JPH05282431A - Environment recognizing device for mobile vehicle - Google Patents
Environment recognizing device for mobile vehicleInfo
- Publication number
- JPH05282431A JPH05282431A JP4077386A JP7738692A JPH05282431A JP H05282431 A JPH05282431 A JP H05282431A JP 4077386 A JP4077386 A JP 4077386A JP 7738692 A JP7738692 A JP 7738692A JP H05282431 A JPH05282431 A JP H05282431A
- Authority
- JP
- Japan
- Prior art keywords
- reflection
- vehicle
- candidate point
- point
- photographic
- 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.)
- Withdrawn
Links
- 230000015654 memory Effects 0.000 abstract description 5
- 238000000034 method Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 230000010287 polarization Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Landscapes
- Length Measuring Devices By Optical Means (AREA)
- Image Processing (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Image Analysis (AREA)
Abstract
Description
【０００１】[0001]
【産業上の利用分野】本発明は移動車の環境認識装置、
特に２眼ステレオと移動ステレオとを用いて写り込みを
検出する移動車の環境認識装置に関するものである。BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an environment recognition device for a mobile vehicle,
In particular, the present invention relates to an environment recognition device for a moving vehicle that detects a reflection using a twin-lens stereo and a moving stereo.
【０００２】[0002]
【従来の技術】従来から、２眼ステレオ等で移動車の環
境を認識する装置が知られているが（例えば、特開平２
−４８７０４号公報）、通常、路面が濡れている等の状
況に起因して、車両前方における、例えば、蛍光灯に代
表される街路灯や信号灯等の発光体が路面上で反射し、
いわゆる写り込みが生じる。そして、従来より、この写
り込みを偏光フィルタ等を用いて除去している。2. Description of the Related Art Conventionally, a device for recognizing the environment of a moving vehicle by a twin-lens stereo system or the like has been known (see, for example, Japanese Patent Laid-Open No. HEI-2)
-48704 gazette), due to a situation where the road surface is wet, etc., a light emitter such as a street light or a signal light typified by a fluorescent light is reflected on the road surface in front of the vehicle.
So-called reflection occurs. Then, conventionally, this reflection is removed by using a polarization filter or the like.
【０００３】[0003]
【発明が解決しようとしている課題】しかしながら、上
記従来の偏光フィルタを用いる方法は、発光体からの光
が一定角度にて入射する場合には有効であるが、通常、
車両の移動にてこの角度は変化するので、すべての場合
に偏光フィルタが有効であるとは言えないという問題が
ある。また、偏光フィルタは、誘電体からの反射に対し
ては有効であるが、金属面等からの鏡面反射に対して
は、反射光の偏光面が変わらないため役に立たない。本
発明は、かかる問題点に鑑みて成されたもので、その目
的とするところは、写り込みを確実に認識できる移動車
の環境認識装置を提供することである。However, the above-mentioned method using the conventional polarization filter is effective when the light from the light-emitting body is incident at a constant angle, but normally,
Since this angle changes as the vehicle moves, there is a problem that the polarization filter cannot be said to be effective in all cases. Further, the polarizing filter is effective for reflection from the dielectric, but is not useful for specular reflection from a metal surface or the like because the polarization plane of reflected light does not change. The present invention has been made in view of the above problems, and an object of the present invention is to provide an environment recognition device for a moving vehicle that can reliably recognize a reflection.
【０００４】[0004]
【課題を解決するための手段】上記の目的を達成するた
め、本発明は、少なくとも２つの画像入力装置にてステ
レオ視を行なう移動車の環境認識装置において、前記画
像入力装置からの画像データより写り込み候補点を抽出
する手段と、前記２つの画像入力装置によるステレオ視
の対応点から写り込みの発光点を検出する手段と、前記
写り込みの発光点より前記写り込み候補点の移動量を算
出する手段と、前記写り込み候補点の移動量と移動車の
移動量とが所定の関係にあるか否かを判断する手段と、
前記所定の関係が判断された場合、前記写り込み候補点
を真の写り込み点と特定する手段とを備える。In order to achieve the above-mentioned object, the present invention provides an environment recognition device for a moving vehicle which performs stereo vision with at least two image input devices. A means for extracting a reflection candidate point, a means for detecting a reflection light emitting point from a stereoscopic corresponding point by the two image input devices, and a movement amount of the reflection candidate point from the reflection light emitting point. Means for calculating, and means for determining whether or not the movement amount of the reflection candidate point and the movement amount of the moving vehicle have a predetermined relationship,
When the predetermined relationship is determined, a means for identifying the reflection candidate point as a true reflection point is provided.
【０００５】[0005]
【作用】以上の構成において、写り込み点を確実に検出
するよう機能する。In the above structure, the function of surely detecting the reflection point is obtained.
【０００６】[0006]
【実施例】以下、添付図面を参照して本発明に係る好適
な実施例を詳細に説明する。図１は、本発明の実施例に
係る環境認識装置全体の構成を示すブロック図である。
同図において、カメラ１（１）及びカメラ２（２）は、
相互に所定の間隔を持って不図示の車両上に設けられ、
車両前方の画像を撮るカメラである。そして、これらカ
メラ１，２からの画像は、それぞれ左画像、右画像とし
てメモリ１（３），メモリ２（４）に入力される。DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings. FIG. 1 is a block diagram showing the configuration of the entire environment recognition apparatus according to the embodiment of the present invention.
In the figure, camera 1 (1) and camera 2 (2) are
It is provided on a vehicle (not shown) with a certain distance from each other,
It is a camera that takes an image of the front of the vehicle. The images from these cameras 1 and 2 are input to the memory 1 (3) and the memory 2 (4) as a left image and a right image, respectively.
【０００７】メモリ１，２に蓄積された左右の画像は、
それぞれ画像処理装置１（５）、画像処理装置２（６）
に入力され、そこで、例えば、２値化処理によるエッジ
処理を行なう。他方、演算部７には、画像処理装置１，
２での画像処理後の画像、及び距離計８からの信号が入
力される。この距離計８は、車輪９の回転に基づいて車
両（不図示）の走行距離を検出するもので、写り込み候
補点を認識する際に必要となる車両の移動量、及び車速
を検出する。The left and right images stored in the memories 1 and 2 are
Image processing device 1 (5) and image processing device 2 (6), respectively
Is input to the edge processing unit, and edge processing by, for example, binarization processing is performed there. On the other hand, the calculation unit 7 includes the image processing device 1,
The image after the image processing in 2 and the signal from the rangefinder 8 are input. The range finder 8 detects the traveling distance of a vehicle (not shown) based on the rotation of the wheels 9, and detects the amount of movement of the vehicle and the vehicle speed necessary for recognizing the reflection candidate point.
【０００８】次に、本実施例における写り込みの認識方
法について説明する。図２は、左右のカメラ１，２が、
平面３０に対する発光体２０の写り込みを観測している
様子を示す図である。同図に示すように、発光体２０の
像は平面３０にて反射し、それが、各々車両上のカメラ
１，２にて捕えられる。つまり、左カメラ１にとっての
発光体２０の写り込みは、平面３０上の点Ａに位置し、
右カメラ２にとっての写り込みは、点Ｂに位置する。ま
た、発光体２０の左右のカメラ１，２の対応点をとる
と、それは、平面３０より下の点２０’にて示される位
置に来る。Next, a method of recognizing a reflection in this embodiment will be described. In FIG. 2, the left and right cameras 1 and 2 are
It is a figure which shows a mode that the reflection of the light-emitting body 20 to the plane 30 is observed. As shown in the figure, the image of the light-emitting body 20 is reflected by the plane 30, which is captured by the cameras 1 and 2 on the vehicle, respectively. That is, the reflection of the light emitting body 20 on the left camera 1 is located at the point A on the plane 30,
The reflection on the right camera 2 is located at the point B. Further, when the corresponding points of the left and right cameras 1 and 2 of the light emitting body 20 are taken, they come to the position shown by a point 20 ′ below the plane 30.
【０００９】また、図３は、左右のカメラ１，２にて捕
えた写り込みの画像を示すもので、左カメラ画像として
写り込み２０Ｌが、また、右カメラ画像として写り込み
２０Ｒが写し出されている。図４は、発光体と写り込
み、そして、カメラの相互の位置関係を示す概念図であ
る。同図に示すように、カメラ１，２の平面３０からの
高さをｈ、カメラ１，２の移動速度（これは、言うまで
もなく、車両の移動速度に等しい）をｖ、写り込みＡ，
Ｂの移動速度をＶ、カメラ１，２の相互の間隔をｌ、そ
して、写り込みの幅、つまり、平面３０上での写り込み
Ａ，Ｂの相対的な距離をＬとすると、発光体２０の高さ
をＨは、 Ｈ＝ｈ・Ｌ／（ｌ−Ｌ） …（１） にて表わされる。よって、写り込みＡ，Ｂの移動速度Ｖ
は、 Ｖ＝ｖ・ｈ／Ｈ＋ｈ …（２） となる。FIG. 3 shows images captured by the left and right cameras 1 and 2, with the left camera image including the reflection 20L and the right camera image including the reflection 20R. There is. FIG. 4 is a conceptual diagram showing the mutual positional relationship between the light emitter, the reflection, and the camera. As shown in the figure, the height of the cameras 1 and 2 from the plane 30 is h, the moving speed of the cameras 1 and 2 (which is, needless to say, equal to the moving speed of the vehicle) is v, the reflection A,
Assuming that the moving speed of B is V, the distance between the cameras 1 and 2 is 1, and the width of the reflection, that is, the relative distance between the reflections A and B on the plane 30, is L. The height H is represented by H = h · L / (1−L) (1). Therefore, the moving speed V of the reflection A and B
Becomes V = v · h / H + h (2)
【００１０】図５は、本実施例に係る環境認識装置での
写り込み認識処理の手順を示すフローチャートである。
同図において、ステップＳ１で、左右のカメラにて入力
された画像に対して２値化処理によるエッジ処理、及び
輝度に基づく写り込みの候補点を抽出する。これは、発
光体の写り込みが、一般にそのエッジがぼやけ、輝度が
高いことを利用するもので、ここでは、画像中において
所定以上の輝度を有するものを候補にあげる。そして、
候補点があれば、ステップＳ２での判定はＹＥＳとなる
からステップＳ３に進み、以降、真の写り込みを判定す
る処理に入る。FIG. 5 is a flow chart showing the procedure of the reflection recognition processing in the environment recognition apparatus according to this embodiment.
In the figure, in step S1, candidate points for edge processing by binarization processing and imprinting based on brightness are extracted from the images input by the left and right cameras. This utilizes the fact that the edges of the illuminant are generally blurred and the brightness is high. Here, candidates having a brightness equal to or higher than a predetermined level in the image are candidates. And
If there is a candidate point, the determination in step S2 is YES, so the process proceeds to step S3, and thereafter, the process for determining the true reflection is started.
【００１１】ステップＳ３では、２眼ステレオ視による
認識、つまり、写り込み候補点が平面上にあるかどうか
の認識を行なう。これは、カメラ１，２にて、写り込み
候補点が、例えば、図３に示す２０Ｌ，２０Ｒのごとく
捕えられた場合、その一方を固定し、他方の候補点の座
標をカメラの視差に合わせた量だけ変換することで認識
する。すなわち、この座標変換により、固定した候補点
が他方の候補点の位置に来れば、この候補点は写り込み
によるものではなく、平面上に位置する物体であると判
断できる。真の写り込みであれば、座標変換を行なって
も相互の位置がずれるからである。In step S3, recognition by twin-eye stereoscopic vision, that is, recognition as to whether or not the reflection candidate point is on a plane is performed. This is because when the camera 1 or 2 captures a reflection candidate point such as 20L or 20R shown in FIG. 3, one of them is fixed and the coordinates of the other candidate point are adjusted to the parallax of the camera. Recognize by converting only the amount. That is, if the fixed candidate point comes to the position of the other candidate point by this coordinate transformation, it can be determined that the candidate point is not an object due to reflection but an object located on a plane. This is because, if they are true reflections, their positions will shift even if coordinate conversion is performed.
【００１２】上記ステップＳ３での処理結果を受けて、
ステップＳ４で、候補点が平面上にないと判断される
と、ステップＳ５の処理に移行する。このステップＳ５
では、移動ステレオによる認識を行なう。この処理で
は、写り込み候補点の相対的な距離を算出し、その結果
をもとに、上記式（１）で表わされる高さＨを算出す
る。そして、上記の式（２）から写り込みＡ，Ｂの移動
速度Ｖを算出する。In response to the processing result in step S3,
If it is determined in step S4 that the candidate point is not on the plane, the process proceeds to step S5. This step S5
Then, recognition by mobile stereo is performed. In this processing, the relative distance between the reflection candidate points is calculated, and based on the result, the height H represented by the above equation (1) is calculated. Then, the moving speed V of the reflections A and B is calculated from the above equation (2).
【００１３】この写り込みと車両との相対移動速度が等
しければ、両者の相対移動量も等しいことになるので、
ステップＳ６での判定結果はＹＥＳとなる。よって、上
記ステップＳ１で抽出された写り込み候補点は真の写り
込みとなるので、続くステップＳ７で写り込みを認識で
きることになる。以上説明したように、本実施例によれ
ば、左右のカメラにて撮影した画像にエッジ処理等を行
なって写り込みの候補点を抽出し、２眼ステレオ視、及
び移動ステレオにて候補点と車両の相対移動量が等しい
かを判定することで、確実に写り込みを認識できるとい
う効果がある。If the reflection and the relative movement speed of the vehicle are equal, the relative movement amounts of the two are also equal.
The determination result in step S6 is YES. Therefore, the reflection candidate point extracted in step S1 is a true reflection, and the reflection can be recognized in subsequent step S7. As described above, according to the present embodiment, the image picked up by the left and right cameras is subjected to edge processing or the like to extract the candidate points for reflection, and the candidate points are selected as the candidate points in the two-eye stereoscopic view and the moving stereo. By determining whether the relative movement amounts of the vehicles are equal, it is possible to reliably recognize the reflection.
【００１４】[0014]
【発明の効果】以上説明したように、本発明によれば、
写り込み候補点と車両の相対的な移動量に基づいて、写
り込み点を確実に認識できるという効果がある。As described above, according to the present invention,
There is an effect that the reflection point can be reliably recognized based on the relative movement amount of the reflection candidate point and the vehicle.
【図１】本発明の実施例に係る環境認識装置全体の構成
を示すブロック図、FIG. 1 is a block diagram showing the overall configuration of an environment recognition device according to an embodiment of the present invention,
【図２】左右のカメラにて、平面に対する発光体の写り
込みを観測している様子を示す図、FIG. 2 is a diagram showing how the left and right cameras observe the reflection of a light emitter on a plane;
【図３】左右のカメラにて捕えた写り込みの画像を示す
図、FIG. 3 is a diagram showing an image of a reflection captured by the left and right cameras,
【図４】発光体と写り込み、カメラの位置関係を示す概
念図、FIG. 4 is a conceptual diagram showing a positional relationship between a light emitting body and a reflection, and a camera,
【図５】実施例に係る環境認識装置での写り込み認識処
理の手順を示すフローチャートである。FIG. 5 is a flowchart showing a procedure of a reflection recognition process in the environment recognition device according to the embodiment.
１，２ カメラ ３，４ メモリ ５，６ 画像処理装置 ７ 演算部 ８ 距離計 ９ 車輪 1, 2 Cameras 3, 4 Memory 5, 6 Image processing device 7 Computing unit 8 Distance meter 9 Wheels
Claims (1)
レオ視を行なう移動車の環境認識装置において、 前記画像入力装置からの画像データより写り込み候補点
を抽出する手段と、 前記２つの画像入力装置によるステレオ視の対応点から
写り込みの発光点を検出する手段と、 前記写り込みの発光点より前記写り込み候補点の移動量
を算出する手段と、 前記写り込み候補点の移動量と移動車の移動量とが所定
の関係にあるか否かを判断する手段と、 前記所定の関係が判断された場合、前記写り込み候補点
を真の写り込み点と特定する手段とを備えることを特徴
とする移動車の環境認識装置。1. An environment recognition device for a moving vehicle that performs stereo vision with at least two image input devices, a means for extracting a reflection candidate point from image data from the image input device, and the two image input devices. Means for detecting a light emitting point of a reflection from a corresponding point of stereoscopic vision, means for calculating a moving amount of the reflection candidate point from the light emitting point of the reflection, a movement amount of the reflection candidate point and a moving vehicle. And a means for determining whether or not there is a predetermined relationship with the movement amount of the object, and a means for specifying the imprinting candidate point as a true imprinting point when the predetermined relationship is judged. An environment recognition device for moving vehicles.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP4077386A JPH05282431A (en) | 1992-03-31 | 1992-03-31 | Environment recognizing device for mobile vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP4077386A JPH05282431A (en) | 1992-03-31 | 1992-03-31 | Environment recognizing device for mobile vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| JPH05282431A true JPH05282431A (en) | 1993-10-29 |
Family
ID=13632456
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP4077386A Withdrawn JPH05282431A (en) | 1992-03-31 | 1992-03-31 | Environment recognizing device for mobile vehicle |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JPH05282431A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002150302A (en) * | 2000-11-15 | 2002-05-24 | Toyota Motor Corp | Road surface recognition device |
| JP2016009429A (en) * | 2014-06-26 | 2016-01-18 | 富士重工業株式会社 | Vehicle exterior environment recognition device |
-
1992
- 1992-03-31 JP JP4077386A patent/JPH05282431A/en not_active Withdrawn
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2002150302A (en) * | 2000-11-15 | 2002-05-24 | Toyota Motor Corp | Road surface recognition device |
| JP2016009429A (en) * | 2014-06-26 | 2016-01-18 | 富士重工業株式会社 | Vehicle exterior environment recognition device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP3596314B2 (en) | Object edge position measuring device and moving object traffic judging device | |
| JP3630100B2 (en) | Lane detection device | |
| JP3861781B2 (en) | Forward vehicle tracking system and forward vehicle tracking method | |
| EP3150961B1 (en) | Stereo camera device and vehicle provided with stereo camera device | |
| CN108645375B (en) | Rapid vehicle distance measurement optimization method for vehicle-mounted binocular system | |
| EP1087257A2 (en) | Mounting stereo camera system of a vehicle | |
| JP3562751B2 (en) | Forward vehicle detection method and device | |
| JP3961584B2 (en) | Lane marking detector | |
| WO2019167531A1 (en) | Stereo camera device | |
| JPH08329393A (en) | Preceding vehicle detector | |
| JP2000266539A (en) | Inter-vehicle distance measuring apparatus | |
| JP3710548B2 (en) | Vehicle detection device | |
| JP4052291B2 (en) | Image processing apparatus for vehicle | |
| JP2018060422A (en) | Object detection device | |
| JP3868915B2 (en) | Forward monitoring apparatus and method | |
| JPH07244717A (en) | Travel environment recognition device for vehicle | |
| JP2940366B2 (en) | Object tracking recognition device | |
| JPH05282431A (en) | Environment recognizing device for mobile vehicle | |
| WO2014050285A1 (en) | Stereo camera device | |
| JP2000259997A (en) | Height of preceding vehicle and inter-vehicle distance measuring device | |
| JP2001108434A (en) | Method and apparatus for measuring distance | |
| JPH0719893A (en) | Curvature of-road detector | |
| WO2020036039A1 (en) | Stereo camera device | |
| JP2012022501A (en) | Vehicle dimension detection system | |
| JP3393767B2 (en) | Obstacle detection device for vehicles |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| A300 | Application deemed to be withdrawn because no request for examination was validly filed |
Free format text: JAPANESE INTERMEDIATE CODE: A300 Effective date: 19990608 |