KR100488694B1 (en) 2002-06-28 2002-06-28 Method of signaling deviation from lane for vehicles

Country Status (1)

Country Link
KR (1) KR100488694B1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8170340B2 (en) 2006-12-18 2012-05-01 Fraunhofer-Gesellschaft Zur Foerderung Der Angewandten Forschung E.V. Device, method and computer program for identifying a traffic sign in an image

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107833492A (en) * 2017-11-24 2018-03-23 南京视莱尔汽车电子有限公司 A kind of zebra stripes real-time monitoring system based on intelligent driving

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH06149359A (en) * 1992-11-02 1994-05-27 Matsushita Electric Ind Co Ltd Traveling lane detector
KR19980043293A (en) * 1996-12-02 1998-09-05 박병재 Camera control method of lane departure warning device
JP3690099B2 (en) * 1998-01-19 2005-08-31 三菱自動車工業株式会社 Light distribution control device for automotive headlights
KR100305797B1 (en) * 1999-07-08 2001-09-13 이계안 Method for noise removing of the beyond lane alarm device for vehicle
KR100435654B1 (en) * 2001-06-20 2004-06-12 현대자동차주식회사 Control method for preventing a lane secession of vehicle

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8170340B2 (en) 2006-12-18 2012-05-01 Fraunhofer-Gesellschaft Zur Foerderung Der Angewandten Forschung E.V. Device, method and computer program for identifying a traffic sign in an image

Also Published As

Publication number Publication date
KR100488694B1 (en) 2005-05-11

Similar Documents

Publication Publication Date Title
JP4374211B2 (en) Lane marker position detection method, lane marker position detection device, and lane departure warning device
JP3503230B2 (en) Nighttime vehicle recognition device
US9349070B2 (en) Vehicle external environment recognition device
US8842884B2 (en) Method and device for lane detection
US20200104608A1 (en) Lane-line recognizing apparatus
US20200372794A1 (en) Method of detecting speed using difference of distance between object and monitoring camera
JP3246243B2 (en) Lane departure warning device
US9524645B2 (en) Filtering device and environment recognition system
TWI629671B (en) Safety warning device and wearable device having the same
JP2003281700A (en) Cutting-in vehicle detecting device and method
KR20040001793A (en) Method of signaling deviation from lane for vehicles
KR101283586B1 (en) Portable apparatus for determining driving condition of automobile and method thereof
KR100766594B1 (en) Early lane departure warning method for vehicle
KR100355993B1 (en) An apparatus for warning lane deviation and a method for warning the same
US9988059B2 (en) Vehicle behavior detection device
JP6302205B2 (en) OBE
JP2008114627A (en) Rear side part monitoring device for vehicle
JP2005309660A (en) Device supporting vehicle in turning right or left
JP2011033494A (en) System and method for determination of entrance into branch road
KR101958605B1 (en) Forward vehicle detection apparatus and method
JP2022021517A (en) Dangerous driving determination device and dangerous driving determination method
JPH0981758A (en) Vehicle detecting device
TWI671717B (en) Driving alarm method and driving alarm system
JP2015055968A (en) Vehicle position detection device and blind spot warning system
KR20150012044A (en) Apparatus and method of lane departure warnning for vehicle

Legal Events

Date Code Title Description
A201 Request for examination
E902 Notification of reason for refusal
E701 Decision to grant or registration of patent right
GRNT Written decision to grant
FPAY Annual fee payment

Payment date: 20130430

Year of fee payment: 9

FPAY Annual fee payment

Payment date: 20140430

Year of fee payment: 10

FPAY Annual fee payment

Payment date: 20150430

Year of fee payment: 11

LAPS Lapse due to unpaid annual fee