JPH11232426A - Road shape recognizing device - Google Patents

Road shape recognizing device

Info

Publication number
JPH11232426A
JPH11232426A JP10028895A JP2889598A JPH11232426A JP H11232426 A JPH11232426 A JP H11232426A JP 10028895 A JP10028895 A JP 10028895A JP 2889598 A JP2889598 A JP 2889598A JP H11232426 A JPH11232426 A JP H11232426A
Authority
JP
Japan
Prior art keywords
road
real space
edge point
segment
line segment
Prior art date
Legal status (The legal status 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 status listed.)
Granted
Application number
JP10028895A
Other languages
Japanese (ja)
Other versions
JP3995782B2 (en
Inventor
Shinichi Matsunaga
慎一 松永
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Honda Motor Co Ltd
Original Assignee
Honda Motor Co Ltd
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 Honda Motor Co Ltd filed Critical Honda Motor Co Ltd
Priority to JP02889598A priority Critical patent/JP3995782B2/en
Publication of JPH11232426A publication Critical patent/JPH11232426A/en
Application granted granted Critical
Publication of JP3995782B2 publication Critical patent/JP3995782B2/en
Anticipated expiration legal-status Critical
Expired - Fee Related legal-status Critical Current

Links

Classifications

    • 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
    • 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
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components

Abstract

PROBLEM TO BE SOLVED: To provide a road shape recognizing device incorporating a signal camera with an improved detection accuracy of the real space position of a road division line. SOLUTION: The length of a segment (w) generated by applying an inverse projection conversion to a road segment S0 on a plane H which is supposed to be flat with a height 0 from the visual point P of a camera is estimated as a road width in a real space. Then the inverse projection conversion in applied to road segments S1 , S2 ...on the plane H to generate segments u1 , u2 ... The left end L1 of a segment U1 of length (w) that has one of its both ends existing on a segment jL connecting the point P and the left end of the segment u1 and the other end existing on a segment jR connecting the point P and the right end of the segment u1 is estimated as the left end position of the segment S1 in the real space, while the right end R1 of the segment U1 Z is estimated as the right end position of the segment S1 in the real space. In the same way, each left end of segments U2 ... is estimated as the left end real space position of each of segments S2 ..., and each right end of segments U2 ... is estimated as the right end real space position of each of segments S2 ... respectively.

Description

【発明の詳細な説明】DETAILED DESCRIPTION OF THE INVENTION

【０００１】[0001]

【発明の属する技術の分野】本発明は、カメラにより撮
像した車両前方の画像から道路区分線の実空間位置を検
出する道路形状認識装置に関する。BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a road shape recognizing device for detecting a real space position of a road dividing line from an image in front of a vehicle taken by a camera.

【０００２】[0002]

【従来の技術】従来より、カメラにより撮像した車両前
方の画像から、道路上に描かれた車両の左右の区分線
（道路区分線）の実空間位置を検出する道路形状認識装
置が広く知られている。2. Description of the Related Art Conventionally, there has been widely known a road shape recognizing device for detecting a real space position of left and right dividing lines (road dividing lines) of a vehicle drawn on a road from an image in front of the vehicle taken by a camera. ing.

【０００３】かかる道路形状認識装置により道路の登坂
や片勾配といった高さの変化のデータを得るためには、
２台のカメラを使用し、それぞれの撮像画像データか
ら、道路区分線の３次元座標（地表面の座標と地表から
の高さの座標）を検出する必要がある。[0003] In order to obtain data of a change in height such as a hill or a steep slope of a road using such a road shape recognition device,
It is necessary to detect the three-dimensional coordinates (the coordinates of the ground surface and the coordinates of the height from the ground surface) of the road dividing line from each captured image data using two cameras.

【０００４】しかし、このように２台のカメラを用いて
道路区分線の３次元座標を検出するには、２台のカメラ
のそれぞれに対して画像データの入力回路やメモリが必
要となるために装置構成が複雑になって装置コストが高
くなると共に、２台のカメラによる撮像画像データから
白線の３次元座標を得るための複雑な演算処理が必要と
なり、処理時間が長くなってしまう。However, in order to detect the three-dimensional coordinates of the road dividing line using two cameras, an input circuit and a memory for image data are required for each of the two cameras. The apparatus configuration becomes complicated and the apparatus cost increases, and complicated calculation processing for obtaining three-dimensional coordinates of a white line from image data captured by two cameras is required, which increases the processing time.

【０００５】そのため、一般には、図９ａに示すよう
に、１台のカメラによる撮像画像から道路区分線のエッ
ジ点ｅを抽出し、抽出したエッジ点の画像データｇを用
いて道路区分線の実空間位置を検出することが行われて
いる。具体的には、道路は平坦で高さ０であると仮定し
て、各エッジ点ｅをカメラの視点Ｐから平坦で高さ０の
平面Ｈに逆射影変換した位置ｌ、ｒを実空間における道
路区分線の位置であると推定して、白線の実空間位置を
検出している。Therefore, generally, as shown in FIG. 9A, an edge point e of a road dividing line is extracted from an image picked up by one camera, and an actual road dividing line is extracted using image data g of the extracted edge point. Detecting spatial position has been performed. Specifically, assuming that the road is flat and has a height of 0, the positions l and r obtained by inversely projecting each edge point e from the viewpoint P of the camera to a plane H having a height of 0 are defined in real space. The position of the road lane marking is estimated, and the real space position of the white line is detected.

【０００６】しかし、図９ｂに示すように実際には登坂
である道路ｃに対して、このように道路は平坦で高さ０
であると仮定して道路区分線の実空間位置を検出したと
きには、実際の道路区分線の実空間位置と検出された道
路区分線の実空間位置との間に大きなずれが生じるとい
う不都合があった。However, as shown in FIG. 9b, the road is flat and has a height of 0 with respect to the road c which is actually uphill.
When the real space position of the road lane marking is detected on the assumption that the actual road lane marking is located, there is an inconvenience that a large deviation occurs between the real space position of the actual road lane marking and the real space position of the detected road lane marking. Was.

【０００７】[0007]

【発明が解決しようとする課題】本発明は上記不都合を
解消し、１台のカメラを用いた道路形状認識装置におい
て、道路区分線の実空間位置の検出精度を向上させた道
路形状認識装置を提供することを目的とする。SUMMARY OF THE INVENTION The present invention solves the above-mentioned disadvantages and provides a road shape recognizing apparatus using one camera, which has improved detection accuracy of the real space position of a road dividing line. The purpose is to provide.

【０００８】[0008]

【課題を解決するための手段】本発明は、上記目的を達
成するためになされたものであり、１台のカメラにより
撮像され、水平方向及び垂直方向の２次元座標にマッピ
ングされた車両前方の画像データから、道路の左側区分
線のエッジ点である左エッジ点と右側区分線のエッジ点
である右エッジ点を抽出するエッジ点抽出手段と、該エ
ッジ点抽出手段により抽出された左エッジ点と右エッジ
点の実空間位置を推定することで、道路の左側区分線と
右側区分線の実空間位置を認識する実空間位置認識手段
とを備えた道路形状認識装置の改良に関する。SUMMARY OF THE INVENTION The present invention has been made to achieve the above-mentioned object, and has been made in consideration of the above-mentioned circumstances. Edge point extracting means for extracting, from the image data, a left edge point which is an edge point of a left dividing line of the road and a right edge point which is an edge point of a right dividing line; and a left edge point which is extracted by the edge point extracting means. The present invention relates to an improvement of a road shape recognition device including real space position recognizing means for recognizing real space positions of a left lane dividing line and a right lane dividing line of a road by estimating a real space position of a road and a right edge point.

【０００９】本発明における前記実空間位置認識手段
は、垂直方向の座標が同一である左エッジ点と右エッジ
点とを結ぶ線分である複数の道路線分を生成する道路線
分生成手段と、該道路線分生成手段により生成された複
数の道路線分の中から、前記２次元座標の下方にある１
本の道路線分を基準道路線分として選択し、前記カメラ
の視点から平坦で高さ０であると仮定した前記車両の走
行平面に、該基準道路線分を逆射影変換して生成した線
分の長さを実空間における道路幅と推定する道路幅推定
手段とを備える。The real space position recognizing means in the present invention includes a road segment generating means for generating a plurality of road segments which are segments connecting the left edge point and the right edge point having the same vertical coordinate. Out of the plurality of road segments generated by the road segment generating means,
This road line segment is selected as a reference road line segment, and a line generated by performing an inverse projection transformation of the reference road line segment on a traveling plane of the vehicle, which is assumed to be flat and has a height of 0 from the viewpoint of the camera. Road width estimating means for estimating the length of the minute as the road width in the real space.

【００１０】そして、前記実空間位置検出手段は、前記
基準道路線分よりも上側にある各道路線分ごとに、前記
カメラの視点から前記走行平面への逆射影変換を行い、
逆射影変換された道路線分と平行な線分であって、その
左端が逆射影変換により生成された線分の左端と前記カ
メラの視点とを結ぶ線分上にあると共にその右端が逆射
影変換により生成された線分の右端と前記カメラの視点
とを結ぶ線分上にあり、且つその長さが前記道路幅推定
手段により推定された道路幅と一致する線分を決定し、
決定した線分の左端の位置を逆射影変換された道路線分
を生成した左エッジ点の実空間位置と推定し、決定した
線分の右端の位置を逆射影変換された道路線分を生成し
た右エッジ点の実空間位置と推定するエッジ点位置推定
手段とを備えたことを特徴とする。[0010] The real space position detecting means performs a reverse projection transformation from the viewpoint of the camera to the traveling plane for each road segment above the reference road segment,
A line segment parallel to the inversely projected road segment, the left end of which is on the line segment connecting the left end of the line segment generated by the inverse projective transformation and the viewpoint of the camera, and the right end of which is the inversely projected line segment. Determining a line segment that is on a line segment connecting the right end of the line segment generated by the conversion and the viewpoint of the camera, and whose length matches the road width estimated by the road width estimation unit;
The left end position of the determined line segment is estimated as the real space position of the left edge point that generated the backprojected road segment, and the right end position of the determined line segment is generated the backprojected road segment. Edge point position estimating means for estimating the real space position of the right edge point.

【００１１】本発明者らは、上記目的を達成するために
各種検討を重ねた結果、前記実空間位置検出手段に、前
記道路線分生成手段と前記道路幅推定手段と前記エッジ
点位置推定手段とを備え、該エッジ点位置推定手段によ
り推された左エッジ点及び右エッジ点の実空間位置から
道路区分線の位置を認識することで、道路区分線の実空
間位置の検出精度が向上することを知見した。The present inventors have conducted various studies to achieve the above object. As a result, the real space position detecting means is provided with the road line segment generating means, the road width estimating means, and the edge point position estimating means. By recognizing the position of the road dividing line from the real space positions of the left edge point and the right edge point estimated by the edge point position estimating means, the detection accuracy of the real space position of the road dividing line is improved. I found that.

【００１２】また、前記実空間位置検出手段は、前記車
両前方の所定距離までの範囲においては、前記エッジ点
位置推定手段により前記左エッジ点と前記右エッジ点の
実空間位置を推定し、該所定距離より遠方の範囲におい
ては、前記エッジ点位置推定手段により各道路線分から
推定された、複数の左エッジ点の実空間位置を上空から
みたときの地表面位置に基づいて近似した放物線を、上
空からみた道路の左側区分線の実空間位置と推定し、ま
た、前記エッジ点位置推定手段により各道路線分から推
定された、複数の右エッジ点の実空間位置を上空からみ
たときの地表面位置に基づいて近似した放物線を上空か
らみた道路の右側区分線の実空間位置と推定することを
特徴とする。Further, the real space position detecting means estimates the real space positions of the left edge point and the right edge point by the edge point position estimating means in a range up to a predetermined distance in front of the vehicle. In the range farther than the predetermined distance, the parabola approximated based on the ground surface position when the real space positions of the plurality of left edge points estimated from each road line segment by the edge point position estimating means are viewed from the sky, The ground surface when the real space positions of a plurality of right edge points estimated from each road line segment by the edge point position estimating means are estimated from the sky as estimated from the real space position of the left lane marking of the road viewed from the sky. The method is characterized in that a parabola approximated based on the position is estimated as the real space position of the right dividing line of the road viewed from the sky.

【００１３】本発明者らは、車両前方の遠方における道
路区分線の実空間位置の検出精度を向上させるべく各種
検討を重ねた結果、前記エッジ点位置推定手段により推
定された、複数の左エッジ点の実空間位置を上空からみ
たときの地表面位置に基づいて近似した放物線を上空か
らみた道路の左側区分線の実空間位置と推定し、また、
前記エッジ点位置推定手段により各道路線分から推定さ
れた、複数の右エッジ点の実空間位置を上空からみたと
きの地表面位置に基づいて近似した放物線を上空からみ
た道路の右側区分線の実空間位置と推定することで、遠
方における道路区分線の検出精度が向上することを知見
した。The present inventors have conducted various studies to improve the detection accuracy of the real space position of the road lane marking in the distance ahead of the vehicle, and as a result, have found that a plurality of left edges estimated by the edge point position estimating means. A parabola approximated based on the ground position when the real space position of the point is viewed from the sky is estimated as the real space position of the left lane marking of the road viewed from the sky,
The parabola approximated based on the ground surface position when the real space positions of the plurality of right edge points are viewed from above, estimated from each road line segment by the edge point position estimating means, are the actual right-side segment lines of the road as viewed from above. It was found that by estimating the spatial position, the detection accuracy of distant road lane markings was improved.

【００１４】そして、本発明によれば、上述した従来の
２台のカメラを用いて道路区分線の実空間位置を検出す
る場合と比べて、簡易な演算処理で精度良く道路区分線
の実空間位置を検出することができる。According to the present invention, the real space of the road lane marking is more accurately calculated by simple arithmetic processing than in the case where the real space position of the road lane marking is detected by using the above-described conventional two cameras. The position can be detected.

【００１５】[0015]

【発明の実施の形態】本発明の実施の形態の一例を図１
〜図９を参照して説明する。図１は本発明の道路形状認
識装置を用いたレーンキープアシストシステムの全体構
成図、図２は本発明の道路形状認識装置において使用す
る座標系の説明図、図３，図４は本発明の道路区分線の
実空間位置推定処理のフローチャート、図５は道路幅推
定処理の説明図、図６は車両近傍におけるエッジ点の実
空間位置推定処理の説明図、図７は車両遠方における道
路区分線の実空間位置推定処理の説明図、図８は本発明
の道路形状認識装置と従来の道路形状認識装置による、
道路区分線の実空間位置の検出結果の比較図、図９は従
来の道路形状認識装置によるエッジ点の実空間位置推定
処理の説明図である。FIG. 1 shows an example of an embodiment of the present invention.
This will be described with reference to FIGS. FIG. 1 is an overall configuration diagram of a lane keeping assist system using the road shape recognition device of the present invention, FIG. 2 is an explanatory diagram of a coordinate system used in the road shape recognition device of the present invention, and FIGS. FIG. 5 is a flowchart of the road width estimation process, FIG. 6 is an illustration of the real space position estimation process of an edge point near the vehicle, and FIG. 7 is a road separation line at a distance from the vehicle. FIG. 8 is an explanatory diagram of the real space position estimating process of FIG.
FIG. 9 is a diagram illustrating a comparison between detection results of the real space position of the road dividing line, and FIG. 9 is an explanatory diagram of a real space position estimation process of an edge point by the conventional road shape recognition device.

【００１６】尚、本発明の道路形状認識装置は、主とし
て高速道路の走行を想定し、道路幅は一定であり、道路
の水平曲線及び縦断（垂直）曲線は緩やかに変化するこ
とを前提として道路区分線の実空間位置を検出する。The road shape recognizing device of the present invention is designed mainly on the assumption that the vehicle runs on a highway, the road width is constant, and the horizontal curve and the vertical (vertical) curve of the road gradually change. The real space position of the lane marking is detected.

【００１７】図１を参照して、本発明の道路形状認識装
置１は、エッジ点抽出手段２と実空間位置検出手段３と
を有し、カメラ４、前処理部５、行動計画作成部６、及
びアクチュエータ７と共に車両に搭載されて、該車両が
走行車線内を走行するようにステアリング角度の補正を
行うレーンキープアシストシステムを構成する。Referring to FIG. 1, a road shape recognition apparatus 1 of the present invention has an edge point extracting means 2 and a real space position detecting means 3, and has a camera 4, a preprocessing section 5, and an action plan creating section 6. , And an actuator 7 to constitute a lane keeping assist system that corrects a steering angle so that the vehicle travels in a traveling lane.

【００１８】カメラ４により取り込まれ、水平方向（ｘ
i ）と垂直方向（ｙi ）の２次元座標系にマッピングさ
れた原画像データａに対しては、前処理部５によりノイ
ズ除去等の前処理が行われる。Captured by the camera 4 and in the horizontal direction (x
The pre-processing unit 5 performs pre-processing such as noise removal on the original image data a mapped to the two-dimensional coordinate system of i ) and the vertical direction (y i ).

【００１９】そして、前処理がなされた原画像データａ
から、エッジ点抽出手段２により右側の道路区分線のエ
ッジ点（右エッジ点）と、左側の道路区分線のエッジ点
（左エッジ点）とが抽出される。尚、エッジ点の抽出は
前処理後の原画像データａに対して、各水平ライン毎に
各画素の明度データを水平方向に走査し、明度データが
明から暗、或いは暗から明に急激に変化する点を検出す
ることで行われる。The preprocessed original image data a
Then, the edge point extracting means 2 extracts the edge point (right edge point) of the right road division line and the edge point (left edge point) of the left road division line. The edge point is extracted by scanning the brightness data of each pixel in the horizontal direction on the original image data a after the preprocessing for each horizontal line, and the brightness data is sharply changed from light to dark or from dark to light. This is performed by detecting a changing point.

【００２０】実空間位置検出手段３は、道路線分生成手
段８と、道路幅推定手段９と、エッジ点位置推定手段１
０とを備え、エッジ点抽出手段２によって得られたエッ
ジ点データｇから、左エッジ点の実空間位置と右エッジ
点の実空間位置とを推定し、推定した左エッジ点の実空
間位置と右エッジ点の実空間位置とに基づいて、道路区
分線の実空間位置を検出する。The real space position detecting means 3 includes a road line segment generating means 8, a road width estimating means 9, and an edge point position estimating means 1.
0, the real space position of the left edge point and the real space position of the right edge point are estimated from the edge point data g obtained by the edge point extraction means 2, and the real space position of the estimated left edge point is The real space position of the road dividing line is detected based on the real space position of the right edge point.

【００２１】そして、行動計画作成部６は、道路形状認
識装置１によって検出された道路区分線の実空間位置に
基づいて、実空間における車両の走行パターンを作成
し、該走行パターンに応じてアクチュエータ７を介して
ステアリング角度を調節する。これにより、左側の道路
区分線と右側の道路区分線の間を走行するように、車両
の位置が制御される。The action plan creating unit 6 creates a running pattern of the vehicle in the real space based on the real space position of the road dividing line detected by the road shape recognizing device 1, and generates an actuator according to the running pattern. The steering angle is adjusted via 7. Thus, the position of the vehicle is controlled so as to travel between the left road lane and the right road lane.

【００２２】次に、図２は実空間位置検出手段３におい
て使用される座標系の説明図である。図２ａを参照し
て、実空間における道路区分線の位置は、車両２０の中
心真下（高さ０）の点を原点とし、車両２０の進行方向
を正とするＸm 軸と、Ｘm 軸と直交し、車両２０の進行
方向に向かって左手を正とするＹm 軸と、Ｘm −Ｙm 平
面と直交して上空方向を正とするＺm 軸からなる、Ｘm
−Ｙm −Ｚm の３次元座標系（以下、実空間座標系とい
う）によって特定される。FIG. 2 is an explanatory diagram of a coordinate system used in the real space position detecting means 3. Referring to FIG. 2A, the position of the road dividing line in the real space is defined as an X m axis having a point immediately below the center of the vehicle 20 (height 0) as an origin and a traveling direction of the vehicle 20 being positive, and an X m axis. perpendicular to the Y m axis to correct the left hand in the traveling direction of the vehicle 20 and a Z m axis the sky direction and positive at right angles to the X m -Y m plane, X m
It is specified by a three-dimensional coordinate system of −Y m −Z m (hereinafter, referred to as a real space coordinate system).

【００２３】また、図２ｂはカメラ４の座標系とエッジ
点データｇの座標系との関係を示したものである。カメ
ラ４の座標系は、カメラ４の視点Ｐを原点とし、カメラ
４の視線方向に対して右手方向を正とするｘc 軸と、視
線方向及びｘc 軸と直交して上方向を正とするｙc 軸
と、視線軸であって視線方向を正とするｚc 軸とからな
るｘc −ｙc −ｚc の３次元座標系（以下、カメラ座標
系という）である。また、エッジ点データｇの座標系
は、カメラ４からみたエッジ点画像ｇの左上を原点と
し、右方向を正とするｘi 軸と、下方向を正とするｙi
軸とからなるｘi −ｙ i の２次元座標系（以下、エッジ
点座標系という）である。FIG. 2B shows the coordinate system of the camera 4 and the edge.
This shows the relationship between the point data g and the coordinate system. turtle
The coordinate system of the camera 4 is based on the viewpoint P of the camera 4 as the origin.
X with the right hand direction being positive with respect to the line of sight 4cAxis and vision
Line direction and xcY whose direction perpendicular to the axis is positivecaxis
And z, which is the visual axis and the visual direction is positivecWith the axis
Xc-Yc-Zc3D coordinate system (hereinafter, camera coordinates)
System). Also, the coordinate system of the edge point data g
Is the origin at the upper left of the edge point image g as viewed from the camera 4.
X with the right direction being positiveiAxis and y with the downward direction as positivei
X consisting of an axisi-Y iTwo-dimensional coordinate system (hereinafter, edge
Point coordinate system).

【００２４】カメラ４の焦点距離ｆは既知であるので、
エッジ点データｇにおける１画素の長さ（ｍｍ／ｄｏ
ｔ）が定まる。そして、カメラ４の視点Ｐの実空間座標
系における座標と、カメラ４の前後左右の傾きも既知で
あるため、カメラ座標系から実空間座標系への座標変換
を行うことができる。Since the focal length f of the camera 4 is known,
Length of one pixel in the edge point data g (mm / do
t) is determined. Since the coordinates of the viewpoint P of the camera 4 in the real space coordinate system and the inclination of the camera 4 in the front, rear, left and right directions are also known, the coordinate transformation from the camera coordinate system to the real space coordinate system can be performed.

【００２５】実空間位置検出手段３は、エッジ点データ
ｇにおける各左エッジ点及び右エッジ点のエッジ座標系
における座標をカメラ座標系の座標に変換し、変換した
左エッジ点及び右エッジ点のカメラ座標系の座標を用い
て、該左エッジ点及び右エッジ点をカメラ４の視点Ｐか
らエッジ点データｇの前方に逆射影変換することで、実
空間における左エッジ点及び右エッジ点のカメラ座標系
の座標を推定する。The real space position detecting means 3 converts the coordinates of each left edge point and right edge point in the edge point data g in the edge coordinate system into the coordinates in the camera coordinate system, and converts the converted left edge point and right edge point. Using the coordinates of the camera coordinate system, the left edge point and the right edge point are inversely projected and transformed from the viewpoint P of the camera 4 to the front of the edge point data g. Estimate the coordinates of the coordinate system.

【００２６】そして、実空間位置検出手段３は、このよ
うにして推定した実空間におけるカメラ座標系の左エッ
ジ点と右エッジ点の座標を実空間座標系の座標に変換
し、該左エッジ点及び右エッジ点の実空間座標系の座標
に基づいて、左右の道路側区分線の実空間位置を検出す
る。Then, the real space position detecting means 3 converts the coordinates of the left edge point and the right edge point of the camera coordinate system in the real space estimated in this manner into the coordinates of the real space coordinate system. And the real space positions of the left and right roadside dividing lines are detected based on the coordinates of the right edge point in the real space coordinate system.

【００２７】以下、図３，図４に示したフローチャート
に従って、実空間位置検出手段３による道路区分線の実
空間位置の検出処理について説明する。The process of detecting the real space position of the road dividing line by the real space position detecting means 3 will be described below with reference to the flowcharts shown in FIGS.

【００２８】図３を参照して、ＳＴＥＰ１で、実空間位
置検出手段３に備えられた道路線分生成手段８は、図５
ａに示すように、エッジ点データｇより、ｙi 座標が同
一である左エッジ点と右エッジ点とを結んだ線分である
道路線分Ｓ0 ，Ｓ1 , ・・・，Ｓn を生成する。Referring to FIG. 3, in STEP 1, the road segment generation means 8 provided in the real space position detection means 3 is
As shown in a, the edge point data g, the road segment S 0, S 1 is a line connecting the left edge point and the right edge point is identical y i coordinate, ..., and S n Generate.

【００２９】続くＳＴＥＰ２で、実空間位置検出手段３
に備えられた道路幅推定手段９は、図５ａに示した道路
線分Ｓ0 ，Ｓ1 ，・・・，Ｓn の中から、最も下側（車
両側）にある道路線分Ｓ0 （図５ａのｙi ＝４００のラ
イン上にある）を基準道路線分として選択する。尚、基
準道路線分として選択するのは、必ずしも最も下側にあ
る道路線分に限られず、場合によっては下から２番目の
道路線分（Ｓ1 ）や、３番目の道路線分（Ｓ2 ）を基準
道路線分としてもよい。In the following STEP2, the real space position detecting means 3
Road width estimation means 9 provided in the road segment S 0 shown in FIG. 5a, S 1, · · ·, from among S n, the road segment S 0 the most to the lower (vehicle) ( 5a on the line y i = 400) is selected as the reference road segment. The selection as the reference road segment is not necessarily limited to the lowermost road segment, and in some cases, the second lower road segment (S 1 ) or the third lower road segment (S 1 2 ) may be used as the reference road segment.

【００３０】そして、ＳＴＥＰ３で、道路幅推定手段９
は、図５ｂに示すように、カメラ４の視点Ｐから平坦で
高さ０（Ｚm ＝０）であると想定した車両前方の平面Ｈ
に基準道路線分Ｓ0 を逆射影変換し、ＳＴＥＰ４で、該
逆射影変換によって生成された線分ｕ0 の長さｗを、実
空間における道路幅と推定する。Then, in STEP 3, the road width estimating means 9
Is a plane H in front of the vehicle which is assumed to be flat and at a height of 0 (Z m = 0) from the viewpoint P of the camera 4 as shown in FIG.
The inverse projective transformation of the reference road line segment S 0, in STEP4, the length w of the line segment u 0 generated by the inverse projective transformation to estimate the road width in the real space.

【００３１】次のＳＴＥＰ５からＳＴＥＰ１０は、実空
間位置検出手段３に備えられたエッジ点位置推定手段１
０による、車両近傍におけるエッジ点データｇの左エッ
ジ点及び右エッジ点の実空間位置の推定処理である。The next STEP 5 to STEP 10 are the edge point position estimating means 1 provided in the real space position detecting means 3.
0 is a process for estimating the real space positions of the left edge point and the right edge point of the edge point data g near the vehicle, based on 0.

【００３２】エッジ点位置推定手段１０は、ＳＴＥＰ５
でカウンタ変数ｉに１を代入し、ＳＴＥＰ６で道路線分
Ｓi （ここではｉ＝１）を、図６に示すように、車両前
方の平坦で高さ０（Ｚm ＝０）であると仮定した平面Ｈ
に逆射影変換する。そして、エッジ点位置推定手段１０
は、逆射影変換により生成された平面Ｈ上の線分ｕ1と
平行な線分であって、その左端がカメラ４の視点Ｐと線
分ｕ1 の左端を結んだ線分ＪL 上にあると共にその右端
がカメラ４の視点Ｐと線分ｕ1 の右端を結んだ線分ＪR
上にあり、且つその長さが道路幅推定手段９によって推
定された道路幅ｗと等しい線分Ｕ1 を決定する。The edge point position estimating means 10 determines in STEP 5
In step 6, 1 is substituted for the counter variable i. In step 6, the road segment S i (here, i = 1) is assumed to be flat and 0 in height (Z m = 0) in front of the vehicle as shown in FIG. Assumed plane H
Is inversely projected. Then, the edge point position estimating means 10
Is a line segment parallel to the line segment u 1 on the plane H generated by the inverse projection transformation, and the left end of the line segment is on the line segment J L connecting the viewpoint P of the camera 4 and the left end of the line segment u 1. A line segment J R connecting the viewpoint P of the camera 4 and the right end of the line segment u 1.
It is above, and its length determines the line U 1 equal to the estimated road width w by the road width estimation means 9.

【００３３】エッジ点位置推定手段１０は、このように
して決定した線分Ｕ1 の右端Ｒ1 を道路線分Ｓ1 の右エ
ッジ点の実空間位置と推定し、線分Ｕ1 の左端Ｌ1 を道
路線分Ｓ1 の左エッジ点の実空間位置と推定する。The edge point position estimating means 10 estimates the right end R 1 of the line segment U 1 determined in this way as the real space position of the right edge point of the road segment S 1 , and calculates the left end L 1 of the line segment U 1 . 1 estimates the actual spatial position of the left edge in the road segment S 1.

【００３４】エッジ点位置推定手段１０は、続くＳＴＥ
Ｐ９でカウンタ変数ｉに１を加え、ＳＴＥＰ１０で、Ｓ
ＴＥＰ８で推定した左エッジ点及び右エッジ点の実空間
位置が、実空間座標系のＹm 軸から車両前方（Ｘm 軸正
方向）に４０ｍ（本発明の所定距離に相当）以上離れて
いるか否かを判定する。そして、ＳＴＥＰ８で推定した
左エッジ点及び右エッジ点の実空間位置が、実空間座標
系のＹm 軸から４０ｍ以上離れていないときは、ＳＴＥ
Ｐ６に分岐して次の道路線分に対してＳＴＥＰ６〜ＳＴ
ＥＰ８の処理を行う。The edge point position estimating means 10 performs the following STE
In P9, 1 is added to the counter variable i, and in STEP10, S
Whether the real space positions of the left edge point and the right edge point estimated in TEP8 are at least 40 m (corresponding to a predetermined distance of the present invention) in front of the vehicle (X m axis positive direction) from the Y m axis of the real space coordinate system. Determine whether or not. Then, when the actual spatial position of the left edge point and the right edge point estimated in STEP8 is not closer than 40m from the Y m axis of the real space coordinate system, STE
Branching to P6, STEP6 to ST for the next road segment
The processing of EP8 is performed.

【００３５】このように、エッジ点位置推定手段１０に
よりＳＴＥＰ６〜ＳＴＥＰ１０のループを実行すること
で、実空間座標系のＹm 軸から車両前方４０ｍまでの範
囲でのエッジ点データｇの左エッジ点の実空間位置
Ｌ1 ，Ｌ2 ，・・・と、右エッジ点の実空間位置Ｒ1 ，
Ｒ2 ，・・・とが推定される。[0035] Thus, by the edge point position estimating means 10 by executing the loop of STEP6～STEP10, left edge points of the edge point data g in the range from Y m axis of the real space coordinate system to the vehicle front 40m real space position of L 1, L 2, and ..., real space position R 1 in the right edge point,
R 2 ,... Are estimated.

【００３６】一方、ＳＴＥＰ１０で、ＳＴＥＰ８で推定
した左エッジ点及び右エッジ点の実空間位置が、実空間
座標系のＹm 軸から車両前方（Ｘm 軸正方向）に４０ｍ
（本発明の所定距離に相当）以上離れていたときには、
ＳＴＥＰ１１に進む。On the other hand, in STEP 10, the real space position of the left edge point and the right edge point estimated in STEP 8 is 40 m ahead of the Ym axis of the real space coordinate system (X m axis positive direction).
(Equivalent to the predetermined distance of the present invention)
Go to STEP11.

【００３７】ＳＴＥＰ１１〜ＳＴＥＰ１２は、実空間位
置検出手段３による、車両前方４０ｍ以上先の道路区分
線の実空間位置の推定処理である。実空間位置検出手段
３は、ＳＴＥＰ１１で、図７に示すように、上空から見
た地表面（Ｘm −Ｙm 平面）において、道路幅推定手段
９と近傍エッジ点位置推定手段１０とにより推定された
エッジ点データｇの左エッジ点の実空間位置Ｌ0 ，
Ｌ1 ，Ｌ2 ，・・・から放物線ｆ1 を近似し、エッジ点
データｇの右エッジ点の実空間位置Ｒ0 , Ｒ1 ，Ｒ 2,・
・・から放物線ｆ2 を近似する。STEP11 to STEP12 are the real space positions.
Road segment 40 m or more ahead of the vehicle by the position detection means 3
This is a process of estimating the real space position of a line. Real space position detection means
3 is STEP11, as seen from above, as shown in FIG.
Ground surface (Xm-YmRoad width estimating means
9 and the neighboring edge point position estimating means 10
Real space position L of left edge point of edge point data g0,
L1, LTwoFrom the parabola f1And the edge points
Real space position R of right edge point of data g0,R1, R 2,・
..From parabola fTwoIs approximated.

【００３８】そして、実空間位置検出手段３は、ＳＴＥ
Ｐ１２で、ＳＴＥＰ１１で近似した放物線ｆ1 を上空か
らみた地表面（Ｘm −Ｙm 平面）における左側の道路区
分線の実空間位置と推定し、ｆ2 を上空からみた地表面
（Ｘm −Ｙm 平面）における右側の道路区分線の実空間
位置と推定する。Then, the real space position detecting means 3
In P12, estimates the actual spatial position of the left side of the road lane marking on the ground surface (X m -Y m plane) as viewed from above the parabola f 1 approximated by STEP 11, the land surface viewed f 2 from above (X m - It is estimated as the real space position of the right road division line on the Ym plane).

【００３９】このようにして、実空間位置検出手段３に
より、車両２０の前方４０ｍまでの範囲では、エッジ点
位置推定手段１０により推定した左エッジ及び右エッジ
点の実空間位置から、また、車両２０の前方４０ｍから
遠方の範囲では、前記放物線ｆ1 及びｆ2 の実空間位置
から、左右の道路区分線の実空間位置を推定したとこ
ろ、図９ａに示した、走行面が平坦であると仮定して逆
射影変換を行ってエッジ点の実空間位置を推定した従来
の道路形状認識装置に比べて、図８に示すように、道路
区分線の実空間位置の検出精度が著しく向上することが
確認できた。As described above, in the range up to 40 m in front of the vehicle 20 by the real space position detecting means 3, the real space positions of the left edge and the right edge point estimated by the edge point position estimating means 10 are used. In a range distant from 40 m in front of 20 from the real space positions of the parabolas f 1 and f 2 , when the real space positions of the left and right road dividing lines were estimated, the running surface shown in FIG. 9A was flat. As shown in FIG. 8, the detection accuracy of the real space position of the road lane marking is significantly improved as compared with the conventional road shape recognition device that presumes the real space position of the edge point by performing the inverse projection transformation. Was confirmed.

【００４０】図８は、車両が、水平方向が２３０Ｒの右
カーブ、垂直方向が２０００Ｒの上り坂、片勾配が１０
％の右下がりである高速道路を走行中であることを想定
して、図９ａに示した従来の道路形状認識装置と本発明
の道路形状認識装置とにより、道路区分線の実空間位置
を検出したときの、上空から見た（Ｘm −Ｙm 平面）道
路区分線の位置を比較したものである。図中、，が
実際の左右の道路区分線の位置、，が本発明の道路
形状認識装置による左右の道路区分線の検出位置、，
が従来の道路形状認識装置による左右の道路区分線の
検出位置である。FIG. 8 shows that the vehicle has a right curve of 230R in the horizontal direction, an uphill slope of 2000R in the vertical direction, and a slope of 10R.
Assuming that the vehicle is traveling on a highway which is downhill to the right, the real space position of the road lane marking is detected by the conventional road shape recognition device shown in FIG. 9A and the road shape recognition device of the present invention. when the saw from above (X m -Y m-plane) is obtained by comparing the position of the road lane marking. In the figure, indicates the actual positions of the left and right road division lines, indicates the detection positions of the left and right road division lines by the road shape recognition device of the present invention,
Are the detection positions of the left and right road dividing lines by the conventional road shape recognition device.

【００４１】図８から明らかなように、従来の道路形状
認識装置では、前方２０ｍ付近から実際の道路区分線の
実空間位置に対して検出位置がずれ始め、４０ｍより遠
方になるにつれてずれ量が急激に増大している。これに
対して、本発明の道路形状認識装置によれば、４０ｍ地
点でのずれはほとんどなく、遠方においても実際の道路
区分線の位置と、検出位置とのずれ量は微量に留まって
いる。As is apparent from FIG. 8, in the conventional road shape recognition device, the detection position starts to shift from the vicinity of 20 m ahead to the real space position of the actual road lane marking, and the amount of shift increases as the distance from the road becomes greater than 40 m. It is increasing rapidly. On the other hand, according to the road shape recognition device of the present invention, there is almost no displacement at the point of 40 m, and the displacement between the actual position of the road lane marking and the detected position is small even in a distant place.

【００４２】以上説明したように、本発明の道路形状認
識装置によれば、１台のカメラを用いた道路区分線の実
空間位置の検出精度を向上することができ、本発明の道
路形状認識装置を用いることで、レーンキープアシスト
システムの信頼性を向上させることができる。As described above, according to the road shape recognition device of the present invention, it is possible to improve the detection accuracy of the real space position of the road lane marking using one camera, and it is possible to improve the road shape recognition device of the present invention. By using the device, the reliability of the lane keep assist system can be improved.

【００４３】尚、本実施形態において、実空間位置検出
手段３は、車両前方４０ｍよりも遠方では、放物線近似
により道路区分線の実空間位置を推定することで、特に
遠方の道路区分線の実空間位置の検出精度を向上させた
が、車両前方の全範囲について、エッジ点位置推定手段
１０により推定した左右のエッジ点の実空間位置から道
路区分線の実空間を推定した場合でも、従来の道路形状
認識装置よりも道路区分線の実空間位置の検出精度を向
上させることができる。In the present embodiment, the real space position detecting means 3 estimates the real space position of the road dividing line by parabolic approximation at a distance more than 40 m ahead of the vehicle, so that the actual spatial position of the distant road dividing line is particularly large. Although the detection accuracy of the spatial position has been improved, even when the real space of the road dividing line is estimated from the real space positions of the left and right edge points estimated by the edge point position estimating means 10 over the entire range in front of the vehicle, The detection accuracy of the real space position of the road dividing line can be improved as compared with the road shape recognition device.

【図面の簡単な説明】[Brief description of the drawings]

【図１】本発明の道路形状認識装置を用いたレーンキー
プアシストシステムの全体構成図。FIG. 1 is an overall configuration diagram of a lane keeping assist system using a road shape recognition device of the present invention.

【図２】道路形状認識装置において使用する座標系の説
明図。FIG. 2 is an explanatory diagram of a coordinate system used in the road shape recognition device.

【図３】道路区分線の実空間位置推定処理のフローチャ
ート。FIG. 3 is a flowchart of a process of estimating a real space position of a road dividing line.

【図４】道路区分線の実空間位置推定処理のフローチャ
ート。FIG. 4 is a flowchart of a process of estimating a real space position of a road dividing line.

【図５】道路幅推定方法の説明図。FIG. 5 is an explanatory diagram of a road width estimation method.

【図６】車両近傍におけるエッジ点の実空間位置推定処
理の説明図。FIG. 6 is an explanatory diagram of a real space position estimation process of an edge point near a vehicle.

【図７】車両遠方におけるエッジ点の実空間位置推定処
理の説明図。FIG. 7 is an explanatory diagram of a process of estimating a real space position of an edge point in a distant place of a vehicle.

【図８】本発明の道路形状認識装置と従来の道路形状認
識装置による道路区分線の検出結果の比較図。FIG. 8 is a comparison diagram of road segmentation line detection results obtained by the road shape recognition device of the present invention and a conventional road shape recognition device.

【図９】従来の道路形状認識装置によるエッジ点の実空
間位置推定処理の説明図。FIG. 9 is an explanatory diagram of a real space position estimation process of an edge point by a conventional road shape recognition device.

【符号の説明】[Explanation of symbols]

１…道路形状認識装置、２…エッジ点抽出手段、３…実
空間位置検出手段、４…カメラ、５…前処理部、６…行
動計画作成部、７…アクチュエータ、８…道路線分生成
手段、９…道路幅推定手段、１０…エッジ点位置推定手
段DESCRIPTION OF SYMBOLS 1 ... Road shape recognition apparatus, 2 ... Edge point extraction means, 3 ... Real space position detection means, 4 ... Camera, 5 ... Pre-processing part, 6 ... Action plan creation part, 7 ... Actuator, 8 ... Road segment generation means , 9 ... road width estimating means, 10 ... edge point position estimating means

Claims (2)

【特許請求の範囲】[Claims] 【請求項１】１台のカメラにより撮像され、水平方向及
び垂直方向の２次元座標にマッピングされた車両前方の
画像データから、道路の左側区分線のエッジ点である左
エッジ点と右側区分線のエッジ点である右エッジ点を抽
出するエッジ点抽出手段と、該エッジ点抽出手段により
抽出された左エッジ点と右エッジ点の実空間位置を推定
することで、道路の左側区分線と右側区分線の実空間位
置を検出する実空間位置検出手段とを備えた道路形状認
識装置において、 前記実空間位置検出手段は、垂直方向の座標が同一であ
る左エッジ点と右エッジ点とを結ぶ線分である道路線分
を生成する道路線分生成手段と、 該道路線分生成手段により生成された複数の道路線分の
中から、前記２次元座標の下方にある１本の道路線分を
基準道路線分として選択し、前記カメラの視点から平坦
で高さ０であると仮定した前記車両の走行平面に、該基
準道路線分を逆射影変換して生成した線分の長さを実空
間における道路幅と推定する道路幅推定手段と、 前記基準道路線分よりも上側にある各道路線分ごとに、
前記カメラの視点から前記走行平面への逆射影変換を行
い、逆射影変換された道路線分と平行な線分であって、
その左端が逆射影変換により生成された線分の左端と前
記カメラの視点とを結ぶ線分上にあると共にその右端が
逆射影変換により生成された線分の右端と前記カメラの
視点とを結ぶ線分上にあり、且つその長さが前記道路幅
推定手段により推定された道路幅と一致する線分を決定
し、決定した線分の左端の位置を逆射影変換された道路
線分を生成した左エッジ点の実空間位置と推定し、決定
した線分の右端の位置を逆射影変換された道路線分を生
成した右エッジ点の実空間位置と推定するエッジ点位置
推定手段とを備えたことを特徴とする道路形状認識装
置。1. A left edge point and a right edge line, which are edge points of a left edge line of a road, based on image data in front of a vehicle imaged by one camera and mapped to two-dimensional coordinates in a horizontal direction and a vertical direction. Edge point extracting means for extracting a right edge point, which is an edge point of the road, and estimating the real space positions of the left edge point and the right edge point extracted by the edge point extracting means, so that the left dividing line and the right A road shape recognition device comprising: real space position detecting means for detecting a real space position of a lane marking; wherein the real space position detecting means connects a left edge point and a right edge point having the same vertical coordinate. A road segment generating means for generating a road segment which is a line segment; and a single road segment below the two-dimensional coordinates from a plurality of road segments generated by the road segment generating means. As the reference road segment And the length of a line segment generated by performing a reverse projection transformation of the reference road line segment on the traveling plane of the vehicle, which is assumed to be flat and has a height of 0 from the viewpoint of the camera, is defined as a road width in a real space. Road width estimating means for estimating, for each road segment above the reference road segment,
Perform a reverse projection transformation from the viewpoint of the camera to the traveling plane, a line segment parallel to the road segment subjected to the reverse projection transformation,
The left end is on a line segment connecting the left end of the line segment generated by the inverse projection transformation and the viewpoint of the camera, and the right end connects the right end of the line segment generated by the inverse projection transformation and the viewpoint of the camera. A line segment that is on the line segment and whose length coincides with the road width estimated by the road width estimating means is determined, and the left end position of the determined line segment is subjected to reverse projection transformation to generate a road segment. Edge point position estimating means for estimating the real space position of the determined left edge point, and estimating the right end position of the determined line segment as the real space position of the right edge point that has generated the road segment subjected to the inverse projection transformation. A road shape recognition device, characterized in that: 【請求項２】前記実空間位置検出手段は、前記車両前方
の所定距離までの範囲においては、前記エッジ点位置推
定手段により前記左エッジ点と前記右エッジ点の実空間
位置を推定し、 該所定距離より遠方の範囲においては、前記エッジ点位
置推定手段により各道路線分から推定された、複数の左
エッジ点の実空間位置を上空からみたときの地表面位置
に基づいて近似した放物線を、上空からみた道路の左側
区分線の実空間位置と推定し、また、前記エッジ点位置
推定手段により各道路線分から推定された、複数の右エ
ッジ点の実空間位置を上空からみたときの地表面位置に
基づいて近似した放物線を上空からみた道路の右側区分
線の実空間位置と推定することを特徴とする請求項１記
載の道路形状認識装置。2. The real space position detecting means estimates the real space positions of the left edge point and the right edge point by the edge point position estimating means in a range up to a predetermined distance in front of the vehicle. In the range farther than the predetermined distance, the parabola approximated based on the ground surface position when the real space positions of the plurality of left edge points estimated from each road line segment by the edge point position estimating means are viewed from the sky, The ground surface when the real space positions of a plurality of right edge points estimated from each road line segment by the edge point position estimating means are estimated from the sky as estimated from the real space position of the left lane marking of the road viewed from the sky. 2. The road shape recognition device according to claim 1, wherein a parabola approximated based on the position is estimated as a real space position of a right-side dividing line of the road viewed from above.
JP02889598A 1998-02-10 1998-02-10 Road shape recognition device Expired - Fee Related JP3995782B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP02889598A JP3995782B2 (en) 1998-02-10 1998-02-10 Road shape recognition device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP02889598A JP3995782B2 (en) 1998-02-10 1998-02-10 Road shape recognition device

Publications (2)

Publication Number Publication Date
JPH11232426A true JPH11232426A (en) 1999-08-27
JP3995782B2 JP3995782B2 (en) 2007-10-24

Family

ID=12261143

Family Applications (1)

Application Number Title Priority Date Filing Date
JP02889598A Expired - Fee Related JP3995782B2 (en) 1998-02-10 1998-02-10 Road shape recognition device

Country Status (1)

Country Link
JP (1) JP3995782B2 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001116512A (en) * 1999-10-20 2001-04-27 Matsushita Electric Ind Co Ltd Method and instrument for measuring distance between vehicles

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2001116512A (en) * 1999-10-20 2001-04-27 Matsushita Electric Ind Co Ltd Method and instrument for measuring distance between vehicles

Also Published As

Publication number Publication date
JP3995782B2 (en) 2007-10-24

Similar Documents

Publication Publication Date Title
JP3868876B2 (en) Obstacle detection apparatus and method
JP3759429B2 (en) Obstacle detection apparatus and method
US7612800B2 (en) Image processing apparatus and method
JP3711405B2 (en) Method and system for extracting vehicle road information using a camera
US7266454B2 (en) Obstacle detection apparatus and method for automotive vehicle
EP1403615B1 (en) Apparatus and method for processing stereoscopic images
JP2003296736A (en) Device for detecting obstacle and method thereof
JPH10208047A (en) On-vehicle traveling environment recognizing device
JP2005148817A (en) Image processor for vehicle
WO2018179281A1 (en) Object detection device and vehicle
JP3656056B2 (en) Interrupting vehicle detection device and method
JP4052291B2 (en) Image processing apparatus for vehicle
JP2014127027A (en) Boundary line recognition device
JP2003281552A (en) Image processor and method
JP2004280194A (en) Forward monitor and method therefor
JP3629935B2 (en) Speed measurement method for moving body and speed measurement device using the method
JP3945919B2 (en) Traveling path detection device, vehicle travel control device, and recording medium
JP3977505B2 (en) Road shape recognition device
JP2000048183A (en) Traveling lane recognizing device
JP7404173B2 (en) Image processing device
JPH11232426A (en) Road shape recognizing device
JP2013196401A (en) Road environment recognizing apparatus
JPH07220194A (en) Road environment recognizing device
Iwata et al. Forward obstacle detection in a lane by stereo vision
JP4397164B2 (en) Obstacle detection device and obstacle detection method

Legal Events

Date Code Title Description
A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20041129

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20070313

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20070511

TRDD Decision of grant or rejection written
A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

Effective date: 20070731

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20070801

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20100810

Year of fee payment: 3

R150 Certificate of patent or registration of utility model

Free format text: JAPANESE INTERMEDIATE CODE: R150

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20100810

Year of fee payment: 3

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20100810

Year of fee payment: 3

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20110810

Year of fee payment: 4

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20110810

Year of fee payment: 4

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20120810

Year of fee payment: 5

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20120810

Year of fee payment: 5

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20130810

Year of fee payment: 6

FPAY Renewal fee payment (event date is renewal date of database)

Free format text: PAYMENT UNTIL: 20140810

Year of fee payment: 7

LAPS Cancellation because of no payment of annual fees