JP2003187227A - Lane detection device - Google Patents

Abstract

(57) [Problem] To provide a lane boundary detection device capable of stably detecting a lane boundary. A first edge detection unit is set to have relatively high sensitivity to a spatial density change of original image data and extracts first contour line information. The second edge detection unit 15
The sensitivity is set relatively low with respect to the spatial density change of the original image data, and the second contour information is extracted. The first contour information includes edge information corresponding to a gap between white lines, and the second contour information does not include the edge information. Then, the outermost contour extraction unit 16 extracts the outermost contour information of the white line group from the first and second outline information.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a lane boundary detecting device for detecting a lane boundary position of a marking line from image data obtained by an image pickup device.

[0002]

2. Description of the Related Art Conventionally, as an apparatus for controlling the traveling of a moving body such as an automobile, there is an automatic driving apparatus for recognizing a running path shape and automatically performing steering control. In order to realize this automatic driving, it is necessary to recognize the road,
For example, a detection device for detecting the lane boundary position based on the marking line is required. As this type of detection device, for example, Japanese Patent Laid-Open No.
Those described in JP-A-3-142478, JP-A-6-20189, and JP-A-6-119594 are known.

These detecting devices utilize the characteristic that the white line is brighter than the road surface, and the image data is subjected to processing such as differentiation to extract the contour data of the high-luminance portion from the photographed image. After that, among the contour data extending in the direction along the road, the data of the interval corresponding to the predetermined interval (for example, the design reference value) is regarded as the outline of the white line.

[0004]

By the way, the lane marking is
The shape differs depending on the condition of the track. FIG. 10 (a)-
(D) is a figure which shows the example. As shown in FIG. 10A, a solid section line 61 is provided on one side (left side) and a dashed section line 62 is provided on the other side (right side) in a general section. On the other hand, as shown in FIG. 10B, a section line 63 with a broken line is provided on one side (on the left side) in a section such as an entrance, an exit, a branch point, an uphill lane of a highway.
Is formed wider than the other (right) partition line 62. In this case, the conventional method may not be able to recognize the lane marking 63 in FIG.

Further, as shown in FIG. 10 (c), in a section requiring attention such as a curve, a marking line (composite line) with a wide broken line is provided on one of the left and right sides of the solid line or the broken line. 64 and 65 are provided.
Further, in the oncoming lane section, a partition line (called a multiple white line) 66 provided with a plurality of solid lines is provided. In these cases, the contour of the lane marking may not be stably detected. The reason is as follows.

Since a wide-angle lens is used in the image pickup device, when the composite white lines 64, 65 and the multiple white line 66 are reflected in the peripheral portion of the screen, they are slightly degenerated, so that the gap between the white lines and the white line can be seen. I can't see it. Also, due to the dirt and peeling of the white line itself, the gaps between them are visible or invisible.

The white line portion is saturated due to improper exposure of the camera and the gap cannot be seen. For example, when the shadow of the vehicle occupies a large area on the screen, the white line portion is overexposed, and it is difficult to determine the boundary position, and it is difficult to determine the gap.

Since the actual white line is thinned due to dirt / peeling and the contrast is lowered, it is difficult to determine the gap. Due to these factors, the appearance of the gap is not always constant, so the contour of the lane markings is not stable, and there is a problem that the lane boundary position cannot be detected stably.

An object of the present invention is to provide a lane boundary detecting device which can stably detect a lane boundary.

[0010]

In order to solve the above-mentioned problems, the invention according to claim 1 is based on image data of a traveling road photographed by an image pickup device and including a marking line in its field of view, based on the lane boundary position of the road surface. In the lane boundary detection device that detects
Sensitivity to the spatial density change of the image data is set to be relatively high, first contour information detecting means for extracting first contour line information from the image data, and to the spatial density change of the image data. A second contour information detecting unit that has a relatively low sensitivity and extracts second contour information from the image data, and extracts the outermost contour information of the white line group from the first and second contour information. And a lane boundary position is set based on the outermost contour information.

According to a second aspect of the present invention, the first and second contour information detecting means are different from each other in the same image data by the operators having different sizes depending on the sensitivity. Extract contour line information.

According to a third aspect of the present invention, there is provided a lane boundary detecting device which detects a lane boundary position of a road surface from image data of a traveling road captured by an image pickup device and including a marking line in its field of view. Outline information detecting means for extracting first and second outline information from the second and second image data, and outline extracting means for extracting outermost outline information of the white line group from the first and second outline information. Therefore, the lane boundary position is set based on the outermost contour information.

The contour information detecting means has a first contour information detecting means for extracting the first contour information from the first image data having a high resolution, and a resolution of the first contour information detecting means. And second contour information detecting means for extracting the second contour information from low second image data.

The contour extracting means compares the first contour line information with a first threshold value set to a noise level or higher to detect an amplitude equal to or higher than the noise level, as in the fifth aspect of the invention. First edge information extracted components having, and second edge information extracted only components having an amplitude of a second threshold or more from the second contour information is generated,
The outermost contour information is extracted by synthesizing the first and second edge information.

(Operation) According to the invention described in claim 1,
The sensitivity of the image data to the spatial density change is set to be relatively high, and the sensitivity to the spatial density change of the image data is compared with the first contour information detecting means for extracting the first outline information from the image data. A second contour information detecting unit that is set to be relatively low and extracts the second contour information from the image data, and a contour extracting unit that extracts the outermost contour information of the white line group from the first and second contour information. A lane boundary position is set based on the outermost contour information. Therefore, by setting the sensitivity to the density change to be high, one side contains the information of the edge corresponding to the gap between the white lines, and the other does not contain the information of the edge. Therefore, the information of the edge corresponding to the gap is deleted. Will be easier.

According to the second aspect of the present invention, the first and second contour information detecting means obtain the first and second contour line information from the same image data by the operators having different sizes depending on the sensitivities. To be extracted. Therefore, it becomes easy to extract the contour line information that does not include the information on the edge corresponding to the gap between the white lines.

According to the third aspect of the invention, the contour information detecting means for extracting the first and second contour line information from the first and second image data having different resolutions, and the first and second contour information detecting means. A contour extracting means for extracting the outermost contour information of the white line group from the contour information is provided, and the lane boundary position is set based on the outermost contour information. Therefore, since the low resolution image data does not include the edges corresponding to the gaps between the white lines,
It becomes easy to delete the information of the edge corresponding to the gap.

According to the fourth aspect of the present invention, the contour information detecting means includes the first contour information detecting means for extracting the first contour information from the first image data having a high resolution and the first contour information detecting means having a low resolution. And second contour information detecting means for extracting second contour information from the second image data. Therefore, it becomes easy to extract the contour line information that does not include the information on the edge corresponding to the gap between the white lines.

According to the fifth aspect of the invention, the contour extracting means compares the first contour line information with the first threshold value set above the noise level and has a component having an amplitude above the noise level. To generate first edge information and second edge information obtained by extracting only components having an amplitude equal to or greater than a second threshold value from the second contour line information. The outermost contour information is extracted by combining the edge information. By setting the second threshold, it is possible to easily create the second contour line information that does not include the information of the edge corresponding to the gap between the white lines, and the contour line that does not include the information of the edge corresponding to the gap between the white lines. Information can be extracted.

[0020]

BEST MODE FOR CARRYING OUT THE INVENTION (First Embodiment) A first embodiment of the present invention will be described below with reference to FIGS.

FIG. 1 is a block diagram showing a schematic configuration of a lane boundary detecting device 10. The lane boundary detection device 10 is installed on a moving body, and processes an image of a running path on which the moving body travels to determine a lane boundary position (lane boundary position).

Lane boundary detecting device (hereinafter, detecting device) 10
Is an image pickup unit 11, an A / D converter 12, a frame buffer
(Frame Buffer) section 13, first edge detecting section 14 and second edge detecting section 15 as contour information detecting means, outermost contour extracting section 16 as outermost contour extracting means, offset setting section 17, lane boundary setting section 18 and an output unit 19.
The detection device 10 is connected to a control unit 20 including, for example, a CPU, and the control unit 20 controls each of the above units 11 to 19.

The image pickup section 11 outputs image data of a road image. The A / D converter 12 performs analog-digital conversion on the image data input from the imaging unit 11, and outputs the converted data. The frame buffer unit 13 is A /
The output signal of the D converter 12 is stored as original image data.

The first edge detection unit 14 performs a first edge detection process on the original image data stored in the frame buffer unit 13 to obtain first contour line information including contour line (edge) information. Extract. The first edge detection process is a process of causing a first operator to act on original image data and extracting first contour line information (differential image data) from the original image data.

The second edge detecting section 15 performs a second edge detecting process on the original image data stored in the frame buffer section 13 to obtain second contour line information including contour line (edge) information. Extract. The second edge detection process is a process of causing a second operator to act on the original image data and extracting second contour line information (differential image data) from the original image data.

The first operator has a smaller matrix size than the second operator. For example, the one-dimensional operator 21 shown in FIG. 3 is used as the second operator, and the one-dimensional operator 22 is used as the second operator. FIG. 4 shows the value of each element of the first operator 21 and the second operator 22.

The first and second edge detectors 14 and 15 are
The first and second operators 21 and 22 used respectively obtain the first and second contour line information in each pixel.
For example, the first edge detection unit 14 uses the first operator 2
1 is used to calculate the difference between the density values of pixels before and after the pixel of interest (before and after in the scanning direction), and the calculated value is used as contour line information for the pixel of interest. When the element values of the operator are set as shown in FIG. 4, the first edge detection unit 14 multiplies the density values of the pixels before and after by the values of the matrix element and sums the calculation results of both pixels to calculate the first value. Obtain one contour line information.

The second edge detection section 15 uses the second operator 22 to calculate the difference between the average value of the density values of the two pixels before and the two pixels after the pixel of interest, The calculated value is used as contour line information for the pixel of interest. still,
When the element values of the operator are set as shown in FIG.
The second edge detection unit 15 sums up the calculation results of each pixel in the same manner as the first edge detection unit 14 to obtain contour line information.

The sizes of the first operator 21 and the second operator 22 are set in advance based on the results of experiments and the like based on the gaps included in the white line group. Specifically, the first operator 21 and the second operator 22 are set so that there is a difference in the intensities of the first and second contour line information. Specifically, the first operator 21 sets the size of the matrix elements on both sides of the pixel of interest to be smaller than the gap between the white lines, and the second operator 22 sets
Its size is set larger than the gap between the white lines.

The original image (a) in FIGS. 5 and 6 is a waveform representing the density value of a pixel along one scanning line in the original image data. In order to make the explanation easy to understand, the density value is binary (0, 1).

In the original image (a), the white line has a gap of one pixel (the portion circled in the upper center of the figure). For this gap, the first operator 21 shown in FIG. 5 has an element b corresponding to the pixel of interest and elements a and c for one pixel on both sides thereof. The first contour line information (differential output) obtained by moving the first operator 21 to each position shown in (b) is shown in (c). In the vicinity of the edge corresponding to the gap of the white line, the differential output is "0, -1, 0, 1,
0 ", and in the vicinity of the edge of the white line (the part surrounded by the circle on the upper right side in the figure) is obtained as" -1, -1, 0 ". In this way, the first contour line information has the same amplitude (intensity) regardless of the position of the edge.

On the other hand, the second operator 22 shown in FIG. 6 has an element c corresponding to the pixel of interest, and elements a and b for two pixels and elements d and e on both sides thereof.
The first contour line information (differential output) obtained by moving the second operator 22 to each position shown in (b) is shown in (c). In the vicinity of the edge corresponding to the gap of the white line, the differential output is obtained as "-0.5, -0.5, 0, 0.5, 0.5, 0, 0", and near the edge of the white line (in the upper right circle in the figure, In the surrounding part), it is obtained as "-1, -1, -0.5". Thus, the second contour line information has an amplitude (intensity) according to the position of the edge.

As described above, the change rate of the differential output in the vicinity of the edge of the first contour line information is larger than that of the second contour line information. In other words, the first operator 21
Is set so that the amplitude of the differential output (first contour line information) with respect to the spatial density change of the original image data, that is, the sensitivity, is higher than that of the second operator 22. . That is, it can be said that the first edge detection unit 14 is set to have a relatively high sensitivity to a spatial density change of the original image data, and the second edge detection unit 15 is set to be a relatively low sensitivity to a density change. . Then, the lane boundary detection device 10 uses the first and second operators 21 and 22 having different sizes, so that the first and second contour line information (having the strength corresponding to the space (gap) between the white lines ( Differential image data).

The two-dimensional operator 23 shown in FIG. 3 may be used as the first operator and the two-dimensional operator 24 may be used as the second operator (FIG. 4 shows the values of each element of the two-dimensional operator). .

The outermost contour extraction unit (hereinafter, extraction unit) 16 is
The first contour line information is collated with the second contour line information, and the position information of the outermost contour of the white line and the white line group is obtained. The white line group is composed of a plurality (a plurality of types) of white lines.
The composite white lines 64 and 65 of (c) and the multiple white line 66 shown in FIG.

The extraction unit 16 collates the output of the first edge detection unit 14 (first contour line information) with the output of the second edge detection unit 15 (second contour line information), and a plurality of white lines are detected. When approaching, the outermost contour information, which is the outermost contour line, is extracted.

Specifically, the extraction unit 16 compares the first contour line information with the first threshold value set above the noise level, and extracts only the component having the amplitude above the noise level. Generate information.

Further, the extraction unit 16 generates second edge information by extracting only the component having the amplitude equal to or more than the second threshold value from the second contour line information. The second threshold value is set in advance based on the results of experiments and the like so as not to extract the edge corresponding to the gap between the white lines. For example, FIG. 6 (c)
In the case of the differential output of, the value larger than 0.5 is set as the threshold value.

Then, the extraction section 16 synthesizes the first edge information and the second edge information to generate the outermost contour information. The synthesizing process is a summing process in the present embodiment, and the extracting unit 16 performs the total value (total differential value) of the first edge information and the second edge information for each corresponding pixel. The execution result is used as the outermost contour information.

The first edge information includes data (edge information) above the noise level, as shown as the differential output in FIG. 5 (d). The second edge information includes information on edges having a level equal to or higher than the second threshold, as shown as a differential output in FIG. 6D. Therefore, the total value at the position of the edge forming the outermost contour of the white line group is the sum of the differential values of the first and second edge information, and the value is almost twice that of one. On the other hand, the total value at positions other than the edge forming the outermost contour is equal to one differential value.
Then, in the first edge information, the differential value of the edge in the place where the plurality of white lines are close to each other is smaller than the differential value of the edge of the contour portion. Therefore, the difference between the differential value of the edge corresponding to the outermost contour of the white line group and the differential value of the other edges becomes extremely large. Therefore, the extraction unit 16
Performs the logical product operation to extract the information of the edge that surely forms the contour (outermost contour information).

When the contour line information is separated in the form of a broken line along the traveling direction, the extraction unit 16 complements the contour line information along the traveling direction to obtain the contour line information of the maximum width (white line group). Of the contour line information), two pieces of contour line information having a wide width are output as contour position information.

The offset setting unit 17 stores the offset value from the outermost lane boundary position used by the lane boundary setting unit 18. This offset value is used by the control unit 20.
Is set in advance.

The lane boundary setting unit 18 generates the first lane boundary position data, which is the intermediate position of both edges of the contour line information, based on the contour position information (contour line information) from the extraction unit 16. Further, the lane boundary setting unit 18 is a second lane boundary position data which is a position where one edge of the contour information is offset by the first offset value from the other edge based on the outermost contour information and the offset value. Then, the third lane boundary position data, which is the position where the other edge is offset to the one edge by the second offset value, is generated. Then, the lane boundary setting unit 18 generates the first
~ Outputs the third lane boundary position data.

The output unit 19 selects one of the first to third lane boundary position data output by the lane boundary setting unit 18 according to an instruction from the control unit 20 and outputs the selected data. This selection data is sent to a system control computer such as an alarm device and a speed control device, and the moving body is controlled based on the selection data.

FIG. 2 is a block diagram showing the structure of the extraction unit 16. The extraction unit 16 includes a first threshold processing unit 31, a second threshold processing unit 32, and an arithmetic processing unit 33.

The first threshold value processing unit 31 compares the output (first contour line information) of the first edge detection unit 14 with the first threshold value set above the noise level, and compares it with the noise level above the noise level. It outputs the first edge information obtained by extracting only the component having the amplitude.

The second threshold value processing section 32 outputs second edge information obtained by extracting from the second contour line information only components having an amplitude equal to or greater than the second threshold value. Arithmetic processing unit 33
Generates the outermost contour information by logically synthesizing the first edge information and the second edge information.

Next, the operation of the lane boundary detecting device configured as described above will be described with reference to FIGS. 7 and 8. 7 and 8 visualize the image data in each process.

Now, the original image data 41 shown in FIG. 7 is recorded in the frame buffer unit 13. The first edge detection unit 14 reads the original image data from the frame buffer unit 13 along the scanning line 42. Then, the first edge detection unit 1
4 operates the first operator 21 on the original image data to generate the first contour line information.

The second edge detector 15 reads the original image data from the frame buffer 13 along the scanning line 42. Then, the second edge detection unit 15 causes the second operator 22 to act on the original image data to generate the second contour line information 43. At this time, the information of the edges corresponding to the gaps between the white lines may or may not appear, as shown in FIG.

Next, the extraction unit 16 collates the first contour line information with the second contour line information and extracts the outermost contour information 44 which is the outermost contour line. FIG. 8B is the extracted outermost contour information (image).

Next, the extraction unit 16 uses the contour position information (see FIG. 8).
Outermost contour line information (contour position information) 45 shown by a solid line in FIG. 8C by complementing the edge data by the white line group on the left side and the edge data by the white line group on the left side in (b) along the traveling direction. , 46 are generated.

Based on these outermost contour line information 45 and 46, the lane boundary setting section 18 of FIG.
The intermediate positions of 5 and 46 are calculated, and the first lane boundary position data 47 and 48 indicated by the alternate long and short dash line in FIG. 8C are generated.

Although not shown, the lane boundary setting unit 18
Generates the second and third lane boundary position data based on the outermost contour line information shown in FIG. As described in detail above, according to this embodiment, the following effects can be obtained.

(1) In the present embodiment, the first edge detection unit 14 is set to have a relatively high sensitivity to the spatial density change of the original image data and extracts the first contour line information. The second edge detection unit 15 is set to have a relatively low sensitivity to a spatial density change of the original image data and extracts the second contour line information. The first contour line information includes information on edges corresponding to the gaps between the white lines, and the second contour line information does not include it. Then, the outermost contour extraction unit 16 extracts the outermost contour information of the white line group from the first and second contour line information.
As a result, since it is easy to delete the information of the edge corresponding to the gap, the contour of the white line group (outermost contour information) is stable, and the lane boundary position can be stably detected.

(2) In the present embodiment, the first and second edge detection sections 14 store the original data stored in the frame buffer section 13 by the first and second operators 21 and 22 each having a size corresponding to the sensitivity. First and second contour line information is extracted from the image data. As a result, it is possible to easily extract the first contour line information including the information of the edge corresponding to the gap between the white lines and the second contour line information that does not include the information.

(3) In the present embodiment, the outermost contour extraction unit 1
Reference numeral 6 is first edge information obtained by comparing the first contour line information with a first threshold value set above the noise level to extract a component having an amplitude above the noise level, and second contour line information. And second edge information obtained by extracting only a component having an amplitude equal to or larger than the second threshold value from. Next, the outermost contour extraction unit 16 extracts the outermost contour information by synthesizing the first and second edge information. As a result, by setting the second threshold, it is possible to easily create the second contour line information that does not include the information of the edge corresponding to the gap between the white lines, and include the information of the edge corresponding to the gap between the white lines. It is possible to extract missing contour line information.

(Second Embodiment) The second embodiment of the present invention will be described below with reference to FIG. It should be noted that, for convenience of description, the same components as those in the first embodiment are designated by the same reference numerals, and the description thereof is partially omitted.

FIG. 9 is a block diagram showing a schematic configuration of the lane boundary detecting apparatus 50. The lane boundary detection device (hereinafter, detection device) 50 includes an imaging unit 11, first and second A / D converters 51 and 52, first and second frame buffers (Frame B).
uffer) units 53, 54, first and second edge detection units 55,
56, an outermost contour extraction unit 16, an offset setting unit 17, a lane boundary setting unit 18, and an output unit 19.

The first A / D converter 51 samples the image data input from the image pickup section 11 at the first sampling interval, and outputs the converted data generated by analog-digital conversion of the sampled value. The first frame buffer unit 53 stores the output signal of the first A / D converter 51 as first original image data.

The second A / D converter 52 samples the image data input from the image pickup section 11 at the second sampling interval and outputs the converted data generated by analog-digital conversion of the sampled value. The second frame buffer unit 54 stores the output signal of the second A / D converter 52 as second original image data.

The first sampling interval and the second sampling interval are set according to the required resolution of the original image data. In this embodiment, the first sampling interval is set narrower than the second sampling interval. Therefore, the resolution of the first original image data stored in the first frame buffer unit 53 is higher than that of the second original image data stored in the second frame buffer unit 54.

The first edge detecting section 14 performs a first edge detecting process on the original image data stored in the first frame buffer section 53 and includes a first contour line including information of a contour line (edge). Extract information. The first edge detection process is a process of causing the first operator 21 (see FIG. 3) to act on the original image data and extracting the first contour line information (differential image data) from the original image data.

The second edge detection unit 55 uses the first operator 21 to perform the first edge detection processing on the original image data stored in the second frame buffer unit 54, as in the first edge detection unit 14. Then, the second contour line information including the contour line (edge) information is extracted.

That is, the lane boundary detection device 50 of this embodiment.
Stores two pieces of image data having different resolutions and uses the same operator for them to extract the first and second contour line information.

The first contour line information having a high resolution includes information on an edge corresponding to a gap between white lines, and the second contour line information having a low resolution does not include it. Therefore, the same effect as that of the first embodiment can be obtained.

It should be noted that the present invention is not limited to the above-mentioned embodiments, but may be modified as follows. In the first embodiment, at least one of the image pickup unit 11, the A / D converter 12, and the frame buffer unit 13 is embodied as a lane boundary detection device separately configured. In the second embodiment, a lane boundary detection device in which at least one of the image pickup unit 11, the first and second A / D converters 51 and 52, and the first and second frame buffer units 53 and 54 is separately configured. Materialize.

As operators to be used in the first and second edge detection sections, Sobel, Roberts, Kirsch, Robin
Edge detection is performed using a son, simple 3-level operator, or the like. In addition, edge detection is performed using a simple Laplacian filter, a noise suppression type Laplacian filter, a bridge filter, a surfboard filter, or the like.

The output unit 19 stores the instruction of the control unit 20 in advance and outputs one of the first to third lane boundary position data selected based on the instruction. The lane boundary setting unit 18 generates one of the first to third lane boundary position data according to the instruction of the control unit 20.

In the first embodiment, the one-dimensional operator and the two-dimensional operator are used in combination, that is, 1
Two-dimensional operator 2 using the two-dimensional operator 21 and the two-dimensional operator 24 as the first and second operators
The three and one-dimensional operators 22 may be used as the first and second operators. Furthermore, the matrix size of each operator may be changed appropriately.

In the second embodiment, other operators including the two-dimensional operator 23 shown in FIG. 3 may be used in the first and second edge detectors 55 and 56. Further, operators having different sizes may be used as in the first embodiment.

Image data obtained by spatially converting the original image data so that the white lines are parallel to each other in the data is stored in each frame buffer unit 13, 53, 54 and processed. In each of the above embodiments, the extraction unit 16 logically combines (sums) the first contour information and the second contour information to extract the outermost contour information, but the outermost contour information is extracted by using other methods. The contour information may be extracted. For example, an exclusive OR operation result of the first and second contour line information is generated. The result of this calculation is a set including the information of the edges corresponding to the intervals of the white lines. Therefore, by extracting the complementary set of the set of the calculation results in the first contour line information, the information of the edge corresponding to the gap is deleted from the first contour line information, and the outermost contour information similar to that in the above embodiment is obtained. Can be extracted. Further, the outermost contour information that is substantially the same as the first contour information may be generated after checking the contour by collating the first and second contour information. Further, the outermost contour information may be generated by performing a logical product operation of the first and second contour line information.

Each of the above embodiments shows an example in which the function is divided into blocks, and the function of a plurality of blocks is provided by one block, or the function of one block is provided by a plurality of blocks. May be modified to provide.
Further, the function included in each block may be appropriately changed and implemented.

Next, the technical idea understood from the above embodiment will be described below along with its effects. (A) The contour extraction means compares the first contour information with a first threshold value set to a noise level or higher to extract first edge information from which a component having an amplitude of a noise level or higher is extracted. A second threshold value processing section that generates a first threshold value generating section and second edge information that extracts only components having an amplitude equal to or greater than a second threshold value from the second contour line information. 5. An arithmetic processing unit that synthesizes the first and second edge information and extracts the outermost contour information. 6. Lane boundary detection device.

(B) An offset setting means for storing the offset information and a boundary setting means for setting the lane boundary position based on the offset information stored in the offset setting means. 6. The lane boundary detection device according to any one of 5 to 5. Therefore, the lane boundary position can be set to an arbitrary position with respect to the outermost contour information of the white line group.

(C) The boundary setting means calculates the first lane boundary position based on the outermost contour data indicating the positions of the two edges corresponding to the white line group of the contour position information, and based on the offset information. A second lane boundary position in which one position of the two outermost contour data is offset, and a third lane in which the other position of the two outermost contour data is offset based on the offset information. The boundary position is calculated, and the first to third are calculated according to the selection instruction.
The lane boundary detection device according to (B) above, further comprising output means for outputting one of the lane boundary positions.
Therefore, the lane boundary position corresponding to the request (selection instruction) can be easily obtained.

[0077]

As described above in detail, according to the present invention, it is possible to provide a lane boundary detecting device capable of stably detecting a lane boundary.

[Brief description of drawings]

FIG. 1 is a block diagram showing a schematic configuration of a lane boundary detection device.

FIG. 2 is a block diagram of an outermost contour extraction unit.

FIG. 3 is an explanatory diagram of a differential operator.

FIG. 4 is an explanatory diagram of a differential operator.

FIG. 5 is an explanatory diagram of contour information detection processing.

FIG. 6 is an explanatory diagram of contour information detection processing.

FIG. 7 is an explanatory diagram of a white line.

FIG. 8 is an explanatory diagram of a white line.

FIG. 9 is a block diagram showing a schematic configuration of a lane boundary detection device.

FIG. 10 is an explanatory diagram of a white line.

[Explanation of symbols]

14, 55 ... First edge detecting section (first contour information detecting means), 15, 56 ... Second edge detecting section (second contour information detecting means), 16 ... Outermost contour extracting section (contour extracting means) ,
21 ... First operator, 22 ... Second operator

Continued front page    (72) Inventor Munehiro Takayama             Aichi, 2-chome, Asahi-cho, Kariya city, Aichi prefecture             N Seiki Co., Ltd. (72) Inventor Toshiaki Kakinami             Aichi, 2-chome, Asahi-cho, Kariya city, Aichi prefecture             N Seiki Co., Ltd. (72) Inventor Hisashi Satonaka             1 Toyota Town, Toyota City, Aichi Prefecture Toyota Auto             Car Co., Ltd. (72) Inventor Makoto Nishida             1 Toyota Town, Toyota City, Aichi Prefecture Toyota Auto             Car Co., Ltd. (72) Inventor Shin Takahashi             Aichi Prefecture Nagachite Town Aichi District             Ground 1 Toyota Central Research Institute Co., Ltd. (72) Inventor Yoshiki Ninomiya             Aichi Prefecture Nagachite Town Aichi District             Ground 1 Toyota Central Research Institute Co., Ltd. F term (reference) 5B057 AA16 BA02 DA08 DB02 DB05                       DB09 DC16                 5H180 AA01 CC04 CC24 LL06 LL09                       LL15                 5L096 AA03 AA06 BA04 CA02 DA01                       FA06 FA14 FA18

Claims (5)

[Claims] 1. A lane boundary detection device for detecting a lane boundary position of a road surface from image data of a traveling road imaged by an imaging device and including lane markings in its field of view, wherein the image data has a sensitivity to a spatial density change. A first contour information detection unit that is set to be relatively high and extracts first contour information from the image data, and a sensitivity to a spatial density change of the image data that is set to be relatively low. Second contour information detecting means for extracting second contour information, and contour extracting means for extracting outermost contour information of a white line group from the first and second contour information, the outermost contour information being provided. A lane boundary detection device, characterized in that the lane boundary position is set based on the above. 2. The first and second contour information detecting means respectively extract the first and second contour information from the same image data by operators having different sizes depending on the sensitivity. The lane boundary detection device according to claim 1. 3. A lane boundary detection device for detecting a lane boundary position of a road surface from image data of a traveling road imaged by an imaging device and including a marking line in its field of view, from first and second image data having different resolutions. Contour information detecting means for extracting first and second contour line information, and contour extracting means for extracting outermost contour information of the white line group from the first and second contour line information, the outermost contour information A lane boundary detection device, characterized in that the lane boundary position is set based on the above. 4. The contour information detecting means comprises: first contour information detecting means for extracting the first contour information from first image data having a high resolution; and second contour information detecting means for extracting the first contour information from the second image data having a low resolution. 4. The lane boundary detecting device according to claim 3, further comprising a second contour information detecting means for extracting the second contour information. 5. The first edge extracting unit compares the first contour line information with a first threshold value set above a noise level to extract a component having an amplitude above a noise level. Information, and second edge information obtained by extracting only a component having an amplitude equal to or greater than a second threshold value from the second contour line information, and combining the first and second edge information. The lane boundary detection device according to any one of claims 1 to 4, wherein the outermost contour information is extracted.