JP6841725B2 - Other vehicle monitoring system - Google Patents
Other vehicle monitoring system Download PDFInfo
- Publication number
- JP6841725B2 JP6841725B2 JP2017112913A JP2017112913A JP6841725B2 JP 6841725 B2 JP6841725 B2 JP 6841725B2 JP 2017112913 A JP2017112913 A JP 2017112913A JP 2017112913 A JP2017112913 A JP 2017112913A JP 6841725 B2 JP6841725 B2 JP 6841725B2
- Authority
- JP
- Japan
- Prior art keywords
- vehicle
- image
- detection
- monitoring system
- image recognition
- 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.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims description 43
- 238000001514 detection method Methods 0.000 claims description 97
- 230000003287 optical effect Effects 0.000 claims description 14
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 14
- 238000004140 cleaning Methods 0.000 claims description 9
- 238000003384 imaging method Methods 0.000 claims description 5
- 238000000034 method Methods 0.000 description 14
- 230000001629 suppression Effects 0.000 description 7
- 239000006185 dispersion Substances 0.000 description 5
- 230000007704 transition Effects 0.000 description 4
- 206010042635 Suspiciousness Diseases 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000007664 blowing Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
Landscapes
- Closed-Circuit Television Systems (AREA)
- Traffic Control Systems (AREA)
- Image Analysis (AREA)
Description
本発明は、自動車の周辺を走行する他車を監視する技術に関するものである。 The present invention relates to a technique for monitoring another vehicle traveling around the vehicle.
自動車の周辺を走行する他車を監視する技術としては、自車の側方を撮影するカメラを設け、カメラで撮影した画像に映り込んだ他車のタイヤをパターンマッチングによって認識すると共に、画像認識したタイヤの位置や大きさ等に基づいて、当該他車の相対位置や相対速度や大きさを検出する技術が知られている（たとえば、特許文献１）。 As a technology for monitoring other vehicles traveling around the vehicle, a camera that captures the side of the vehicle is provided, and the tires of the other vehicle reflected in the image taken by the camera are recognized by pattern matching and image recognition. There is known a technique for detecting the relative position, relative speed, and size of the other vehicle based on the position and size of the tire (for example, Patent Document 1).
また、自動車に搭載された自動車周辺を撮影するカメラに関する技術としては、予め各道路区間について当該道路区間の路面標示のパターンを登録しておき、走行中の道路区間について登録されている路面標示のパターンと、実際にカメラで撮影された路面上のパターンとの相違に基づいて、カメラの光学系に付着した水滴や汚れを検出する技術が知られている（たとえば、特許文献２）。 In addition, as a technology related to a camera mounted on an automobile to photograph the surroundings of an automobile, a pattern of road markings on the road section is registered in advance for each road section, and the road markings registered for the running road section. There is known a technique for detecting water droplets and dirt adhering to the optical system of a camera based on the difference between the pattern and the pattern on the road surface actually photographed by the camera (for example, Patent Document 2).
カメラで撮影した画像に映り込んだ他車のタイヤをパターンマッチングによって認識し、認識したタイヤに基づいて他車を検出する技術においては、カメラのレンズの前玉や、カメラのレンズの前方に設けた光学窓などの、撮像光学系の入射側端の光学部品に雨滴が付着したときに、当該雨滴をパターンマッチングによってタイヤとして認識してしまい、他車を誤検出してしまうことがある。 In the technology of recognizing the tires of other vehicles reflected in the image taken by the camera by pattern matching and detecting other vehicles based on the recognized tires, it is provided in the front lens of the camera lens or in front of the camera lens. When raindrops adhere to the optical components at the incident side end of the imaging optical system, such as an optical window, the raindrops may be recognized as tires by pattern matching, and other vehicles may be erroneously detected.
また、このような他車の誤検出は、タイヤに代えて、雨滴の形状と類似性のある自動車の特定の形状の外観部分をパターンマッチングによって認識し、認識した外観部分に基づいて他車を検出する場合にも同様に生じ得る
一方で、雨滴の付着を検出して他車の検出を抑止すれば、他車の誤検出を抑止することができるが、上述したカメラの光学系に付着した水滴や汚れを検出する技術では、路面標示が存在し、かつ、当該路面標示のパターンが予め登録されている道路区間でしか雨滴付着を検出することができない。
Further, in such a false detection of another vehicle, instead of the tire, the appearance portion of a specific shape of the automobile having a shape similar to the shape of raindrops is recognized by pattern matching, and the other vehicle is recognized based on the recognized appearance portion. On the other hand, if the adhesion of raindrops is detected and the detection of other vehicles is suppressed, the false detection of other vehicles can be suppressed, but it adheres to the optical system of the above-mentioned camera. In the technique for detecting water droplets and dirt, raindrop adhesion can be detected only in a road section in which a road marking is present and the pattern of the road marking is registered in advance.
そこで、本発明は、カメラに付着した雨滴による他車の誤検出を抑止することを課題とする。 Therefore, an object of the present invention is to prevent erroneous detection of another vehicle due to raindrops adhering to the camera.
前記課題達成のために、本発明は、自動車に搭載される、当該自動車の周辺の他車を監視する他車監視システムに、本発明は、自動車に搭載される、当該自動車の周辺の他車を監視する他車監視システムに、前記自動車の周辺を撮影するカメラと、前記カメラが撮影した画像中の他車の外観に円形に表れる部分の像を認識する画像認識手段と、前記画像認識手段の認識結果に基づいて他車を検出する他車検出手段と、前記画像認識手段が認識した前記部分の像の前記画像中の配置に基づいて、他車の相対位置を算定する算定手段と、前記算定手段が算定した他車の相対位置が示す、前記自動車と当該他車との間の前記自動車の左右方向の距離のばらつきの程度が所定のレベルより大きくなったときに、前記他車検出手段の他車の検出を停止させる他車検出抑止手段とを備えたものである。 In order to achieve the above-mentioned problems, the present invention is applied to another vehicle monitoring system mounted on an automobile to monitor other vehicles around the automobile, and the present invention is applied to another vehicle mounted on the automobile to monitor other vehicles around the automobile. The other vehicle monitoring system that monitors the vehicle includes a camera that photographs the surroundings of the vehicle, an image recognition means that recognizes an image of a portion of the image taken by the camera that appears in a circle on the appearance of the other vehicle, and the image recognition means. Another vehicle detection means that detects another vehicle based on the recognition result of the other vehicle, and a calculation means that calculates the relative position of the other vehicle based on the arrangement of the image of the portion recognized by the image recognition means in the image. The other vehicle is detected when the degree of variation in the lateral distance of the vehicle between the vehicle and the other vehicle indicated by the relative position of the other vehicle calculated by the calculation means becomes larger than a predetermined level. It is equipped with other vehicle detection deterrence means for stopping the detection of other vehicles.
また、前記課題達成のために、自動車に搭載される、当該自動車の周辺の他車を監視する他車監視システムに、
前記自動車の周辺を撮影するカメラと、前記カメラが撮影した画像中の他車の外観に円形に表れる部分の像を認識する画像認識手段と、前記画像認識手段の認識結果に基づいて他車を検出する他車検出手段と、前記画像認識手段が認識した前記部分の像の前記画像中の配置に基づいて、前記部分の相対位置を算定する算定手段と、前記算定手段が算定した前記部分の相対位置が示す、前記自動車と当該部分との間の前記自動車の左右方向の距離のばらつきの程度が所定のレベルより大きくなったときに、前記他車検出手段の他車の検出を停止させる他車検出抑止手段を備えたものである。
In addition, in order to achieve the above-mentioned problem, another vehicle monitoring system that monitors other vehicles around the vehicle is installed in the vehicle.
A camera that photographs the periphery of the automobile, an image recognition means that recognizes an image of a portion that appears in a circle on the appearance of the other vehicle in the image taken by the camera, and another vehicle based on the recognition result of the image recognition means. A calculation means for calculating the relative position of the portion based on the other vehicle detecting means to be detected, the arrangement of the image of the portion recognized by the image recognition means in the image, and the portion calculated by the calculation means. When the degree of variation in the lateral distance of the automobile between the automobile and the portion indicated by the relative position becomes larger than a predetermined level, the detection of the other vehicle by the other vehicle detecting means is stopped. It is equipped with vehicle detection deterrence means.
また、本発明は、前記課題達成のために、自動車に搭載される、当該自動車の周辺の他車を監視する他車監視システムに、前記自動車の周辺を撮影するカメラと、前記カメラが撮影した画像中の他車の外観に円形に表れる部分の像を認識する画像認識手段と、前記画像認識手段の認識結果に基づいて他車を検出する他車検出手段と、前記画像認識手段が認識した前記部分の像の前記画像中の配置に基づいて、他車の相対位置を算定する算定手段と、前記算定手段が算定した他車の相対位置が示す、過去所定期間における、前記自動車と当該他車との間の前記自動車の左右方向の距離の分散または標準偏差である不審度が所定のしきい値より大きくなったときに、前記他車検出手段の他車の検出を停止させる他車検出抑止手段とを備えたものである。 Further, in order to achieve the above-mentioned problem, in order to achieve the above-mentioned problems, a camera for photographing the periphery of the automobile and a camera for photographing the periphery of the automobile are photographed by another vehicle monitoring system mounted on the automobile for monitoring other vehicles in the vicinity of the automobile. The image recognition means recognized an image recognition means for recognizing an image of a portion appearing in a circle on the appearance of another vehicle in an image, another vehicle detection means for detecting another vehicle based on the recognition result of the image recognition means, and the other vehicle detection means for detecting another vehicle. Based on the arrangement of the image of the portion in the image, the calculation means for calculating the relative position of the other vehicle and the relative position of the other vehicle calculated by the calculation means indicate the vehicle and the other vehicle in the past predetermined period. Another vehicle detection that stops the detection of another vehicle by the other vehicle detection means when the suspiciousness, which is the dispersion or standard deviation of the distance between the vehicle and the vehicle in the left-right direction, becomes larger than a predetermined threshold value. It is equipped with deterrent means.
また、前記課題達成のために、本発明は、自動車に搭載される、当該自動車の周辺の他車を監視する他車監視システムに、前記自動車の周辺を撮影するカメラと、前記カメラが撮影した画像中の他車の外観に円形に表れる部分の像を認識する画像認識手段と、前記画像認識手段の認識結果に基づいて他車を検出する他車検出手段と、前記画像認識手段が認識した前記部分の像の前記画像中の配置に基づいて、前記部分の相対位置を算定する算定手段と、前記算定手段が算定した前記部分の相対位置が示す、過去所定期間における、前記自動車と当該部分との間の前記自動車の左右方向の距離の分散または標準偏差である不審度が所定のしきい値より大きくなったときに、前記他車検出手段の他車の検出を停止させる他車検出抑止手段とを備えたものである。 Further, in order to achieve the above-mentioned problems, in the present invention, a camera for photographing the periphery of the automobile and a camera for photographing the periphery of the automobile are photographed by another vehicle monitoring system mounted on the automobile for monitoring other vehicles in the vicinity of the automobile. The image recognition means recognized an image recognition means for recognizing an image of a portion appearing in a circle on the appearance of another vehicle in an image, another vehicle detection means for detecting another vehicle based on the recognition result of the image recognition means, and the other vehicle detection means for detecting another vehicle. The vehicle and the portion in the past predetermined period indicated by the calculation means for calculating the relative position of the portion based on the arrangement of the image of the portion in the image and the relative position of the portion calculated by the calculation means. When the suspiciousness, which is the dispersion or standard deviation of the distance between the vehicle and the vehicle in the left-right direction, becomes larger than a predetermined threshold value, the detection of the vehicle by the other vehicle is stopped. It is equipped with means.
ここで、以上のような不審度に応じて他車検出手段の他車の検出を停止させる他車監視システムにおいては、前記他車検出抑止手段において、前記他車検出手段の他車の検出を停止させた後、前記不審度が所定のレベルより小さくなったならば、前記他車検出手段の他車の検出を再開させるようにしてもよい。 Here, in the other vehicle monitoring system that stops the detection of the other vehicle by the other vehicle detection means according to the suspicious degree as described above, the other vehicle detection deterrent means detects the other vehicle by the other vehicle detection means. If the degree of suspicion becomes smaller than a predetermined level after the stop, the detection of the other vehicle by the other vehicle detection means may be restarted.
また、以上のような他車監視システムにおいて、前記部分は、タイヤであってよい。
また、以上のような、他車監視システムに、さらに、前記他車検出手段が検出した他車の存在をユーザに対して提示する他車提示手段を備えるようにしてもよい。
また、以上のような他車監視システムは、前記他車検出抑止手段において、前記他車検出手段の他車の検出を停止させる際に、当該停止の旨をユーザに対して警告するように構成してもよい。
Further, in the other vehicle monitoring system as described above, the portion may be a tire.
Further, the other vehicle monitoring system as described above may be further provided with the other vehicle presenting means for presenting the existence of the other vehicle detected by the other vehicle detecting means to the user.
Further, the other vehicle monitoring system as described above is configured so that when the other vehicle detection deterrent means stops the detection of the other vehicle by the other vehicle detection means, the user is warned of the stop. You may.
また、以上のような他車監視システムに、さらに、前記カメラの撮像光学系に付着した水滴を除去する清掃機構と、前記他車検出抑止手段が前記他車検出手段の他車の検出を停止させたときに、前記清掃機構に前記水滴の除去を行わせる水滴除去制御手段とを設けるようにしてもよい。 Further, in the other vehicle monitoring system as described above, a cleaning mechanism for removing water droplets adhering to the image pickup optical system of the camera and the other vehicle detection suppressing means stop the detection of the other vehicle by the other vehicle detection means. The cleaning mechanism may be provided with a water droplet removal control means for removing the water droplets when the water droplets are removed.
以上のような他車監視システムによれば、識別された他車や他車の前記部分の相対位置のばらつきが大きい場合には、他車の検出が抑止される。また、通常、自車と同じ道路を走行している他車や前記部分の、前記相対位置のばらつきは小さいのに対して、カメラに付着した雨滴を前記部分として誤認識とした場合の、前記相対位置のばらつきは、雨滴が移動、変形するために一般的に大きくなる。
したがって、本発明によれば、カメラが撮影した画像中の他車の外観に円形に表れる部分の像に基づいて他車を検出する他車監視システムにおいて、カメラに付着した雨滴の像を当該部分の像として誤認識してしまうことによる、他車の誤検出を抑止することができる。
According to the other vehicle monitoring system as described above, the detection of the other vehicle is suppressed when the identified other vehicle or the relative position of the portion of the other vehicle has a large variation. In addition, when the variation in the relative position of another vehicle or the portion traveling on the same road as the own vehicle is small, the raindrops adhering to the camera are erroneously recognized as the portion. The variation in relative position is generally large due to the movement and deformation of raindrops.
Therefore, according to the present invention, in the other vehicle monitoring system that detects another vehicle based on the image of the portion appearing in a circle on the appearance of the other vehicle in the image taken by the camera, the image of raindrops adhering to the camera is captured in the portion. It is possible to prevent erroneous detection of other vehicles due to erroneous recognition as an image of.
以上のように、本発明によれば、カメラに付着した雨滴による他車の誤検出を抑止することができる。 As described above, according to the present invention, it is possible to suppress erroneous detection of another vehicle due to raindrops adhering to the camera.
以下、本発明の実施形態について、自動車に搭載された、自車の側方を走行する他車を監視する他車監視システムへの適用を例にとり説明する。
図１に、本実施形態に係る他車監視システムの構成を示す。
図示するように、他車監視システムは、リアカメラ１、他車検出部２、警告制御部３、音声出力装置４、表示装置５、入力装置６を備えている。
ここで、図２に示すように、リアカメラ１は、自動車の後部に設置されており、自車の後方を撮影する。
次に、他車検出部２は、リアカメラ１が撮影した画像中に映り込んだ他車のタイヤを画像中のエッジとのパターンマッチング等による画像認識によって識別すると共に、識別したタイヤの自車に対する相対位置、タイヤの大きさ等を、画像中のタイヤの位置や大きさに基づいて算出する。
Hereinafter, an embodiment of the present invention will be described by taking as an example an application to another vehicle monitoring system mounted on an automobile to monitor another vehicle traveling on the side of the own vehicle.
FIG. 1 shows the configuration of the other vehicle monitoring system according to the present embodiment.
As shown in the figure, the other vehicle monitoring system includes a rear camera 1, another vehicle detection unit 2, a warning control unit 3, a voice output device 4, a display device 5, and an input device 6.
Here, as shown in FIG. 2, the rear camera 1 is installed at the rear of the automobile and photographs the rear of the own vehicle.
Next, the other vehicle detection unit 2 identifies the tires of the other vehicle reflected in the image taken by the rear camera 1 by image recognition such as pattern matching with the edges in the image, and the own vehicle of the identified tires. The relative position with respect to the tire, the size of the tire, etc. are calculated based on the position and size of the tire in the image.
また、他車検出部２は、算出したタイヤの相対位置、タイヤの大きさや、その推移等に基づいて、他車の自車に対する相対位置や、他車の自車に対する相対速度を算定して、警告制御部３に通知する。 Further, the other vehicle detection unit 2 calculates the relative position of the other vehicle with respect to the own vehicle and the relative speed of the other vehicle with respect to the own vehicle based on the calculated relative position of the tire, the size of the tire, its transition, and the like. , Notifies the warning control unit 3.
但し、他車検出部２は、識別したタイヤの相対位置や、識別したタイヤの自車に対する相対速度を、他車の自車に対する相対位置や、他車の自車に対する相対速度として、警告制御部３に通知するようにしてもよい。 However, the other vehicle detection unit 2 warns that the relative position of the identified tire and the relative speed of the identified tire with respect to the own vehicle are set as the relative position of the other vehicle with respect to the own vehicle and the relative speed of the other vehicle with respect to the own vehicle. You may notify the part 3.
警告制御部３は、他車検出部２から通知された、他車の自車に対する相対位置や、他車の自車に対する相対速度に基づいて他車を検出し、検出した他車についての警告や警報を出力する処理を行う。 The warning control unit 3 detects another vehicle based on the relative position of the other vehicle with respect to the own vehicle and the relative speed of the other vehicle with respect to the own vehicle notified from the other vehicle detection unit 2, and warns about the detected other vehicle. Or to output an alarm.
すなわち、たとえば、警告制御部３は、他車検出部２から、他車の自車に対する相対位置や、他車の自車に対する相対速度を通知されたならば、他車を検出する。
そして、警告制御部３は、検出した他車の自車に対する相対位置が、自車から所定距離内に、自車の側方を走行している他車が存在していることを表している期間中、表示装置５の表示を用いて側方車が存在していることを運転者に提示する警告出力を行う。
That is, for example, if the warning control unit 3 is notified by the other vehicle detection unit 2 of the relative position of the other vehicle with respect to the own vehicle and the relative speed of the other vehicle with respect to the own vehicle, the warning control unit 3 detects the other vehicle.
Then, the warning control unit 3 indicates that the detected relative position of the other vehicle with respect to the own vehicle is within a predetermined distance from the own vehicle and that there is another vehicle traveling on the side of the own vehicle. During the period, a warning output is performed to indicate to the driver that a side vehicle is present by using the display of the display device 5.
また、警告制御部３は、検出した他車の自車に対する相対位置や、他車の自車に対する相対速度が、所定期間内に他車が自車に所定レベル以上接近することを表しているときに、側方車の異常接近を知らせる所定の警報音や音声メッセージを音声出力装置４から出力する警報出力を行う。 Further, the warning control unit 3 indicates that the detected relative position of the other vehicle with respect to the own vehicle and the relative speed of the other vehicle with respect to the own vehicle approach the own vehicle by a predetermined level or more within a predetermined period. Occasionally, an alarm output is performed to output a predetermined alarm sound or voice message notifying the abnormal approach of the side vehicle from the voice output device 4.
さて、ここで、図３に、リアカメラ１で撮影される画像の例を示す。
図中、図３ａは、リアカメラ１のレンズの前玉や、カメラのレンズの前方に設けた光学窓などの、撮像光学系の入射側端の光学部品に雨滴が付着していないときにリアカメラ１によって撮影される画像を示し、図３ｂは、撮像光学系の入射側端の光学部品に雨滴が付着しているときにリアカメラ１によって撮影される画像を示している。
Now, FIG. 3 shows an example of an image taken by the rear camera 1.
In the figure, FIG. 3a shows the rear when raindrops are not attached to the optical components at the incident side end of the imaging optical system, such as the front lens of the lens of the rear camera 1 and the optical window provided in front of the lens of the camera. The image taken by the camera 1 is shown, and FIG. 3b shows the image taken by the rear camera 1 when raindrops are attached to the optical component at the incident side end of the imaging optical system.
図３ｂに示すように、雨滴が付着しているときには、雨滴による円形や楕円形のパターンが画像中に表れ、他車検出部２において、このパターンが他車のタイヤとして識別されてしまうことがある。 As shown in FIG. 3b, when raindrops are attached, a circular or elliptical pattern due to the raindrops appears in the image, and this pattern may be identified as a tire of another vehicle by the other vehicle detection unit 2. is there.
そして、他車検出部２において、このように雨滴が他車のタイヤとして識別されてしまうと、警告制御部３において、他車が誤検出されてしまい、不要な警告出力や警報出力が行われてしまうこととなる。 Then, if the raindrops are identified as the tires of the other vehicle by the other vehicle detection unit 2, the other vehicle is erroneously detected by the warning control unit 3, and unnecessary warning output or alarm output is performed. Will end up.
そこで、警告制御部３は、図４に示す警告抑止処理を行う。
図示するように、警告制御部３は、警告抑止処理において、過去所定期間内（たとえば、過去５秒以内）に他車検出部２から通知された、他車の自車に対する相対位置の座標の不審度Ｍを算定する処理（ステップ４０２）を、しきい値Th1超の不審度Ｍが算定されるまで（ステップ４０４）繰り返す。
Therefore, the warning control unit 3 performs the warning suppression process shown in FIG.
As shown in the figure, in the warning suppression process, the warning control unit 3 has the coordinates of the relative position of the other vehicle with respect to the own vehicle notified by the other vehicle detection unit 2 within the past predetermined period (for example, within the past 5 seconds). The process of calculating the suspicious degree M (step 402) is repeated until the suspicious degree M exceeding the threshold value Th1 is calculated (step 404).
ここで、自車の左右方向の軸をＸ軸として、不審度Ｍとしては、他車の自車に対する相対位置のＸ軸方向（自車の左右方向）の座標をｘ、Avg(ｘ)を座標ｘの平均値として、下式によって示される分散σ2を用いる。なお、座標ｘは、自車の左右方向についての自車と他車との距離を表す。 Here, the left-right axis of the own vehicle is the X-axis, and the suspicious degree M is the coordinates of the position of the other vehicle relative to the own vehicle in the X-axis direction (horizontal direction of the own vehicle) x and Avg (x). As the average value of the coordinates x, the variance σ 2 shown by the following equation is used. The coordinates x represent the distance between the own vehicle and another vehicle in the left-right direction of the own vehicle.
そして、しきい値Th1超の不審度Ｍが算定されたならば（ステップ４０４）、他車検出停止モードを設定する（ステップ４０６）。なお、他車検出停止モードは初期状態では設定されておらず、解除されている。
ここで、他車検出停止モードが設定されている期間中、警告制御部３は、他車の検出を抑止し、警告出力と警報出力を停止する。
Then, when the suspicious degree M exceeding the threshold value Th1 is calculated (step 404), the other vehicle detection stop mode is set (step 406). The other vehicle detection stop mode is not set in the initial state and is canceled.
Here, during the period in which the other vehicle detection stop mode is set, the warning control unit 3 suppresses the detection of the other vehicle and stops the warning output and the alarm output.
そして、次に、他車の検出を停止することを運転者に警告する（ステップ４０８）。
ここで、ステップ４０８では、たとえば、音声出力装置４から他車の検出を停止することを伝える音声メッセージを出力すると共に、表示装置５の表示による他車の検出を停止していることの運転者への提示を開始する。または、ステップ４０８では、音声メッセージを出力する代わりに、入力装置６に対してユーザが解除操作を行うまで警告音を音声出力装置４から出力するようにしてもよい。
Then, the driver is warned to stop the detection of the other vehicle (step 408).
Here, in step 408, for example, the driver that outputs a voice message notifying that the detection of the other vehicle is stopped from the voice output device 4 and stops the detection of the other vehicle by the display of the display device 5. Start presenting to. Alternatively, in step 408, instead of outputting the voice message, a warning sound may be output from the voice output device 4 until the user performs a release operation on the input device 6.
そして、過去所定期間内（たとえば、過去５秒以内）に他車検出部２から通知された、他車の自車に対する相対位置の座標の不審度Ｍを算定する処理（ステップ４１０）を、しきい値Th2未満の不審度Ｍが算定されるまで（ステップ４１２）繰り返す。ここで、Th2は、Th2＜Th1を満たす値を設定する。 Then, the process (step 410) of calculating the suspiciousness M of the coordinates of the relative position of the other vehicle with respect to the own vehicle, which is notified from the other vehicle detection unit 2 within the past predetermined period (for example, within the past 5 seconds), is performed. Repeat until a suspicious degree M less than the threshold value Th2 is calculated (step 412). Here, Th2 sets a value that satisfies Th2 <Th1.
そして、しきい値Th2未満の不審度Ｍが算定されたならば（ステップ４１２）、他車検出停止モードを解除する（ステップ４１４）。
ここで、他車検出停止モードが解除されると、以降、警告制御部３は、他車検出部２から、他車の自車に対する相対位置や、他車の自車に対する相対速度を通知されたならば、他車を検出し、検出した他車についての警告出力や警報出力を上述のように行う。
Then, when the suspicious degree M less than the threshold value Th2 is calculated (step 412), the other vehicle detection stop mode is released (step 414).
Here, when the other vehicle detection stop mode is released, the warning control unit 3 is subsequently notified by the other vehicle detection unit 2 of the relative position of the other vehicle with respect to the own vehicle and the relative speed of the other vehicle with respect to the own vehicle. If so, the other vehicle is detected, and the warning output and the warning output for the detected other vehicle are performed as described above.
そして、次に、他車の検出を再開したことを運転者に通知し（ステップ４１６）、ステップ４０２からの処理に戻る。
ここで、ステップ４１６では、たとえば、音声出力装置４から他車の検出を再開することを伝える音声メッセージを出力すると共に、表示装置５の表示による他車の検出を停止していることの運転者への提示を消去する。
Then, the driver is notified that the detection of the other vehicle has been restarted (step 416), and the process returns to the process from step 402.
Here, in step 416, for example, the driver that outputs a voice message notifying that the detection of the other vehicle is restarted from the voice output device 4 and stops the detection of the other vehicle by the display of the display device 5. Erase the presentation to.
以上、警告制御部３が行う警告抑止処理について説明した。
さて、ここで、図３ａのように雨滴が付着していない映像がリアカメラ１によって撮影されている期間中の、他車検出部２において検出された他車の自車に対する相対位置のＸ軸方向（自車の左右方向）の座標ｘの推移を図５ａに示し、図３ｂのように雨滴が付着している映像がリアカメラ１によって撮影されている期間中の、他車検出部２において検出された他車の自車に対する相対位置のＸ軸方向（自車の左右方向）の座標ｘの推移を図５ｂに示す。
The warning suppression process performed by the warning control unit 3 has been described above.
Now, here, as shown in FIG. 3a, the X-axis of the position of the other vehicle relative to the own vehicle detected by the other vehicle detection unit 2 during the period in which the image without raindrops is being captured by the rear camera 1. FIG. 5a shows the transition of the coordinates x in the direction (horizontal direction of the own vehicle), and the other vehicle detection unit 2 during the period in which the image with raindrops attached is taken by the rear camera 1 as shown in FIG. 3b. FIG. 5b shows the transition of the detected coordinates x of the position relative to the own vehicle of the other vehicle in the X-axis direction (left-right direction of the own vehicle).
ただし、図５ａ、ｂにおいては、他車を検出していないときの座標ｘの値を０としている。
他車は自車と同じ道路を走行しているので、他車の自車対する左右方向の相対位置は頻繁に大きく変動することがなく、雨滴が付着していないときには他車検出部２で正しく他車の相対位置を検出できるので、他車検出部２で検出される他車の自車に対する相対位置のＸ軸方向（自車の左右方向）の座標ｘは、図５ａに示されるように、安定的に、特定の値の周辺の値となる。
However, in FIGS. 5a and 5b, the value of the coordinate x when no other vehicle is detected is set to 0.
Since the other vehicle is traveling on the same road as the own vehicle, the relative position of the other vehicle in the left-right direction with respect to the own vehicle does not fluctuate significantly frequently, and when raindrops are not attached, the other vehicle detection unit 2 is correct. Since the relative position of the other vehicle can be detected, the coordinate x of the position relative to the own vehicle of the other vehicle detected by the other vehicle detection unit 2 in the X-axis direction (left-right direction of the own vehicle) is as shown in FIG. 5a. , Stable, values around a specific value.
一方、雨滴が付着しており、他車検出部２が雨滴をタイヤと誤認識している場合、付着した雨滴は自動車の走行に伴い頻繁に移動したり形状が変化したりするので、他車検出部２で検出される他車の自車に対する相対位置のＸ軸方向（自車の左右方向）の座標ｘは、図５ｂに示されるように頻繁に大きく変動する。 On the other hand, if raindrops are attached and the other vehicle detection unit 2 mistakenly recognizes the raindrops as tires, the attached raindrops frequently move or change shape as the vehicle runs. The coordinates x of the position of the other vehicle relative to the own vehicle in the X-axis direction (left-right direction of the own vehicle) detected by the protrusion 2 frequently and greatly fluctuate as shown in FIG. 5b.
したがって、他車検出部２において検出された他車の自車に対する相対位置のＸ軸方向（自車の左右方向）の座標ｘの分散σ2は、雨滴が付着していないときには小さい値となり、付着した雨滴による誤認識が発生しているときには大きい値となる。
よって、上述した警告抑止処理によって、過去所定期間内において、他車検出部２において検出された他車の自車に対する相対位置のＸ軸方向（自車の左右方向）の座標ｘの分散σ2が大きい期間中、他車の検出を抑止して、警告出力や警報出力を停止することにより、リアカメラ１に付着した雨滴による他車の誤検出や、当該誤検出に基づく警告出力や警報出力を抑止することができる。
Therefore, the variance σ 2 of the coordinates x in the X-axis direction (horizontal direction of the own vehicle) of the position relative to the own vehicle of the other vehicle detected by the other vehicle detection unit 2 becomes a small value when no raindrops are attached. It is a large value when erroneous recognition due to attached raindrops occurs.
Therefore, by the warning suppression process described above, the dispersion σ 2 of the coordinates x in the X-axis direction (left-right direction of the own vehicle) of the position relative to the own vehicle of the other vehicle detected by the other vehicle detection unit 2 within the past predetermined period. By suppressing the detection of other vehicles and stopping the warning output and alarm output during the period when the speed is large, false detection of other vehicles due to raindrops adhering to the rear camera 1 and warning output and alarm output based on the false detection Can be deterred.
以上、本発明の実施形態について説明した。
ここで、以上の実施形態では、図４の警告抑止処理のステップ４０２、ステップ４１０において、不審度Ｍとして、他車検出部２から通知された他車の自車に対する相対位置のＸ軸方向（自車の左右方向）の座標ｘの分散を算出したが、これは、ステップ４０２、４１０において、他車検出部２が算出した他車のタイヤの自車に対する相対位置のＸ軸方向（自車の左右方向）の座標ｘの分散を算出するようにしてもよい。
The embodiment of the present invention has been described above.
Here, in the above embodiment, in step 402 and step 410 of the warning suppression process of FIG. 4, the X-axis direction of the position of the other vehicle relative to the own vehicle notified from the other vehicle detection unit 2 as the suspicious degree M ( The dispersion of the coordinates x in the left-right direction of the own vehicle) was calculated, and this is the X-axis direction (own vehicle) of the position of the tire of the other vehicle calculated by the other vehicle detection unit 2 relative to the own vehicle in steps 402 and 410. The dispersion of the coordinates x in the left-right direction of) may be calculated.
また、以上の実施形態では、不審度Ｍとして、座標ｘの分散σ2を用いたが、不審度Ｍとしては、座標ｘのばらつきの程度が大きいほど大きくなる値であれば他の指標を用いるようにしてもよい。すなわち、たとえば、不審度Ｍとしては、標準偏差や、過去所定期間中に、座標ｘが所定の大きさ以上大きく変化した回数などを用いるようにしてもよい。
また、以上の実施形態の他車監視システムに、リアカメラ１の撮像光学系の入射側端の光学部品に付着した雨滴等の水滴を拭き取るワイパーや、当該水滴を吹き飛ばす送風機などの、当該水滴を除去する清掃機構を設け、図４の警告抑止処理のステップ４０６で他車検出停止モードを設定したならば、ステップ４０８において、他車の検出を停止することを運転者に警告すると共に、清掃機構に水滴を除去する動作である除去動作（清掃機構がワイパーであればワイパーの駆動、清掃機が送風機であれば送風）を開始させるようにしてもよい。なお、この場合、ステップ４１４において、他車検出停止モードを解除する際に、清掃機構の水滴の除去動作を停止するようにする。
Further, in the above embodiment, the variance σ 2 of the coordinate x is used as the suspicious degree M, but as the suspicious degree M, another index is used as long as the value increases as the degree of variation of the coordinate x increases. You may do so. That is, for example, as the suspicious degree M, the standard deviation, the number of times the coordinates x have changed significantly by a predetermined magnitude or more during the past predetermined period, or the like may be used.
Further, in the other vehicle monitoring system of the above embodiment, the water droplets such as a wiper that wipes off water droplets such as raindrops adhering to the optical component at the incident side end of the imaging optical system of the rear camera 1 and a blower that blows off the water droplets are applied. If a cleaning mechanism for removing is provided and the other vehicle detection stop mode is set in step 406 of the warning suppression process of FIG. 4, in step 408, the driver is warned that the detection of the other vehicle is stopped, and the cleaning mechanism is used. The removal operation (driving the wiper if the cleaning mechanism is a wiper, blowing air if the cleaning machine is a blower), which is an operation for removing water droplets, may be started. In this case, in step 414, when the other vehicle detection stop mode is released, the operation of removing water droplets from the cleaning mechanism is stopped.
また、以上の実施形態は、リアカメラ１を用いて自車側方の他車を検出する場合について説明したが、本実施形態は、自動車の前方や側方に設けたカメラを用いて他車を検出する場合について同様に適用することができる。 Further, in the above embodiment, the case where the rear camera 1 is used to detect another vehicle on the side of the own vehicle has been described, but in the present embodiment, the other vehicle is detected by using the cameras provided in front of or on the side of the vehicle. The same can be applied to the case of detecting.
また、以上の実施形態は、タイヤを画像認識して他車を検出する場合について説明したが、本実施形態は、タイヤ以外の、自動車の雨滴と類似する形状の外観部分を画像認識して他車を検出する場合について同様に適用することができる。すなわち、本実施形態は、たとえば、自動車のヘッドライトやその照明光の像などの、自動車の外観に円形に表れる部分を画像認識して他車を検出する場合等について同様に適用することができる。 Further, in the above embodiment, the case where the tire is image-recognized to detect another vehicle has been described, but in the present embodiment, the appearance portion having a shape similar to that of a raindrop of an automobile other than the tire is image-recognized. The same can be applied to the case of detecting a car. That is, the present embodiment can be similarly applied to a case where, for example, an image of a portion appearing in a circle on the appearance of an automobile, such as an image of a headlight of an automobile or an image of its illumination light, is recognized to detect another vehicle. ..
１…リアカメラ、２…他車検出部、３…警告制御部、４…音声出力装置、５…表示装置、６…入力装置。 1 ... rear camera, 2 ... other vehicle detection unit, 3 ... warning control unit, 4 ... voice output device, 5 ... display device, 6 ... input device.
Claims (9)
前記自動車の周辺を撮影するカメラと、
前記カメラが撮影した画像中の他車の外観に円形に表れる部分の像を認識する画像認識手段と、
前記画像認識手段の認識結果に基づいて他車を検出する他車検出手段と、
前記画像認識手段が認識した前記部分の像の前記画像中の配置に基づいて、他車の相対位置を算定する算定手段と、
前記算定手段が算定した他車の相対位置が示す、前記自動車と当該他車との間の前記自動車の左右方向の距離のばらつきの程度が所定のレベルより大きくなったときに、前記他車検出手段の他車の検出を停止させる他車検出抑止手段とを有することを特徴とする他車監視システム。 It is a vehicle monitoring system installed in a vehicle that monitors other vehicles around the vehicle.
A camera that shoots the area around the car,
An image recognition means for recognizing an image of a part appearing in a circle on the appearance of another vehicle in the image taken by the camera, and an image recognition means.
Another vehicle detection means that detects another vehicle based on the recognition result of the image recognition means, and
A calculation means for calculating the relative position of another vehicle based on the arrangement of the image of the portion recognized by the image recognition means in the image, and
The other vehicle is detected when the degree of variation in the lateral distance of the vehicle between the vehicle and the other vehicle indicated by the relative position of the other vehicle calculated by the calculation means becomes larger than a predetermined level. Another vehicle monitoring system characterized by having another vehicle detection deterrent means for stopping the detection of another vehicle.
前記自動車の周辺を撮影するカメラと、
前記カメラが撮影した画像中の他車の外観に円形に表れる部分の像を認識する画像認識手段と、
前記画像認識手段の認識結果に基づいて他車を検出する他車検出手段と、
前記画像認識手段が認識した前記部分の像の前記画像中の配置に基づいて、前記部分の相対位置を算定する算定手段と、
前記算定手段が算定した前記部分の相対位置が示す、前記自動車と当該部分との間の前記自動車の左右方向の距離のばらつきの程度が所定のレベルより大きくなったときに、前記他車検出手段の他車の検出を停止させる他車検出抑止手段とを有することを特徴とする他車監視システム。 It is a vehicle monitoring system installed in a vehicle that monitors other vehicles around the vehicle.
A camera that shoots the area around the car,
An image recognition means for recognizing an image of a part appearing in a circle on the appearance of another vehicle in the image taken by the camera, and an image recognition means.
Another vehicle detection means that detects another vehicle based on the recognition result of the image recognition means, and
A calculation means for calculating the relative position of the portion based on the arrangement of the image of the portion recognized by the image recognition means in the image.
When the degree of variation in the lateral distance of the automobile between the automobile and the portion indicated by the relative position of the portion calculated by the calculation means becomes larger than a predetermined level, the other vehicle detecting means Another vehicle monitoring system characterized by having another vehicle detection deterrent means for stopping the detection of another vehicle.
前記自動車の周辺を撮影するカメラと、
前記カメラが撮影した画像中の他車の外観に円形に表れる部分の像を認識する画像認識手段と、
前記画像認識手段の認識結果に基づいて他車を検出する他車検出手段と、
前記画像認識手段が認識した前記部分の像の前記画像中の配置に基づいて、他車の相対位置を算定する算定手段と、
前記算定手段が算定した他車の相対位置が示す、過去所定期間における、前記自動車と当該他車との間の前記自動車の左右方向の距離の分散または標準偏差である不審度が所定のしきい値より大きくなったときに、前記他車検出手段の他車の検出を停止させる他車検出抑止手段とを有することを特徴とする他車監視システム。 It is a vehicle monitoring system installed in a vehicle that monitors other vehicles around the vehicle.
A camera that shoots the area around the car,
An image recognition means for recognizing an image of a part appearing in a circle on the appearance of another vehicle in the image taken by the camera, and an image recognition means.
Another vehicle detection means that detects another vehicle based on the recognition result of the image recognition means, and
A calculation means for calculating the relative position of another vehicle based on the arrangement of the image of the portion recognized by the image recognition means in the image, and
The degree of suspicion, which is the variance or standard deviation of the lateral distance of the vehicle between the vehicle and the other vehicle in the past predetermined period indicated by the relative position of the other vehicle calculated by the calculation means, is a predetermined threshold. The other vehicle monitoring system comprising the other vehicle detection suppressing means for stopping the detection of the other vehicle by the other vehicle detection means when the value becomes larger than the value.
前記自動車の周辺を撮影するカメラと、
前記カメラが撮影した画像中の他車の外観に円形に表れる部分の像を認識する画像認識手段と、
前記画像認識手段の認識結果に基づいて他車を検出する他車検出手段と、
前記画像認識手段が認識した前記部分の像の前記画像中の配置に基づいて、前記部分の相対位置を算定する算定手段と、
前記算定手段が算定した前記部分の相対位置が示す、過去所定期間における、前記自動車と当該部分との間の前記自動車の左右方向の距離の分散または標準偏差である不審度が所定のしきい値より大きくなったときに、前記他車検出手段の他車の検出を停止させる他車検出抑止手段とを有することを特徴とする他車監視システム。 It is a vehicle monitoring system installed in a vehicle that monitors other vehicles around the vehicle.
A camera that shoots the area around the car,
An image recognition means for recognizing an image of a part appearing in a circle on the appearance of another vehicle in the image taken by the camera, and an image recognition means.
Another vehicle detection means that detects another vehicle based on the recognition result of the image recognition means, and
A calculation means for calculating the relative position of the portion based on the arrangement of the image of the portion recognized by the image recognition means in the image.
A predetermined threshold value is the degree of suspicion, which is the variance or standard deviation of the lateral distance of the automobile between the automobile and the portion in the past predetermined period indicated by the relative position of the portion calculated by the calculation means. The other vehicle monitoring system, which comprises the other vehicle detection suppressing means for stopping the detection of the other vehicle by the other vehicle detection means when the size becomes larger.
前記他車検出抑止手段は、前記他車検出手段の他車の検出を停止させた後、前記不審度が所定のレベルより小さくなったならば、前記他車検出手段の他車の検出を再開させることを特徴とする他車監視システム。 The other vehicle monitoring system according to claim 3 or 4.
After stopping the detection of the other vehicle by the other vehicle detection means, the other vehicle detection deterrent means restarts the detection of the other vehicle by the other vehicle detection means when the suspicious degree becomes smaller than a predetermined level. Another vehicle monitoring system characterized by letting you do it.
前記部分は、タイヤであることを特徴とする他車監視システム。 The other vehicle monitoring system according to claim 1, 2, 3, 4 or 5.
The other vehicle monitoring system is characterized in that the portion is a tire.
前記他車検出手段が検出した他車の存在をユーザに対して提示する他車提示手段を有することを特徴とする他車監視システム。 The other vehicle monitoring system according to claim 1, 2, 3, 4, 5 or 6.
The other vehicle monitoring system comprising the other vehicle presenting means for presenting the existence of the other vehicle detected by the other vehicle detecting means to the user.
前記他車検出抑止手段は、前記他車検出手段の他車の検出を停止させる際に、当該停止の旨をユーザに対して警告することを特徴とする他車監視システム。 The other vehicle monitoring system according to claim 1, 2, 3, 4, 5, 6 or 7.
The other vehicle detection deterrent means is a other vehicle monitoring system characterized in that when the detection of another vehicle by the other vehicle detection means is stopped, the user is warned of the stop.
前記カメラの撮像光学系に付着した水滴を除去する清掃機構と、
前記他車検出抑止手段が前記他車検出手段の他車の検出を停止させたときに、前記清掃機構に前記水滴の除去を行わせる水滴除去制御手段とを有することを特徴とする他車監視システム。 The other vehicle monitoring system according to claim 1, 2, 3, 4, 5, 6, 7 or 8.
A cleaning mechanism that removes water droplets adhering to the imaging optical system of the camera,
Another vehicle monitoring characterized in that the other vehicle detection deterrent means has a water droplet removal control means for causing the cleaning mechanism to remove the water droplets when the detection of the other vehicle by the other vehicle detection means is stopped. system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2017112913A JP6841725B2 (en) | 2017-06-07 | 2017-06-07 | Other vehicle monitoring system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2017112913A JP6841725B2 (en) | 2017-06-07 | 2017-06-07 | Other vehicle monitoring system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| JP2018206214A JP2018206214A (en) | 2018-12-27 |
| JP6841725B2 true JP6841725B2 (en) | 2021-03-10 |
Family
ID=64958012
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP2017112913A Active JP6841725B2 (en) | 2017-06-07 | 2017-06-07 | Other vehicle monitoring system |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JP6841725B2 (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2020261703A1 (en) * | 2019-06-25 | 2020-12-30 | ソニー株式会社 | Information processing device, information processing method, and program |
| JP7268616B2 (en) * | 2020-01-30 | 2023-05-08 | いすゞ自動車株式会社 | Notification device |
| JP2021120773A (en) * | 2020-01-30 | 2021-08-19 | いすゞ自動車株式会社 | Notification device |
| JP2025015059A (en) * | 2023-07-20 | 2025-01-30 | 日立Astemo株式会社 | Object recognition device and object recognition method |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008134877A (en) * | 2006-11-29 | 2008-06-12 | Alpine Electronics Inc | Perimeter monitoring device |
| JP6003986B2 (en) * | 2012-07-27 | 2016-10-05 | 日産自動車株式会社 | Three-dimensional object detection device, three-dimensional object detection method, and foreign object detection device |
| JP6337601B2 (en) * | 2014-05-08 | 2018-06-06 | 日産自動車株式会社 | Three-dimensional object detection device |
| JP2016192177A (en) * | 2015-03-31 | 2016-11-10 | 株式会社デンソーアイティーラボラトリ | Vehicle detection system, vehicle detection device, vehicle detection method and vehicle detection program |
-
2017
- 2017-06-07 JP JP2017112913A patent/JP6841725B2/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| JP2018206214A (en) | 2018-12-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6174975B2 (en) | Ambient environment recognition device | |
| JP6120395B2 (en) | In-vehicle device | |
| JP6841725B2 (en) | Other vehicle monitoring system | |
| US9956941B2 (en) | On-board device controlling accumulation removing units | |
| JP5887219B2 (en) | Lane departure warning device | |
| US10824883B2 (en) | Method and apparatus for determining a road condition | |
| KR101774692B1 (en) | Apparatus and method for controlling airbag | |
| CN107018314A (en) | Camera system | |
| JP5759950B2 (en) | In-vehicle camera device | |
| WO2018092265A1 (en) | Driving assistance device and driving assistance method | |
| JP6081034B2 (en) | In-vehicle camera control device | |
| WO2016017340A1 (en) | Surrounding environment recognition device | |
| JP7557587B2 (en) | Determination device and determination method | |
| CN114537333A (en) | Vehicle control device | |
| JP5543938B2 (en) | Outside monitoring device | |
| JP5749405B2 (en) | Method and camera assembly for detecting raindrops on a vehicle windshield | |
| JP2008009843A (en) | Obstacle discrimination device | |
| EP2227406B1 (en) | A vehicle safety system | |
| JP2014146267A (en) | Pedestrian detection device and driving support device | |
| JP2021131869A (en) | Road surface state estimation device | |
| JP2018148345A (en) | On-vehicle camera system, adhered matter detecting apparatus, adhered matter removing method, and adhered matter detecting program | |
| JP4397719B2 (en) | Gaze detection device | |
| CN115428055A (en) | driving aids | |
| JP4601376B2 (en) | Image abnormality determination device | |
| JP4798576B2 (en) | Attachment detection device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| A621 | Written request for application examination |
Free format text: JAPANESE INTERMEDIATE CODE: A621 Effective date: 20200306 |
|
| 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: 20210209 |
|
| A61 | First payment of annual fees (during grant procedure) |
Free format text: JAPANESE INTERMEDIATE CODE: A61 Effective date: 20210218 |
|
| R150 | Certificate of patent or registration of utility model |
Ref document number: 6841725 Country of ref document: JP Free format text: JAPANESE INTERMEDIATE CODE: R150 |