JP2012001081A - Parking support system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a parking support system capable of improving the selection precision of a parking frame in double parking or parallel parking and presenting a parking frame optimum to a driver.SOLUTION: The parking supporting system is characterized in that the following steps are performed under the control of a parking support controller 10. A step of detecting white lines around a vehicle based on an image around the vehicle imaged by in-vehicle cameras 1 to 4 attached to the vehicle. A step of calculating the size of the parking frame stipulated by the white lines which are detected and selected. A step of deciding whether the parking frame is one which permits double parking or one which permits parallel parking based on a comparison result between the size of the parking frame and a threshold set according to the size of the vehicle. A step of deciding whether the white lines are present within the parking frame excluding the parking frame within which the white lines are present and selecting the parking frame, when a plurality of parking frames whose parking types are decided are present.

Description

  The present invention relates to a parking support system that is mounted on a vehicle and supports parallel parking (also referred to as parking in a garage or back parking, but in this specification unified with parallel parking) or parallel parking.

  Conventionally, as this type of technology, for example, those described in the following documents are known (see Patent Document 1). This document 1 describes a technique for detecting a parking frame based on an overhead view image around a vehicle. In this technique, a white line drawn on a road surface is detected from a bird's-eye view image, and an area surrounded by a white line where no obstacle exists is detected as a parking frame.

JP 2009-101989

  In the above conventional technology, depending on the combination of white lines detected based on the overhead image, a parking frame that is inappropriate as a parking frame may be detected and presented to the driver. In such a case, an inappropriate parking frame may be selected, and the accuracy of selecting the parking frame may be reduced.

  Therefore, the present invention has been made in view of the above, and an object of the present invention is to provide a parking assistance system capable of presenting a suitable parking frame to the driver in parallel parking or parallel parking. It is in.

  In order to achieve the above object, the present invention detects a white line around a vehicle, calculates a size of a parking frame defined by including the detected white line, and calculates the size of the calculated parking frame and the size of the vehicle. When there are a plurality of parking frames for which the parking type is determined by determining whether the parking frame is a parking frame for parallel parking or a parking frame for parallel parking based on a comparison result with a threshold set in advance according to Is characterized by determining whether or not there is a white line in each parking frame, selecting and presenting the parking frame excluding the parking frame determined to have a white line in the parking frame. .

  According to the present invention, a parking frame in which a white line is present in the parking frame is excluded from the parking frames that are determined to be a parking frame for parallel parking or a parking frame for parallel parking. Therefore, a suitable parking frame can be presented to the driver.

It is a figure which shows the structure of the parking assistance system which concerns on Embodiment 1-3 of this invention. It is a figure which shows the image example of the bird's-eye view image around the own vehicle displayed on a display. It is a figure which shows the mode of parallel parking and parallel parking. It is a flowchart which shows the procedure which determines the parking classification which concerns on Embodiment 1 of this invention. It is a figure which shows a mode that a parking classification is determined in the procedure which concerns on Embodiment 1 of this invention. It is a flowchart which shows the other procedure which determines the parking classification which concerns on Embodiment 1 of this invention. It is a flowchart which shows the other procedure which determines the parking classification which concerns on Embodiment 1 of this invention. It is a flowchart which shows the other procedure which determines the parking classification which concerns on Embodiment 1 of this invention. It is a figure which shows a mode that parking classification is determined in the other procedure which concerns on Embodiment 1 of this invention. It is a figure which shows a mode that parking classification is determined in the other procedure which concerns on Embodiment 1 of this invention. It is a flowchart which shows the procedure which selects the parking frame which concerns on Embodiment 1 of this invention. It is a figure which shows a mode that a parking frame is selected in the procedure which concerns on Embodiment 1 of this invention. It is a flowchart which shows the procedure which selects the parking frame which concerns on Embodiment 2 of this invention. It is a figure which shows a mode that a parking frame is selected in the procedure which concerns on Embodiment 2 of this invention. It is a flowchart which shows the procedure which gives a priority to the parking frame which concerns on Embodiment 3 of this invention. It is a figure which shows a mode that a priority order is given to a parking frame in the procedure which concerns on Embodiment 3 of this invention. It is a figure which shows the other mode which gives a priority to a parking frame in the procedure which concerns on Embodiment 3 of this invention. It is a figure which shows the other mode which gives a priority to a parking frame in the procedure which concerns on Embodiment 3 of this invention. It is a figure which shows a mode that priority is given to a parking frame in the other procedure which concerns on Embodiment 3 of this invention.

  Hereinafter, embodiments for carrying out the present invention will be described with reference to the drawings.

(Embodiment 1)
FIG. 1 is a configuration diagram showing a configuration of a parking assistance system to which the present invention is applied. This parking support system supports a driver's driving operation when the vehicle is parked while displaying a bird's-eye view around the vehicle. As shown in FIG. 1, a parking support controller 10 that forms the core of the system is shown. On the other hand, four in-vehicle cameras 1 to 4 that capture images around the vehicle, a display 5 that displays images for parking assistance, and an operation input device 6 that receives an operation input by a driver are connected. The

  The in-vehicle cameras 1 to 4 are composed of, for example, a wide-angle CCD camera or a CMOS camera having an angle of view of about 180 degrees so that these four in-vehicle cameras 1 to 4 can capture images of all areas surrounding the vehicle. It is installed in the right place of the car. Specifically, the in-vehicle camera 1 is attached to the front grille of the own vehicle, the in-vehicle camera 2 is attached to the rear finisher, the in-vehicle camera 3 is attached to the right door mirror, and the in-vehicle camera 4 is attached to the left door mirror. Shoot the image in a direction looking down at an angle with respect to the road surface.

    The display 5 is a display device such as a liquid crystal display installed in the passenger compartment of the host vehicle, and displays a bird's-eye view image for parking assistance generated by the parking assistance controller 10.

    The operation input device 6 receives an operation input such as setting of a parking target position by a driver of the own vehicle, and includes, for example, a direction key and a touch panel. This operation input device 6 will input the operation signal according to the operation input into the parking assistance controller 10, if operation by a driver is made.

  The parking support controller 10 includes, for example, a microcomputer that operates according to a predetermined processing program, a frame memory, and the like. The processing program is executed by the CPU of the microcomputer, thereby realizing various functions for parking support. To do.

  Specifically, the parking support controller 10 inputs images taken by the four on-vehicle cameras 1 to 4, and views each of the images as viewed from a virtual viewpoint above the own vehicle according to a predetermined coordinate conversion algorithm. By converting and connecting, a bird's-eye view image of the surrounding area of the host vehicle is generated from above, and the generated bird's-eye view image of the surrounding area of the vehicle is displayed on the display 5.

  An example of a bird's-eye view image around the vehicle displayed on the display 5 is shown in FIG. In the image example of FIG. 2, the area A1 is an image obtained by changing the viewpoint of the image taken by the in-vehicle camera 1 attached to the front grille, and the area A2 is an image taken by the in-vehicle camera 2 attached to the rear finisher. It is the image which changed the viewpoint. The area A3 is a video obtained by converting the viewpoint of the video captured by the in-vehicle camera 3 attached to the right side camera, and the area A4 is the viewpoint of the video captured by the in-vehicle camera 4 attached to the left side camera. It is a picture. The center of the bird's-eye view image is a vehicle position mark representing the vehicle position, and a computer graphics image is superimposed on the vehicle position mark. Like the video example of FIG. 2, the bird's-eye view video displayed on the display 5 is a video that allows the user to check the situation around 360 degrees around the host vehicle from above the host vehicle.

  Moreover, the parking assistance controller 10 recognizes a white line on the road surface by performing image processing on the video imaged by the in-vehicle camera 2, and detects a parking frame based on the white line. Details regarding white line recognition and parking frame detection will be described later.

  Next, the parallel parking and parallel parking procedures supported by this system will be described.

  FIG. 3 is a diagram showing general procedures for parallel parking and parallel parking. In the side-by-side parking shown in FIG. 3A, the vehicle M sets a target parking position 203 at the position 201, moves forward to the position 202, and then moves backward to the parking position 203. In the parallel parking shown in FIG. 3B, the vehicle M sets a target parking position 214 at the position 211, moves forward to the position 212, and then moves back to the parking position 214 via the position 213.

  Thus, since the parking procedure is different between parallel parking and parallel parking, it is necessary to set the parking type (parallel parking or parallel parking) at the position 201 or the position 211 in the parking assistance system.

  FIG. 4 is a flowchart showing a procedure for determining the parking type using the widths of two white lines.

  In FIG. 4, after the parking type determination is started in step S301, a white line on the ground drawn around the vehicle is recognized in step S302. In step S303, two white lines having a predetermined angle (for example, vertical) with the traveling direction of the host vehicle are selected from the white lines recognized in step S302, and the width v is calculated. In step S304, the size of the width v and the preset threshold value D is determined. When the width v is smaller than the threshold value D, the process proceeds to step S305, and it is determined that the parking frame surrounded by two white lines is a parking frame for parallel parking that can be parked in parallel. On the other hand, when the width v is larger than the threshold value D, the process proceeds to step S306, and it is determined that the parking frame surrounded by the two white lines is a parking frame for parallel parking that can perform parallel parking. In step S307, it is determined whether all white lines recognized in step S302 have been determined. As a result, if the determination is not completed, the processing from step S303 is repeated. If the determination is completed, the process proceeds to step S308, and the parking type determination is terminated.

  FIG. 5 is a diagram showing the result of determining the parking type using the procedure shown in the flowchart of FIG. As a result of starting parking type determination in the surrounding situation of the vehicle M shown in FIG. 5 (1A) and recognizing the white line parking frame around the vehicle based on the images taken by the in-vehicle cameras 1 to 4, FIG. 5 (1B) It is assumed that the straight lines 401 to 403 are recognized as shown in FIG. Since the straight line 403 faces the same direction as the traveling direction of the vehicle M, it is excluded, and the parking type is determined by the combination of the straight line 401 and the straight line 402. The distance between the straight line 401 and the straight line 402 is v1, and when the threshold value D is set to a value larger than the vehicle width W of the vehicle M and smaller than the total length L of the vehicle M, v1 <D is established. The area surrounded by can be determined as a parking frame for parallel parking. Therefore, the parking target position is the parking frame 406 as shown in FIG. Here, the parking frame is an area virtually set in the approximate center inside the white line delimited by the white line, and expresses the inner area of the white line delimited by the white line for convenience.

  Next, the case of parallel parking will be described. Assuming that the parking type determination is started in the situation shown in FIG. 5 (2A) and the parking frames around the vehicle are recognized, the straight lines 411 to 414 are recognized as shown in FIG. 5 (2B). The straight lines 413 and 414 are excluded because they face the same direction as the traveling direction of the vehicle M, and the parking type is determined by the combination of the straight lines 411 and 412. Since the distance between the straight line 401 and the straight line 402 is v2, and v2> D is satisfied, the area surrounded by the straight lines 411 and 412 can be determined as a parking frame for a column. Therefore, the parking target position is the parking frame 417 as shown in FIG. 5 (2C).

  FIG. 6 is a flowchart showing a procedure for determining the parking type based on the length of the white line. The difference between the procedure shown in FIG. 6 and the procedure shown in FIG. 4 is that the lengths of the two white lines are calculated in step S503 and the determination conditions based on the threshold value D in step S504 are different. Therefore, the process shown in steps S501 to 502 is the same as the process shown in steps S301 to 302 shown in FIG. 4, and the process shown in steps S505 to 508 is the same as the process shown in steps S305 to 308 shown in FIG.

  As shown in FIG. 5 (1B), when the length h1 of the white line satisfies h1> D, it is determined as a parking frame for parallel parking, and the length of the white line as shown in FIG. 5 (2B). When h2 satisfies h2 <D, it is determined as a parking frame for a column. In the case of determining the parking type based on the length of the white line, it can be determined not with two white lines but with one white line. In that case, parking frames are set on both sides of the vehicle traveling direction side and the traveling direction opposite side with the noticed white line as a boundary.

  FIG. 7 is a flowchart showing a procedure for determining the parking type based on the width of the end points. The difference from the procedure shown in FIG. 4 is that the definition of the end point (or intersection) in step S603 is added. Further, the length v of the two end points (or intersections) is calculated in step S604, and the magnitude relationship between the length v and the threshold value D is determined in step S605. Therefore, the processing shown in steps S601 to 602 is the same as the processing shown in steps S301 to 302 shown in FIG. 4, and the processing shown in steps S606 to 609 is the same as the processing shown in steps S305 to 308 shown in FIG.

  Here, the end point is an intersection of two white lines, or an end point closer to the vehicle M in one white line. For example, the intersection point 404 of the straight line 401 and the straight line 403 and the intersection point 405 of the straight line 402 and the straight line 403 shown in FIG. 5 (1B), the intersection point 415 of the straight line 411 and the straight line 414 in FIG. This is the intersection 416. In FIG. 5 (1B), when the straight line 403 is not detected and the straight line 401 and the straight line 402 are detected, the end point 404 and the end point 405 are obtained.

  FIG. 8 is a flowchart showing a procedure when the threshold value is increased to two in the process shown in step S304 in FIG. FIG. 9 is a diagram showing the determination result of the parking type when the procedure shown in FIG. 8 is executed.

  The difference between the procedure shown in FIG. 8 and the procedure shown in FIG. 4 is that the parking type is determined by executing steps S704 and S706 instead of step S304 shown in FIG. Therefore, the process shown in steps S701 to S703 is the same as the process shown in steps S301 to S303 shown in FIG. 4, the process shown in step S705 is the same as the process shown in step S305 shown in FIG. 4, and steps S707 to 709 are executed. The process shown in FIG. 4 is the same as the process shown in steps S306 to S308 in FIG.

  Assume that the white line is recognized as shown in FIGS. 9 (1B) and 9 (2B) as a result of recognizing the white line in the situation shown in FIGS. 9 (1A) and 9 (2A). Under the condition of the threshold value D shown in FIG. 4, it can be determined that the combination of the straight line 801 and the straight line 802 is correctly parallel parking, but the combination of the straight line 802 and the straight line 803 is also determined to be parallel parking. Similarly, it can be determined that the combination of the straight line 812 and the straight line 813 is correctly parallel parking, but the combination of the straight line 811 and the straight line 813 is also determined as parallel parking.

  Therefore, D1 = W−α (0 <α <W) with respect to the vehicle width W, D2 = W + β (0 <β <W), D3 = L + γ (0 <γ <L) with reference to the total length L, D4 = Threshold values D1, D2, D3, and D4 that satisfy L + δ (0 <δ <L) and D1 <D2 <D3 <D4 are set. The magnitude relationship between these threshold values D1 to D4 and the width v of the white line is determined. That is, in step S704 shown in FIG. 8, when the width v of the two white lines satisfies D1 <v <D2, it is determined in step S705 that the parking frame is a parallel parking frame. On the other hand, if D3 <v <D4 is satisfied in step S706, it is determined in step S707 that the parking frame is for the column. By executing such a procedure, the parking frame 805 and the parking frame 816 can be selected as shown in FIG. 9 excluding the combination of the straight line 802 and the straight line 803 and the combination of the straight line 811 and the straight line 813. .

  In the above description, the determination result of the parking type when the parking frame is decided in a single way is shown. As a result of recognizing the white line, three or more white lines having a certain angle with the vehicle M are detected. In some cases, there may be a plurality of parking frames. An example of determining the parking type in such a case will be described below.

  As a result of recognizing white lines in the situation shown in FIG. 10A, it is assumed that three white lines of straight lines 901 to 903 are recognized as shown in FIG. 10B. At this time, combinations of straight lines are considered to be (1) straight line 901 and straight line 902, (2) straight line 901 and straight line 903, and (3) straight line 902 and straight line 903. As a result of determining the parking type based on the width v of the white line in step S704 and step S706 shown in FIG. 8, the combination of (1) is a parking frame for parallel parking, and the combination of (2) is parking for a column. The combination of the frame and the above (3) becomes a parking frame for parallel parking.

  However, when the parking type is determined by paying attention to the length of the white line, the above (2) is no longer a parking frame for the column. Therefore, the parking frame is a parking frame 904 and a parking frame 905 as shown in FIG.

  Thus, there may be a plurality of parking frames. In that case, it is inconvenient to present two or more parking frames to the driver and select one parking frame from the plurality of parking frames presented by the driver because the setting effort increases. . Therefore, in the first embodiment, when two or more parking frames are detected, a proper or suitable (easy parking operation) parking frame is selected from the detected plurality of parking frames. The procedure will be described below.

  FIG. 11 is a flowchart showing a procedure for selecting a regular parking frame from a plurality of detected parking frames.

  The procedure shown in FIG. 11 differs from the procedure shown in FIG. 8 in that the process shown in step S1003 is executed instead of step S703 shown in FIG. 8, and steps S1009 to S709 are executed between steps S708 and S709 shown in FIG. That is, the processing shown in S1012 has been executed. Therefore, the process shown in steps S1001 to 1002 is the same as the process shown in steps S701 to S702 shown in FIG. 8, the process shown in steps S1004 to S1008 is the same as the process shown in steps S704 to S708 shown in FIG. The process shown in step S1013 is the same as the process shown in step S709 shown in FIG.

  In step S1003, two white lines are selected except for the combination of the already selected white lines, and the width v of the two selected white lines is calculated. In step S1009, it is determined that parallel parking is performed in step S1005, and it is determined whether parallel parking is included in the frame of the parking frame and in step S1007, and whether or not a white line is included in the frame of the parking frame (whether there is a white line). To do. This determination can be realized by a method of detecting a conventionally known white line described above. As a result of the determination, if a white line is included, the process proceeds to step S1010. If a white line is not included, the process proceeds to step S1011.

  In step S1010, a parking frame that includes a white line is determined to have a high possibility of an unauthorized parking frame, and is excluded from the parking frame. In step S1011, a parking frame that does not include a white line is highly likely to be a regular parking frame, and is therefore selected as a parking frame. In step S1012, it is determined whether or not the processing shown in steps S1009 to S1011 has been executed for all parking frames in parallel parking and parallel parking.

  As a result of recognizing white lines in the situation shown in FIG. 12A, it is assumed that three white lines of straight lines 1101 to 1103 are recognized as shown in FIG. In such a case, the combinations of white lines are (1) straight line 1101 and straight line 1102, (2) straight line 1101 and straight line 1103, and (3) straight line 1102 and straight line 1103.

  Assume that the combination of the above (2) and (3) is determined to be a parking frame for parallel parking as a result of determining the parking type based on the width v of the white line by the processing of step S1004 and step S1006 shown in FIG. However, the frame determined by the combination of (2) above includes a straight line 1102 within the frame. Therefore, it is determined that the parking frame of the combination (2) is not likely to be an original parking frame, and is excluded from this parking frame. Thereby, as shown in FIG. 12C, the parking frame 1106 is selected as a regular parking frame and presented to the driver.

  Thus, in this Embodiment 1, since the parking frame containing a white line is excluded from the plurality of parking frames, a regular parking frame can be selected and presented to the driver, and the selection accuracy Can be increased. Thereby, the driver can surely park in the parking frame at the correct position. Furthermore, one parking frame can be selected from a plurality of parking frames and presented to the driver. Thereby, it becomes possible to save the effort and time which a driver | operator selects a parking frame. As a result, it is possible to shift to an operation for quickly parking, and to shorten the time for parking.

(Embodiment 2)
FIG. 13 is a flowchart showing an operation process of the parking assistance system according to the second embodiment of the present invention.

  In the parking assistance controller 10 that performs the operation process of the flowchart shown in FIG. 13, the parking frame selection function of the first embodiment includes the following functions instead of the functions described above. That is, the parking frame selection function employed in the second embodiment is that when it is determined that a white line is present in the parking frame, the white line is present in the parking frame based on the density of the white line present in the parking frame. A parking frame is excluded from the determined plurality of parking frames.

  The difference between the procedure shown in FIG. 13 and the procedure shown in FIG. 11 is that the process shown in step S1210 is executed between the process shown in step S1009 shown in FIG. 11 and the processes shown in steps S1010 and S1011. Therefore, the processing shown in steps S1201 to 1208 is the same as the processing shown in steps S1001 to 1008 shown in FIG. 11, and the processing shown in steps S1211 to S1214 is the same as the processing shown in steps S1010 to S1013 shown in FIG.

  In step S1210, it is determined whether or not the white density in the white line included in the two selected white lines is darker than the white density in the white line included in the other two selected white lines. As a result of the determination, if it is dark, it is determined that the two white lines including the dark white line on the inner side are likely not to be a regular parking frame, and are excluded from the parking frame. On the other hand, if the result of the determination is that it is not dark, the two white lines including the white line that is not dark inside are determined to be regular parking frames and are selected as parking frames.

  As a result of recognizing white lines in the situation shown in FIG. 14A, it is assumed that four white lines 1311 to 1314 shown in FIG. 14B are recognized. Here, it is assumed that the density of the straight line 1311 and the straight line 1313 and the density of the straight line 1312 and the straight line 1314 are substantially equal, and the density of the straight line 1311 and the straight line 1313 is higher than the density of the straight line 1312 and the straight line 1314.

  In such a case, the parking type is determined in steps S1204 and S1206 in FIG. As a result of the determination, combinations of white lines that can be determined as parking frames include (1) straight line 1311 and straight line 1313, and (2) straight line 1312 and straight line 1314, both of which can be determined as parking frames for parallel parking.

  Therefore, the density of the straight line 1313 included in the parking frame 1316 determined by the combination of (2) above by the processing in step S1210 shown in FIG. 13 and the parking frame 1315 determined by the combination of (1) above are included. The density of the straight line 1312 is compared. As a result, since the density of the straight line 1313 is higher than the density of the straight line 1312, it is determined that the parking frame 1315 is likely to be a regular parking frame, and is selected as a parking frame as shown in FIG. . On the other hand, since the parking frame 1316 includes a darker white line than the others, it is determined that there is a high possibility that it is not a regular parking frame, and is excluded from the parking frame.

  Thus, in this Embodiment 2, when the density of the inner white line is darker than the other compared among the plurality of parking frames including the inner white line, the second white line including the white line on the inner side is configured. Parking frames are excluded. Thereby, a parking frame with high possibility of a regular parking frame can be selected and shown to a driver, and selection accuracy can be raised. Thereby, the driver can surely park in the parking frame at the correct position. Furthermore, one parking frame can be selected from a plurality of parking frames and presented to the driver. Thereby, it becomes possible to save the effort and time which a driver | operator selects a parking frame. As a result, it is possible to shift to an operation for quickly parking, and to shorten the time for parking.

(Embodiment 3)
FIG. 15 is a flowchart showing an operation process of the parking assistance system according to the third embodiment of the present invention. In this Embodiment 3, based on the distance between the reference line set based on the position of the vehicle M and the center of gravity of the parking frame, priority is given to a plurality of selected parking frames that preferentially encourage parking. It is characterized by giving a ranking and presenting it to the driver. In order to realize such a feature, the parking support controller 10 that performs the operation processing of the flowchart shown in FIG. 15 sets the priority order instead of the function of selecting the parking frame provided in the first and second embodiments. It has a function to do. This priority setting function calculates the distance between the reference line perpendicular to the traveling direction of the vehicle and the center of gravity of the parking frame when there are multiple parking frames for which the parking type is determined. Based on the distance, a priority order for recommending parking is set in the parking frame. Alternatively, the priority setting function calculates the distance between the reference line parallel to the traveling direction of the vehicle and the parking frame when there are multiple parking frames for which the parking type is determined. Based on this, a priority order for recommending parking is set in the parking frame.

  In FIG. 15, first, in step S1401, a process for giving priority to parking frames is started. In step S1402, a reference line is set in a direction substantially perpendicular to the traveling direction of the vehicle M. Next, in step S1403, the center of gravity of the parking frame determined in the series of processes shown in steps S903 to 907 of FIG. 11 is obtained, and the distance between the center of gravity and the reference line is calculated.

  Here, the center of gravity is the intersection of two diagonal lines of the parking frame. If all the detected parking frames are vertical parking frames, the process advances from step S1404 to step S1405. On the other hand, when the detected parking frame is other than that, that is, when all the parking frames for parallel parking, or when the parking frame for parallel parking and the parking frame for tandem are mixed, the process proceeds from step S1404 to step S1406. .

  In step S1405, the priority order of the parking frames whose center of gravity is on the opposite side of the traveling direction from the reference line is set higher. In step S1406, a higher priority is set in order from a parking frame having a short distance between the reference line and the center of gravity. In step S1407, the prioritization of parking frames ends.

  Next, prioritization in actual parking conditions will be described with reference to FIGS.

  First, FIG. 16 (A) to FIG. 16 (C) show how to assign priorities when the determined parking frames are all parallel parking. As shown in FIG. 16A, it is assumed that the straight line 1501 to the straight line 1505 are recognized, and as a result of using the parking frame determination so far, the parking frame 1511 to the parking frame 1514 for parallel parking are determined. Next, as shown in FIG. 16B, a reference line 1522 perpendicular to the traveling direction of the vehicle M and barycentric lines 1521 and 1523 for the respective parking frames are set. Here, the reference line 1522 is set at a position crossing the vehicle M, for example, passing through the windshield. The center of gravity line is set as a line parallel to the reference line through the center of gravity of the parking frame.

  In such a case, (distance L1 between reference line 1522 and barycentric line 1521) <(distance L2 between reference line 1522 and barycentric line 1523). Accordingly, the priority order of the parking frames 1512 is set higher than other parking frames by the process shown in step S1406 of FIG. In this manner, distances are obtained for all parking frames and priorities are assigned. As a result, as shown in FIG. 16C, the priority order of the parking frames is: parking frame 1512> parking frame 1513> parking frame 1511> parking frame 1514 in descending order of priority.

  FIGS. 17A to 17C show how to assign priorities when the determined parking frames are all parallel parking. As shown in FIG. 17A, it is assumed that the straight line 1601 to the straight line 1603 are recognized and the parking frame 1611 and the parking frame 1612 for parallel parking are determined as a result of using the parking frame determination so far. Next, as shown in FIG. 17B, a reference line 1622 perpendicular to the traveling direction of the vehicle M (set at the same position as the reference line 1322 shown in FIG. 16) and the center of gravity with respect to each parking frame. Lines 1621 and 1623 are set.

  In such a case, since the barycentric line 1623 is on the opposite side of the reference line 1622 with respect to the traveling direction of the vehicle M, the priority of the parking frame 1612 is made higher than the others by the process shown in step S1405 of FIG. . Therefore, as shown in FIG. 17C, the parking frame priority order is parking frame 1612> parking frame 1611 in descending order of priority.

  FIGS. 18A to 18C show how to assign priorities in the case where the determined parking frame includes a parallel parking frame and a parallel parking frame. As shown in FIG. 18A, it is assumed that the straight line 1701 to the straight line 1704 are recognized and the parking frame 1711 and the parking frame 1712 for parallel parking are determined as a result of using the parking frame determination so far. Next, as shown in FIG. 18B, a reference line 1722 perpendicular to the traveling direction of the vehicle M (set at the same position as the reference line 1322 shown in FIG. 16) and the center of gravity with respect to each parking frame. Lines 1721 and 1723 are set.

  In such a case, (distance L1 between reference line 1721 and barycentric line 1721) <(distance L2 between reference line 1722 and barycentric line 1723). Therefore, the priority of the parking frame 1711 is set higher than other parking frames by the process shown in step S1406 of FIG. As a result, as shown in FIG. 18C, the priority order of the parking frames becomes parking frame 1711> parking frame 1712 in descending order of priority.

  Next, as shown in FIG. 16 above, in addition to the case where a parking frame for parallel parking is detected on the left side in the traveling direction of the vehicle M, in addition, parking for parallel parking is also performed on the left side in the traveling direction of the vehicle M. In the case where a frame is detected, how to assign priorities will be described with reference to FIG.

  As a result of recognizing the white line in the situation as shown in FIG. 19A, the parking type and the priority order are determined for the left and right parking frames of the vehicle M according to the series of processes shown in FIG. As a result, as shown in FIG. 19B, the priority order of the parking frame 1801 is the highest on the left side in the traveling direction of the vehicle M, and the priority order of the parking frame 1802 is the highest on the right side.

  Here, a reference line 1810 passing through the approximate center of the vehicle M in parallel with the traveling direction of the vehicle M is set. Next, the distance between the reference line 1810 and the parking frame 1801 and the distance between the reference line 1810 and the parking frame 1802 is calculated. As a result of the calculation, (distance L1 between reference line 1810 and parking frame 1801) <(distance L2 between reference line 1810 and parking frame 1802), as shown in FIG. 19C, the reference line and the parking frame The priority of the parking frame 1801 having a short distance is set higher than that of the parking frame 1802.

  Thus, in this Embodiment 3, since the priority is provided to the selected several parking frame, the selection accuracy of a parking frame is raised and a suitable parking frame can be shown to a driver | operator. . Thereby, the driver can save time and effort for selecting a suitable parking frame from among a plurality of parking frames. As a result, it is possible to shift to an operation for quickly parking, and to shorten the time for parking.

  The correspondence relationship between the configuration requirements of the first to third embodiments and the configuration requirements in the claims is as follows. That is, the in-vehicle cameras 1 to 4 constitute white line detection means, and the parking support controller 10 includes white line detection means, parking frame size calculation means, parking type determination means, white line presence / absence determination means, parking frame selection means, and priority order setting means. Configure. The parking support controller 10 realizes the above-described means by the cooperation of the hardware resources and software resources described above.

1-4 ... In-vehicle camera 5 ... Display 6 ... Operation input device 10 ... Parking support controller

Claims (15)

A white line detecting means for detecting a white line around the vehicle;
A parking frame size calculating unit that selects a white line detected by the white line detecting unit and calculates a size of the parking frame defined by the selected white line;
A parking frame in which the size of the parking frame calculated by the parking frame size calculating means is compared with a threshold set in advance according to the size of the vehicle, and the parking frame can be parked in parallel based on the comparison result. Parking type determination means for determining whether there is a parking frame that can be parked in parallel or
When there are a plurality of parking frames for which the parking type is determined by the parking type determination unit, a white line presence / absence determination unit that determines whether there is a white line in each parking frame;
A parking frame that selects a parking frame from a plurality of parking frames whose parking type has been determined by the parking type determination unit, excluding a parking frame that has been determined to have a white line in the parking frame by the white line presence determination unit. A parking support system comprising a selection means. A white line detecting means for detecting a white line around the vehicle;
A parking frame size calculating unit that selects a white line detected by the white line detecting unit and calculates a size of the parking frame defined by the selected white line;
A parking frame in which the size of the parking frame calculated by the parking frame size calculating means is compared with a threshold set in advance according to the size of the vehicle, and the parking frame can be parked in parallel based on the comparison result. Parking type determination means for determining whether there is a parking frame that can be parked in parallel or
When there are a plurality of parking frames for which the parking type is determined by the parking type determination unit, a white line presence / absence determination unit that determines whether there is a white line in each parking frame;
When the white line presence / absence determining means determines that there is a white line in the parking frame, based on the density of the white line existing in the parking frame, among the plurality of parking frames determined to have a white line in the parking frame A parking frame selection means for selecting a parking frame by excluding the parking frame from
A parking support system comprising: a presenting unit that presents the parking frame selected by the parking frame selecting unit. A white line detecting means for detecting a white line around the vehicle;
A parking frame size calculating unit that selects a white line detected by the white line detecting unit and calculates a size of the parking frame defined by the selected white line;
A parking frame in which the size of the parking frame calculated by the parking frame size calculating means is compared with a threshold set in advance according to the size of the vehicle, and the parking frame can be parked in parallel based on the comparison result. Parking type determination means for determining whether there is a parking frame that can be parked in parallel or
When there are a plurality of parking frames for which the parking type is determined by the parking type determining means, the distance between the reference line perpendicular to the traveling direction of the vehicle and the gravity center position of the parking frame is calculated, and based on the calculated distance And a priority setting means for setting a priority for recommending parking to the parking frame. A white line detecting means for detecting a white line around the vehicle;
A parking frame size calculating unit that selects a white line detected by the white line detecting unit and calculates a size of the parking frame defined by the selected white line;
A parking frame in which the size of the parking frame calculated by the parking frame size calculating means is compared with a threshold set in advance according to the size of the vehicle, and the parking frame can be parked in parallel based on the comparison result. Parking type determination means for determining whether there is a parking frame that can be parked in parallel or
When there are a plurality of parking frames for which the parking type is determined by the parking type determining means, the distance between the reference line parallel to the traveling direction of the vehicle and the parking frame is calculated, and the parking frame is calculated based on the calculated distance. And a priority order setting means for setting a priority order for recommending parking. The parking assistance system according to any one of claims 1 to 4, wherein the parking type determination unit uses a width and a length of the vehicle as a size of the vehicle. The parking frame size calculating means calculates the size of the parking frame using at least one of the length of the white line, the interval between two arbitrarily selected white lines, and the interval between the intersections of two intersecting white lines. The parking assistance system according to any one of claims 1 to 5, wherein When the parking frame size calculating means calculates the size of the parking frame using the interval between two arbitrarily selected white lines, the parking type determining means sets the interval between the white lines in advance according to the size of the vehicle. When the threshold value is smaller than the threshold value, the parking type is determined as parallel parking, and when the white line interval is larger than a preset threshold value according to the size of the vehicle, the parking type is determined as parallel parking. The parking support system according to claim 6. When the parking frame size calculating means calculates the size of the parking frame using the length of the white line, the parking type determining means determines that the length of the white line is greater than a threshold set in advance according to the size of the vehicle. The parking type is determined as parallel parking when it is short, and the parking type is determined as parallel parking when the length of the white line is longer than a preset threshold according to the size of the vehicle. 6. The parking assistance system according to 6. When the parking frame size calculating unit calculates the size of the parking frame using the interval between the intersections of two intersecting white lines, the parking type determining unit determines whether the interval between the intersections is in advance according to the size of the vehicle. When it is shorter than the set threshold, the parking type is determined as parallel parking, and when the interval between the intersections is longer than a preset threshold according to the size of the vehicle, the parking type is determined as parallel parking. The parking support system according to claim 6. The parking assistance system according to any one of claims 7 to 9, wherein the threshold is set to be larger than a width of the vehicle and smaller than a length of the vehicle. When the parking frame size calculation unit calculates the size of the parking frame using the interval between two arbitrarily selected white lines, the parking type determination unit determines that the white line interval is 4 according to the size of the vehicle in advance. Two threshold values (first threshold value, second threshold value, third threshold value, fourth threshold value) are set, and the magnitude relationship between the four threshold values is as follows: first threshold value <second threshold value <third threshold value <Set to the fourth threshold, first threshold <interval between two white lines <second threshold when the magnitude relationship of the second threshold is satisfied, the parking frame is determined to be parallel parking, and the third threshold <2 The parking assist system according to claim 6, wherein the parking frame is determined to be parallel parking when the white line interval <the fourth threshold value is satisfied. When the parking frame size calculating means calculates the size of the parking frame using an interval between two arbitrarily selected white lines, the two white lines are drawn substantially parallel to the road surface. The parking support system according to any one of claims 6, 7, and 11. When calculating the size of the parking frame using the length of the white line, the parking frame size calculating means is arranged on the side of the vehicle traveling direction and the direction opposite to the vehicle traveling method with respect to the selected white line. The parking support system according to claim 6 or 8, wherein a size is calculated by setting parking frames on both sides. When the parking frame size calculating means calculates the size of the parking frame using the interval between two arbitrarily selected white lines or the length of the white line, the white line has a predetermined angle with respect to the vehicle. The parking assistance system according to claim 6, wherein the parking assistance system is drawn on a road surface. The parking assistance system according to any one of claims 1 to 14, wherein the white line detection means detects a white line based on an image captured by a camera attached to the vehicle.

Images