JPH09178482A - Running path detector - Google Patents

Abstract

PROBLEM TO BE SOLVED: To enable the detection of a white line which reduces erroneous detection by calculating a position on a picture image of a vehicle from distance of a vehicle ahead which is detected by a radar device and setting a white line detection region in nearer distance than it. SOLUTION: An image photographed by a TV camera 1 becomes 8 bit image data by an A/D converter 2. A profile image is obtained by processing this image. A radar equipment 5 receives reflected light of radar beam projected to obtain information of distance up to an obstacle and position. The position information from the radar equipment 5 is given to a ahead vehicle detection means 41 of a CPU 4, and the vehicle detection means 41 outputs the distance to a specified means 42 if a vehicle exists ahead. The specified means 42 specifies a possible scope of a white line detection region on more own vehicle side than the vehicle ahead from the distance information. A white line detection means 44 scans the inside of the white line detection region on the image set in the specified scope by a white line detection region setting means 43 to detect a white line position.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to preventive safety of an automobile and relates to a device for detecting a traveling path in front of the own vehicle by using image processing technology. Further, the present invention relates to a traveling road detecting device that monitors the surroundings of the vehicle in combination with a radar device.

[0002]

2. Description of the Related Art Conventionally, various devices for recognizing a white line position on a road surface and detecting a traveling road ahead have been proposed. However, the major problems of this type of device are the accuracy of white line recognition and the high speed of arithmetic processing. It is difficult to achieve both. That is, in general, in this type of device, it is not necessary to obtain the white line position information in all the areas from immediately before the vehicle to the far side, and the white line position in a specific area (hereinafter, referred to as a white line detection area) that is a predetermined distance away from the vehicle. You only need to get the information. Therefore, the white line recognition processing is not performed on the entire area of the captured front image of the own vehicle, but the white line recognition processing is performed only on the predetermined white line detection area, thereby speeding up the calculation process. ing. However, in that case, a vehicle traveling ahead (especially a white vehicle) in the predetermined white line detection area.
Is present, there arises a problem that the present position of the vehicle is erroneously recognized as a white line position. An example of this type of device that prevents this erroneous recognition is disclosed in Japanese Patent Application Laid-Open No. 5-113482. In this device, the horizontal line Lo of the Ys coordinate in the front image of the own vehicle is predetermined as a white line detection area, and the white line position in this white line detection area is recognized to detect the traveling path. In order to prevent the erroneous recognition as described above, first, the recognition of the white line position is started from the position where the vehicle traveling in front cannot exist, that is, the position where the white line position can be surely recognized. This starting point corresponds to immediately before the host vehicle, that is, the lower end of the front image. In this device, the white line position is surely recognized immediately before the host vehicle, and then the white line positions up to the Ys coordinates are sequentially recognized over all the areas while considering the continuity with the first recognized white line position. Do. If a white line position that does not have continuity, for example, a white line position that is significantly different from the previous white line position, is recognized, the recognition process is stopped because there is a possibility of erroneous recognition as described above.

[0003]

By the way, in the conventional road detecting apparatus, the white line positions of all the areas up to a predetermined white line detection area are sequentially recognized in order to recognize the white line position of the white line detection area. However, it has a problem that it takes a very long time to perform arithmetic processing, and cannot be adopted as a preventive safety device for automobiles that require high-speed arithmetic processing.

Further, in the conventional road detecting apparatus, since only one white line detection area is set in advance, there is a problem that accurate information on the shape of the road ahead (degree of curve, etc.) cannot be detected.

Further, in the conventional traveling road detecting apparatus, there is a problem that correction is delayed because it takes time to calculate the bending degree of the radar device depending on the bending degree of the vehicle lane.

The present invention has been made in order to solve the above problems, and an object of the present invention is to provide a traveling road detecting apparatus which achieves both accuracy of white line recognition and high speed of arithmetic processing.

Another object of the present invention is to provide a traveling road detecting device capable of promptly and accurately determining the shape of a traveling road.

It is another object of the present invention to provide a traveling road detecting device capable of promptly and accurately correcting the projection direction of light of a radar device according to the shape of the traveling road.

[0009]

A traveling road detecting apparatus according to the present invention is a radar apparatus for projecting light in front of a host vehicle and receiving light reflected by an obstacle to obtain position information of the obstacle. Front vehicle detection means for detecting the position of the front vehicle traveling in front of the own vehicle based on the position information, a camera for photographing the traveling road surface in front of the own vehicle, and an image obtained by this camera are drawn on the traveling road surface. The white line detection area setting means for setting the white line detection area for detecting the white line, the white line detection means for detecting the white line by scanning the image of the white line detection area, and the settable range of the white line detection area with respect to the preceding vehicle. The vehicle is provided with a regulation means for regulating the vehicle side.

Further, the traveling road detecting device according to the present invention is
A camera that captures the road surface ahead of the host vehicle and multiple white line detection areas that detect white lines drawn on the road surface on the image obtained by this camera are set at equal intervals on the road surface An area setting means, a white line detecting means for scanning an image of a plurality of white line detecting areas to detect each white line, and a shape determining means for determining a shape of a traveling road based on position information of the plurality of white lines are provided. It is a thing.

Further, the traveling road detecting apparatus according to the present invention is
A radar device that projects light in front of the host vehicle and receives light reflected by an obstacle to obtain position information of the obstacle, and projection of light from the radar device according to the shape of the traveling path determined by the shape determination means. And a correction means for correcting the direction.

[0012]

BEST MODE FOR CARRYING OUT THE INVENTION

Embodiment 1 FIG. FIG. 1 is a block diagram showing the configuration of the traveling road detection apparatus according to the first embodiment. In the figure, 1 is a TV camera as a camera for shooting the front of the vehicle, 2 is an A / D converter for A / D (analog / digital) converting the picked-up image to 8-bit image data, and 3 is an image An image memory 4 for storing data is a CPU. Reference numeral 5 denotes a radar device that projects light in front of the host vehicle and receives reflected light reflected by the light hitting an obstacle to obtain information on the distance and position to the obstacle. The position information from the radar device 5 is input to the CPU 4 and the front vehicle detecting means 41 is detected.
Given to. The front vehicle detecting means 41 detects the presence or absence of a front vehicle, and outputs the distance when the front vehicle exists. Reference numeral 42 is a defining means that defines the settable range of the white line detection area based on the distance information from the front vehicle detecting means 41. A white line detection area setting means 43 sets and updates the white line detection area within the settable range defined by the defining means 42. Reference numeral 44 denotes a white line detection means, which scans the white line detection area on the image set by the white line detection area setting means to detect the white line position.

Next, the outline of the operation will be described with reference to the drawings. FIG. 2 is a flow chart showing the flow of processing in the first embodiment. In step 1, the image captured by the TV camera 1 is converted by the A / D converter 2 into 8
It becomes bit image data and is stored in the image memory 3.
In step 2, edge components are extracted from the image obtained in step 1 and binarized with a predetermined threshold value to obtain a contour line image.
On the other hand, in step 3, the radar device 5 projects a laser beam in front of the vehicle by the beam projection means, the laser beam hits an obstacle, is reflected, and the distance to the obstacle depends on the time until it returns to the radar device 5. To measure. Further, step 4 constitutes the front vehicle detecting means 41, and in this step 4, the front vehicle is found from the distance information obtained by the distance measuring means, and the inter-vehicle distance to the own vehicle is detected.

Step 5 constitutes the defining means 42. In this step, the settable range of the white line detection area is defined based on the distance information obtained in step 4. This is shown in FIG. FIG. 3 is an explanatory diagram showing how the apparatus of the first embodiment operates. As shown in the figure, the position of the front vehicle 7 on the image is calculated from the distance between the front vehicle and the host vehicle obtained by the front vehicle detection means 41, and the position of the front vehicle 7 is lower than the front vehicle 7, that is, lower on the image. The white line detection area can be set on the side. For example, 6 is a scanning line as a white line detection area, and this scanning line 6 is the upper end of the settable range defined in step 5. In step 5, the position of the scanning line 6 is defined and the first white line detection area is set to an arbitrary position on the lower side of the image. This position is freely set according to the characteristics of the device. Step 6 is a white line detecting process as the white line detecting means 44. In FIG.
Reference numeral 8 is a scanning line arbitrarily set within the settable range to search in the left-right direction from the center of the screen of the binarized image, and detect a point where an edge exists as a white line position. The information on the position of the white line is sent to other processing in the CPU 4 or another circuit connected to the CPU 4 for use. Step 7
Is to determine whether or not the scanning line 8 is set above the scanning line 6 in the next update of the white line detection area. If the scanning line 8 does not exceed the scanning line 6 even if it is updated, the process proceeds to step 8. .
In step 8, white line detection area setting means sets and updates the scanning line as the white line detection area. That is, when it is determined to be Y in step 7, the scanning line 8 is reset to the upper side of the image and the process is returned to step 6. Then, the scan line 8 is gradually updated to the upper side of the image, and when it is predicted that the scan line 6 will be exceeded in the next update, it is determined as N in step 7, and the process is returned to step 1.

As described above, the distance of the vehicle ahead is detected by the radar device 5, the position of the vehicle on the image is calculated from the distance, and the white line detection area is set on the side of the own vehicle, that is, at a short distance. As a result, it is possible to prevent the vehicle image from entering the white line detection area and erroneously detect the vehicle image as a white line, and it is possible to realize white line detection with few false detections.

Embodiment 2 In the second embodiment, the shape of the own vehicle lane in which the own vehicle travels is calculated using the information on the white line position obtained by the device of the first embodiment.
FIG. 4 is a block diagram showing the configuration of the second embodiment.
In the figure, reference numeral 45 designates a shape determining means for determining the shape of the traveling path based on the white line position information from the white line detecting means 44.
Reference numeral 6 is a correction means for correcting the projection direction of the laser beam of the radar device 5 according to the shape of the traveling road determined by the shape determination means 45. Reference numeral 47 denotes a white line detection area setting means, which has a uniform distance detection area setting means for setting a plurality of white line detection areas so as to be evenly spaced on the traveling road surface.

Next, an outline of the operation will be described. FIG. 5 is a flowchart showing the flow of processing in the traveling road detection apparatus according to the second embodiment. In the figure, the description corresponding to FIG. 2 is simplified to avoid duplication. TV
The image captured by the camera 1 is converted into 8-bit image data in step 11 by the A / D converter 2. In step 12, edge components are extracted from the image obtained in step 11 and binarized with a predetermined threshold value to obtain a contour line image. In step 13, the settable range of the white line detection area is defined on the host vehicle side from the position of the preceding vehicle 7 detected last time, and the position of the first scanning line is set. Step 14
Then, the white line position is detected on the set scanning line. In step 15, it is determined whether or not the scan line exceeds the settable range at the next update of the scan line, and when it is determined that the scan line is within the settable range even after the next update, step 16 is performed.
And the position of the scanning line is updated above the image. Step 1
At 6, the position of the scanning line is updated. This update is sequentially updated so that the white line detection positions are evenly spaced on the actual traveling road.

FIG. 6 shows the position of the scan line updated in step 16. (A) is a top view which shows the white line detection position on a driving road. The scanning line 6 is located at the upper limit of the settable range of the scanning line defined in step 16, and is set so as to detect the position of the white line immediately in front of the forward vehicle 7 as shown in the figure. The scanning line 8 is a scanning line that is sequentially updated in step 16, and is set so as to detect the position of the white line on the traveling path at intervals of 5 m. (B) shows the white line detection position set as shown in (a) on the image. As shown in the figure, if the road surfaces are evenly spaced, the intervals are set to be wide on the lower side of the image and narrow on the upper side of the image. The interval between the scanning lines 8 on the image is arbitrarily determined according to the conditions such as the mounting angle of the camera and the set interval (5 m, 7 m, 10 m, etc.). Therefore, steps 14 to 16
By the processing of (1), it is possible to obtain information on the position of the white line at a plurality of detection positions at equal intervals on the traveling road.

In step 15, when the scanning of the scanning line 6 is completed, the process proceeds to step 17. In step 17, the shape determining means 45 calculates the shape of the traveling path based on the position information of the plurality of white lines obtained by the white line detecting means 44. The calculation of the shape of the traveling road is performed on the plane coordinates when the traveling road is viewed from above. FIG. 7 is an explanatory diagram for explaining how the travel path shape is calculated. In the drawing, 9 is the position of the white line in the white line detection area at equal intervals. In the figure, the white line position is detected although the white line is interrupted because of the interpolation method. In step 17, the shape of the traveling road is calculated using the least squares method based on these position information. The least-squares method is to obtain an approximate straight line in a predetermined range. For example, the approximate straight lines in the range of every three white line positions 9 are sequentially calculated, and the shape of the traveling road is calculated. At this time, in the second embodiment, the interval between the white line positions 9 is every 5 m, so that the arithmetic expression can be simplified and the processing speed can be increased. Since the least squares method is a well-known calculation method, detailed description is omitted here. Then, in step 17, the direction θ in which the forward vehicle 7 is present is calculated based on the shape of the traveling road obtained as described above. Further, the calculation result of step 17 is given to and used by other processing in the CPU 4 or another circuit connected to the CPU 4.

Step 18 constitutes the correction means 46. In this step, the projection direction is corrected so that the laser beam projected from the radar device 5 is projected in the direction θ obtained in step 17. In step 19, the radar device 5 determines the direction θ corrected in step 18.
A laser beam is projected toward, the laser beam hits an obstacle in front and is reflected, and the distance to the obstacle is measured by the time until it returns to the radar device 5.
Further, in step 21, the forward vehicle 7 is found from the distance information obtained by the distance measurement in step 20, and the inter-vehicle distance to the own vehicle is detected. The information on the inter-vehicle distance is used to define the settable range of the white line detection area in the next step 13.

Therefore, according to the second embodiment, by setting the white line detection intervals on the road to equal distances, the process of obtaining the road shape from the white line positions detected in each area can be performed at high speed. You can Therefore, it is possible to promptly perform the correction processing related to the shape of the traveling path, for example, the correction of the projection direction of the laser beam.

Further, the inclination of the white line with respect to the own vehicle detected by the shape determining means 45 is determined by the forward vehicle 7 with respect to the own vehicle.
Since the laser beam is projected in this direction θ, the accuracy of vehicle detection is improved. In addition, the process of recognizing the preceding vehicle 7 from the obtained distance information can be performed at high speed.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a configuration of a first embodiment.

FIG. 2 is a flowchart showing a flow of processing according to the first embodiment.

FIG. 3 is an explanatory diagram illustrating a settable range of a white line detection area.

FIG. 4 is a block diagram showing a configuration of a second embodiment.

FIG. 5 is a flowchart showing a flow of processing according to the second embodiment.

FIG. 6 is an explanatory diagram showing a detection position of a white line.

FIG. 7 is an explanatory diagram illustrating a state of calculation of a travel path shape.

[Explanation of symbols]

1: TV camera 2: A / D converter 3: Image memory
4: CPU 5: Radar device 6: Scan line 7: Forward vehicle
8: Scan line 9: White line position

Claims (3)

[Claims] 1. A radar device for projecting light in front of the own vehicle and receiving the light reflected by an obstacle to obtain position information of the obstacle, and traveling in front of the own vehicle based on the position information. Front vehicle detecting means for detecting the position of the front vehicle, and a camera for photographing the traveling road surface in front of the own vehicle,
White line detection area setting means for setting a white line detection area for detecting a white line drawn on the road surface on an image obtained by this camera, and white line detection means for scanning the image of the white line detection area to detect the white line. And a defining means for defining the settable range of the white line detection area on the host vehicle side with respect to the preceding vehicle. 2. A camera for photographing a traveling road surface in front of the host vehicle, and a white line detection area for detecting a white line drawn on the traveling road surface on an image obtained by the camera so that the white road detection areas are evenly spaced on the traveling road surface. Equal interval detection area setting means for setting a plurality of, white line detection means for scanning the image of the plurality of white line detection areas to detect each of the white lines, and based on the positional information of the plurality of white lines A travel path detection device comprising: a shape determination unit that determines a shape. 3. A radar device for projecting light in front of the host vehicle and receiving the light reflected by an obstacle to obtain position information of the obstacle, and a radar device according to the shape of the traveling path determined by the shape determining means. 3. The traveling road detecting apparatus according to claim 2, further comprising: a correcting unit that corrects a projection direction of the light of the radar device.