KR101103526B1 - Collision Avoidance Method Using Stereo Camera - Google Patents

Collision Avoidance Method Using Stereo Camera Download PDF

Info

Publication number
KR101103526B1
KR101103526B1 KR1020060086311A KR20060086311A KR101103526B1 KR 101103526 B1 KR101103526 B1 KR 101103526B1 KR 1020060086311 A KR1020060086311 A KR 1020060086311A KR 20060086311 A KR20060086311 A KR 20060086311A KR 101103526 B1 KR101103526 B1 KR 101103526B1
Authority
KR
South Korea
Prior art keywords
distance
obstacle
lane
displacement
collision
Prior art date
Application number
KR1020060086311A
Other languages
Korean (ko)
Other versions
KR20080022748A (en
Inventor
이윤희
Original Assignee
주식회사 만도
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 주식회사 만도 filed Critical 주식회사 만도
Priority to KR1020060086311A priority Critical patent/KR101103526B1/en
Publication of KR20080022748A publication Critical patent/KR20080022748A/en
Application granted granted Critical
Publication of KR101103526B1 publication Critical patent/KR101103526B1/en

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
    • B60W30/09—Taking automatic action to avoid collision, e.g. braking and steering
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60R—VEHICLES, VEHICLE FITTINGS, OR VEHICLE PARTS, NOT OTHERWISE PROVIDED FOR
    • B60R21/00—Arrangements or fittings on vehicles for protecting or preventing injuries to occupants or pedestrians in case of accidents or other traffic risks
    • B60R21/01—Electrical circuits for triggering passive safety arrangements, e.g. airbags, safety belt tighteners, in case of vehicle accidents or impending vehicle accidents
    • B60R21/013—Electrical circuits for triggering passive safety arrangements, e.g. airbags, safety belt tighteners, in case of vehicle accidents or impending vehicle accidents including means for detecting collisions, impending collisions or roll-over
    • B60R21/0134—Electrical circuits for triggering passive safety arrangements, e.g. airbags, safety belt tighteners, in case of vehicle accidents or impending vehicle accidents including means for detecting collisions, impending collisions or roll-over responsive to imminent contact with an obstacle, e.g. using radar systems
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W10/00—Conjoint control of vehicle sub-units of different type or different function
    • B60W10/18—Conjoint control of vehicle sub-units of different type or different function including control of braking systems
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
    • B60W40/06—Road conditions
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/10—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to vehicle motion
    • B60W40/105—Speed
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
    • B60W2050/0001—Details of the control system
    • B60W2050/0043—Signal treatments, identification of variables or parameters, parameter estimation or state estimation
    • B60W2050/0057—Frequency analysis, spectral techniques or transforms
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2420/00—Indexing codes relating to the type of sensors based on the principle of their operation
    • B60W2420/40—Photo, light or radio wave sensitive means, e.g. infrared sensors
    • B60W2420/403—Image sensing, e.g. optical camera
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2552/00—Input parameters relating to infrastructure
    • B60W2552/50—Barriers
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2720/00—Output or target parameters relating to overall vehicle dynamics
    • B60W2720/10—Longitudinal speed
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60Y—INDEXING SCHEME RELATING TO ASPECTS CROSS-CUTTING VEHICLE TECHNOLOGY
    • B60Y2300/00—Purposes or special features of road vehicle drive control systems
    • B60Y2300/08—Predicting or avoiding probable or impending collision
    • B60Y2300/09—Taking automatic action to avoid collision, e.g. braking or steering

Landscapes

  • Engineering & Computer Science (AREA)
  • Mechanical Engineering (AREA)
  • Transportation (AREA)
  • Automation & Control Theory (AREA)
  • Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Traffic Control Systems (AREA)

Abstract

본 발명은 스테레오 카메라를 이용한 충돌회피 방법에 관한 것으로, 차량의 자차선을 인식하여 자차선만의 장애물을 감지하여 미리 충돌 가능성을 운전자에게 경고하며, 충돌 회피를 위해 능동 제동 시스템을 이용하여 차속을 감속시키도록 하는 방법을 제공하는데 그 목적이 있다.The present invention relates to a collision avoidance method using a stereo camera, to recognize the vehicle's own lanes to detect obstacles of the own lanes to warn the driver of possible collisions in advance, and to use the active braking system to avoid collisions. Its purpose is to provide a way to slow down.

또한, 거리에 따라 달라지는 변위의 양을 반영하여 적응적으로 장애물과의 거리를 측정하는 방법을 제공하는데 그 목적이 있다.Another object of the present invention is to provide a method for adaptively measuring a distance to an obstacle by reflecting an amount of displacement that varies with distance.

상기 목적을 달성하기 위하여 특징 추출 및 스테레오 매칭단계; 도로영역 검출단계; 차선검출 및 자차선 영역추출단계; 장애물거리측정단계; 충돌가능성 판단단계; 및 제동수행단계로 이루어진 방법을 제공하여, 차량의 자차선을 인식하여 자차선만의 장애물을 감지하도록 하여 검색량이 적어 검색시간 및 계산량이 적어지며, 장애물의 다양한 변화에 대하여 적응적으로 대응하도록 하는 등의 효과가 있다.Feature extraction and stereo matching to achieve the object; Road area detection step; Lane detection and own lane area extraction step; Obstacle distance measuring step; Possibility of collision determination; And by providing a method consisting of a braking performance step, by detecting the own lane of the vehicle to detect the obstacle of the own lane, the search amount is small, the search time and calculation amount is reduced, and adaptively respond to various changes of the obstacle There is an effect such as.

스테레오 카메라, 충돌회피, 관심영역(Region Of Interest, ROI) Stereo Camera, Collision Avoidance, Region of Interest (ROI)

Description

스테레오 카메라를 이용한 충돌회피 방법{Collision Avoidance Method Using Stereo Camera}Collision Avoidance Method Using Stereo Camera

도 1은 본 발명의 실시예에 따른 스테레오 카메라를 이용한 충돌회피 시스템의 구성을 보인 블록도.1 is a block diagram showing the configuration of a collision avoidance system using a stereo camera according to an embodiment of the present invention.

도 2는 본 발명의 실시예에 따른 스테레오 카메라를 이용한 충돌회피 동작 과정을 보인 흐름도.2 is a flow chart showing a collision avoidance operation using a stereo camera according to an embodiment of the present invention.

도 3은 본 발명의 실시예에 따른 장애물 감지 및 거리 측정을 과정을 보인 예시도.Figure 3 is an exemplary view showing a process of obstacle detection and distance measurement according to an embodiment of the present invention.

도 4는 본 발명의 실시예에 따른 변위 히스토그램에서 적응 한계치를 이용한 장애물의 거리 측정을 보인 히스토그램.4 is a histogram showing a distance measurement of an obstacle using an adaptive limit value in a displacement histogram according to an exemplary embodiment of the present invention.

*** 도면의 주요부분에 대한 설명 ****** Description of the main parts of the drawing ***

100 : 충돌 회피시스템 110 : 차속 센서100: collision avoidance system 110: vehicle speed sensor

200 : 충돌 경고 에치엠아이(HMI) 300 : 능동 제동 시스템200: collision warning HMI 300: active braking system

본 발명은 스테레오 카메라를 이용한 충돌회피 방법에 관한 것으로, 특히 차 량의 자차선을 인식하여 차선의 장애물을 감지하고, 충돌 회피를 위해 능동 제동 시스템을 이용하여 차속을 감속시키도록 하는 방법에 관한 것이다. BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a collision avoidance method using a stereo camera, and more particularly, to a method for recognizing a vehicle's own lane to detect an obstacle in a lane and decelerating a vehicle speed using an active braking system to avoid a collision. .

종래 간행물(IEEE 인텔리전트 차량 심포지움, 2000년 10월, U.Franke), '도시 교통 실황 파악을 위한 실시간 스테레오 감시장치'에 3차원 영상의 녹화를 위한 스테레오 카메라를 포함하는 영상기록 장치에 의해 차량의 주변을 기록하는 것이 공지되어 있다. 녹화된 장면을 분석함으로써 예컨대 차량 주변의 다른 차량, 승객 또는 사물의 위치가 조사될 수 있다. Previous publications (IEEE Intelligent Vehicle Symposium, Oct. 2000, U.Franke), "Real-time Stereo Surveillance for the Realization of Urban Traffic," included a video recording device containing a stereo camera for recording three-dimensional images. It is known to record the surroundings. By analyzing the recorded scene, for example, the location of other vehicles, passengers or things around the vehicle can be investigated.

이러한 정보 덕분으로 차량의 종 또는 횡방향 주행은 조절기에 의해 영향을 받으므로, 운전자는 차량주행 시 보호되고, 승차감 및 교통 안전이 개선될 수 있다. 예컨대 위험한 충돌 시 자동 회피조작 또는 브레이크 조종은 충돌을 방지하거나 적어도 충돌 에너지를 감소시킨다.Thanks to this information, the longitudinal or transverse driving of the vehicle is affected by the regulator, so that the driver can be protected while driving, and the riding comfort and traffic safety can be improved. For example, in case of a dangerous collision, automatic avoidance or brake control prevents collision or at least reduces collision energy.

그러나, 종래 방법은 자차선 뿐만 아니라 주변 노이즈 및 다른 차선의 장애물에 대한 검색도 같이 수행함으로써, 검색량이 많아 검색시간이 길어지고 많은 계산량을 요구하는 단점이 있다. However, the conventional method performs a search for not only the own lane but also the ambient noise and obstacles of other lanes together, so that the search time is large and the search time is long and requires a large amount of calculation.

또한, 장애물과의 거리 측정 방법으로 변위 히스토그램(disparity histogram) 상에서 피크(peak)를 찾는 방법을 사용함으로써, 장애물의 다양한 변화에 대하여 적응적으로 대응하기가 어렵다 등의 문제점이 있었다.In addition, by using a method of finding a peak on a disparity histogram as a method of measuring a distance from an obstacle, it is difficult to adaptively respond to various changes of the obstacle.

따라서, 본 발명은 상기와 같은 종래의 문제점을 해결하기 위하여 창안한 것으로, 차량의 자차선을 인식하여 자차선만의 장애물을 감지하여 미리 충돌 가능성 을 운전자에게 경고하며, 충돌 회피를 위해 능동 제동 시스템을 이용하여 차속을 감속시키도록 하는 방법을 제공하는데 그 목적이 있다.Accordingly, the present invention has been made to solve the above-mentioned conventional problems, recognizes the own lane of the vehicle to detect the obstacle of the own lane only to warn the driver of the possibility of collision in advance, and an active braking system for collision avoidance. It is an object of the present invention to provide a method for decelerating a vehicle speed by using.

또한, 거리에 따라 달라지는 변위의 양을 반영하여 적응적으로 장애물과의 거리를 측정하는 방법을 제공하는데 그 목적이 있다.Another object of the present invention is to provide a method for adaptively measuring a distance to an obstacle by reflecting an amount of displacement that varies with distance.

이와 같은 목적을 달성하기 위한 본 발명 스테레오 카메라를 이용한 충돌회피 방법은 스테레오 카메라를 통해서 입력되는 좌,우 영상에서 특징을 추출하여 좌 영상에 우 영상의 매칭되는 점을 찾는 동작을 수행하는 특징 추출 및 스테레오 매칭단계; 상기 특징 추출 및 스테레오 매칭단계의 매칭 결과를 통해서 도로 영역과 도로가 아닌 영역을 소정의 영역검출식을 이용하여 검출하는 도로영역 검출단계; 임의의 차선검출방법을 통해 차량의 진행 방향을 알 수 있는 차선을 검출하고, 자차선 영역을 관심영역(Region Of Interest, ROI)으로 설정한 후, 주변 물체에 대한 변위 정보를 배제하고 차량의 진행방향에 있는 장애물에 대한 변위만을 구하는 차선검출 및 자차선 영역추출단계; 변위 히스토그램에서 설정치 이상의 변위 값 중 자차와 가장 가까운 거리의 값을 장애물과의 거리로 판단하고, 만약 설정치를 넘는 변위 값이 다수 존재할 때에는 검증(verification) 과정을 통해 다수의 변위 값에서 가장 적합한 장애물과의 거리를 검출하는 장애물거리측정단계; 장애물과의 거리와 자차의 속도 및 제동거리를 기반으로 충돌 가능성을 판단하는 충돌가능성 판단단계; 및 상기 충돌가능성 판단단계에서 판단결과 충돌 가능성이 있다고 판단되면 운전자의 제동지시가 없어도 캔(CAN) 통신을 통해 제동장치를 구동시켜 차량의 속 도를 감속시키는 제동수행단계로 이루어진 것을 특징으로 한다.In order to achieve the above object, the collision avoidance method using the stereo camera of the present invention extracts a feature from a left and right image input through a stereo camera and performs a feature extraction operation to find a matching point of a right image to a left image. Stereo matching step; A road area detection step of detecting a road area and a non-road area by using a predetermined area detection equation through a matching result of the feature extraction and stereo matching step; Detect lanes that know the direction of the vehicle through any lane detection method, set the own lane area as the Region Of Interest (ROI), exclude the displacement information on the surrounding objects, and proceed with the vehicle. Lane detection and own lane area extraction for finding a displacement of an obstacle in a direction; In the displacement histogram, the distance closest to the host vehicle is determined as the distance from the obstacle, and if there are a large number of displacement values above the set value, a verification process is performed to verify that the most suitable obstacle and Obstacle distance measuring step of detecting the distance of; A collision possibility determination step of determining a collision possibility based on the distance between the obstacle and the speed and the braking distance of the vehicle; And a braking performance step of reducing the speed of the vehicle by driving the braking device through a CAN communication without a driver's braking instruction, if it is determined that there is a collision possibility in the collision possibility determination step.

이하, 본 발명에 따른 실시예를 첨부한 도면을 참조하여 상세히 설명하면 다음과 같다.Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings.

도 1은 본 발명의 실시예에 따른 스테레오 카메라를 이용한 충돌회피 시스템의 구성을 보인 블록도로서, 이에 도시한 바와 같이 크게 충돌 회피시스템(100), 충돌 경고 에치엠아이(Human Matching Interface, HMI, 200), 능동 제동 시스템(300)으로 구성되어 있는데, 상기 충돌 회피시스템(100)은 스테레오 카메라(120)를 장착하여 이를 통해 전방 장애물을 감지하여 장애물과의 거리를 판별하고, 차속 센서(110)를 통해 차량의 속도를 입력받아 이에 따른 충돌거리를 계산하여 충돌 가능성 여부를 판단하며, 상기 충돌 경고 HMI(200)는 운전자에게 충돌 경고 메시지를 음성, 또는 화면 디스플레이 등을 통해 알리는 기능을 하고, 상기 능동 제동 시스템(300)은 운전자의 제동지시가 없어도 제동장치를 구동시켜 차량의 속도를 감속시킨다. 1 is a block diagram showing the configuration of a collision avoidance system using a stereo camera according to an embodiment of the present invention, as shown in the collision avoidance system 100, collision warning ICH (Human Matching Interface, HMI, 200) ), The active braking system 300, the collision avoidance system 100 is equipped with a stereo camera 120 to detect the front obstacle through this to determine the distance to the obstacle, the vehicle speed sensor 110 The speed of the vehicle is input to determine the possibility of a collision by calculating a collision distance. The collision warning HMI 200 notifies the driver of a collision warning message through a voice or a screen display. The braking system 300 drives the braking device to reduce the speed of the vehicle even without the driver's braking instruction.

이와 같이 구성한 본 발명에 따른 실시예의 동작 과정을 설명하면 다음과 같다.Referring to the operation of the embodiment according to the present invention configured as described above are as follows.

도 2는 본 발명의 실시예에 따른 스테레오 카메라를 이용한 충돌회피 동작 과정을 보인 흐름도이고, 도 3은 본 발명의 실시예에 따른 장애물 감지 및 거리 측정을 과정을 보인 예시도로서, 이에 도시한 바와 같이 스테레오 카메라(120)를 통해서 입력되는 좌,우 영상에서 특징을 추출하여 좌 영상에 우 영상의 매칭되는 점을 찾는 동작을 수행하는데, 특징은 세로 에지(edge)를 통해서 추출한다(S100 ~ S102). 2 is a flowchart illustrating a collision avoidance operation process using a stereo camera according to an exemplary embodiment of the present invention, and FIG. 3 is an exemplary view illustrating a process of detecting an obstacle and measuring a distance according to an exemplary embodiment of the present invention. As described above, the feature is extracted from the left and right images input through the stereo camera 120 to find a matching point of the right image on the left image, and the feature is extracted through the vertical edge (S100 to S102). ).

상기 단계(S102)의 매칭 결과를 통해서 도로 영역과 도로가 아닌 영역을 소정의 영역검출식을 이용하여 검출하는데(S103), 이때 이용되는 영역검출식은 다음과 같다. The road area and the non-road area are detected using a predetermined area detection equation through the matching result of step S102 (S103). The area detection equation used at this time is as follows.

Figure 112006064791467-pat00001
Figure 112006064791467-pat00001

(여기서, B : 두 카메라 사이의 거리, H : 카메라의 높이,

Figure 112006064791467-pat00002
: 카메라의 x축 초점길이(focal length),
Figure 112006064791467-pat00003
: 카메라의 y축 초점길이,
Figure 112006064791467-pat00004
: 카메라의 경사(tilt) 각도,
Figure 112006064791467-pat00005
: 영상좌표 x,y에서의 변위 값, (x,y): 픽셀(pixel)의 카메라 좌표)(Where B is the distance between two cameras, H is the height of the camera,
Figure 112006064791467-pat00002
Is the x-axis focal length of the camera,
Figure 112006064791467-pat00003
Is the y-axis focal length of the camera,
Figure 112006064791467-pat00004
: Tilt angle of the camera,
Figure 112006064791467-pat00005
: Displacement value at image coordinate x, y, (x, y): camera coordinate of pixel)

상기 단계(S103)의 수행이 완료되면 임의의 차선검출방법을 통해 차량의 진행 방향을 알 수 있는 차선을 검출하고, 자차선 영역을 관심영역(Region Of Interest, ROI)으로 설정한 후, 주변 물체(가로수, 신호등, 옆 차선의 장애물 등)에 대한 변위 정보를 배제하고 차량의 진행방향에 있는 장애물에 대한 변위만을 추출하도록 하는데(S104 ~ S106), 이는 주변 물체에 대한 변위 정보를 배제하여 잘못된 물체를 정면 장애물로 인식하는 경우(false alarm)에 대한 가능성을 낮추고, 주변 노이즈로 인한 잘못된 거리 정보를 배제하기 위함이다. 또한, 상기에서 임의의 차선검출방법으로는 적용 화상에 대해 임의의 각도의 직선상에 존재하는 모든 점들의 총합만을 구해 그 각도의 직선과 다른 각도의 직선에 대한 상대적인 길이의 크기를 비교하는 허프변환(Hough transform)을 이용한 방법과 스플라인(Spline)을 이용하는 방법 및 버즈 아이 뷰(Bird's eye view) 이미지에서의 템플릿 매칭(Template matching) 방법이 주로 사용된다.After performing the step (S103) is completed, any lane detection method detects the lane to know the direction of the vehicle, and set the own lane area to the Region Of Interest (ROI), and then surrounding objects It excludes displacement information about roadsides, traffic lights, and obstacles in the next lane and extracts only displacements for obstacles in the direction of the vehicle (S104 ~ S106). This is to reduce the possibility of false alarms and to exclude false distance information due to ambient noise. In addition, in the lane detection method described above, a Hough transform that obtains only the sum of all points existing on a straight line of an angle with respect to an applied image, and compares the magnitudes of the lengths of the straight line of the angle with the straight line of the other angle. A method using a Hough transform, a method using a Spline, and a template matching method in a Bird's eye view image are mainly used.

상기 단계(S106)의 수행이 완료되면 도 4에 도시한 바와 같이 추출한 변위 히스토그램에서 설정치 이상의 변위 값 중 자차와 가장 가까운 거리의 값을 장애물과의 거리로 판단하는데(S107), 상기 설정치는 변위가 큰 값에서는 한계치 값이 커지고 변위 값이 작은 값에서는 한계치 값이 작아지는 적응 한계치(Adaptive Threshold, AT)이며, 이 적응 한계치를 구하는 방법으로는 다양한 차량에 대한 거리에 따른 영상에서의 변위 값을 통해 라인 조정(line fitting)하여 각 변위에 대한 한계치 값을 얻는 방법과 거리에 따른 도로의 영상 좌표 y와 관심영역(ROI)이 가지는 영상 좌표의 최소점 y의 차를 통한 방법이 있다.When the execution of the step (S106) is completed as shown in FIG. 4, the value of the distance closest to the host vehicle among the displacement values greater than or equal to the set value in the displacement histogram extracted as shown in FIG. 4 is determined as the distance to the obstacle (S107). Adaptive Threshold (AT), which is larger at larger values and smaller at lower displacement values, is the adaptive threshold, which is determined by the displacement value in the image according to the distance to various vehicles. There are a method of obtaining a threshold value for each displacement by line fitting, and a method through a difference between the image coordinate y of the road and the minimum point y of the image coordinate of the ROI according to the distance.

만약, 상기 적응 한계치(AT)를 넘는 변위 값이 다수 존재할 때에는 검증(verification) 과정을 통해 다수의 변위 값에서 가장 적합한 장애물과의 거리를 검출하는데(S108 ~ S109), 검증 과정은 좌 영상에서 후보군 영역을 차선의 넓이와 차선의 넓이만큼의 높이만큼의 사각형을 변위에 따른 도로 좌표 y를 기준으로 만들고 변위만큼 이동한 우 영상의 영역과 비교하여 가장 상관(correlation)이 높은 값을 선택하는 과정이다.If there are a large number of displacement values exceeding the adaptation threshold value (AT), a verification process detects the distance between the most suitable obstacles in the plurality of displacement values (S108 to S109). It is the process of selecting the highest correlation value by comparing the area of the lane with the height of the lane and the width of the lane based on the road coordinate y according to the displacement and comparing it with the area of the right image moved by the displacement. .

상기에서 검출한 장애물과의 거리와 속도 센서(110)로부터 입력되는 자차의 속도 및 제동거리를 기반으로 충돌 가능성을 판단하는데(S110 ~ S111), 이때 판단을 위한 계산식을 보면 다음과 같다. The possibility of collision is determined based on the distance between the obstacle detected above and the speed and braking distance of the host vehicle input from the speed sensor 110 (S110 to S111).

Figure 112006064791467-pat00006
Tp〈 T,
Figure 112006064791467-pat00006
T p <T,

(여기서, T : 충돌 시간,

Figure 112006064791467-pat00007
: 예상 충돌 시간,
Figure 112006064791467-pat00008
: 자차와 장애물과의 거리, B
Figure 112006064791467-pat00009
: 자차의 속도, B
Figure 112006064791467-pat00010
: 장애물 속도)Where T is the collision time,
Figure 112006064791467-pat00007
: Estimated collision time,
Figure 112006064791467-pat00008
: Distance between vehicle and obstacle, B
Figure 112006064791467-pat00009
: Speed of vehicle, B
Figure 112006064791467-pat00010
: Obstacle speed)

상기 단계(S111)의 판단결과 충돌 가능성이 있다고 판단되면 운전자의 제동지시가 없어도 캔(CAN) 통신을 통해 제동장치를 구동시켜 차량의 속도를 감속시킨다(S112).If it is determined in the step S111 that there is a possibility of collision, the braking device is driven through CAN communication without the driver's braking instruction (S112).

이상에서 본 발명의 구체적인 실시예를 상세히 설명하였으나, 본 발명은 이에 한정되는 것은 아니며, 이 분야의 통상의 지식을 가진 자라면 본 발명의 기술적 사상을 바탕으로 다양한 변경과 수정이 가능할 것이다.Although specific embodiments of the present invention have been described in detail above, the present invention is not limited thereto, and those skilled in the art may make various changes and modifications based on the technical idea of the present invention.

이상에서 설명한 바와 같이 본 발명 스테레오 카메라를 이용한 충돌회피 방법은 차량의 자차선을 인식하여 자차선만의 장애물을 감지하도록 하여 검색량이 적어 검색시간 및 계산량이 적어지며, 장애물의 다양한 변화에 대하여 적응적으로 대 응하도록 하는 등의 효과가 있다.As described above, the collision avoidance method using the stereo camera of the present invention recognizes the own lane of the vehicle and detects only the obstacle of the own lane so that the search amount is small and the search time and calculation amount are reduced, and it is adaptive to various changes of the obstacle. It has the effect of responding to.

Claims (5)

스테레오 카메라를 통해서 입력되는 좌,우 영상에서 특징을 추출하여 좌 영상에 우 영상의 매칭되는 점을 찾는 동작을 수행하는 특징 추출 및 스테레오 매칭단계; Extracting a feature from a left and right image input through a stereo camera and searching for a matching point of the right image to the left image; 상기 특징 추출 및 스테레오 매칭단계의 매칭 결과를 통해서 도로 영역과 도로가 아닌 영역을 소정의 영역검출식을 이용하여 검출하는 도로영역 검출단계; A road area detection step of detecting a road area and a non-road area by using a predetermined area detection equation through a matching result of the feature extraction and stereo matching step; 임의의 차선검출방법을 통해 차량의 진행 방향을 알 수 있는 차선을 검출하고, 자차선 영역을 관심영역(Region Of Interest, ROI)으로 설정한 후, 주변 물체에 대한 변위 정보를 배제하고 차량의 진행방향에 있는 장애물에 대한 변위만을 구하는 차선검출 및 자차선 영역추출단계; Detect lanes that know the direction of the vehicle through any lane detection method, set the own lane area as the Region Of Interest (ROI), exclude the displacement information on the surrounding objects, and proceed with the vehicle. Lane detection and own lane area extraction for finding a displacement of an obstacle in a direction; 변위 히스토그램에서 설정치 이상의 변위 값 중 자차와 가장 가까운 거리의 값을 장애물과의 거리로 판단하고, 만약 설정치를 넘는 변위 값이 다수 존재할 때에는 검증(verification) 과정을 통해 다수의 변위 값에서 자차와 가장 가까운 거리의 장애물과의 거리를 검출하는 장애물거리측정단계; In the displacement histogram, the distance closest to the host vehicle among the displacement values above the set value is determined as the distance from the obstacle. If there are a large number of displacement values exceeding the set value, a verification process is performed to verify the closest distance to the host vehicle. An obstacle distance measuring step of detecting a distance from an obstacle of a distance; 장애물과의 거리와 자차의 속도 및 제동거리를 기반으로 충돌 가능성을 판단하는 충돌가능성 판단단계; 및 A collision possibility determination step of determining a collision possibility based on the distance between the obstacle and the speed and the braking distance of the vehicle; And 상기 충돌가능성 판단단계에서 판단결과 충돌 가능성이 있다고 판단되면 운전자의 제동지시가 없어도 캔(CAN) 통신을 통해 제동장치를 구동시켜 차량의 속도를 감속시키는 제동수행단계로 이루어진 것을 특징으로 하는 스테레오 카메라를 이용한 충돌회피 방법.If it is determined that there is a possibility of a collision in the determination of the possibility of collision, the stereo camera comprises a braking performance step of reducing the speed of the vehicle by driving a braking device through CAN communication without a driver's braking instruction. Collision avoidance method used. 제1항에 있어서 상기 장애물 감지 및 거리측정단계의 설정치는 According to claim 1, wherein the set value of the obstacle detection and distance measuring step 변위가 큰 값에서는 한계치 값이 커지고 변위 값이 작은 값에서는 한계치 값이 작아지는 적응 한계치인 것을 특징으로 하는 스테레오 카메라를 이용한 충돌회피 방법.Collision avoidance method using a stereo camera, characterized in that the higher the displacement value is the threshold value, the smaller the displacement value is the adaptive threshold value is smaller. 제1항에 있어서, 상기 검증(verification) 과정은 The method of claim 1, wherein the verification process is 좌 영상에서 후보군 영역을 차선의 넓이와 차선의 넓이만큼의 높이만큼의 사각형을 변위에 따른 도로 좌표 y를 기준으로 만들고 변위만큼 이동한 우 영상의 영역과 비교하여 가장 상관(correlation)이 높은 값을 선택하는 과정인 것을 특징으로 하는 스테레오 카메라를 이용한 충돌회피 방법.In the left image, the candidate area is defined by the width of the lane and the height of the lane as a rectangle based on the road coordinate y according to the displacement, and compared with the area of the right image moved by the displacement. Collision avoidance method using a stereo camera, characterized in that the process of selecting. 제1항에 있어서, 상기 임의의 차선검출방법은 The method of claim 1, wherein the lane detection method 적용 화상에 대해 임의의 각도의 직선상에 존재하는 모든 점들의 총합만을 구해 그 각도의 직선과 다른 각도의 직선에 대한 상대적인 길이의 크기를 비교하는 허프변환(Hough transform)을 이용한 방법인 것을 특징으로 하는 스테레오 카메라를 이용한 충돌회피 방법.It is a method using a Hough transform that obtains only the sum of all points existing on a straight line of an arbitrary angle with respect to an applied image and compares the magnitude of the length of the straight line of the angle with respect to the straight line of another angle. Collision avoidance method using a stereo camera. 제1항에 있어서, 상기 임의의 차선검출방법은 The method of claim 1, wherein the lane detection method 버즈 아이 뷰(Bird's eye view) 이미지에서의 템플릿 매칭(Template matching) 방법인 것을 특징으로 하는 스테에로 카메라를 이용한 충돌회피 방법.A collision avoidance method using a steroid camera, which is a template matching method in a bird's eye view image.
KR1020060086311A 2006-09-07 2006-09-07 Collision Avoidance Method Using Stereo Camera KR101103526B1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020060086311A KR101103526B1 (en) 2006-09-07 2006-09-07 Collision Avoidance Method Using Stereo Camera

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020060086311A KR101103526B1 (en) 2006-09-07 2006-09-07 Collision Avoidance Method Using Stereo Camera

Publications (2)

Publication Number Publication Date
KR20080022748A KR20080022748A (en) 2008-03-12
KR101103526B1 true KR101103526B1 (en) 2012-01-06

Family

ID=39396572

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020060086311A KR101103526B1 (en) 2006-09-07 2006-09-07 Collision Avoidance Method Using Stereo Camera

Country Status (1)

Country Link
KR (1) KR101103526B1 (en)

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR100938195B1 (en) * 2008-07-28 2010-01-21 재단법인대구경북과학기술원 Method for distance estimation and apparatus for the same using a stereo matching
KR101714783B1 (en) * 2009-12-24 2017-03-23 중앙대학교 산학협력단 Apparatus and method for detecting obstacle for on-line electric vehicle based on GPU
KR101239718B1 (en) * 2010-12-14 2013-03-06 주식회사 이미지넥스트 System and method for detecting object of vehicle surroundings
KR101415206B1 (en) * 2011-03-22 2014-08-06 주식회사 만도 Collision damage mitigation control method and apparatus
KR101611261B1 (en) 2013-12-12 2016-04-12 엘지전자 주식회사 Stereo camera, driver assistance apparatus and Vehicle including the same
KR101519261B1 (en) 2013-12-17 2015-05-11 현대자동차주식회사 Monitoring method and automatic braking apparatus
KR101676656B1 (en) 2014-12-22 2016-11-16 현대모비스 주식회사 Apparatus and method for detecting obstacle
KR101982263B1 (en) * 2018-01-10 2019-05-27 주식회사 만도 Vehicle control apparatus and vehicle control method
FR3077547A1 (en) * 2018-02-08 2019-08-09 Renault S.A.S SYSTEM AND METHOD FOR DETECTING A RISK OF COLLISION BETWEEN A MOTOR VEHICLE AND A SECONDARY OBJECT LOCATED ON CIRCULATION PATHS ADJACENT TO THE VEHICLE DURING CHANGE OF TRACK
CN110962847B (en) * 2019-11-26 2021-10-08 清华大学苏州汽车研究院（吴江） Lane centering auxiliary self-adaptive cruise trajectory planning method and system
CN113504782B (en) * 2021-09-09 2022-02-18 北京智行者科技有限公司 Obstacle collision prevention method, device and system and moving tool

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2008129764A (en) 2006-11-20 2008-06-05 Mazda Motor Corp Vehicle collision prevention apparatus

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2008129764A (en) 2006-11-20 2008-06-05 Mazda Motor Corp Vehicle collision prevention apparatus

Also Published As

Publication number Publication date
KR20080022748A (en) 2008-03-12

Similar Documents

Publication Publication Date Title
KR101103526B1 (en) Collision Avoidance Method Using Stereo Camera
CN106485233B (en) Method and device for detecting travelable area and electronic equipment
US7046822B1 (en) Method of detecting objects within a wide range of a road vehicle
JP5297078B2 (en) Method for detecting moving object in blind spot of vehicle, and blind spot detection device
EP2214149B1 (en) Collision avoidance assisting system for vehicle
JP6254083B2 (en) In-vehicle ambient environment recognition device
JP5690688B2 (en) Outside world recognition method, apparatus, and vehicle system
CN106647776B (en) Method and device for judging lane changing trend of vehicle and computer storage medium
KR101982298B1 (en) Method and apparatus for detecting sudden moving objecj appearance at vehicle
WO2016129403A1 (en) Object detection device
EP2463843A2 (en) Method and system for forward collision warning
EP1918897A2 (en) Apparatus and method for generating driver assistance information of traveling vehicle
JP2006184276A (en) All-weather obstacle collision preventing device by visual detection, and method therefor
Aytekin et al. Increasing driving safety with a multiple vehicle detection and tracking system using ongoing vehicle shadow information
JP2008219063A (en) Apparatus and method for monitoring vehicle&#39;s surrounding
KR101326943B1 (en) Overtaking vehicle warning system and overtaking vehicle warning method
KR102051397B1 (en) Apparatus and Method for Assisting Safe Driving
US20090052742A1 (en) Image processing apparatus and method thereof
JP5077088B2 (en) Image processing apparatus and image processing method
JP2008117073A (en) Interruption vehicle detection device
JP4937844B2 (en) Pedestrian detection device
WO2019065970A1 (en) Vehicle exterior recognition device
KR20150096924A (en) System and method for selecting far forward collision vehicle using lane expansion
CN111222441A (en) Point cloud target detection and blind area target detection method and system based on vehicle-road cooperation
KR20120086577A (en) Apparatus And Method Detecting Side Vehicle Using Camera

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: 20141222

Year of fee payment: 4

FPAY Annual fee payment

Payment date: 20151222

Year of fee payment: 5

FPAY Annual fee payment

Payment date: 20161222

Year of fee payment: 6

FPAY Annual fee payment

Payment date: 20171222

Year of fee payment: 7

FPAY Annual fee payment

Payment date: 20181226

Year of fee payment: 8

FPAY Annual fee payment

Payment date: 20191219

Year of fee payment: 9