JP2002092598A - Vehicle position detection device when parking - Google Patents

Abstract

(57) [Summary] [Problem] To display a positional relationship between a partition line separating a parking space and a host vehicle on a monitor screen, thereby making it possible to easily perform a garage entering operation into the parking space. The problem is to provide a vehicle position detecting device. SOLUTION: A rear camera 5 captures a rear image of a vehicle, and detects a white line image included in the rear image. Then, one end point of the detected white line image is set as a reference point, and the position of this reference point is determined. Further, the angle between the direction of the white line based on this reference point and the direction in the image set in advance is determined. Based on these data, the positional relationship between the white line and the own vehicle is obtained, and a process of projecting the own vehicle on the rear image is performed using the data of the obtained positional relationship. Thus, the driver can easily and reliably recognize the positional relationship between the parking space and the vehicle.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a parking system for assisting a steering operation by allowing a driver to recognize a relative position between a partition line for partitioning a parking space and a host vehicle when the vehicle enters the parking space. The present invention relates to a device for detecting the position of the own vehicle at the time.

[0002]

2. Description of the Related Art In general, in a parking lot for parking a vehicle, partition lines such as a white line and a yellow line are drawn on a road surface in order to partition a parking space.
An operation of moving the vehicle backward or forward to enter a parking space separated by this partition line is performed. Here, in order to grasp the positional relationship between the own vehicle and the partition line when the vehicle enters the parking space while retreating,
It is necessary to check the left and right rearview mirrors, or to reverse the vehicle while looking directly at the rear. In addition, when the vehicle does not fit within the parking space, it is necessary to perform an operation of moving the vehicle forward and then back again.

In order to facilitate such a driving operation, a vehicle position detecting device is disclosed in, for example, Japanese Patent Application Laid-Open No. 10-1998.
One described in US Pat. No. 83500 (hereinafter referred to as a conventional example) is known. In the conventional example, an image sensor is attached to the bottom surface of a vehicle to capture an image of a white line on a road surface, and image processing is performed to determine an angle between the white line and the host vehicle.
Then, by displaying the data of the obtained angle as a symbol on a display screen installed at an appropriate position in the driver's seat, the driver is made to recognize the positional relationship of the vehicle with respect to the white line. With such a configuration, the driver can grasp the angle between the host vehicle and the partition line that separates the parking space, which is useful when the vehicle retreats and enters the parking space.

[0004]

A conventional vehicle position detecting device for assisting a parking operation recognizes a partition line that partitions a parking space, finds an angle between the partition line and the own vehicle, and calculates an angle between the partition line and the own vehicle. Is displayed as a symbol on the monitor screen. Therefore, since only the angle between the partition line of the parking space and the host vehicle is detected, the driver can recognize the angle between the partition line and the host vehicle, but the driver can recognize the angle between the partition line and the host vehicle. I cannot recognize the positional relationship. That is, it is not possible to grasp whether the rear end of the vehicle has reached the rear end of the parking space. Therefore, since the front-rear relationship between the parking space and the own vehicle is not recognized, there is a disadvantage that it is not possible to get a sense of distance in the front-rear direction when the vehicle gets into the parking space.

SUMMARY OF THE INVENTION The present invention has been made to solve such a conventional problem. It is an object of the present invention to provide an angle between a vehicle and a partition line and a longitudinal direction of the vehicle with respect to a parking space. An object of the present invention is to provide a vehicle position detecting device at the time of parking, which can make a driver recognize a position.

[0006]

In order to achieve the above object, according to the first aspect of the present invention, a partition line dividing a parking space is imaged, and a positional relationship between the partition line and the own vehicle is detected. A parking position detection device for displaying a detected positional relationship on a screen to inform a driver of the position of the vehicle, which is installed in a vehicle and captures an image of the vehicle; and an image captured by the imaging device Image processing means for extracting a partition line from the reference line, a reference position on a line segment forming the partition line, and an inclination angle of the partition line with respect to a preset reference direction, and a reference position obtained by the image processing means A vehicle position calculating means for calculating a relative position of the vehicle with respect to the partition line on the image from the inclination angle; and a relative position between the vehicle and the partition line calculated by the vehicle position calculating means. Display means for displaying Characterized in that Bei was.

According to a second aspect of the present invention, when the image processing unit includes a plurality of partition lines in an image captured by the imaging unit, the image processing unit includes:
It is characterized by extracting the longest one.

The invention according to a third aspect is characterized in that the reference position is set at one end point existing at a portion other than a corner on the image in the line segment of the extracted partition line.

According to a fourth aspect of the present invention, the image processing means creates a bird's-eye image based on the image taken by the imaging means, and the display means displays the bird's-eye image on the bird's-eye image. It is characterized by displaying a relative position with respect to a partition line.

[0010]

According to the first aspect of the present invention, one end point of a partition line that divides a parking space is set as a reference point, and the reference point position and this reference point are used as a reference. The position of the own vehicle with respect to the partition line is obtained based on the angle of the partition line, and the screen is displayed on the display means. Therefore,
Since the driver can easily and surely recognize the position of the vehicle with respect to the partition line, the operation of putting the garage into the parking space can be performed extremely easily.

In the vehicle position detecting device for parking according to the second aspect of the present invention, when the existence of a plurality of partition lines is confirmed, the longest one is selected and extracted, so that it is reliably desired. Partition lines can be extracted.

In the vehicle position detecting device for parking according to the third aspect, an end point which is not a corner on the screen of the line segment forming the extracted partition line is selected as a reference point. Can be selected as the reference point.

According to the vehicle position detecting device for parking according to the fourth aspect, the relative position between the vehicle and the partition line is displayed on the bird's-eye view image, so that the driver can objectively confirm the vehicle position. Can be.

[0014]

An embodiment of the present invention will be described below with reference to FIG.

Reference numeral 1 denotes a vehicle position detecting device.

Reference numeral 5 denotes a rear camera disposed behind the vehicle and capturing an image of a predetermined range behind the host vehicle.

Reference numeral 6 denotes an auxiliary camera for preliminarily imaging a parking space, which will be described later in detail.

Reference numeral 4 denotes a parking monitor switch provided in the vicinity of the driver's seat. The parking monitor switch is turned on by direct operation of the driver, and an image of the rear camera 5 can be obtained. The parking monitor switch 4 may be turned on when it is detected that the lever has entered the back.

Reference numeral 7 denotes a memory which stores images captured by the rear camera 5 and the auxiliary camera 6.

Reference numeral 3 denotes a monitor provided in the passenger compartment,
The image on which the processing described later has been performed is displayed.

Reference numeral 2 denotes a controller, which includes a CPU and an RO.
It has peripheral components such as M and RAM, and executes a control program stored in ROM.

FIG. 2 is an explanatory diagram showing an image pickup area behind the own vehicle 9 picked up by the rear camera 5. The rear camera 5 picks up an image of a trapezoidal area indicated by reference numeral S 1 behind the own vehicle 9. be able to. FIG. 3 shows a case where the rear camera 5 is parked when another vehicle 10 is parked on both sides of the parking space.
FIG. 5 is an explanatory diagram showing an area imaged by the camera, and the presence of another vehicle 10 can be confirmed on the monitor 3 during a parking operation.

FIG. 4 is a flowchart showing a control program stored in the controller 2. The operation of this embodiment will be described with reference to this flowchart.

When the driver turns on the parking monitor switch 4 near the driver's seat of the vehicle 9 (YE in step ST1).
S), the rear camera 5 is activated and captures a rear image of the vehicle 9 (step ST2).

Then, a process of changing the viewpoint of the image captured by the rear camera 5 to obtain a bird's-eye image is performed. Thus, the rear image as shown in FIG. 5A is converted into a bird's-eye image as shown in FIG. Next, a process of detecting a white line (partition line) included in the bird's-eye image is performed (step ST3). If the white line is not detected (NO in step ST4), the driver is notified by the monitor 3 that the parking operation is difficult in the current situation (step ST5). The same processing is performed also when a white line is detected once but is not detected immediately thereafter.

On the other hand, when it is detected that a white line exists in the bird's-eye view image, a process for obtaining one end point of the white line is performed (step ST6). FIG. 6 is an explanatory diagram showing the concept of a method for obtaining the end point of the white line. The luminance in the bird's-eye image is compared with a predetermined threshold value for each pixel. If it is less than the value, a so-called binarization process of “0” is performed, and a plurality of pixels Q1 whose pixel value changes from “0” to “1” and a plurality of pixels Q1 whose pixel value changes from “1” to “0” And performs edge processing. A straight line connecting each pixel Q1 subjected to the edge processing and each pixel Q2
Is detected as a line at the center of the white line, and a point P which is an end of the straight line S is determined as an end point.

By detecting a line as described above and judging the degree of straightness of the line with a predetermined threshold value, it is possible to prevent a curve such as a puddle from being erroneously recognized as a white line. .

Then, it is determined whether or not the obtained position of the end point is at a corner of the bird's-eye image. If the end point is not at the corner (NO in step ST7), this end point is set as a reference point (step ST9). . On the other hand, if it is determined that the white line is located at the corner (YES in step ST7), the other end point of the white line is obtained and a process is performed using this end point as a reference point (step ST8).

When the reference point is set in steps ST8 and ST9 described above, a process is performed to determine the angle between the line segment extending from the reference point in the direction of the white line and the reference direction on the image (step ST10). ).

FIG. 7 shows steps ST6 to ST10 described above.
Is an explanatory diagram schematically showing the processing procedure of FIG. 1. When a white line image W1 as shown in FIG. 3A is extracted and an end point P1 is designated, the end point P1 is not at a corner of the image. Therefore, it is set as the reference point of the white line, and the angle θ1 between the direction Y2 of the white line based on this reference point and the reference direction Y1 on the image is obtained.

Thereafter, when the own vehicle 9 moves and the end point P1 on the white line W1 reaches the corner of the image as shown in FIG. 3B, the white line is then turned on as shown in FIG. An end point P2 on the opposite side of W1 is set as a reference point, and the direction Y3 of the white line W1 based on this reference point and the reference direction Y1 on the image
Is determined.

Then, the mounting position of the rear camera 5 and
The position of the reference point (P1, P2) in the image obtained by the above-described processing, and the angle (θ1, θ1) between the white line W1 and the reference direction Y1
Based on (θ2), processing is performed to determine the positional relationship between the white line W1 and the host vehicle 9 (step ST11). Then, an image in which the image of the vehicle 9 is superimposed on the bird's-eye image of the parking space is displayed on the monitor 3 (step ST12).

The driver can easily recognize the position of the vehicle 9 with respect to the parking space by looking at the image on the monitor 3, so that the driver moves the vehicle backward and enters the parking space. Can be performed very easily.

FIG. 8 is a diagram showing the selection of the reference point shown in FIG. 7 for each parking phase. When the rear camera 5 captures an image of the area S1 shown in FIG. P11 is obtained as a point. Thereafter, even when the vehicle moves and enters the phase shown in FIG.
Is not at a corner of the image and is therefore selected as a reference point.

Further, when the parking operation proceeds to the position shown in FIG. 3C, the reference point moves to the end point P12 on the opposite side to the previous one, and the parking operation ends as shown in FIG. This position is selected as a reference point until the position is determined.

The above-described procedure is based on the above-described procedure. When parking, there is always a parking space in the rear, and two white lines that determine the parking space are drawn on the road surface. The algorithm effectively utilizes that at least one end point always exists on the imaging screen of the rear camera 5 having a certain angle of view.

As described above, in the present embodiment, the rear camera 5 captures an image of a white line (partition line) that partitions the parking space, sets a reference position on the white line, and establishes a connection between the white line and the host vehicle 9. Determine the angle to be made, and based on the determined result,
The position of the vehicle with respect to the parking space is detected, and this is displayed as an image. Therefore, since the position of the vehicle with respect to the parking space can be accurately displayed on the screen, the driver can easily and surely get the vehicle 9 into the parking space.

Further, the rear image captured by the rear camera 5 is converted into a bird's-eye image, and the image of the vehicle 9 is superimposed and displayed on the bird's-eye image, so that the position of the vehicle can be viewed objectively. . Further, if the parking monitor switch 4 is turned on in conjunction with the shift lever of the vehicle being shifted to the reverse gear, the driver operates the parking monitor switch 4 every time the parking operation is performed. The operation of inputting can be omitted, and the operability is good.

In the above-described embodiment, the image captured by the rear camera 5 is converted into a bird's-eye image, and the image of the vehicle 9 is superimposed on the bird's-eye image and displayed on the monitor 3. Although the configuration is such that the positional relationship between the parking space and the own vehicle is recognized, the own vehicle can be displayed on an image of the parking space captured by the auxiliary camera 6 in advance.

FIG. 9 is an explanatory diagram showing an example of a parking space image previously captured by the auxiliary camera 6 and stored and stored in the memory 7, and reference numeral S11 shown in FIG. 9 indicates an imaging range of this parking space image. . Then, as shown in FIG. 10, the two end points of the white line 71 included in the parking space image S11 are set as P21 and P22, and the reference position obtained in the processing of steps ST8 and ST9 in the flowchart shown in FIG. (Points P11 and P12 shown in FIG. 8)
On the parking space image S11 by matching with the end points P21 and P22 on the parking space image S11.
The image of the own vehicle 9 can be superimposed and displayed. As a result, an image as shown in FIG. 11 is displayed on the monitor 3.

Using such a display method,
The driver can confirm the parking operation of the vehicle 9 while observing an objectively displayed image such that only the image of the vehicle 9 moves without the background moving, and the driver can further move the vehicle into the vehicle space. 9 can be easily operated.

In the above-described embodiment, a white line is used as an example of a partition line for partitioning a parking space.
It is needless to say that the present invention can be applied to other partition lines.

[Brief description of the drawings]

FIG. 1 is a block diagram showing a configuration of an embodiment of a vehicle position detecting device at the time of parking according to the present invention.

FIG. 2 is an explanatory diagram showing a range of a rear field of view of an own vehicle captured by a rear camera.

FIG. 3 is an explanatory diagram showing a rear field of view captured by a rear camera when a vehicle enters a parking space.

FIG. 4 is a flowchart showing the operation of the embodiment.

FIG. 5A is an explanatory diagram illustrating an image captured by a rear camera, and FIG. 5B is an explanatory diagram illustrating a bird's-eye image obtained from the image.

FIG. 6 is an explanatory diagram showing an operation of extracting an end point of a white line.

FIG. 7 is an explanatory diagram showing a method of setting a reference position and setting an angle of a white line.

FIG. 8 is an explanatory diagram showing a change in a reference position accompanying movement of the own vehicle.

FIG. 9 is an explanatory diagram illustrating an image captured by an auxiliary camera.

FIG. 10 is an explanatory diagram showing how a reference point is set on a white line included in an image captured by an auxiliary camera.

FIG. 11 is an explanatory diagram illustrating a state in which the own vehicle is displayed on an image captured by an auxiliary camera.

[Explanation of symbols]

 Reference Signs List 1 self-vehicle position detecting device 2 controller 3 monitor (display means) 4 parking monitor switch 5 rear camera (imaging means) 6 auxiliary camera 7 memory

Claims (4)

[Claims] 1. An image of a partition line that separates a parking space, a positional relationship between the partition line and the host vehicle is detected, and the detected positional relationship is displayed on a screen to inform a driver of the position of the host vehicle during parking. An apparatus, which is installed in a vehicle and captures an image around the vehicle, and extracts a partition line from an image captured by the image capturing unit, and a reference position on a line segment forming the partition line, and Image processing means for obtaining an inclination angle of the partition line with respect to a reference direction set in advance; and a reference position obtained by the image processing means, and a relative position of the vehicle with respect to the partition line on the image based on the inclination angle. And a display means for displaying a relative position between the own vehicle and a partition line calculated by the own vehicle position calculating means, wherein the own vehicle at the time of parking is provided. Position detection device. 2. The image processing device according to claim 1, wherein, when a plurality of partition lines are present in the image captured by the image capturing unit, the image processing unit extracts a longest one of the plurality of partition lines. The self-vehicle position detecting device at the time of parking according to claim 1. 3. The method according to claim 1, wherein the reference position is set at one end point of a line segment of the extracted partition line, which is located at a portion other than a corner on the image. The self-vehicle position detection device for parking described in Crab. 4. The image processing means creates a bird's-eye image based on the image picked up by the image pickup means, and the display means displays a relative position between the vehicle and a partition line on the bird's-eye image. The self-vehicle position detection device at the time of parking according to any one of claims 1 to 3, wherein the display is performed.