JP2970974B2 - Road white line detection method - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a road white line detecting method for converting a road image into a line drawing and detecting a white line drawn on the road as data for automatic steering on a highway or the like.

[0002]

2. Description of the Related Art Conventionally, an apparatus used for detecting a white line on a road is constructed as shown in FIGS. 4 and 5, and an image of a running road is captured by an image pickup means 2 mounted on a vehicle 1 and obtained. The image of the road is A / D converted by an A / D / memory unit 3 comprising an A / D conversion circuit and a frame memory and stored. The stored image data is subjected to a predetermined differentiation operator by an image processing unit 4. The road image is subjected to line drawing conversion to detect a white line drawn on the road, and data of the detected white line is used as data for automatic steering.

The differential operator applied to an image is, for example, as shown in FIGS. 6 (a) and 6 (b). Conventionally, a change in image density in the X direction as shown in FIG. a differential operator E _X for viewing, two differential operator E _X of the differential operator E _Y to see the change in the image density in the Y direction as shown in FIG. 6 (b), E _Y are used, these differential operator E _X, E _Y is previously stored in the internal memory of the image processing unit 4.

The operation of the actual line drawing conversion will be briefly described. As shown in FIG. 7 (a), the differential operator has nine pixels, and the values of the pixels are a, b, c,. When the density of nine pixels centered on the pixel corresponding to the coordinates (X, Y) of the obtained image is as shown in FIG. 7B, the density is differentiated with respect to the density I of each pixel as follows. The value of the corresponding pixel of the operator is multiplied and the sum is represented by coordinates (X,
The calculation is performed as line drawing conversion data of the pixel Y).

[0005]

(Equation 1)

Further, such an operation is performed for each pixel to calculate line drawing conversion data of all the pixels of the one frame image. Pixels of each data whose sign changes are detected as line portions, and a road image is obtained. When an image as shown in FIG. 8A is displayed on the monitor screen as a road image after the line drawing conversion, for example, when the image density changes due to the line drawing conversion described above, for example, the boundary between the road surface and the white line, the guardrail and the background And the like are extracted, and a line drawing as shown in FIG. 8B is obtained, from which data of a white line of the road is extracted.

[0007]

[SUMMARY OF THE INVENTION However, since there are only two types of E _X and E _Y as a conventional line drawing conversion differential operator, these differential operator E _X, the direction of the actual white line portion and the differential direction of E _Y There is a problem that white lines cannot be detected accurately in many cases.

SUMMARY OF THE INVENTION The present invention has been made to solve the above problems, and has as its object to enable accurate detection of a white line on a traveling road.

[0009]

According to a method for detecting a white line on a road according to the present invention, an image of a running road is captured by an image capturing means mounted on a vehicle, and a predetermined image is obtained by image processing means on the obtained image of the road. In a road white line detecting method for performing line drawing conversion on the image by performing a line drawing conversion differential operator and detecting a white line drawn on the road to use as automatic steering data, three or more types of line drawing conversion differential operators are used as the line drawing conversion differential operator. The ones with different differentiation directions are stored in the storage unit in advance,
Each data of the direction, the current position, and the traveling direction of the vehicle detected by the navigation device is taken into the image processing means, and the image processing means differentiates the direction, the current position, and the differentiation direction corresponding to the traveling direction of the vehicle. An operator is read from the storage unit, and the read differential operator is applied to an image captured by the imaging unit.

[0010]

In the present invention, three or more types of differential operators in different differentiation directions are stored in the storage unit in advance, and the differential operators in the differentiation direction corresponding to the direction of the vehicle obtained by the navigation device are read from the storage unit. Since the differential operator is applied to the captured image, a differential operator in a differential direction that matches the direction of the actual white line can be selected, and the differential operator is applied to the captured image to detect a white line on a traveling road. Accuracy is improved than before.

[0011]

FIG. 1 is a block diagram of a detecting device in an embodiment of a road white line detecting method according to the present invention, and FIGS. 2 and 3 are operation explanatory diagrams.

In FIG. 1, the same reference numerals as those in FIG. 5 denote the same or corresponding components, and the differences from FIG.
A storage unit 11 in which three or more types of differentiating directions are stored in advance as a line drawing conversion differential operator is provided, and a geomagnetic sensor 12 that outputs data of the detected azimuth to the image processing unit 4 and a GPS [Global Positioning].
ng System] 13 and map data and
Output the corresponding map data based on the output of S13 1
A navigation device 15 including the data of the azimuth, current position, and traveling direction of the vehicle obtained by the navigation device 15 by the image processing means 4, and a differential operator in a differential direction corresponding to these azimuths and the like. Is read out from the storage unit 11 and the differentiated operator read out is applied to the image captured by the image capturing means 2 to perform line drawing conversion.

At this time, the differential operators to be stored in the storage section 11 in advance are, for example, as shown in FIGS. 2 and 3, and the dashed arrows in the respective drawings indicate the differential directions. Is 25 pixels,
As can be seen by comparing FIGS. 2 and 3, “1”,
The arrangement of “0” and “−1” is shifted due to the difference in the differentiation direction, and other plural differentiation operators having different differentiation directions are stored in the plural storage units 11.

Therefore, by selecting an optimal differential operator corresponding to the azimuth, current position, and traveling direction of the own vehicle, the differential operator in the differential direction that matches the actual white line direction is applied to the captured image. can be, compared with the prior art can be improved in detection accuracy of the white line of the traveling road, and since one kind of differential operator selected need only performed on the captured image, E _X, 2 kinds of E _Y The time required for the calculation can be shortened as compared with the conventional case where the differential operator is applied.

Note that the differential operator is not limited to 25 pixels as shown in FIGS. 2 and 3. By further increasing the number of pixels, the differential direction can be further subdivided and the accuracy of white line detection can be further improved. The effect that it can be obtained is obtained.

[0016]

As described above, according to the road white line detection method of the present invention, three or more differentiating operators in different differentiating directions are stored in the storage unit in advance, and the own vehicle obtained by the navigation device is obtained. The differential operator in the differential direction corresponding to the azimuth or the like is read from the storage unit and applied to the captured image, so that the differential operator in the differential direction that matches the direction of the actual white line can be selected. The white line detection accuracy can be improved, and the calculation time can be shortened, so that the safety at the time of automatic steering on a highway or the like can be improved.

[Brief description of the drawings]

FIG. 1 is a block diagram of an embodiment of a road white line detection method according to the present invention.

FIG. 2 is an operation explanatory diagram of FIG. 1;

FIG. 3 is an operation explanatory diagram of FIG. 1;

FIG. 4 is a schematic explanatory view of an arrangement of a conventional road white line detection device.

FIG. 5 is a block diagram of the device of FIG.

FIG. 6 is an operation explanatory diagram of FIG. 5;

FIG. 7 is an operation explanatory diagram of FIG. 5;

FIG. 8 is an operation explanatory diagram of FIG. 5;

[Explanation of symbols]

 2 imaging means 4 image processing means 11 storage unit 15 navigation device

Claims (1)

(57) [Claims] 1. An image of a running road is imaged by an image pickup means mounted on a vehicle, and a predetermined line image conversion differential operator is applied to an obtained image of the road by an image processing means to convert the image into a line image, In the road white line detection method for detecting a white line drawn on the road and using it as data for automatic steering, three or more types of differential operators having different differentiation directions are stored in the storage unit in advance as the line drawing conversion differential operator, The direction, current position,
Each data of the traveling direction is taken into the image processing means, and the image processing means reads out the differential operator in the differentiation direction corresponding to the azimuth, the current position, and the traveling direction of the own vehicle from the storage section, Applying the read differential operator to the road.