JP2003044836A - Device for recognizing partition line - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a lane partition line recognizing device capable of estimating one white line with high accuracy on the basis of another white line without depending upon the road shape in front of one's own vehicle. SOLUTION: This partition line recognizing device has a monitoring camera 1 for photographing an image in front of the self-vehicle, a storing part 8 for dividing the image photographed by the monitoring camera 1 into a plurality of areas and preliminarily storing a road width calculation parameter for every area, an image processing part 6 for extracting a white line painted on a road surface from the image photographed by the camera 1, and a white line estimating part 9 for estimating the position of an unextracted white line on the basis of the coordinates of a plurality of sample points set on an extracted white line, a road width calculation parameter corresponding to the sample points and data of the road width of a traffic lane on which one's own vehicle travels when the image processing part 6 extracts either the white line of the left side or the right side.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a partition line recognition device for recognizing a partition line such as a white line drawn on a road surface in front of a vehicle.

[0002]

2. Description of the Related Art There is known a technique for detecting a white line (partition line) drawn on a road surface by mounting a camera in front of a host vehicle and performing edge processing on an image of the host vehicle taken by the camera. There is. In the conventional white line detection technology, when there is a vehicle in front of the white line, or when the white line is interrupted or faint,
The white line cannot be detected with high accuracy.

Therefore, as a method for solving this problem,
JP-A-5-334595 (hereinafter referred to as Conventional Example 1) and JP-A-8-87700 (hereinafter referred to as Conventional Example 2)
That is) is known.

FIG. 12 is an explanatory diagram showing the processing on the screen by the white line detection technique shown in the conventional examples 1 and 2, and the left white line 11 of the left and right white lines of the traveling lane of the own vehicle as shown in FIG. If only the right side white line is not detected, the detected left side white line 11 is linearly approximated, and based on the approximate straight line and the preset road width data,
The right white line position 14 at the specific location 12 in the image is estimated.

Further, the vanishing point 13 of the approximate straight line is obtained based on the data showing the relationship between the approximate straight line and the camera mounting position, and the estimated right side white line position 14 and the vanishing point 13 are connected by a straight line to obtain the right white line. 15 is estimated.

[0006]

DISCLOSURE OF THE INVENTION Problems to be Solved by the Invention
In the technique described in the second conventional example, it is assumed that the road ahead of the host vehicle is a straight line, and the white line that cannot be detected is estimated based on the road width and the vanishing point. As shown in 13, when the road ahead of the host vehicle is curved, the white line cannot be recognized with high accuracy.

That is, when the front road is curved, a straight line is approximated based on the left white line 21 shown in FIG.
The white line position 24 on the right side is estimated based on the approximate straight line and preset road width data. Further, the vanishing point 23 of the approximate straight line is obtained based on the data showing the relationship between the approximate straight line and the camera mounting position, and the estimated right side white line position 24
And the vanishing point 23 are connected by a straight line, the right white line 25
Therefore, there is a problem that the right white line is estimated at a position that is largely deviated from the original right white line 26.

The present invention has been made to solve such conventional problems, and the purpose thereof is to
It is an object of the present invention to provide a partition line recognition device that can accurately estimate the other partition line from the one partition line (white line or the like) that can be detected regardless of the shape of the road ahead.

[0009]

In order to achieve the above object, the invention according to claim 1 of the present invention is a partition line recognition device for recognizing a partition line drawn on a road surface in front of the own vehicle. The captured image is divided into a plurality of areas, the road width calculation parameter is set in advance for each area, and when either the left or right partition line is extracted from the image in front of the host vehicle, this Setting a plurality of sample points on the partition line, the road width calculation parameter corresponding to the sample points, the coordinates in the image of the sample points, and the road width data of the lane in which the vehicle is traveling, extracted The feature is that the position of the partition line that is not closed is estimated.

According to a second aspect of the present invention, in a partition line recognition device for recognizing a partition line drawn on a road surface in front of the host vehicle, an image capturing means for capturing an image in front of the host vehicle and an image captured by the image capturing means. The divided image is divided into a plurality of areas, and a storage line in which a road width calculation parameter is stored in advance for each area and a partition line drawn on the road surface are extracted from the image photographed by the photographing unit. When either the left side or the right side partition line is extracted by the image processing means and the image processing means, the coordinates of a plurality of sample points set on the extracted partition line and the sample points A partition line estimating means for estimating the position of the partition line which is not extracted by the image processing means, based on the road width calculation parameter corresponding to the above and the road width data of the lane in which the vehicle is traveling. What you did And it features.

According to a third aspect of the present invention, when both the left and right partition lines are extracted by the image processing means, the coordinates of sample points set on the both partition lines and the road. It is characterized by comprising a road width calculating means for calculating a road width along which the vehicle travels based on the width calculation parameter.

According to a fourth aspect of the present invention, the road width calculating means determines whether the front lane of the host vehicle is a straight road based on a detection signal provided by a driving status sensor that detects the driving status of the host vehicle. Or, whether it is a curved road,
A feature is that the road width is calculated when it is determined that the road is a straight road.

According to a fifth aspect of the present invention, the partition line estimating means matches the extracted partition line with a reference position in the image when either the left or right partition line is extracted. As described above, offset processing is performed in the left-right direction, and in this state, the road width calculation parameter at each sample point is set, the position of the partition line that is not extracted is estimated, and then the offset processing is performed. It is characterized by restoring the amount that was done.

[0014]

According to the first and second aspects of the invention, when only one of the left and right partition lines is extracted from the image in front of the vehicle, it is set on the extracted partition line. The partition line that is not extracted is estimated based on the coordinates of the sample points, the preset road width calculation parameter, and the road width data of the lane in which the vehicle is traveling. Therefore, it is possible to recognize the partition line with high accuracy regardless of whether the lane ahead of the host vehicle is a straight road or a curved road.

According to the third aspect of the present invention, when the image processing means extracts the left and right partition lines, the two partition lines,
Since the road width of the lane in which the vehicle is traveling can be obtained based on the road width calculation parameter and the road width calculation parameter, even when the lane width is different, such as on an expressway and an ordinary road,
An appropriate road width can be set, and the partition line recognition processing can be performed with higher accuracy.

According to the fourth aspect of the invention, when the lane in front of the host vehicle is a straight road, the road width is obtained. Therefore, it is possible to calculate the road width with higher accuracy.

According to the fifth aspect of the present invention, when one of the extracted partition lines is deviated from the reference position on the screen, it can be adjusted to the reference position by the offset process. The line can be estimated with high accuracy.

[0018]

BEST MODE FOR CARRYING OUT THE INVENTION Embodiments of the present invention will be described below with reference to the drawings. In addition, in this embodiment, a white line is described as an example of the partition line drawn on the road surface, but the present invention is not limited to this, and a yellow line and a partition line of other colors can also be applied.

First, prior to the description of the configuration, the operation principle of the partition line recognition device according to the present embodiment will be described. FIG. 2 is an explanatory diagram showing an image taken by the surveillance camera 1 (described later) when the road is straight or curved.

Reference symbol L1 shown in the figure is a white line when the front lane is curved to the left of the vehicle, L2 is a white line when the front lane is a straight line, and reference symbol L3 is the front lane when the vehicle is a vehicle. Shows the appearance of the white line when curved to the right of.

Looking at each of the white lines L1 to L3, a point q1 on each white line at a desired height H1 on the image corresponds to the degree of curve of the road, that is, the inclination of the road (white line) on the image. It can be understood that the lateral distance between the q3 and the white line position q0 at the bottom of the image is changed.

That is, on the white line L1 that curves to the left,
The lateral distance of the point q1 is x1 and the white line L2 is a straight line.
Then, it is understood that the lateral distance of the point q2 is x2, and the lateral distance of the point q3 is x3 on the white line L3 that curves to the right, and x1 <x2 <x3.

From this result, if the lateral distance between the point on the white line at the desired height H1 on the image and the starting point q0 of the white line is calculated, the inclination of the road at that point can be estimated.

FIG. 3 is a schematic plan view when the road is a straight line and when the road is curved to the left and right. Reference L11 is a curve to the left and reference L12 is a straight line. , L13 shows the case where it curves to the right. Further, reference numeral 31 indicates the own vehicle. Then, even if the actual road width is the same as shown in the figure, it is understood that the apparent road width at the desired height H1 on the image differs depending on the inclination of the road as shown in FIG. To be done. That is, the white lines L11 to L13 shown in FIG.
Although the road widths are all the same at the position of the line H2, the white lines L1 and L3 that curve to the left and right at the height H1 portion of FIG. The road width is displayed wide.

In view of the above, regarding the point P (Xi, Yj) on the white line on either the left or right of the own lane detected in the white line recognition processing, the inclination of the road at this point P and the screen of the point P By using a predetermined road width calculation parameter for the vertical position above, the apparent road width at that point on the screen (road width when displayed on the screen) is based on the actual road width. It can be calculated.

Further, the position of a point P '(Xi', Yj '(= Yj)) existing on the white line not detected by the white line recognition processing and having the same vertical position as the point P is expressed by the following equation. It can be estimated from (1).

Xi ′ = Xi + Wr · aij (1) where Wr is the actual road width and aij is the road width calculation parameter for calculating the apparent road width on the image from the actual road width. .

Then, a plurality of points are taken on the detected white line, the above-mentioned formula (1) is executed for each point to find the corresponding point, and the obtained points are connected by a straight line. Of the left and right white lines of the own lane, the white line position that has not been detected can be estimated.

Specific embodiments will be described below. FIG. 1 is a block diagram showing the configuration of a partition line recognition device according to an embodiment of the present invention. As shown in the figure, this partition line recognition device 10 is composed of a surveillance camera (photographing means) 1 for photographing an image in front of the host vehicle, and a white line recognition ECU (electro control unit) 2. The ECU 2 is connected to a vehicle speed sensor (driving condition sensor) 4 and a steering angle sensor (driving condition sensor) 5 mounted on the vehicle.

The ECU 2 receives an image of the front of the vehicle captured by the surveillance camera 1 and performs image processing on the image, a vehicle front image, vehicle speed data given from the vehicle speed sensor 4, steering. A road width calculation unit (road width calculation unit) 7 that calculates the road width in front of the vehicle based on the steering angle data provided by the angle sensor 5, a white line estimation unit (white line estimation unit) 9, and a storage unit (storage) Means) 8. Then, the white line detection image 3 is output.

The storage unit 8 divides the image photographed by the surveillance camera 1 into a plurality of areas, and for each of the divided areas, the road width calculation parameter aij shown in the above equation (1).
Memorize That is, as shown in FIG. 4A, the area below the horizontal line H0 of the image is divided into n equal parts in the vertical direction to set lines 0 to n, and the horizontal direction is (m + 1). It is divided into equal parts and areas 0 to m are set. Area i in the horizontal direction (0 ≦ i ≦ m) and line j in the vertical direction (0 ≦ j ≦
The road width calculation parameter aij is determined for each coordinate determined in n) and stored and saved in advance. As a result, a map matrix A [i] [j] of n rows and m columns is set as shown in FIG.

As the map matrix, a map matrix Mr for estimating the right white line and a map matrix Mn for estimating the left white line are prepared. That is, of the left and right white lines, the right white line is detected, and when the left white line is estimated based on this, the map matrix Mn for left white line estimation is used, while the left lane is detected and based on this. When estimating the right side white line by using the right side white line, the map matrix Mr for estimating the right side white line is used.

Further, the storage unit 8 stores the road width of the lane in which the vehicle is traveling, and by the processing described later,
This road width data is updated sequentially.

The white line estimating unit 9 detects the white line on one side on the basis of the data of the white line extracted by the image processing unit 6, the above-mentioned map matrix, and the road width, and detects the other line which is not detected. The process of estimating the white line is performed.

FIG. 5 is a flow chart showing the processing procedure of the partition line recognition apparatus 10 according to this embodiment, and the operation of this embodiment will be described below with reference to the flow chart.

First, in the processing of step S100, the image photographed by the monitoring camera 1 is taken into the white line recognition ECU 2. Next, for the image captured in the ECU 2,
In the process of step S200, white line recognition processing is performed. As a process of recognizing the white line included in the image, a conventionally known method such as a method of detecting the white line included in the captured image by performing a gradation process is used.

Then, in the processing of steps S300 and S500, it is confirmed whether or not the white line is detected. Then, when only one of the left and right white lines is detected, the one-side white line position estimation process of estimating the white line position that is not detected is performed in the process of step S400. If both the left and right white lines are detected, the road width data for obtaining the actual road width and updating the road width data stored in the storage unit 8 in the process of step S600. Perform update processing.

Next, a detailed processing procedure of steps S400 and S600 will be described.

FIG. 6 is a flow chart specifically showing the one-side white line position estimating process (the process of step S400 in FIG. 5), and FIGS. 7 and 8 schematically show the procedure for estimating the other white line from the one-side white line. FIG. 7 shows the case of a straight road, and FIG. 8 shows the case of a curved road.

First, in the processing of step S401 of FIG. 6, the white line detected by the white line recognition processing of the image processing unit 6 is a white line located on the right side of the own lane or a lane located on the left side. Is determined. Here, it is determined depending on which of the left and right positions the starting point of the white line (the position of the white line at the bottom of the screen) is with respect to the center of the screen.

Next, in step S402, a process of laterally translating the screen by .DELTA.X is performed so that the start point of the detected white line comes to a predetermined position on the screen. That is, when the front lane is a straight line, for example, reference numeral 4 in FIG.
The white line image at the position of 1a is translated to the left side by ΔX, and the lowest point is aligned with the position of 40 (reference position). As a result, the white line image moves to the position of reference numeral 41b. In the case of a curved road, for example, the white line image located at the position 51a in FIG. 8A is translated to the left side by ΔX, and the lowest point is aligned with the position 50. As a result, the white line image moves to the position of reference numeral 51b.

Thereafter, in step S403, as shown in FIG. 4, the area below the horizontal line of the image photographed by the monitoring camera 1 is divided into n equal parts in the vertical direction (Y-axis direction),
(N + 1) sample points are extracted. That is, FIG.
8B, points P0 to Pn shown in FIG. 8B (in this example, n
= 6) is extracted.

Then, the road width calculation parameter aij (see FIG. 4) corresponding to the coordinates of this sample point is read from the storage unit 8. The road width calculation parameter aij is determined as shown in FIG. 9 based on the coordinates of the sample points. That is,
In FIG. 9, a52 is selected at the point P2, a43 is selected at the point P3, and a34 is selected at the point P4.

Next, in the processing of step S404, the candidate position of the white line that is not detected is estimated by using the above-mentioned equation (1). That is, the X coordinate of the candidate position corresponding to the points P0 to P6 (X coordinate is X0 to X6) is X0 '.
.About.X6 ', the X coordinate of the candidate position can be obtained by the following equation (2).

X0 '= X0 + Wr.a50 X1' = X1 + Wr.a51 X2 '= X2 + Wr.a42 X3' = X3 + Wr.a33 X4 '= X4 + Wr.a24 X5' = X5 + Wr.a25 X6 '= X6 + Wr.a16 (2) By this, as shown in FIG. 7C and FIG. 8C, the coordinates of the white line which is not detected by the white line recognition processing are obtained. The road width calculation parameter a shown in the equation (2)
As ij, the value based on FIG. 7C is used.

Then, in the processing of step S405, the obtained candidate positions are connected by a straight line, and the white line which is not detected by the white line recognition processing is estimated. After that, step S
In the process of 406, the process of returning the position of the parallel-moved white line in the process of step S402 is performed. That is, FIG.
As shown in (d) and FIG. 8 (d), a process of translating the image by -ΔX is performed. Thus, even if only one of the white lines is detected, the position of the other white line can be estimated based on the coordinate data of the white line.

Next, a processing procedure for updating the road width (processing in step S600 in FIG. 5) will be described with reference to the flowchart shown in FIG.

First, in step S601, the curve radius of the road near the point where the host vehicle is traveling is calculated based on the steering angle data given by the steering angle sensor 5 and the vehicle speed sensor 4 and the vehicle speed data. For example, the curve radius R when the steering angle of the vehicle traveling at the vehicle speed V is θ is
It is expressed by the following equation (3).

R = (1 + A · V ² ) · N · L / θ (3) where A is a stability factor which is a value peculiar to the vehicle, N is a steering gear ratio, and L is a wheel base. .

Next, in step S602, straight line determination is performed based on the curve radius R of the road calculated by the equation (3). For example, if R ≧ 600 m, it is determined that this road is a straight line.

When it is determined that the traveling lane of the host vehicle is a straight line, in the process of step S603, the area below the horizontal line of the image is divided into n equal parts at equal intervals.
From the intersection of the vertical dividing line and the white line, several sample points are extracted on the left and right white lines.

Here, the points where arbitrary vertical division lines and white lines on the left and right of the own lane intersect are point P (Xi, Yj) and point P ', respectively.
If (Xi ′, Yj ′) (where Yj = Y
j ′), the actual road width Wr [m] can be obtained by the following equation (4) using the road width parameter aij corresponding to the position of the point P.

Wr = (Xi′−Xi) / aij (4) In the processing of step S604, the actual road width is calculated using the equation (4) for each sample point of the white lines on both sides. . Next, in the process of step S605, the average of the actual road widths calculated in the above process is calculated.

This will be specifically described below. Figure 11
(A) is an explanatory view showing a state in which an image in which both left and right white lines are detected is divided into n equal parts in the vertical direction, and the left white line L2
1 and the white line L22 on the right side are detected, for example, three sample points Pa and P for the white line L21 on the left side are detected.
Three sample points Pa ', Pb', and Pc 'are extracted for b, Pc, and the right white line L22. The coordinates of the sample points Pa, Pb, Pc on the left white line L21 are (Xi, Ya), (Xj, Yb), (Xk, Yc), respectively.
Sample points Pa ', Pb', Pc 'on the right white line L22
The coordinates of (Xi ', Ya), (Xj', Yb),
(Xk ', Yc).

Next, a road width calculation parameter aij corresponding to each sample point Pa, Pb, Pc on the left white line L21.
Is read from the storage unit 8. That is, for point Pa, ai
a, ab for point Pb, and akc for point Pc.

Thereafter, as shown in FIG. 11B, the distance between the left and right three sample points corresponding to each other is calculated based on the X coordinate of each sample point and the road width calculation parameter. Calculate using.

That is, the road width Wra is determined by the points Pa and Pa '.
Is calculated by the following equation (5).

Wra = (Xi′−Xi) / aia (5) Similarly, the road widths Wrb and Wrc are calculated by the following formula (6) by the points Pb and Pb ′ and the points Pc and Pc ′. Desired.

Wrb = (Xj'-Xj) / ajb Wrc = (Xk'-Xk) / akc (6) Then, the average value of the results of the above equations (5) and (6), that is, The road width Wr is calculated by the equation (7).

[0060] Wr = (Wra + Wrb + Wrc) / 3 (7) In this way, the road width Wr is calculated.

Thereafter, in step S606 of FIG.
The actual road width value currently held is replaced with the newly calculated average road width value. Thus
You can update the width of the road you are actually traveling on.

In this way, in the partition line recognition device 10 according to the present embodiment, when both the left and right white lines of the front lane are detected from the image photographed by the monitoring camera 1, the image of the white line is detected. Based on the data, processing is performed to obtain the road width of the lane in which the vehicle is currently traveling. On the other hand, when only one of the left and right white lines (for example, the left side) is detected from the image captured by the surveillance camera 1, the coordinate data of the detected left side white line and the preset road width are detected. The coordinates of the white line on the right side are estimated based on the calculated parameter and the data of the road width, and the image is displayed.

Therefore, even if the white line drawn on the road surface is interrupted or the vehicle ahead is running across the white line, the data of the white line drawn on the road surface in front of the host vehicle can be obtained with high accuracy. . Further, when the front lane is a straight line, it is possible to perform the highly accurate white line estimation processing even when the vehicle is curved in either the left or right direction.

[Brief description of drawings]

FIG. 1 is a block diagram showing a configuration of a partition line recognition device according to an embodiment of the present invention.

FIG. 2 is an explanatory diagram showing a screen display example when a front road is curved left and right and when it is a straight line.

FIG. 3 is a plan view of a case where a road ahead is curved to the left and right and a straight line.

FIG. 4A is an explanatory diagram showing how an image is divided into a plurality of areas, and FIG. 4B is an explanatory diagram showing road width calculation parameters set in each area.

FIG. 5 is a flowchart showing a processing operation of the partition line recognition processing device according to the embodiment of the present invention.

FIG. 6 is a flowchart showing a processing procedure of one-sided white line position estimation processing.

FIG. 7 is an explanatory diagram schematically showing the procedure of white line estimation processing when the road ahead is a straight line.

FIG. 8 is an explanatory diagram schematically showing the procedure of white line estimation processing when the front road is a curved road.

FIG. 9 is an explanatory diagram showing how road width calculation parameters are set for the extracted sample points on the white line.

FIG. 10 is a flowchart showing a processing procedure of road width data update processing.

FIG. 11 is an explanatory diagram showing a procedure for calculating a road width on which the vehicle travels from the extracted left and right white lines.

FIG. 12 is an explanatory diagram showing a successful example when a white line on one side is estimated by a conventional method.

FIG. 13 is an explanatory diagram showing a failure example when a white line on one side is estimated by a conventional method.

[Explanation of symbols]

1 Surveillance camera (imaging means) 2 White line recognition ECU 3 White line detection image 4 Vehicle speed sensor (driving status sensor) 5 Steering angle sensor (driving status sensor) 6 Image processing unit (image processing means) 7 Road width calculation unit (road width calculation means) 8 storage unit (storage means) 9 White line estimation unit (white line estimation means) 10 Partition line recognition device 31 own vehicle

Front page continuation (51) Int.Cl. ⁷ identification code FI theme code (reference) G06T 7/60 200 G06T 7/60 200J G08G 1/16 G08G 1/16 C F term (reference) 5B057 AA16 BA11 CF03 CF05 CH08 CH11 DA07 DA16 DA17 DC03 DC09 5H180 AA01 CC04 LL01 LL15 5L096 BA04 CA02 DA01 EA35 FA03 FA64 FA67 FA69 GA53 JA16

Claims (5)

[Claims] 1. A partition line recognition device for recognizing a partition line drawn on a road surface in front of the host vehicle, wherein an image of the front of the host vehicle is divided into a plurality of areas, and a road width calculation parameter is set in advance for each area. Set, when one of the left or right partition line is extracted from the image in front of the host vehicle, set a plurality of sample points on this partition line, and calculate the road width corresponding to the sample point. Parameters and coordinates of the sample point in the image,
And a partition line recognition device that estimates the position of the partition line that is not extracted based on the data of the road width of the lane in which the host vehicle travels. 2. A partition line recognition device for recognizing a partition line drawn on a road surface in front of the own vehicle, a photographing means for photographing an image in front of the own vehicle, and an image photographed by the photographing means in a plurality of areas. Storage means for preliminarily storing road width calculation parameters for each area, image processing means for extracting the partition line drawn on the road surface from the image photographed by the photographing means, and the image When either the left or right partition line is extracted by the processing means, the coordinates of a plurality of sample points set on the extracted partition line and the road width calculation corresponding to the sample point A partition line estimating means for estimating the position of the partition line which is not extracted by the image processing means, based on the parameter and the road width data of the lane in which the vehicle is traveling, Recognition Apparatus. 3. When both the left and right partition lines are extracted by the image processing means, based on the coordinates of sample points set on the both partition lines and the road width calculation parameter. 3. The partition line recognition device according to claim 2, further comprising a road width calculation means for calculating a road width along which the host vehicle travels. 4. The road width calculation means determines whether the front lane of the host vehicle is a straight road or a curved road based on a detection signal provided by a driving status sensor that detects the driving status of the host vehicle. The road width is calculated when it is determined that the road is a straight road.
The partition line recognition device described in. 5. The partition line estimating means, when any one of the left and right partition lines is extracted, moves in the left-right direction so that the extracted partition line matches a reference position in the image. Perform offset processing, set the road width calculation parameter at each sample point in this state, estimate the position of the partition line that is not extracted, and then restore the amount moved in the offset processing. The partition line recognition device according to any one of claims 2 to 4.