JP3525733B2 - Road white line detector - Google Patents

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a device for detecting a white line on a road to recognize the shape of the road.

[0002]

2. Description of the Related Art There is known a device for detecting a white line (lane marker) indicating a traveling section on a road in order to recognize the shape of the road (see, for example, Japanese Patent Laid-Open No. 8-5388). According to this device, the shape of the road white line on the captured image is represented by a mathematical expression model, and the parameters of the mathematical expression model are updated so that the detection result of the road white line and the white line model match so that the shape of the road is changed. It has recognized.

[0003]

However, in the above-described conventional road white line detection device, the white line of the traveling lane must be detected at the junction with the main line such as an interchange on a highway as shown in FIG. However, the white line of the branch lane may be detected, and an accurate road shape may not be recognized.

An object of the present invention is to accurately detect the white line of the driving lane.

[0005]

According to a first aspect of the present invention, white line detection is performed by setting an image pickup means for picking up an image of a vehicle surroundings and an area for detecting a white line of a road on the picked-up image. A parameter for updating the multiple parameters so that the white line shape is represented by a mathematical model using the white line detection means and multiple parameters indicating the road shape and vehicle behavior, and the white line model and the white line detection result match. Updating means, area changing means for changing the white line detection area according to the white line detection result, vehicle behavior detecting means for detecting the behavior of the vehicle, and a parameter representing the road shape based on the vehicle behavior detected value, the current running A parameter determining means for determining whether or not the shape of the road matches, and the parameter representing the shape of the road matches the shape of the current road by the parameter updating means. If it is determined that there is no, to achieve the above object by the return parameters representing the road shape in the predetermined initial value. (2) The road white line detection device according to claim 2 includes an image pickup means for picking up an image of the surroundings of the vehicle, and a white line detection means for setting a region for detecting a white line of the road on the picked-up image and performing white line detection. A parameter updating means for expressing the shape of a road white line by a mathematical model using a plurality of parameters indicating the road shape and vehicle behavior, and updating a plurality of parameters so that the white line model and the white line detection result match, and a white line detection Area changing means for changing the white line detection area according to the result, vehicle behavior detecting means for detecting the behavior of the vehicle, and a parameter representing the vehicle behavior based on the vehicle behavior detection value matches the shape of the current traveling road. And a parameter determining means for determining whether or not the parameter indicating the vehicle behavior does not match the current shape of the road. Case, to achieve the above object by the return parameters representing the vehicle behavior to a predetermined initial value. (3) The road white line detection device according to claim 3 is adapted to restore the white line detection area to a predetermined initial value when the white line detection means does not detect a predetermined amount of white lines in the white line detection area. Is. (4) In the road white line detection device according to claim 4, the white line detection means changes the white line detection area to an area smaller than an initial value when a predetermined amount of white lines is detected in the white line detection area. It was done.

[0006]

According to the inventions of claims 1 to 4, it is possible to prevent erroneous detection of a line other than a road white line as a white line,
It is possible to accurately detect the white line of the driving lane, and even if the white line of the branch road is erroneously detected as the white line of the driving lane, it is possible to prevent the erroneous detection result from being reflected in the white lane model. The white line of can be accurately detected.

[0007]

DESCRIPTION OF THE PREFERRED EMBODIMENTS FIG. 1 is a diagram showing a configuration of an embodiment. As shown in FIG. 2, the camera 1 is mounted at the center of the vehicle width direction and above the front window in the vehicle compartment such that the yaw angle between the optical axis of the lens and the vehicle center line is 0 and the pitch angle is α. Image the road in front of the vehicle. The image processing device 2 processes the image captured by the camera 1 to detect a white line on the road. The microcomputer 3
The road white line is detected by updating the parameters so that the road white line detection result matches the white line model by expressing the road white line shape in a mathematical model using multiple parameters that indicate the road shape and vehicle behavior. Recognize the road shape. The memory 4 is a storage device that stores parameters of the white line model, and the sensor 5 is a detection device that detects a vehicle speed, a pitch angle, a yaw angle, and the like, which represent the behavior of the vehicle. The display 7 is a display device for displaying the road shape and the like as the detection result.

3 and 4 show a microcomputer 4
It is a flow chart which shows road white line detection processing of. The operation of the embodiment will be described with reference to this flowchart. In step 1, parameters indicating road shape and vehicle behavior (hereinafter simply referred to as road parameters) are initialized. On the screen coordinate system xy as shown in FIG. 5, the white line model is expressed by the following equation using road parameters.

[Equation 1] x = (a + ie) (y-d) + b / (y-d) + c

In Equation 1, a to e are road parameters, and assuming that the height of the camera from the road surface is constant, each road parameter represents the following shapes of roads and white lines or vehicle behavior. . That is, a is the lateral displacement of the host vehicle in the lane, b is the curvature of the road, c is the yaw angle of the host vehicle (optical axis of the camera) to the road, and d is the host vehicle (optical axis of the camera). The pitch angle for the road and e for the lane width of the road.

Further, since the shapes of roads and white lines and vehicle behavior are unknown in the initial state, a value corresponding to the median value is set as an initial value for each road parameter. That is, the lane center is set at the position a in the lane, and the road curvature b
Is set to a straight line, and the yaw angle c with respect to the lane is set to 0 degree. Further, the pitch angle d with respect to the lane is set to α degrees in the stopped state, and the lane width e is set to the lane width of the expressway indicated by the Road Structure Ordinance.

The road parameters may be initialized based on the value indicating the behavior of the vehicle detected by the sensor 5. For example, when the steering wheel is steered to the right or left in the initial state, it is determined that the vehicle is traveling on a road having a curvature corresponding to the steering angle, and the parameter b is set to a value corresponding to the steering angle. Good. Similarly, when pitching occurs in the initial state, the initial value of the parameter d may be shifted by the pitch angle detection value.

In step 2, as shown in FIG.
Initialize a small area for detecting white line candidate points.
In the initial state, it is expected that there will be a large difference between the white line model in which the initial values are set for the road parameters and the actual road white line on the screen, so it is desirable to set the area as large as possible. In the example shown in FIG. 6, ten white line candidate point detection areas are set, five for each of the left and right white lines. If the road white line has already been detected by the previous process, it is considered that the difference between the actual road white line and the white line model is small, so it is better to set a region as small as possible as shown in FIG. , The possibility of erroneously detecting anything other than the white line is low, and the processing speed can be improved. In step 3, the image captured by the camera 1 and processed by the image processing device 2 is input.

In step 4, a white line candidate point detection area is set on the input road image. At this time, it is shown in FIG. 8 based on the white line candidate point detection area set in step 2 or step 17 described later and the white line model based on the road parameters calculated in step 1 or step 12, step 14, or step 15 described later. As described above, the white line candidate point detection area is set so that the white line model obtained in the previous process is located at the center of the area. In the example shown in FIG. 8, ten white line candidate point detection areas are set, five for each of the left and right white lines. It should be noted that the white line candidate point detection area may be set at a position offset in the changing direction of the white line model from the past change state of the white line model.

In step 5, white line candidate points are detected in the white line candidate point detection area. The white line candidate points are detected by first generating a differential image of the input image through a sobel filter or the like. Next, as shown in FIG. 9, for all line segments formed by connecting one point on the upper bottom and one point on the lower line of the white line candidate point detection area, the density of the pixels on the line segment is not less than a predetermined value. Measure the number of pixels. Further, among all the line segments, the line segment having the largest number of pixels having the density equal to or higher than the predetermined value is set as the detection straight line, and the start point and the end point of the line segment are set as the white line candidate points. At this time, if the number of detected pixels having a density equal to or higher than a predetermined value on the straight line is smaller than a predetermined ratio to the length of the detection area, it is considered that the white line candidate point has not been detected.
For example, in the detection area in which the length of the detection area is 15 pixels, and the number of pixels having a density equal to or higher than a predetermined value is 1/2 or more, that is, the white line candidate point is detected when 8 or more pixels are detected,
When the number of pixels on the line segment having the largest number of pixels having the density equal to or higher than the predetermined value is less than 7, it is assumed that no white line candidate point is detected in the detection area. On the other hand, in the case of 9 pixels, it is assumed that the white line candidate point is detected, and the start point and the end point of the line segment are the detection results. The above processing is executed for all white line candidate point detection areas. At this time, the above-mentioned predetermined ratio to the length of the detection area for determining whether or not the white line candidate point is detected may be the same for all areas or may be set for each detection area. Further, the predetermined value of the density may be the same for all detection areas, or may be different for each detection area.

In step 6, it is confirmed whether the number of white line candidate points detected in all the white line candidate point detection areas is equal to or more than a predetermined value. If the number is less than the predetermined value, the road white line is included in the white line candidate point detection area. If not, step 2
Then, as described above, the white line candidate point detection area is initialized. On the other hand, when the white line candidate points are detected by the predetermined value or more, the process proceeds to step 7 and, as shown in FIG. 10, the deviation amount between the detected white line candidate points and the point on the white line model obtained in the previous process is calculated. Calculate for each point. In the following step 8, the road parameter fluctuation amounts Δa to Δe are calculated based on the deviation amounts of the respective points.
To calculate. A method of calculating this variation is disclosed in, for example, Japanese Patent Laid-Open No. Hei 8
It is possible to use a method as disclosed in Japanese Patent No. 5388. In step 9, the road parameters a to e are corrected by the calculated road parameter fluctuation amounts Δa to Δe. For example, in the case of the white line model shown in Formula 1, the road parameters a to e are corrected by the following formula.

[Formula 2] a = a + Δa, b = b + Δb, c = c + Δc, d = d + Δd, e = e + Δe

In step 10, it is confirmed whether the parameter representing the road shape is normal among the road parameters, and if it is not normal, the process proceeds to step 15 to initialize the parameter representing the road shape. In the case of the white line model shown in Expression 1, the parameter b reflects the road curvature and the parameter e reflects the lane width. Therefore,
The road curvature estimated from the parameter b is the sensor 5
If the curvature that cannot be obtained on the road currently running is judged from the vehicle behavior detection value according to the parameter b, the parameter b is initialized. Similarly, when the lane width estimated from the parameter e becomes a lane width which cannot be determined on the road currently running, as judged from the vehicle behavior detection value by the sensor 5, the parameter e is initialized.

If the parameter representing the road shape is normal, it is confirmed in step 11 whether the parameter representing the vehicle behavior is normal. If not, the process proceeds to step 16 to initialize the parameter representing the vehicle behavior. In the case of the white line model shown in Expression 1, the parameter a reflects the lateral displacement in the lane, the parameter c reflects the yaw angle with respect to the road surface, and the parameter d reflects the pitch angle with respect to the road surface. Therefore, when the lateral displacement estimated from the parameter a is judged from the estimated value of the road curvature or the vehicle behavior detection value by the sensor 5 and becomes the lateral displacement which is not possible on the currently traveling road, a
To initialize. Similarly, when the yaw angle estimated by the parameter c becomes an angle which cannot be the road currently running judging from the estimated value of the road curvature or the vehicle behavior detection value by the sensor 5, the parameter c To initialize. Further, when the pitch angle estimated from the parameter d becomes an angle which cannot be determined from the vehicle behavior detection value detected by the sensor 5 on the road currently running, the parameter d is initialized.

When the parameter indicating the vehicle behavior is normal, in step 12, the road parameters a to e corrected in step 9 are stored in the memory 5 as road parameters of the new white line model. In the following step 13, the road shape is estimated by the new road parameters,
Output to the display 7 or the like. In step 14, it is confirmed whether the white line candidate point detection area in this processing is the initial value set in step 2 or the one set in step 17, and if it is the initial value, the white line candidate point detection area is detected. Assuming that the size of the area is not optimal, the process proceeds to step 17. In step 17, it is less likely to erroneously detect anything other than the white line by setting the smallest possible area as described above, and the processing speed can be improved.
As shown in FIG. 7, the white line candidate point detection area is optimized. When the above process is completed, the process returns to step 3 and the above process is repeated.

In the configuration of the above embodiment, the camera 1 serves as an image pickup means, the microcomputer 3 serves as a white line detecting means, a parameter updating means, an area changing means and a parameter determining means, and the sensor 5 serves as a vehicle behavior detecting means. Constitute.

[Brief description of drawings]

FIG. 1 is a diagram showing a configuration of an embodiment.

FIG. 2 is a diagram showing a mounting position of a camera.

FIG. 3 is a flowchart showing road white line detection processing.

FIG. 4 is a flowchart showing a road white line detection process subsequent to FIG. 3;

FIG. 5 is a diagram illustrating a white line model.

FIG. 6 is a diagram for explaining a method of setting an initial value of a white line candidate point detection area.

FIG. 7 is a diagram for explaining a method of setting an initial value of a white line candidate point detection area when a road white line has already been detected.

FIG. 8 is a diagram for explaining a method of setting a white line candidate point detection area on a captured road image.

FIG. 9 is a diagram for explaining a method of detecting white line candidate points.

FIG. 10 is a diagram showing a deviation amount between a currently detected white line candidate point and a previously obtained point on the white line model.

FIG. 11 is a diagram for explaining erroneous detection of a white line by a conventional device.

[Explanation of symbols]

1 camera 2 Image processing device 3 microcomputer 4 memory 5 sensors 6 display

─────────────────────────────────────────────────── ─── Continuation of the front page (58) Fields surveyed (Int.Cl. ⁷ , DB name) G06T 1/00 330 G01C 21/00 G08G 1/16

Claims (4)

(57) [Claims] 1. An image pickup means for picking up an image of a vehicle surroundings, a white line detection means for setting a region for detecting a white line of a road on the picked-up image to detect a white line, and a road shape and a vehicle behavior. Representing the shape of the road white line with a mathematical expression model using a plurality of parameters, parameter updating means for updating the plurality of parameters so that the white line model and the white line detection result match, depending on the white line detection result. an area changing means for changing the white line detection area, and the vehicle behavior detection means for detecting a behavior of the vehicle, based on the vehicle behavior detection value, path representing the road shape
Whether the parameters match the shape of the current road
And a parameter determining means, wherein the parameter updating means is a parameter representing the road shape.
It is determined that the meter does not match the shape of the current road.
If it is found, the parameter representing the road shape is specified.
Road white line detection device characterized by returning to the initial value of . 2. An image pickup means for picking up an image of a vehicle surroundings, and an area for detecting a white line of a road on the picked-up image.
By using the white line detection means that performs fixed white line detection and multiple parameters that indicate road shape and vehicle behavior
Express the shape of the road white line with a mathematical model,
So that the white line detection result and the white line detection result match.
Parameter updating means for updating the meter and changing the white line detection area according to the white line detection result
Region changing means, vehicle behavior detecting means for detecting vehicle behavior, and a pattern representing the vehicle behavior based on the vehicle behavior detection value.
Whether the parameters match the shape of the current road
And a parameter determining means for determining, wherein the parameter updating means is a parameter representing the vehicle behavior.
It is determined that the meter does not match the shape of the current road.
If the vehicle is hit, the parameters that represent the vehicle behavior are specified.
Road white line detection device characterized by returning to the initial value of . 3. A road white line detecting apparatus according to claim 1 or 2, wherein the white line detection means, a predetermined amount of white in the white line detection area
If no line is detected, the white line detection area is
A road white line detection device characterized by returning to a constant initial value . 4. The road white line detection device according to claim 3 , wherein the white line detection means is a predetermined amount of white line in the white line detection area.
When a line is detected, the white line detection area is set to the initial
Road white line detection device characterized by changing to an area smaller than the value .