JP2001180510A - Tandem supporting device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a tandem parking supporting device facilitating a driver's grasp of steering timing and steering quantity in tandem parking. SOLUTION: A target point for parking is recognized by image processing of an image from a camera 2 by means of an image processing unit 13. On the basis of a positional relationship between the target point and a guide display displayed in the form of superimposition a screen of a monitor 4 by means of a superimposing unit 14, steering timing and steering quantity required for tandem parking is outputted.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a parallel parking support device, and more particularly to a device for recognizing a target parking frame by image processing.

[0002]

2. Description of the Related Art Conventionally, there has been proposed an apparatus for displaying a rear view of a vehicle on a monitor when a driver cannot see a target place due to a blind spot of the vehicle when the vehicle moves backward. For example, in Japanese Patent Publication No. 2-36417,
A television camera for photographing the rear of the vehicle, a monitor television for projecting an image captured by the television camera, a sensor for outputting an information signal related to a tire steering angle, and a marker signal generated in accordance with the information signal from the sensor; A rear monitor monitoring device for a vehicle, comprising a circuit for superimposing a marker on a television screen, is disclosed. In this device, tire steering angle data and marker position data along the reverse direction of the vehicle corresponding to the steering angle are stored in the ROM, and the estimated reverse trajectory of the vehicle according to the steering angle at that time is stored in the ROM. The image is displayed as a column on the television screen so as to be superimposed on the video taken by the television camera.

[0003] According to such a device, when the vehicle is traveling in reverse, the expected backward trajectory of the vehicle in accordance with the steering angle is displayed on the screen of the monitor television together with the visibility of the conditions of the road behind and the like. The vehicle can be moved backward by operating the steering wheel while looking at the television screen without turning around.

[0004]

In the case of parallel parking, for example, the vehicle is moved backward in parallel with the road, the steering wheel is turned at an appropriate position to enter the parking space, and the steering wheel is turned back in the opposite direction to reach the target. It is necessary to guide the vehicle to the parking position where the vehicle is parked. However, with the conventional rear monitoring monitor device, the driver only needs to look at the rear field of view and the expected reverse trajectory of the vehicle on the television screen to determine where the steering wheel should be turned or turned back, and the amount of steering. There is a problem that it is difficult to determine how much to do, and sufficient support for parallel parking cannot be provided. The present invention has been made to solve such problems.
It is an object of the present invention to provide a parallel parking assist device that allows a driver to easily grasp a steering timing and a steering amount when parking in parallel.

[0005]

According to a first aspect of the present invention, there is provided a parallel parking assist system, wherein a camera for photographing a rear side of a vehicle, and a camera disposed at a driver's seat of the vehicle and displaying an image by the camera when the vehicle retreats. A monitor, a steering sensor for detecting a steering angle of a steering wheel, a superimposing unit for superimposing and displaying a guide display for assisting driving of the vehicle at the time of parallel parking on a screen of the monitor; An image processing unit is provided for recognizing a target point for parking and outputting a steering timing and a steering amount necessary for parallel parking based on the positional relationship between the target point and the guide display.

According to a second aspect of the present invention, there is provided the parallel parking assisting apparatus according to the first aspect, wherein the image processing unit recognizes two straight lines included in the parking frame from an image captured by the camera and sets an intersection of the two straight lines as a target point. The target point is tracked in accordance with the movement of the image accompanying the backward movement of the vehicle. The parallel parking assist device according to claim 3 is the device according to claim 2, wherein the image processing unit includes:
This is to predict and correct the position of the target point when the movement of the target point due to the retreat of the vehicle is greatly shifted.

According to a fourth aspect of the present invention, there is provided the parallel parking assist apparatus according to any one of the first to third aspects, which operates by emitting sounds corresponding to the steering timing and the steering amount output from the image processing unit. And a voice selecting unit for guiding the steering to the user. According to a fifth aspect of the present invention, there is provided the parallel parking assistance device according to the fourth aspect, wherein the image processing unit outputs the steering timing and the steering amount to the superimpose unit together with the voice selection unit and displays the steering guidance. Is performed on the screen of the monitor. The parallel parking assist device according to claim 6 is the device according to any one of claims 1 to 5, further comprising a parallel parking mode switch disposed in a driver's seat of the vehicle, and when the parallel parking mode switch is turned on. The guide display is displayed on the screen of the monitor by the superimposing unit.

[0008] In the parallel parking assist device according to the first aspect,
The image processing unit recognizes a target point for parking by performing image processing on the image by the camera, and based on a positional relationship between the target point and a guide display superimposed on the monitor screen by the superimposing unit. It outputs the timing and amount of steering required for parallel parking. According to a second aspect of the present invention, in the parallel parking assist device, the image processing unit obtains, as a target point, an intersection of two straight lines included in the parking frame, and the target point is determined as the vehicle retreats. To track. In the parallel parking assist device according to the third aspect, the second aspect is the second aspect.
In the above device, the image processing unit predicts and corrects the position of the target point when the movement of the target point is greatly shifted. In the parallel parking assist device according to the fourth aspect, in the device according to any one of the first to third aspects, the voice selecting unit emits a voice corresponding to the steering timing and the steering amount output from the image processing unit. To provide steering guidance. In the parallel parking assist device according to the fifth aspect, in the device according to the fourth aspect, the image processing unit outputs the steering timing and the steering amount to the superimposing unit and displays the display corresponding to the steering guidance on the monitor. On the screen. According to a sixth aspect of the present invention, the guide display is displayed on the monitor screen when the parallel parking mode switch is turned on in the device of any one of the first to fifth aspects.

[0009]

Embodiments of the present invention will be described below with reference to the accompanying drawings. Embodiment 1 FIG. As shown in FIG. 1, a camera 2 that captures a field of view behind the vehicle 1 is attached to a rear portion of the vehicle 1. The rear bumper 3 of the vehicle 1 is located at the near-side end of the view range of the camera 2. A monitor 4 composed of a liquid crystal display of a color type is arranged in a driver's seat of the vehicle 1 and is usually used as a display device of a navigation device, and a shift lever 5 provided in the driver's seat is operated to R (reverse position). Then, an image from the camera 2 is displayed. The front wheel 6 as a steering wheel is a steering wheel 7
Is steered by the operation of.

FIG. 2 shows a form of drawing on the monitor 4. The vehicle 1 is stopped parallel to the roadside 8. Column Guideline 9
Guides the start position of the steering wheel operation and makes the vehicle 1 recede straight so that the target position TP overlaps with the start position. When the tandem guideline 9 and the target point TP overlap, the vehicle stops when the handle mark 10 moves on the tandem guideline 9 in accordance with the steering amount of the handlebar 7 and the handle 7 until the target point TP overlaps.
Operate. When the handle mark 10 and the target point TP overlap with each other, the handle 7 is held at the same position, and the handle 7 is retracted until the eye mark 11 matches the target point TP. When the eye mark 11 coincides with the target point TP, the steering wheel 7 is fully turned in the opposite direction to retreat. When the vehicle 1 retreats while paying attention to the rear, the parallel parking is completed when the vehicle 1 becomes parallel to the roadside 8.

FIG. 3 shows a configuration of the parallel parking assist device according to the first embodiment of the present invention. The rear image captured by the camera 2 is output from the external input processing unit 12 to the image processing unit 13 and the superimposing unit 14. The superimposing section 14 superimposes the guide display as shown in FIG. 2 and outputs it to the monitor 4 together with the rear image. Further, the external input processing unit 12 receives a signal corresponding to the shift position from the shift switch 15, and instructs the superimposing unit 14 to display the rear image and the image processing unit 13 if the signal is R (reverse position). To output a signal. When it becomes other than R, a signal is output to stop these. The steering sensor 16 outputs a pulse when the steering wheel 7 is operated. The external input processing unit 12 receives this and counts it, and outputs it to the steering angle calculation unit 17 of the image processing unit 13.

The operation is started from a state in which the vehicle 1 is parked parallel to the roadside 8. In the stop image processing unit 13, first, the binarization / edge detection unit 18 binarizes the rear image, and detects an edge. As shown in FIG. 4, a substantially trapezoidal parking frame 19 is provided.
The histogram area 21 is set at the position where the vertical white line 20 crosses vertically, and a histogram is obtained. As shown in FIG. 5, a density level that exceeds the number of pixels of p% from the maximum density level side of the obtained histogram for the first time is set as a threshold value Th for binarization. As shown in FIG. 6, the binarization is performed only in the designated processing area 22 that does not include the horizontal line in front of the parking frame 19. From the binarized image,
The respective edges in the horizontal direction are obtained, and they are combined to obtain an edge image. Processing area 2 limited as shown in FIG.
Since the processing is performed by using only 2, the processing is lighter than processing the entire image. This processing area 22 can be set at the top of the screen as shown in FIG. 6 because the parking frame 19 is located at the top of the screen when parallel parking is started. Further, as shown in FIG. 7, the processing area 22 may be a small area including at least the corner A of the parking frame 19. However, irrespective of the front-back position of the vehicle 1, the inclination of the horizontal straight line is assumed to be substantially constant.

The switching section 23 switches the output destination of the edge image. From the start of processing, for example, from the first frame to the first frame
The data is output to the shape recognizing unit 24 up to the 0th frame, and thereafter is output to the approximate straight line extracting unit 25. The shape recognizing unit 24 is for detecting the target point TP as securely as possible at the start of the processing.
Detect P. The positions of points P1 to P4 in FIG. 8 in the processing area 22 differ depending on the distance of the vehicle 1 from the roadside 8.
Therefore, the target point TP is detected by learning a plurality of states in advance and determining which state the processed image is close to.

Next, specific processing will be described. The processed image is a binary image in which an edge portion indicated by a black line in FIG. 8 is white and other portions are black. First, the points P1 and P
Search for 2. A white pixel is searched rightward from the origin O of the processing area 22, and the first place found is a point P1. Similarly, a white pixel is searched upward from the origin O to find a point P2. Depending on the distance of the vehicle 1 from the roadside 8, the point P1
9, the slope m1 of the straight line connecting the points P1 and P3, the slope m2 of the straight line connecting the points P2 and P4, and the average mc of these slopes m1 and m2 are obtained, for example, as shown in FIG. Learn as 1-3. Then, it is determined which shape is closer to the position of the detected points P1 and P2. Here, suppose that no. 2 shape.

Next, points P3 and P4 are searched. First,
The middle point between the point P1 and the origin O is defined as Pc, from which the slope M2 is calculated.
Search for white pixels in the direction of c. If you find a white pixel,
The y coordinate of the point Pc 'is stored. A point shifted from the point P1 to the left by the number of pixels s is defined as P1 ', and the slope M2
A point P3 'is obtained by searching for white pixels in the direction of 1. Similarly, a white pixel is searched for in the direction of the slope M22 from the point P2 'shifted to the right by the number of pixels t from the point P2, and a point P4' is obtained.
At this time, the y coordinates of the points P3 ′ and P4 ′ and the y coordinate of the point Pc ′
If the difference from the coordinates is large, it is determined that there is some noise, and the search is started again. A point shifted from the point P3 'to the right by the number of pixels s is defined as P3, and a point shifted from the point P4' to the left by the number of pixels t is defined as P4. This process is repeated for 10 frames. FIG. 10 shows a flowchart of the shape recognition unit 24 and the result determination unit 26. Here, when the detection is normally performed, the coordinates of each point, the slope m1 of the straight line connecting the points P1 and P3, and the slope of the straight line connecting the points P3 and P4 are output as data. Each point P1 in all processing for 10 frames
, P1 ′ to P4 ′, Pc and Pc ′, if there is any undetectable one, the result determination unit 26 outputs a signal for guiding the fact as an error to the voice selection unit 2 as an error.
7 and a sound is emitted from the speaker 28.

Next, the approximate straight line extracting unit 25 performs an approximate straight line extracting process as shown in the flowchart of FIG. 11 after the shape recognizing process by the shape recognizing unit 24 is completed, that is, for the images after the eleventh frame. Perform processing. Here, an approximate straight line of the straight line L0 connecting the points P1 and P3 and the straight line L1 connecting the points P3 and P4 is extracted. First, a contour line is extracted from the input edge image. As shown in FIG. 12, a white pixel (for example, a density level 2
55) is scanned and searched. When the start point SP is found, the contour is traced in the horizontal direction. At this time, the outline is labeled with a value other than the density level 255, and for each point on the outline, white pixels (density level 255) located below the point are erased as indicated by arrows.
After the end of the horizontal direction, the vertical outline is similarly labeled with a value other than the density level 255, and white pixels located on the right side of the outline are erased. Next, an approximate straight line of the extracted contour is obtained by a Hough transformation in a coordinate system within the processing area 22. After that, the search for the start point SP is started again from the position of the start point SP just obtained. However, the outline is labeled with a value other than the density level 255, and the white pixels below and on the right side of the outline have been deleted. This point on the edge is not detected as the starting point SP. This process is continued until the search position of the start point SP comes to the lower right corner of the processing area 22.

Next, the Hough transform will be described. One straight line is the distance r from the origin and the inclination θ from the x-axis.
R = x · sin θ + y · cos θ (1) For a plurality of points on a straight line, this (1)
When mapping to the (r, θ) space using the equation, the curves in the (r, θ) space intersect at one point. The intersection (r, θ) indicates the inclination of the straight line and the distance from the origin. Using this property, points on the contour are mapped to the (r, θ) space, and (r,
By determining the intersection of the curves in the θ) space, the parameters of the approximate straight line of the contour can be determined.

In practice, a two-dimensional array corresponding to θ and r is prepared. This becomes the (r, θ) space. In advance, for example, “0” is put in all (r, θ) positions,
By changing θ in the equation (1), r at that time is obtained, and (r,
For example, “1” is added to the position of θ) and counting is performed.
When this process is performed for all points on the contour, the count value at the position of the intersection (r, θ) becomes larger than the others, so that this point may be extracted as a straight line parameter. At this time, the angle obtained in the previous approximate straight line extraction process is received from the data updating unit 29 as a reference angle, and an intersection is obtained within a range of several degrees before and after the angle. That is, a straight-line parameter is extracted only when (r, θ) at which the count value becomes maximum is within the angle range. By doing so, only those close to the slope of the white line are extracted.

When the two approximate straight lines L0 and L1 are extracted, the intersection calculating unit 30 calculates the intersection P (corresponding to the point A in FIG. 2) of these approximate straight lines. Here, since it is the coordinate system of the processing area 22, it is necessary to convert to the coordinate system of all images. Assuming that the coordinate system of the processing area 22 is (x, y) and the coordinate system of all images is (X, Y), from FIG. 13, the relational expression X = sp _x + x Y = sp _y + y R = X · sin θ + Y · cos θ Using r = x · sin θ + y · cos θ, the parameters of the intersections and the straight lines can be converted into the respective coordinate systems. The data of the intersection and the straight line are output to the target point calculator 31. If the approximate line cannot be extracted,
If no intersection is obtained, the information is output to the target point calculation unit 31.

The target point calculator 31 calculates a target point TP shown in FIG. 2 from the obtained intersection point P. FIG. 14 (a)
As shown in FIG. 14, a point POL on the approximate line L0 in the vertical direction is obtained from the intersection P, and these points P and POL are determined as shown in FIG.
The coordinates are transformed on the road surface as in. On the road surface, a point translated from the point P by a width W of the parking frame 19 in a direction perpendicular to a straight line connecting the point P and the point POL is determined as the target point TP. The target point TP on the road surface is coordinate-transformed again, and FIG.
A target point TP on the screen is obtained as shown in FIG. In this process, until the target point TP overlaps the column guideline 9 in FIG. 2, the point POL is not determined, and the target point TP is determined using only the intersection P. This is because the vehicle 1 is parallel to the roadside 8 in this portion, and the angle φ in FIG. When the target point TP is calculated, the coordinate data is output to the guide coincidence determination unit 32. further,
It is also output to the data updating unit 29 together with the parameters of the approximate straight lines L0 and L1. If information without an intersection is received from the intersection calculation unit 30, the information is transmitted to the data update unit 2.
9 is output.

The data updating section 29 stores past data, changes the position and size of the processing area 22 in accordance with the amount of movement of the intersection P, and outputs it to the binarization / edge detecting section 18. Further, the data updating unit 29 outputs the inclination of the approximate straight line to the approximate straight line extracting unit 25. This becomes a reference angle in the next straight line extraction processing. When the information indicating that the intersection point P has not been detected is received from the target point calculation unit 31, each data is continuously used without being updated. The coordinates of the points P1, P3, and P4 in FIG. 7 are received from the shape recognition result determination unit 26, and the slope of the straight line connecting the points P1 and P3 and the slope of the straight line connecting the points P3 and P4 are obtained. The average value is obtained and used as the initial value of the reference angle at the time of approximation straight line extraction.

The guide coincidence judging unit 32 obtains the distance between the calculated target point TP and various guides,
The approach and coincidence of the target point TP with various guides are determined.
At this time, the steering angle calculation unit 17 calculates the steering angle based on the count value from the external input processing unit 12, and the coincidence with the guide determination unit 32 uses the steering angle input from the steering angle calculation unit 17 to handle the steering wheel mark. Calculate the position of. When the handle 7 is operated, the handle mark 10 moves on the column guide line 9 and approaches the target point TP. As for the tandem guideline 9 and the eye mark 11, the target point TP approaches each as shown in FIG. Target point TP
A signal is sent to the voice selection unit 27 in accordance with the distance between the voice and various guides, and the voice selection unit 27 outputs a corresponding voice from the speaker 28.

FIG. 16 shows the output timing of the voice guide. (A) is a state until the target point TP overlaps the column guideline 9, and the target point TP approaches the column guideline 9 in the order of S1, S2, and S3, and sequentially “Po-npo-”.
"" (Sound 1), "Pom" (sound 2),
Like “pawn” (sound 3), the pitch and / or length of the sound are changed so that the degree of approach can be recognized. In S3, a voice for guiding the next operation is output as a voice guide such as "Please turn the handle until the handle mark (for example, red mark) matches the target point". (B) shows a state until the handle mark 10 is aligned with the target point TP. As in (a), S4,
When the handle mark 10 approaches the target point TP in the order of S5 and S6, sound 1, sound 2, and sound 3 are output according to the distance. In S6, a voice for guiding the next operation is output, such as "Please retreat until the eye mark (for example, a yellow mark) matches the target point". (C) is a state until the target point TP coincides with the eye mark 11, and S7, S8,
When the eye mark 11 approaches the target point TP in the order of S9, sound 1, sound 2, and sound 3 are output according to the distance. In S9, a guidance voice such as "Please turn the steering wheel fully in the opposite direction" is output. In (d), when the steering wheel is turned in the opposite direction by a certain angle or more, a guidance sound such as "Please move backward while paying attention to the rear" is output. After this,
When the white line of the parking frame 19 disappears from the screen, a guidance sound such as "Please stop the car paying attention to the vehicle behind" is output.

Embodiment 2 FIG. In the second embodiment, for example, between the column guideline 9 and the eye mark 11,
Even if the target point TP is lost, a prediction method of the target point TP is introduced so that tracking can be continued to some extent. FIG. 17 shows a configuration of a parallel parking assistance device according to the second embodiment. This apparatus is different from the apparatus according to the first embodiment shown in FIG.
Are connected to the external input processing unit 12, and the rest is the same as the device of the first embodiment. This image processing unit 3
Numeral 3 is provided with a target point predicting unit 34 instead of the intersection calculating unit 30 and the target point calculating unit 31 of the image processing unit 13 in FIG. FIG. 18 shows a flowchart of the target point prediction section 33. The processing until the target point TP overlaps the column guideline 8 and the handle mark 10 matches the target point TP is defined as the first half processing, and then the processing until the target point TP overlaps the eye mark 11 is defined as the second half processing. In the first half processing, the intersection point calculation and the target point calculation are performed in the same manner as in the apparatus of the first embodiment. In the latter half of the process, switch to target point prediction.

Next, the principle of target point prediction will be described. In FIG. 19, the turning center C of the vehicle 1 is
Determined by the angle of cut. The point P, the target point TP, and the point POL on the vertical straight line rotate around the center C when viewed from the vehicle 1. Finally, the target point TP overlaps the eye mark EM, and the point P overlaps the virtual eye mark VEM. The turning radii of these points P, TP, POL are R _VEM ,
R _EM and R _POL . FIG. 20 shows a method of correcting and estimating the point P. Although the point P makes a rotational movement on the road surface, when the point P detected from the image is converted to the road surface, the point P does not necessarily ride on the circumference. (A) shows a correction method when the detected point P deviates significantly from the circumference. Obtains distances between the point P _i and the center C, when the difference between R _EM becomes large, the point P
Correct so that the distance between _i and the center C becomes _REM . At this time, the angle θi and the angle change φi between the x-axis and the line segment P _i C are obtained. (B) shows an estimation method when the point P is not detected. The average value φ of the angle change is obtained from the past several processes. If the point P is not detected, the angle θ = θi + φ, obtain the point P at a radius R _EM. φ is used to obtain the next average of the angle change. Points TP and PO
Since the angle change of L is the same as that of the point P, the points TP and PO are changed using the angle change obtained as a result of detecting and estimating the point P.
Find L. At this time, the radii are R _VEM and R _POL .

If the point P is not corrected, it is necessary to correct the point POL. As shown in FIG. 21, when the distance D _PC from the center C of the point P is larger than the radius R _EM but is not corrected,
If the point POL at the position of the point B is not corrected, the points P and P
An error occurs in the inclination of the white line L1 connecting the line OL. Therefore, the point POL is corrected by multiplying R _POL by the ratio of the distance D _PC between the point P and the center C to the radius R _EM . That is, △ ABC is similarly converted. By doing so, the inclination of the straight line L2 connecting the points P and POL can be made equal to the inclination of the straight line L3 connecting the points A and B. Further, as shown in FIG. 22, when the processing is advanced,
The calculated straight line _Li-1 and the slope of the white line may be shifted. In order to absorb this, R _VEM , R
Update _POL and angle data. If point P _i is detected, point P
OL _i is calculated, and the radius is updated to R _VEMi and R _POLi . At this time, the angle from the x axis is also updated.

FIG. 23 shows a flowchart of the target point prediction. When the latter half process is started, the turning center C and the turning radius _REM of the eye mark are calculated from the turning angle of the steering wheel. Subsequently, the point POL is calculated, and the radii R _VEM , R _POL , and the angle from the x axis are obtained as initial values. If the point P is detected and the data is updated, the calculation of the point POL, the calculation of the turning radii R _VEM and R _POL , and the update of the angle data from the x-axis are performed. Thereafter, if the point P is detected, the point P is corrected, the angle data (angle change, angle from the x-axis) is updated, and the target point TP and the point POL are calculated. When the point P is not detected, the point P is estimated, the angle data (the angle change adopts an average angle change) is updated, and the target point TP and the point POL are estimated. The calculated points are converted on the screen of the monitor 4 to obtain inclination data. This inclination is used for straight line extraction. Thereafter, a process of detecting the next point P is performed.
FIG. 24A is a flowchart of the correction of the point P. When the correction is not performed, the rotation radius ratio rate is obtained, and the point PO is corrected.
Used to modify L. FIG. 24B is a flowchart for calculating the target point TP and the point POL, and FIG. 24C is a flowchart for estimating the point P.

Embodiment 3 FIG. 25 shows a configuration of a parallel parking assistance device according to the third embodiment. This device differs from the device of the first embodiment shown in FIG. 3 in that a cascade mode switch 35 is additionally provided in the driver's seat and connected to the external input processing unit 12. When performing parallel parking, the driver turns on the vertical mode switch 35 to enter the vertical mode. Only when the shift lever 5 is operated to R (retreat position) to turn on the column mode switch 35, the column guideline 9 is displayed on the screen of the monitor 4 and image processing is performed. That is, only necessary items are displayed when necessary. In addition, in order to inform that the vehicle has entered the parallel mode, the image processing unit 13 outputs a mode guidance voice saying “it is in the parallel parking mode” and an operation guidance voice saying “Please go backward until the target point matches the blue line”. Is output from the speaker 28 via the audio selection unit 27. Note that the cascade mode switch 35 may be connected to the device of the second embodiment.

FIG. 26 shows the configuration of a parallel parking assist system according to the fourth embodiment. This device has a configuration in which the image processing unit 13 is connected to the superimposing unit 14 in the device of the first embodiment shown in FIG. The guide information matching unit 32 of the image processing unit 13 sends the approach information of the target point TP and the various guides to the superimposing unit 14, and the display corresponding to the voice selected by the voice selecting unit 27 is displayed on the screen of the monitor 4. Done in For example, as shown in FIG.
An approach indicator 36 is provided at the bottom of the scene, and as the sound changes sequentially to sound 1, sound 2, and sound 3 according to the approach, blue,
The colors are sequentially changed, such as yellow and red, and displayed on the approach display section 36. Further, the operation steps to be performed by the driver can be displayed in characters. For example, the names of guides that need to be noted, such as “guideline”, “handle mark”, and “eye mark”, are displayed on the approach display section 36. Note that the image processing unit 33 of the apparatus according to the second embodiment may be connected to the superimposing unit 14 so that the display corresponding to the sound is similarly displayed on the screen of the monitor 4.

[0030]

As described above, according to the parallel parking assist apparatus of the first aspect, the image processing unit recognizes the target point for parking by image processing and the position of the target point and the guide display. Since the steering timing and the steering amount required for parallel parking are output based on the relationship, the driver can very easily perform the parallel parking operation of the vehicle. Claim 2
According to the parallel parking assist device described in the item (1), in the device according to the item (1), the image processing unit tracks the target point formed by the intersection of two straight lines included in the parking frame as the vehicle retreats. A person can gradually grasp the situation until the vehicle reaches the target point as the vehicle retreats. According to the parallel parking assist device of the third aspect, in the device of the second aspect, the image processing unit predicts and corrects the position of the target point when the movement of the target point is greatly displaced. Even if the driver once loses sight of the vehicle, it is possible to continue supporting the driving operation to some extent. According to the parallel parking assist device of the fourth aspect, in the device of any one of the first to third aspects, a sound corresponding to the steering timing and the steering amount output from the image processing unit is emitted to perform steering. The driver does not need to look closely at the monitor, and can easily park while confirming the surrounding safety. According to the parallel parking assist device of the fifth aspect, in the device of the fourth aspect, the display corresponding to the steering guidance is performed on the monitor screen, so that the driver can visually confirm the approaching state. It is also possible to visually confirm the current operation step even if a voice is missed by character display. According to the parallel parking assist device described in claim 6, in the device according to any one of claims 1 to 5, the guide display is displayed on the monitor screen when the parallel parking mode switch is turned on. Therefore, it is possible to consciously distinguish between parallel parking and other reverse driving, and only necessary drawings can be displayed, so that the screen is easy to see.

[Brief description of the drawings]

FIG. 1 is a side view showing a vehicle equipped with a parallel parking assist device according to Embodiment 1 of the present invention.

FIG. 2 is a diagram showing a form of drawing on a monitor.

FIG. 3 is a block diagram illustrating a configuration of a parallel parking assistance device according to the first embodiment.

FIG. 4 is a diagram showing a monitor screen on which a histogram area is displayed.

FIG. 5 is a graph showing the relationship between the density level of an image and the number of pixels.

FIG. 6 is a diagram showing a monitor screen on which a processing area is shown.

FIG. 7 is a diagram showing a monitor screen on which another processing area is shown.

FIG. 8 is a diagram showing a state in a processing area when a target point is detected.

FIG. 9 is a diagram showing a relationship between a plurality of shapes of a processed image in a processing area, positions of respective points, and inclinations of straight lines.

FIG. 10 is a flowchart illustrating operations of a shape recognition unit and a result determination unit.

FIG. 11 is a flowchart illustrating an approximate straight line extraction process.

FIG. 12 is a diagram showing a method of extracting a contour line.

FIG. 13 is a diagram showing a coordinate conversion method.

14A and 14B are diagrams illustrating a method of calculating a target point, wherein FIG. 14A illustrates a monitor screen, and FIG. 14B illustrates a road surface.

FIG. 15 is a diagram showing a movement of a target point on a monitor screen.

FIG. 16 is a diagram showing the output timing of the audio guide in a stepwise manner.

FIG. 17 is a block diagram illustrating a configuration of a parallel parking assist device according to a second embodiment.

FIG. 18 is a flowchart illustrating the operation of a target point prediction unit.

FIG. 19 is a diagram illustrating the principle of target point prediction.

FIG. 20 is a diagram showing a method of correcting and estimating a point P.

FIG. 21 is a diagram illustrating a method of correcting a point POL.

FIG. 22 is a diagram showing a data update method.

FIG. 23 is a flowchart showing a target point prediction process.

24A is a flowchart illustrating a method of correcting a point P, FIG. 24B is a flowchart illustrating a method of calculating a target point and a point POL, and FIG.

FIG. 25 is a block diagram illustrating a configuration of a parallel parking assist device according to a third embodiment.

FIG. 26 is a block diagram illustrating a configuration of a parallel parking assistance device according to a fourth embodiment.

FIG. 27 is a diagram showing a monitor screen according to the fourth embodiment.

[Explanation of symbols]

1 vehicle, 2 cameras, 3 rear bumpers, 4 monitors, 5 shift levers, 6 front wheels, 7 handles, 8
Roadside, 9 tandem guidelines, 10 handle marks,
11 eye mark, 12 external input processing unit, 13, 33
Image processing unit, 14 superimpose unit, 15 shift switch, 16 steering sensor, 17 steering angle calculation unit, 18 binarization / edge detection unit, 19 parking frame, 20 white line, 21 histogram area, 22 processing area, 23 switching Unit, 24 shape recognition unit, 25 approximate line extraction unit, 26 result determination unit, 27 voice selection unit, 28
Speaker, 29 data update unit, 30 intersection calculation unit,
31 Target point calculation unit, 32 Guide coincidence determination unit, 3
4 Target point prediction unit, 35 tandem mode switch, 36 approach display unit.

──────────────────────────────────────────────────続 き Continued on the front page (51) Int.Cl. ⁷ Identification symbol FI Theme coat ゛ (Reference) B62D 137: 00 G06F 15/62 380 F-term (Reference) 3D032 CC01 DA03 DA81 DA84 DA91 DA95 DB03 DB07 DC38 DD02 EA10 EB30 EC40 GG01 5B057 AA20 BA01 CA08 CB08 CC03 DA07 DA16 DB09 DC01

Claims (6)

[Claims] 1. A camera for photographing the rear of a vehicle, a monitor arranged at a driver's seat of the vehicle and displaying an image by the camera when the vehicle retreats, a steering sensor for detecting a steering angle of a steering wheel, A superimposing unit for superimposing and displaying a guide display for assisting driving of the vehicle on the screen of the monitor; and performing image processing of an image from the camera to recognize a target point for parking and displaying the target point and the guide. A parallel parking assist device comprising: an image processing unit that outputs a steering timing and a steering amount necessary for parallel parking based on a positional relationship between the vehicle and the parallel parking. 2. The image processing unit recognizes two straight lines included in a parking frame from an image captured by the camera, sets an intersection thereof as a target point, and sets the target point according to the movement of the image accompanying the retreat of the vehicle. The parallel parking assist device according to claim 1, wherein the parallel parking assist device tracks the vehicle. 3. The parallel parking assist device according to claim 2, wherein the image processing unit predicts and corrects the position of the target point when the movement of the target point accompanying the retreat of the vehicle is significantly shifted. 4. The apparatus according to claim 1, further comprising: a voice selection unit that generates a voice corresponding to a steering timing and a steering amount output from the image processing unit and guides a driver to steering.
The parallel parking assist device according to any one of the above. 5. The image processing unit outputs a steering timing and a steering amount to the superimposing unit together with the voice selecting unit to cause a display corresponding to a steering guide to be displayed on a screen of the monitor. Item 5. A parallel parking support device according to item 4. 6. The vehicle according to claim 1, further comprising a parallel parking mode switch disposed in a driver's seat of the vehicle, wherein a guide display is displayed on a screen of the monitor by the superimposing unit when the parallel parking mode switch is turned on. The parallel parking assist device according to any one of claims 1 to 5.