JP5012607B2 - Vehicle travel support device, vehicle, vehicle travel support program - Google Patents

Description

  The present invention relates to an apparatus and the like that supports the traveling of a vehicle based on an image obtained through an imaging device mounted on the vehicle.

A technique for recognizing a lane mark provided along a road on which the vehicle travels has been proposed based on an image captured by a camera mounted on the vehicle (Patent Document 1 and Patent Document 1). 2).
JP 2001-023094 A JP 2002-362396 A

  However, if the image captured by the camera contains not only the true lane mark but also disturbances that may be misrecognized as a lane mark, such as the body part of another vehicle running ahead or side by side, the true lane mark Recognition accuracy may be reduced.

  Therefore, an object of the present invention is to provide an apparatus and the like that can recognize with high accuracy whether or not the recognition accuracy of lane marks has been lowered due to disturbance.

The vehicle travel support device according to the present invention is a vehicle travel support device that recognizes a lane mark on a road on which the vehicle is traveling based on an image representing a situation in a traveling direction of the vehicle obtained through an imaging device mounted on the vehicle. A first processing element for recognizing a lane mark candidate in a second region defined farther from the vehicle than the first region in the traveling direction of the vehicle based on the image; and the first processing Based on the recognition result by the element, the recognition accuracy of the lane mark is evaluated low as a requirement that the second condition that the density of the lane mark candidates in the second region is equal to or lower than the second appropriate value is not satisfied. and a second processing element, wherein the first processing element, based on the image, the lane mark candidates in the first region in addition to the second region The first condition that the density of the lane marks in the first region is not less than a first appropriate value based on the recognition result of the first processing element is not satisfied. As a requirement, the recognition accuracy of the lane mark is evaluated low .

The density of the lane mark candidates recognized in the second region, which should be relatively difficult to recognize the lane mark based on the image (more accurately, the presence / absence of the lane mark and the arrangement thereof) because it is relatively far from the vehicle In this case, there is a high probability that disturbance is affecting the recognition result. Further, when the density of lane mark candidates recognized in the first region, which should be relatively easy to recognize the lane mark based on the image because it is relatively close to the vehicle, the disturbance affects the recognition result. The probability is high. In view of these points, according to the vehicle travel support device of the present invention, the “second condition” that the density of the lane mark candidates recognized in the second region is not more than the second appropriate value is not satisfied. As a requirement, the recognition accuracy of lane marks is evaluated low. In addition, the recognition accuracy of the lane mark is evaluated low as a requirement that the “first condition” that the density of the lane mark candidates recognized in the first region is equal to or higher than the first appropriate value is not satisfied. Therefore, it can be recognized with high accuracy whether or not the recognition accuracy of the lane mark is deteriorated due to disturbance.

  Note that the component of the present invention “recognizes” information means that the component retrieves information from a database, reads information from a storage device such as a memory, and measures information based on an output signal from a sensor or the like. It means performing any information processing necessary to prepare or prepare the information for further information processing, such as calculating, estimating, determining, storing the measured information in a memory, and the like.

In the vehicle travel support device of the present invention , the first processing element recognizes the lane mark candidate on each of the left and right sides of the vehicle, and the second processing element recognizes the lane mark on each of the left and right sides of the vehicle. It is preferable to evaluate the recognition accuracy.

According to the vehicle travel support device of the configuration , although there are disturbances on both the left and right sides of the vehicle, the left lane mark candidates are excessive, while the right lane mark candidates are insufficient. As a result of canceling out these disturbances, a situation in which the recognition accuracy of the lane mark is highly evaluated can be avoided. Therefore, it can be recognized with high accuracy whether or not the recognition accuracy of the lane mark is deteriorated due to disturbance.

In the vehicle travel support device of the present invention, the second processing element, the requirement that the period in which the second condition is not satisfied exceeds the allowable duration, it is preferable to underestimate the recognition accuracy of the lane mark .

According to the vehicle travel support device having the above configuration , the recognition accuracy of the lane mark is evaluated to be low on the condition that a high probability that a disturbance exists, such as the second condition is not satisfied, has continued for a long period of time. . Therefore, the presence or absence of disturbance is recognized with high accuracy according to the level of recognition accuracy of the lane mark.

  DESCRIPTION OF EMBODIMENTS Embodiments of a vehicle travel support device and the like of the present invention will be described with reference to the drawings.

  A vehicle (four-wheeled vehicle) 1 shown in FIGS. 1 and 2 is equipped with a camera (imaging device) 12 such as a CCD camera or a near infrared camera, and a vehicle travel support device 10. The camera 12 is attached to the interior space so as to capture an image of the front of the vehicle 1 through the front window. Note that the location of the camera 12 may be changed as appropriate to the front portion of the vehicle 1 or the like. As shown in FIG. 2, the vehicle 1 further includes sensors such as a vehicle speed sensor 122, an acceleration sensor 124 and a yaw rate sensor 126, a steering device 14, and a braking device 16. Each of the vehicle speed sensor 122, the acceleration sensor 124, and the yaw rate sensor 126 outputs signals corresponding to the speed, acceleration, and yaw rate of the vehicle 1, respectively.

  The vehicle travel support device 10 is configured by a computer or an ECU (electronic control unit) (comprising a CPU, ROM, RAM, and electronic circuits such as an I / O circuit and an A / D conversion circuit). Output signals from the camera 12 and the speed sensor 122 are input to the vehicle travel support device 10. The “vehicle driving support program” is read from the memory by the CPU, and various processes described later are executed according to the read program. The program may be distributed or broadcast from the server to the vehicle 1 via a network or satellite at an arbitrary timing, and stored in a storage device such as a RAM of the in-vehicle computer. The vehicle travel support device 10 controls the operation of one or both of the steering device 14 and the braking device 16 to execute travel support control for assisting the travel of the vehicle 1 so that the vehicle 1 does not depart from the travel region. The vehicle travel support device 10 includes a first processing element 110 and a second processing element 120. The first processing element 110 recognizes lane mark candidates based on the image obtained through the camera 12. The second processing element 12 evaluates the recognition accuracy of the lane mark by the first processing element 11.

  Functions of the vehicle 1 and the vehicle travel support device 10 having the above-described configuration will be described.

  First, an image representing the situation in front of the vehicle 1 or in the traveling direction is acquired through the camera 12 (FIG. 3 / S002). Thereby, for example, an image of a road extending in front of the vehicle 1 as shown in FIG. 4A or 5A is acquired.

The first processing element 110 recognizes lane mark candidates in each of the first area A ₁ and the second area A ₂ defined in the vehicle coordinate system based on the acquired image (S004 in FIG. 3). Thereby, as shown in FIG. 4B or FIG. 5B, lane mark candidates (black dots) are recognized in each of the first area A ₁ and the second area A ₂ . The lane mark candidates are recognized separately on the left side and the right side of the vehicle 1. The lane mark candidates may be recognized without being divided into the left side and the right side of the vehicle 1. Lane mark candidates such as botsdots and lanes (white lines) can be recognized according to image processing methods disclosed in Japanese Patent Application Laid-Open Nos. 2006-269605, 2006-309499, and 2006-331193. . In the vehicle coordinate system, as shown in FIG. 4B, representative points such as the center point of the vehicle 1, the forward direction and the left direction are defined as the origin O, the + x direction, and the + y direction, respectively. . Rectangular area in the front of the vehicle 1 in the vehicle coordinate system is defined as the first region A _1, the rectangular region second region A ₂ in the distance from the vehicle 1 than the first region A ₁ on the traveling direction of the vehicle 1 Is defined. Coordinate conversion from the image coordinate system to the vehicle coordinate system can be performed according to a known method based on the height, angle, and the like of the camera 12. In order to omit such coordinate conversion, the first image region C ₁ and the second image region 2 shown in FIG. 4A corresponding to the first region A ₁ and the second region A ₂ in the image, respectively. lane mark candidate may be recognized in each image area C _2.

Further, the second processing element 120 determines whether or not the first condition is satisfied based on the recognition result of the first processing element 110 (FIG. 3 / S006). The “first condition” is a condition that the density of lane mark candidates in the first area A ₁ is equal to or higher than the first appropriate value. As the density of the lane mark candidates, the number of lane mark candidates per unit length in the x direction or the number of pixels constituting the lane mark candidates per unit length in the vertical direction of the image is calculated. For example, when the width in the x direction of the first area A ₁ shown in each of FIGS. 4B and 5B is defined as the unit length, the left side of the vehicle 1 in the first area A ₁ The density of each lane mark candidate on the right side is evaluated as “2”. Further, when the first appropriate value is set to “2” in this state, it is determined that the first condition is satisfied because the density is equal to or higher than the first appropriate value. When it is determined that the first condition is satisfied (FIG. 3 / S006... YES), the recognition accuracy of the lane mark by the vehicle travel support device 10 is highly evaluated (FIG. 3 / S010).

On the other hand, when it is determined that the first condition is not satisfied (FIG. 3 / S006... NO), it is further determined whether or not the second condition is satisfied (FIG. 3 / S008). The “second condition” is a condition that the density of the second lane mark candidates in the second area A ₂ is equal to or lower than the second appropriate value. As described above, as the density of lane mark candidates, the number of lane mark candidates per unit length in the x direction or the number of pixels constituting the lane mark candidates per unit length in the vertical direction of the image is calculated. For example, when the width in the x direction of the second area A ₂ shown in FIG. 4B is defined as the unit length, the left and right lane mark candidates of the vehicle 1 in the second area A ₂ The density of is evaluated as “2”. In this state, when the second appropriate value is set to “2”, it is determined that the second condition is satisfied because the density is equal to or less than the second appropriate value. Further, although the density of the right lane mark candidate of the vehicle 1 in the second area A ₂ shown in FIG. 5B is evaluated as “2”, the density of the left lane mark candidate is “4”. Be evaluated. This is because, for example, in the image region corresponding to the region relatively far from the vehicle 1, as a result of the fact that a part of the other vehicle running side by side or in front of the vehicle 1 appears to form substantially the same lane as the true lane mark This is because some of the other vehicles running on the left side of 1 are recognized as lane mark candidates. In this state, when the second appropriate value is set to “2”, since the density exceeds the second appropriate value on the left side of the vehicle 1, it is determined that the second condition is not satisfied. When it is determined that the second condition is satisfied (FIG. 3 / S008... YES), the recognition accuracy of the lane mark by the vehicle travel support device 10 is highly evaluated (FIG. 3 / S010). On the other hand, when it is determined that the second condition is not satisfied (FIG. 3 / S008... NO), the recognition accuracy is evaluated low (FIG. 3 / S012).

  Further, the vehicle travel support device 10 determines the level of lane mark recognition accuracy on both the left and right sides of the vehicle 1 (FIG. 3 / S014). When it is determined that the recognition accuracy of the lane mark is high on both the left and right sides (FIG. 3 / S014... YES), the left and right lane mark candidates are accepted as true lane marks, and the left and right are defined by the lane marks. Is set (FIG. 3 / S016). Then, by controlling the operation of one or both of the steering device 14 and the braking device 16, travel support control for assisting the travel of the vehicle 1 so that the vehicle 1 does not depart from the travel region is executed ( FIG. 3 / S018). On the other hand, when it is determined that the recognition accuracy of the lane mark is low in either one or both of the left and right (NO in FIG. 3 / S014), the setting of the travel area and the travel support control are omitted.

According to the vehicle travel support device 10 that exhibits the above function, it is required that the “first condition” that the density of the lane mark candidates recognized in the first area A ₁ is equal to or higher than the first appropriate value is not satisfied. As a result, the recognition accuracy of the lane mark is evaluated to be low (FIG. 3 / S006... NO, S012). This is relatively close to the vehicle 1, and therefore the density of the lane mark candidates recognized in the first area A ₁ that should be relatively easy to recognize the lane mark based on the image is low enough to be lower than the first aptitude value. This is because there is a high probability that disturbance is affecting the recognition result.

In addition, the recognition accuracy of the lane mark is evaluated to be low on the condition that the “second condition” that the density of the lane mark candidates recognized in the second area A ₂ is not more than the second appropriate value is not satisfied. (See FIG. 3 / S008... NO, S012). This is relatively high from the vehicle 1, and the density of the lane mark candidates recognized in the second region A ₂ , which should be relatively difficult to recognize the lane mark based on the image, is high enough to exceed the second suitability value. This is because there is a high probability that the recognition result is affected by a disturbance such as a parallel running vehicle (shaded portion) shown in FIG.

  Furthermore, the recognition accuracy of the lane mark is evaluated on each of the left side and the right side of the vehicle 1. As a result, even though there are disturbances on both the left and right sides of the vehicle 1, the left lane mark candidates are excessive, while the right lane mark candidates are insufficient. As a result, a situation in which the recognition accuracy of the lane mark by the vehicle travel support device 10 is highly evaluated can be avoided.

  Therefore, the presence or absence of a drop due to disturbance in the recognition accuracy of the lane mark by the vehicle travel support device 10 can be recognized with high accuracy.

  In addition, the recognition accuracy of the lane mark by the vehicle travel support apparatus 10 is low on the condition that the number of times or the period determined that the second condition is not satisfied by the second processing element 120 exceeds the allowable number or the allowable period. You may evaluate (refer FIG. 3 /S008...NO, S012). As a result, the recognition accuracy of the lane mark is evaluated low as a requirement that a state in which there is a high probability that a disturbance exists, such as the second condition is not satisfied, has continued for a long period of time. Therefore, it can be recognized with high accuracy whether or not the recognition accuracy of the lane mark is deteriorated due to disturbance.

Configuration diagram of the vehicle of the present invention Configuration explanatory diagram of the vehicle travel support device of the present invention The flowchart which shows the function of the vehicle travel assistance device of this invention Explanation of lane mark candidate recognition method part 1 Illustration 2 for recognizing lane mark candidates

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 ... Vehicle, 10 ... Vehicle travel support apparatus, 12 ... Camera (imaging device), 110 ... 1st processing element, 120 ... 2nd processing element

Claims (3)

A vehicle travel support device for recognizing a lane mark on a road on which the vehicle is traveling based on an image representing a situation in a traveling direction of the vehicle obtained through an imaging device mounted on the vehicle,
A first processing element for recognizing lane mark candidates in a second area defined farther from the vehicle than the first area in the traveling direction of the vehicle based on the image;
Based on the recognition result by the first processing element, the second condition that the density of the lane mark candidates in the second region is not more than a second appropriate value is not satisfied, and the recognition accuracy of the lane mark is not satisfied. the a second processing element which dislike,
The first processing element recognizes the lane mark candidate in the first area in addition to the second area based on the image;
Based on the recognition result of the first processing element, the second processing element is based on the recognition result of the first condition that the density of the lane marks in the first region is not less than a first appropriate value. A vehicle driving support apparatus characterized by evaluating low recognition accuracy of the lane mark . The vehicle travel support device according to claim 1 ,
The first processing element recognizes the lane mark candidate on each of the left and right sides of the vehicle;
The vehicle travel support apparatus, wherein the second processing element evaluates the recognition accuracy of the lane mark on each of the left side and the right side of the vehicle. The vehicle travel support device according to claim 1 or 2 ,
The vehicle travel support device according to claim 2, wherein the second processing element evaluates the recognition accuracy of the lane mark low on the condition that a period in which the second condition is not satisfied exceeds an allowable period.

Images