JP3580152B2 - Inter-vehicle distance detection device - Google Patents

Inter-vehicle distance detection device Download PDF

Info

Publication number
JP3580152B2
JP3580152B2 JP32231898A JP32231898A JP3580152B2 JP 3580152 B2 JP3580152 B2 JP 3580152B2 JP 32231898 A JP32231898 A JP 32231898A JP 32231898 A JP32231898 A JP 32231898A JP 3580152 B2 JP3580152 B2 JP 3580152B2
Authority
JP
Japan
Prior art keywords
inter
vehicle distance
vehicle
distance
tracking
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.)
Expired - Lifetime
Application number
JP32231898A
Other languages
Japanese (ja)
Other versions
JP2000149199A (en
Inventor
恭一 阿部
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.)
Mitsubishi Motors Corp
Original Assignee
Mitsubishi Motors Corp
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 Mitsubishi Motors Corp filed Critical Mitsubishi Motors Corp
Priority to JP32231898A priority Critical patent/JP3580152B2/en
Publication of JP2000149199A publication Critical patent/JP2000149199A/en
Application granted granted Critical
Publication of JP3580152B2 publication Critical patent/JP3580152B2/en
Anticipated expiration legal-status Critical
Expired - Lifetime legal-status Critical Current

Links

Images

Landscapes

  • Traffic Control Systems (AREA)
  • Radar Systems Or Details Thereof (AREA)
  • Optical Radar Systems And Details Thereof (AREA)
  • Length Measuring Devices By Optical Means (AREA)
  • Measurement Of Optical Distance (AREA)

Description

【0001】
【発明の属する技術分野】
本発明は先行車までの車間距離を検出する車間距離検出装置に係り、特に先行車に接近したときの車間距離を精度良く検出するのに好適な車間距離検出装置に関する。
【0002】
【従来の技術】
従来より、ドライバーが安全な車間距離で楽に運転できるように車両の自動追尾システムが提案されている。このシステムは、例えば車両が先行車に近づいたときは自動的にスロットル又はブレーキを制御して車両を減速し、逆に遠ざかったときは自動的にスロットルを制御して車両を加速し、これによって先行車までの車間距離を所定範囲に維持するものである。従って、この種のシステムには先行車までの車間距離を検出する車間距離検出装置が備えられている。
【0003】
車間距離を検出する装置としては、例えば特開平4−276585号公報に開示された車載用測距装置がある。この装置は近距離用測距センサと遠距離用測距センサを併用したもので、近距離用測距センサにはCCDカメラや超音波レーダ装置が、また遠距離用測距センサにはレーザレーダや電波レーダが用いられている。そして、近距離を走行する先行車までの車間距離の測定において、先行車のコントラストがほとんどない場合や超音波が反射されずに先行車までの測距を近距離用測距センサで行うことができなかった場合に、車速から推定される対象物までの距離および本来距離出力として採用されない遠距離用測距センサからの距離出力に基づいて距離を演算し、いずれか小なる方の距離を採用して先行車の追従走行を行うものである。
【0004】
【発明が解決しようとする課題】
従来の技術では、近距離用測距センサとして用いられるCCDカメラを車両フロント部に所定間隔離間して2個上下又は左右に設置し、両CCDカメラの結像位置の相違を検出して三角測量の原理を用いて先行車までの車間距離を計測する。しかしながら、このセンサは2台のCCDカメラを有することから、センサ自体のコストが高くなり、しかもカメラ2台分の取付スペースが必要となるという問題がある。その上、このセンサは長時間使用した場合、車両走行中の振動等により2台のCCDカメラの離間間隔が変化し、その結果、三角測量の原理を用いて行う車間距離測定の精度が低下するという問題もある。
そこで、このような複数のCCDカメラを用いることなく、レーザレーダ等の車間距離検出センサの精度を上げて、遠距離から近距離までの車間距離をこの車間距離検出センサにより計測するように構成することが考えられる。しかし、この場合には、車間距離検出センサが何らかの原因で不作動状態となったときでも車間距離の検出ができるように構成する必要がある。そのため、このような場合に備えて簡易な車間距離検出用の補助的手段を設けることが求められる。
【0005】
従って本発明の目的は、車間距離検出手段の不作動時に、1台の撮像手段を用いて先行車までの車間距離を精度良く検出し得る車間距離検出装置を提供することにある。
【0006】
【課題を解決するための手段】
本発明に係る車間距離検出装置は、カメラ等の撮像手段で得られた先行車画像を入力し、別途レーザレーダ等の車間距離検出手段で得られた先行車までの車間距離及び方向に基づいて前記先行車画像の複数箇所にそれぞれ追尾点を配置し、この追尾点の集団の位置情報および前記先行車までの車間距離から車間距離計測用係数を算出し、前記算出した車間距離計測用係数および現時点における追尾点の集団の位置情報から車間距離を算出するよう構成した車間距離推定手段を備え、前記レーザレーダ等の車間距離検出手段の不作動時には、前記車間距離推定手段を用いて、先行車との車間距離を推定するものである。ここで、追尾点の集団の位置情報としては、例えば追尾点の集団の分散の値を用いることができる。この場合、車間距離と画像における先行車の幅には相関関係があるため、分散の算出は計算を簡略化するため水平方向について求め、垂直方向については省略することができる。
【0007】
また、車間距離検出手段の不作動時とは、例えば、車間距離検出手段としてレーザレーダが用いられる装置においては、レーザレーダ自体の故障により出力が得られない場合、あるいは大型トラックのような先行車に車両が接近してレーザレーダからのレーザ光が先行車下部に潜り込んで反射光が得られない場合、レーザレーダに太陽光もしくは他車のレーザ光が入り込み、検出精度が低下し一時的に作動不能になった場合、さらには距離検出の主体がレーザレーダからカメラに自動的に又は人為的に切り換えられた場合等が含まれる。上述のように構成することにより、車間距離検出手段の不作動時において、その直前に計算し保持された車間距離計測用係数を用いて、追尾点の集団の位置情報から先行車までの車間距離を精度良く検出することができる。
なお、車間距離推定手段は、撮像手段で得られた先行車画像を入力する画像入力部と、車間距離検出手段で得られた先行車までの車間距離D及び方向に基づいて前記先行車画像の複数個所にそれぞれ追尾点を配置する画像処理部と、先行車画像の前記複数箇所の追尾点について追尾を行うことによって得られる追尾点の集団の位置情報、および、この際に、車間距離検出手段によって得られる前記先行車までの車間距離から車間距離計測用係数hを算出し、前記算出した車間距離計測用係数hおよび現時点における追尾点の集団の位置情報から車間距離Dを算出する車間距離計算部とを備えて構成される。
また、前記車間距離計測用係数hは、ある時点において得られる、前記追尾点の集団の水平方向の分散値σと前記車間距離検出手段による前記先行車までの車間距離Dとの乗算値(D×σ)とすることができる。そして、車間距離推定手段では、車間距離検出手段の不作動時に、予め得られた前記車間距離計測用係数hを現時点において得られる、前記追尾点の集団の水平方向の分散値σ e で除して、前記先行車との車間距離の推定値D e (h/σ e )を得ることができる。
さらに、前記車間距離計算部では、前記複数箇所の追尾点について追尾を行う際に、前記複数の追尾点を順次に注目点として選択し、この注目点周りにテンプレートを設定し、所定時間後に、かかる注目点が移動したと考えられる候補点を含む範囲に上記テンプレートと同様な窓を設定し、該注目点のテンプレート内の画素の明るさと、該候補点の窓内の画素の明るさとの差が、最小なものを移動した追尾点に設定することができる。
【0008】
【発明の実施の形態】
図1は、本発明に係る車間距離検出装置を搭載した車両の模式図である。図のように、コントローラ1は車間距離推定手段2および制御信号生成部3を備えており、車両4の室内前方上部に配置されたカメラ5で得られた先行車の画像情報を入力し、また車両4の先端部に配置された車間距離検出センサ6、例えばレーザレーダや電波レーダなど(以下、総称してレーザレーダという)で得られた先行車までの車間距離及び方向を入力する。コントローラ1は、通常時においては、レーザレーダ6で得られた先行車までの車間距離情報に基づいてブレーキアクチュエータ7やスロットルアクチュエータ8を制御する。一方、レーザレーダ6の不作動時においては、コントローラ1は、カメラ5で得られた先行車の画像情報およびレーザレーダ6の正常作動時に得られた先行車までの車間距離情報に基づいて算出された車間距離の値にしたがってブレーキアクチュエータ7やスロットルアクチュエータ8を制御する。また車間距離の値は、車両室内の操作・情報表示部9に表示される。
【0009】
図2は、本発明に係る車間距離検出装置の一実施例を示す図である。図のように、車間距離推定手段2は、カメラ5で得られた先行車の画像情報を入力する画像入力部21と、レーザレーダ6で得られた先行車までの車間距離情報を用いて上述の先行車画像上の複数箇所にそれぞれ後述する追尾点を配置する画像処理部22と、これらの追尾点の集団の位置情報および上述の先行車までの車間距離情報から車間距離計測用係数を算出し、この算出した車間距離計測用係数および現時点における追尾点の集団の位置情報から車間距離を算出する車間距離計算部23とを備える。制御信号生成部3にはスイッチ10が接続される。スイッチ10の入力端子の一方は車間距離推定手段2側に接続され、他方はレーザレーダ6側に接続される。スイッチ10は、レーザレーダ(L/R)不作動検出部11からの出力で切り換えられる。
【0010】
通常時、スイッチ10はレーザレーダ6側に接続されている。制御信号生成部3は、レーザレーダ6で得られた先行車までの車間距離情報をスイッチ10を介して入力し、ブレーキアクチュエータ7やスロットルアクチュエータ8を制御する信号、および操作・情報表示部9へ表示する信号を生成する。レーザレーダ不作動検出部11はレーザレーダ6で得られた車間距離情報を監視し、レーザレーダ6の不作動が検出されると、スイッチ10をレーザレーダ6側から車間距離推定手段2側に切り換える。レーザレーダ6の不作動の検出は、例えば車間距離情報に特異な値が現れた場合に行われる。これにより制御信号生成部3は、車間距離推定手段2で得られた車間距離の算出値をスイッチ10を介して入力し、ブレーキアクチュエータ7やスロットルアクチュエータ8を制御する信号、および操作・情報表示部9へ表示する信号を生成する。
【0011】
図3は、本発明に係る車間距離検出装置の動作を示すフローチャートである。図のように、ステップ31にて、カメラ5で得られた画像を入力する。ステップ32では、図4(a)に示すように、レーザレーダ(L/R)6で得られた先行車までの車間距離及び方向に基づいて、入力画像中において先行車の存在する範囲48を決定する。ステップ33では、図4(b)に示すように、先行車画像42の存在範囲48に複数の追尾点を配置する。ステップ34では、これらの追尾点を順次に注目点43として選択し先行車の追尾を行うためのテンプレート44を作成する。ここでテンプレート44は、追尾点の周りに仮想的に設けた小さな窓である。ステップ35では、このテンプレート44を用いて、次のようにして先行車を追尾する。すなわち、時刻tから時間dt経過後、図4(c)に示すように、この注目点が移動したと考えられる候補点を含む範囲に対して、テンプレートと同様な複数の小さな窓を考える。この候補点の窓と移動前の注目点の窓との間で、窓内の画素の明るさの差の絶対値和を求める。この絶対値和(SSD:Sum of Squared Differences)は、注目座標(x,y)の明るさをB(x,y)、追尾の候補点の座標(xt+dt,yt+dt)の明るさをB(xt+dt,yt+dt)、そして窓をWとすると、次の(数1)より求められる。
【0012】
【数1】

Figure 0003580152
【0013】
候補点のうちでSSD値の最も小さい(相関が高い)窓に対応する点46を移動先の点として決定する。ステップ36では、それぞれの点が追尾に成功したか失敗したかを判定する。この判定部分はレーザレーダが正常に作動しているときのみ動作し、レーザレーダ不作動時には動作しない。図4(c)に示すように、レーザレーダによる先行車存在範囲45の範囲内にある点は追尾に成功したものとし、ステップ34に戻って追尾を継続する。一方、範囲外にある点47は追尾に失敗した点とし、ステップ37にて新たな追尾点を作成し追尾をやり直す。そして最終的に全ての追尾点が先行車画像上に配置されるようにする。以上のような画像処理を行なった後、車間距離を算出する動作に移る。
【0014】
車間距離の算出では、まずステップ38にて、先行車画像上に配置された複数の追尾点の集団の重心を計算する。そしてステップ39にて、この重心との関係を用いて追尾点位置の水平方向の分散σを算出する。追尾点の集団(n個)の重心を(X,Y)、追尾点の座標を(X,Y)としたとき、n個の追尾点の集団の水平方向の分散σは次の(数2)で求められる。
【0015】
【数2】
Figure 0003580152
【0016】
図4(a)のように、先行車までの車間距離が小さくなったときは、先行車画像は画面中で大きくなり画像上の各追尾点の間隔が広がって、水平方向の各追尾点位置(X)が重心位置(X)から離れるので分散σは大きくなる。逆に、図4(c)のように、先行車までの車間距離が大きくなったときは、先行車画像は画面中で小さくなり画像上の各追尾点の間隔が狭まって、水平方向の各追尾点位置(X)が重心位置(X)に近づくので分散σは小さくなる。ステップ40では、この分散と車間距離との関係を用いて車間距離計測用係数hを算出する。即ち、ある時点においてレーザレーダ6で得られた先行車までの車間距離をDとし分散をσとすると、車間距離計測用係数hは、h=D×σより算出される。算出された車間距離計測用係数hは、車間距離計算部23に備えられた図示しない記録媒体に保持される。ステップ41では、レーザレーダ6の不作動時において、この算出された車間距離計測用係数hおよびレーザレーダ不作動時点における分散σを用いて、先行車までの車間距離Dを計算し推定する。推定車間距離Dは、D=h/σより算出される。この推定車間距離Dの値に基づいて、制御信号生成部3は制御信号を出力し、ブレーキアクチュエータ7やスロットルアクチュエータ8を制御し、また推定車間距離の値を車両室内の操作・情報表示部9に表示する。
【0017】
このように本実施例では、レーザレーダ6の不作動時において、その直前に得られたレーザレーダによる先行車までの車間距離および追尾点の集団の分散から車間距離を計算し推定しているので、先行車までの車間距離を精度良く推定することができる。また、1台のカメラで得られた先行車画像に複数の追尾点を付与し同時に追尾するので、追尾に失敗した点が何点かあっても車間距離算出の精度に影響が少ない。
【0018】
【発明の効果】
本発明によれば、車間距離検出手段の不作動時に、1台の撮像手段を用いて先行車までの車間距離を精度良く検出可能な車間距離検出装置を提供できる。
【図面の簡単な説明】
【図1】本発明に係る車間距離検出装置を搭載した車両の模式図である。
【図2】本発明に係る車間距離検出装置の一実施例を示す図である。
【図3】本発明に係る車間距離検出装置の動作を示すフローチャートである。
【図4】(a)、(b)、(c)はそれぞれ追尾点を用いて先行車を追尾する方法を説明するための図である。
【符号の説明】
1 コントローラ
2 車間距離推定手段
3 制御信号生成部
4 車両
5 カメラ
6 レーザレーダ
7 ブレーキアクチュエータ
8 スロットルアクチュエータ
9 操作・情報表示部
10 スイッチ
11 L/R不作動検出部
21 画像入力部
22 画像処理部
23 車間距離計算部[0001]
TECHNICAL FIELD OF THE INVENTION
The present invention relates to an inter-vehicle distance detection device that detects an inter-vehicle distance to a preceding vehicle, and more particularly to an inter-vehicle distance detection device suitable for accurately detecting an inter-vehicle distance when approaching a preceding vehicle.
[0002]
[Prior art]
2. Description of the Related Art Conventionally, an automatic vehicle tracking system has been proposed so that a driver can easily drive with a safe inter-vehicle distance. This system, for example, automatically controls the throttle or brake to decelerate the vehicle when the vehicle approaches the preceding vehicle, and conversely, automatically controls the throttle to accelerate the vehicle when it moves away, The inter-vehicle distance to the preceding vehicle is maintained within a predetermined range. Therefore, this type of system is provided with an inter-vehicle distance detecting device for detecting an inter-vehicle distance to a preceding vehicle.
[0003]
As a device for detecting an inter-vehicle distance, there is, for example, an in-vehicle distance measuring device disclosed in JP-A-4-276585. This device uses a short-distance distance sensor and a long-distance distance sensor together. A CCD camera or ultrasonic radar device is used for the short-distance distance sensor, and a laser radar is used for the long-distance distance sensor. And radio wave radar. Then, in the measurement of the inter-vehicle distance to a preceding vehicle traveling a short distance, when there is almost no contrast of the preceding vehicle or when the ultrasonic wave is not reflected, the distance to the preceding vehicle can be measured by the short-distance ranging sensor. If the distance cannot be determined, the distance is calculated based on the distance to the object estimated from the vehicle speed and the distance output from the distance measuring sensor for long distance that is not originally used as the distance output, and the smaller distance is used. Then, the vehicle follows the preceding vehicle.
[0004]
[Problems to be solved by the invention]
In the prior art, two CCD cameras used as a distance measuring sensor for a short distance are installed at the front of a vehicle at predetermined intervals and vertically or horizontally, and a difference in the image forming positions of both CCD cameras is detected to perform triangulation. Is used to measure the inter-vehicle distance to the preceding vehicle. However, since this sensor has two CCD cameras, there is a problem that the cost of the sensor itself is high, and an installation space for two cameras is required. In addition, when this sensor is used for a long time, the separation distance between the two CCD cameras changes due to vibrations during running of the vehicle, and as a result, the accuracy of the inter-vehicle distance measurement using the principle of triangulation decreases. There is also a problem.
Therefore, without using such a plurality of CCD cameras, the accuracy of an inter-vehicle distance detection sensor such as a laser radar is improved, and the inter-vehicle distance from a long distance to a short distance is measured by the inter-vehicle distance detection sensor. It is possible. However, in this case, it is necessary to be able to detect the inter-vehicle distance even when the inter-vehicle distance detection sensor becomes inoperative for some reason. Therefore, it is required to provide a simple auxiliary means for detecting the following distance in preparation for such a case.
[0005]
Accordingly, it is an object of the present invention to provide an inter-vehicle distance detection device that can accurately detect an inter-vehicle distance to a preceding vehicle using one imaging unit when the inter-vehicle distance detection unit is not operated.
[0006]
[Means for Solving the Problems]
An inter-vehicle distance detection device according to the present invention inputs a preceding vehicle image obtained by an imaging unit such as a camera, and based on an inter-vehicle distance and a direction to a preceding vehicle separately obtained by an inter-vehicle distance detection unit such as a laser radar. Tracking points are respectively arranged at a plurality of places in the preceding vehicle image, an inter-vehicle distance measurement coefficient is calculated from the position information of the group of the tracking points and the inter-vehicle distance to the preceding vehicle, and the calculated inter-vehicle distance measurement coefficient and An inter-vehicle distance estimating unit configured to calculate an inter-vehicle distance from the position information of the group of tracking points at the present time. This is for estimating the inter-vehicle distance. Here, as the position information of the group of tracking points, for example, a variance value of the group of tracking points can be used. In this case, since there is a correlation between the inter-vehicle distance and the width of the preceding vehicle in the image, the variance can be calculated in the horizontal direction to simplify the calculation, and can be omitted in the vertical direction.
[0007]
In addition, when the inter-vehicle distance detecting means is not operated, for example, in a device using a laser radar as the inter-vehicle distance detecting means, when no output is obtained due to a failure of the laser radar itself, or when a preceding vehicle such as a large truck If the vehicle approaches and the laser light from the laser radar enters the lower part of the preceding vehicle and the reflected light cannot be obtained, sunlight or the laser light of another vehicle enters the laser radar, the detection accuracy decreases, and it temporarily operates. The case where the detection becomes impossible and the case where the subject of the distance detection is automatically or artificially switched from the laser radar to the camera are included. With the above-described configuration, when the inter-vehicle distance detecting means is not operated, the inter-vehicle distance from the position information of the group of tracking points to the preceding vehicle is calculated using the inter-vehicle distance measurement coefficient calculated and held immediately before. Can be accurately detected.
The inter-vehicle distance estimating means includes an image input unit for inputting a preceding vehicle image obtained by the imaging means, and an inter-vehicle distance D and a direction to the preceding vehicle obtained by the inter-vehicle distance detecting means. An image processing unit for arranging tracking points at a plurality of locations, position information of a group of tracking points obtained by tracking the tracking points at the plurality of locations in the preceding vehicle image, and, at this time, an inter-vehicle distance detecting means Calculation of the inter-vehicle distance measurement coefficient h from the inter-vehicle distance to the preceding vehicle obtained as described above, and calculation of the inter-vehicle distance D from the calculated inter-vehicle distance measurement coefficient h and the current position information of the group of tracking points. And a unit.
The inter-vehicle distance measurement coefficient h is a multiplication value (D) of a horizontal variance value σ of the group of tracking points obtained at a certain point in time and the inter-vehicle distance D to the preceding vehicle by the inter-vehicle distance detection means. × σ). The inter-vehicle distance estimating means divides the inter-vehicle distance measuring coefficient h obtained in advance by the horizontal variance σ e of the group of the tracking points obtained at the present time when the inter-vehicle distance detecting means is not operating. Thus, the estimated value D e (h / σ e ) of the inter-vehicle distance from the preceding vehicle can be obtained.
Further, the inter-vehicle distance calculation unit, when performing tracking for the plurality of tracking points, sequentially selects the plurality of tracking points as a point of interest, sets a template around the point of interest, after a predetermined time, A window similar to that of the template is set in a range including the candidate point where the attention point is considered to have moved, and the difference between the brightness of the pixel in the template of the attention point and the brightness of the pixel in the window of the candidate point is set. However, the smallest tracking point can be set as the moved tracking point.
[0008]
BEST MODE FOR CARRYING OUT THE INVENTION
FIG. 1 is a schematic view of a vehicle equipped with an inter-vehicle distance detection device according to the present invention. As shown in the figure, the controller 1 includes an inter-vehicle distance estimating unit 2 and a control signal generating unit 3, and inputs image information of a preceding vehicle obtained by a camera 5 disposed in an upper front part of the vehicle 4. An inter-vehicle distance and a direction to a preceding vehicle obtained by an inter-vehicle distance detection sensor 6 disposed at a front end portion of the vehicle 4, for example, a laser radar or a radio radar (hereinafter, collectively referred to as a laser radar) are input. Normally, the controller 1 controls the brake actuator 7 and the throttle actuator 8 based on the following distance information to the preceding vehicle obtained by the laser radar 6. On the other hand, when the laser radar 6 is not operating, the controller 1 calculates based on the image information of the preceding vehicle obtained by the camera 5 and the inter-vehicle distance information to the preceding vehicle obtained when the laser radar 6 operates normally. The brake actuator 7 and the throttle actuator 8 are controlled according to the value of the inter-vehicle distance. The value of the inter-vehicle distance is displayed on the operation / information display unit 9 in the vehicle cabin.
[0009]
FIG. 2 is a diagram showing an embodiment of an inter-vehicle distance detection device according to the present invention. As shown in the figure, the inter-vehicle distance estimating means 2 uses the image input unit 21 for inputting the image information of the preceding vehicle obtained by the camera 5 and the inter-vehicle distance information to the preceding vehicle obtained by the laser radar 6. And an image processing unit 22 for arranging tracking points to be described later at a plurality of locations on the preceding vehicle image, and calculating an inter-vehicle distance measurement coefficient from the position information of a group of these tracking points and the above-described inter-vehicle distance information to the preceding vehicle. An inter-vehicle distance calculation unit 23 that calculates the inter-vehicle distance from the calculated inter-vehicle distance measurement coefficient and the position information of the group of tracking points at the current time. The switch 10 is connected to the control signal generator 3. One of the input terminals of the switch 10 is connected to the inter-vehicle distance estimating means 2 side, and the other is connected to the laser radar 6 side. The switch 10 is switched by an output from the laser radar (L / R) non-operation detecting unit 11.
[0010]
Normally, the switch 10 is connected to the laser radar 6 side. The control signal generation unit 3 inputs the inter-vehicle distance information to the preceding vehicle obtained by the laser radar 6 via the switch 10, and controls the brake actuator 7 and the throttle actuator 8, and sends the signal to the operation / information display unit 9. Generate the signal to be displayed. The laser radar non-operation detecting unit 11 monitors the inter-vehicle distance information obtained by the laser radar 6, and when the non-operation of the laser radar 6 is detected, switches the switch 10 from the laser radar 6 side to the inter-vehicle distance estimating means 2 side. . The detection of the inactivity of the laser radar 6 is performed, for example, when a unique value appears in the following distance information. Thereby, the control signal generation unit 3 inputs the calculated value of the following distance obtained by the following distance estimation means 2 through the switch 10, and controls the brake actuator 7 and the throttle actuator 8, and the operation / information display unit. 9 to generate a signal to be displayed.
[0011]
FIG. 3 is a flowchart showing the operation of the inter-vehicle distance detection device according to the present invention. As shown in the figure, in step 31, an image obtained by the camera 5 is input. In step 32, based on the inter-vehicle distance and direction to the preceding vehicle obtained by the laser radar (L / R) 6 as shown in FIG. decide. In Step 33, as shown in FIG. 4B, a plurality of tracking points are arranged in the existing range 48 of the preceding vehicle image 42. In step 34, these tracking points are sequentially selected as points of interest 43, and a template 44 for tracking the preceding vehicle is created. Here, the template 44 is a small window virtually provided around the tracking point. In step 35, the preceding vehicle is tracked using the template 44 as follows. That is, after a lapse of time dt from the time t, as shown in FIG. 4C, a plurality of small windows similar to the template are considered for a range including the candidate point where the point of interest is considered to have moved. The absolute value sum of the difference in brightness of the pixels in the window between the window of the candidate point and the window of the point of interest before movement is obtained. The absolute value sum (SSD: Sum of Squared Differences) are of interest coordinates (x t, y t) Brightness and B of the (x t, y t), the candidate points of the tracking coordinates (x t + dt, y t + dt) Assuming that the brightness is B ( xt + dt , yt + dt ) and the window is W, it can be obtained from the following (Equation 1).
[0012]
(Equation 1)
Figure 0003580152
[0013]
The point 46 corresponding to the window having the smallest SSD value (high correlation) among the candidate points is determined as the destination point. In step 36, it is determined whether each point has succeeded or failed in tracking. This determination part operates only when the laser radar is operating normally, and does not operate when the laser radar is not operating. As shown in FIG. 4 (c), it is assumed that a point within the range 45 of the preceding vehicle by the laser radar has been successfully tracked, and the process returns to step 34 to continue the tracking. On the other hand, a point 47 outside the range is determined as a point at which tracking has failed, and a new tracking point is created in step 37 and the tracking is performed again. Finally, all the tracking points are arranged on the preceding vehicle image. After performing the image processing as described above, the operation proceeds to the operation for calculating the inter-vehicle distance.
[0014]
In calculating the inter-vehicle distance, first, in step 38, the center of gravity of a group of a plurality of tracking points arranged on the preceding vehicle image is calculated. In step 39, the horizontal variance σ of the tracking point position is calculated using the relationship with the center of gravity. Assuming that the center of gravity of the group of tracking points (n) is (X, Y) and the coordinates of the tracking points are (X k , Y k ), the horizontal variance σ of the group of n tracking points is Equation 2) is obtained.
[0015]
(Equation 2)
Figure 0003580152
[0016]
As shown in FIG. 4A, when the inter-vehicle distance to the preceding vehicle decreases, the preceding vehicle image becomes larger in the screen, the interval between the tracking points on the image increases, and the position of each tracking point in the horizontal direction increases. Since (X k ) is away from the position of the center of gravity (X), the variance σ increases. Conversely, as shown in FIG. 4C, when the inter-vehicle distance to the preceding vehicle increases, the preceding vehicle image becomes smaller on the screen, the interval between the tracking points on the image decreases, and the horizontal Since the tracking point position (X k ) approaches the center of gravity position (X), the variance σ decreases. In step 40, the inter-vehicle distance measurement coefficient h is calculated using the relationship between the variance and the inter-vehicle distance. That is, assuming that the inter-vehicle distance to the preceding vehicle obtained by the laser radar 6 at a certain time is D and the variance is σ, the inter-vehicle distance measurement coefficient h is calculated from h = D × σ. The calculated inter-vehicle distance measurement coefficient h is stored in a recording medium (not shown) provided in the inter-vehicle distance calculation unit 23. In step 41, during non-operation of the laser radar 6, using a dispersion sigma e in the calculated inter-vehicle distance measuring coefficient h and the laser radar inoperative time, the inter-vehicle distance D e to the preceding vehicle calculated estimated . Estimated inter-vehicle distance D e is calculated from D e = h / σ e. Based on the value of the estimated inter-vehicle distance D e, the control signal generating unit 3 outputs a control signal to control the brake actuator 7 and the throttle actuator 8, also the operation-information display unit of a vehicle interior value of the estimated inter-vehicle distance 9 is displayed.
[0017]
As described above, in the present embodiment, when the laser radar 6 is not operating, the inter-vehicle distance is calculated and estimated from the inter-vehicle distance to the preceding vehicle and the dispersion of the group of tracking points by the laser radar obtained immediately before. In addition, it is possible to accurately estimate the inter-vehicle distance to the preceding vehicle. Further, since a plurality of tracking points are added to the preceding vehicle image obtained by one camera and tracking is performed at the same time, even if there are some points where tracking has failed, the accuracy of calculating the inter-vehicle distance is little affected.
[0018]
【The invention's effect】
According to the present invention, it is possible to provide an inter-vehicle distance detection device that can accurately detect the inter-vehicle distance to a preceding vehicle using one imaging unit when the inter-vehicle distance detection unit does not operate.
[Brief description of the drawings]
FIG. 1 is a schematic view of a vehicle equipped with an inter-vehicle distance detection device according to the present invention.
FIG. 2 is a diagram showing an embodiment of an inter-vehicle distance detection device according to the present invention.
FIG. 3 is a flowchart showing an operation of the inter-vehicle distance detection device according to the present invention.
FIGS. 4A, 4B, and 4C are diagrams illustrating a method of tracking a preceding vehicle using tracking points.
[Explanation of symbols]
Reference Signs List 1 controller 2 inter-vehicle distance estimating means 3 control signal generating unit 4 vehicle 5 camera 6 laser radar 7 brake actuator 8 throttle actuator 9 operation / information display unit 10 switch 11 L / R non-operation detecting unit 21 image input unit 22 image processing unit 23 Distance calculation unit

Claims (6)

自車と先行車との車間距離を検出する車間距離検出手段と、前記先行車を撮像する1つの撮像手段とを備えた車間距離検出装置において、
前記車間距離検出手段の不作動時に、前記先行車との車間距離Dを推定する車間距離推定手段をそなえ、
前記車間距離推定手段は、
前記撮像手段で得られた先行車画像を入力する画像入力部と、
前記車間距離検出手段で得られた先行車までの車間距離及び方向に基づいて前記先行車画像の複数個所にそれぞれ追尾点を配置する画像処理部と、
前記先行車画像の前記複数箇所の追尾点について追尾を行うことによって得られる前記追尾点の集団の位置情報および、この際に前記車間距離検出手段によって得られる前記先行車までの車間距離から車間距離計測用係数を算出し、前記算出した車間距離計測用係数および現時点における追尾点の集団の位置情報から車間距離を算出する車間距離計算部とを備えて構成されている
ことを特徴とする車間距離検出装置。
An inter-vehicle distance detection device including an inter-vehicle distance detection unit that detects an inter-vehicle distance between the own vehicle and a preceding vehicle, and one imaging unit that images the preceding vehicle.
When the inter-vehicle distance detection unit is not operated , the vehicle includes an inter-vehicle distance estimation unit that estimates an inter-vehicle distance D to the preceding vehicle;
The inter-vehicle distance estimation means,
An image input unit for inputting a preceding vehicle image obtained by the imaging unit;
An image processing unit that arranges tracking points at a plurality of locations in the preceding vehicle image based on the following distance D and the direction to the preceding vehicle obtained by the following distance detection unit,
The position information of the group of the tracking points obtained by performing the tracking for the plurality of tracking points of the preceding vehicle image , and the inter-vehicle distance to the preceding vehicle obtained by the inter-vehicle distance detection means at this time. distance calculating a measurement factor h, characterized in that it is constituted by a vehicle distance calculating section that calculates the inter-vehicle distance D from the position information of the population of the tracking point in the calculated inter-vehicle distance measuring coefficient h and the present time to, inter-vehicle distance detection device.
前記追尾点の集団の位置情報には、前記追尾点の分散値が用いられることを特徴とする、請求項1記載の車間距離検出装置。The inter-vehicle distance detection device according to claim 1, wherein a variance value of the tracking points is used as the position information of the group of the tracking points. 前記分散値は、前記追尾点の集団の水平方向の分散値σであることを特徴とする、請求項2記載の車間距離検出装置。The inter-vehicle distance detection device according to claim 2, wherein the variance value is a variance value σ of the group of the tracking points in a horizontal direction. 前記車間距離計測用係数hは、ある時点において得られる、前記追尾点の集団の水平方向の分散値σと前記車間距離検出手段による前記先行車までの車間距離Dとの乗算値(D×σ)であることを特徴とする、請求項3記載の車間距離検出装置。The inter-vehicle distance measurement coefficient h is a multiplication value (D × σ) of a horizontal variance value σ of the group of tracking points obtained at a certain time and the inter-vehicle distance D to the preceding vehicle by the inter-vehicle distance detection means. 4. The inter-vehicle distance detecting device according to claim 3, wherein 前記車間距離推定手段では、前記車間距離検出手段の不作動時に、予め得られた前記車間距離計測用係数hを現時点において得られる、前記追尾点の集団の水平方向の分散値σThe inter-vehicle distance estimating means obtains the inter-vehicle distance measuring coefficient h obtained at the present time when the inter-vehicle distance detecting means does not operate, and obtains a horizontal variance σ of the group of the tracking points. ee で除して、前記先行車との車間距離の推定値DDivided by the estimated distance D from the preceding vehicle ee を得ることを特徴とする、請求項4記載の車間距離検出装置。The inter-vehicle distance detecting device according to claim 4, wherein 前記車間距離計算部では、前記複数箇所の追尾点について追尾を行う際に、前記複数の追尾点を順次に注目点として選択し、該注目点周りにテンプレートを設定し、所定時間後に、該注目点が移動したと考えられる候補点を含む範囲に上記テンプレートと同様な窓を設定し、該注目点のテンプレート内の画素の明るさと、該候補点の窓内の画素の明るさとの差が、最小なものを移動した追尾点に設定することを特徴とする、請求項1〜5の何れか1項に記載の車間距離検出装置。The inter-vehicle distance calculating unit sequentially selects the plurality of tracking points as a point of interest when performing tracking on the plurality of tracking points, sets a template around the point of interest, and sets the template after a predetermined time. A window similar to the template is set in a range including the candidate point where the point is considered to have moved, and the difference between the brightness of the pixel in the template of the target point and the brightness of the pixel in the window of the candidate point is: The inter-vehicle distance detection device according to any one of claims 1 to 5, wherein the smallest one is set as the moved tracking point.
JP32231898A 1998-11-12 1998-11-12 Inter-vehicle distance detection device Expired - Lifetime JP3580152B2 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP32231898A JP3580152B2 (en) 1998-11-12 1998-11-12 Inter-vehicle distance detection device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
JP32231898A JP3580152B2 (en) 1998-11-12 1998-11-12 Inter-vehicle distance detection device

Publications (2)

Publication Number Publication Date
JP2000149199A JP2000149199A (en) 2000-05-30
JP3580152B2 true JP3580152B2 (en) 2004-10-20

Family

ID=18142304

Family Applications (1)

Application Number Title Priority Date Filing Date
JP32231898A Expired - Lifetime JP3580152B2 (en) 1998-11-12 1998-11-12 Inter-vehicle distance detection device

Country Status (1)

Country Link
JP (1) JP3580152B2 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102713511A (en) * 2009-08-06 2012-10-03 松下电器产业株式会社 Distance calculation device for vehicle

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4626054B2 (en) * 2000-12-21 2011-02-02 日産自動車株式会社 Vehicle travel control device
JP2004085337A (en) * 2002-08-27 2004-03-18 Fujitsu Ltd Vehicle detection method and vehicle detection device
WO2021230314A1 (en) * 2020-05-14 2021-11-18 国立大学法人 東京大学 Measurement system, vehicle, measurement device, measurement program, and measurement method

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102713511A (en) * 2009-08-06 2012-10-03 松下电器产业株式会社 Distance calculation device for vehicle

Also Published As

Publication number Publication date
JP2000149199A (en) 2000-05-30

Similar Documents

Publication Publication Date Title
JP4043416B2 (en) Safe movement support device
JP4104233B2 (en) Driving environment recognition device
JP3671825B2 (en) Inter-vehicle distance estimation device
JP3779280B2 (en) Collision prediction device
JP5555778B2 (en) Traffic jam prediction method
JPH11212640A (en) Autonomously traveling vehicle and method for controlling autonomously traveling vehicle
RU2734740C1 (en) Parking assistance method and parking assistance device
KR100929689B1 (en) Traffic accident record apparatus using stereo image information and controlling method for the same
JP2001216519A (en) Traffic monitor device
JP4134803B2 (en) Automotive electronic devices
KR20060021922A (en) Two camera based obstacle detection method and device
WO2019044625A1 (en) Collision prediction device, collision prediction method, and program
JP3888055B2 (en) Train forward anomaly detection device using optical flow
US11643071B2 (en) Parking assistance device and parking assistance method
JP3580152B2 (en) Inter-vehicle distance detection device
JP2536986B2 (en) Inter-vehicle distance detector
WO1998021631A1 (en) Remote controller for mobile station
JP2009276906A (en) Travelling information providing device
JPH0981757A (en) Vehicle position detecting device
JP3235831B2 (en) Stereo exterior monitoring device
JP2018199368A (en) Parking control method and parking control device
US20210118300A1 (en) Vehicle control device
CN113492846B (en) Control device, control method, and computer-readable storage medium storing program
JP7385502B2 (en) sensing system
KR102388881B1 (en) Apparatus and method for predicting pitch motion of vehicle body

Legal Events

Date Code Title Description
A977 Report on retrieval

Free format text: JAPANESE INTERMEDIATE CODE: A971007

Effective date: 20040225

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20040302

A521 Written amendment

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20040430

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: 20040629

A61 First payment of annual fees (during grant procedure)

Free format text: JAPANESE INTERMEDIATE CODE: A61

Effective date: 20040712

S531 Written request for registration of change of domicile

Free format text: JAPANESE INTERMEDIATE CODE: R313531

R350 Written notification of registration of transfer

Free format text: JAPANESE INTERMEDIATE CODE: R350

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

Free format text: PAYMENT UNTIL: 20080730

Year of fee payment: 4

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

Free format text: PAYMENT UNTIL: 20090730

Year of fee payment: 5

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

Free format text: PAYMENT UNTIL: 20100730

Year of fee payment: 6

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

Free format text: PAYMENT UNTIL: 20110730

Year of fee payment: 7

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

Free format text: PAYMENT UNTIL: 20120730

Year of fee payment: 8

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

Free format text: PAYMENT UNTIL: 20120730

Year of fee payment: 8

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

Free format text: PAYMENT UNTIL: 20130730

Year of fee payment: 9

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

Free format text: PAYMENT UNTIL: 20130730

Year of fee payment: 9

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

Free format text: PAYMENT UNTIL: 20140730

Year of fee payment: 10

EXPY Cancellation because of completion of term