JP2018103751A - Parking support device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a parking support device which has high flexibility on setting of a target parking position.SOLUTION: The parking support device comprises an image acquisition unit, a storage unit, a recognition unit, and a parking position calculation unit. The image acquisition unit acquires a photographed image in which a circumference of a vehicle is photographed. The storage unit stores a shape of a marker, and a positional relationship of a position of the marker and a target parking position. The recognition unit recognizes a marker which has a shape corresponding to the shape stored in the storage unit in the photographed image. The parking position calculation unit calculates the target parking position based on the position of the marker recognized by the recognition unit, and the positional relationship stored in the storage unit.SELECTED DRAWING: Figure 2

Description

  The present disclosure relates to a parking assistance device.

  Conventionally, the following parking assistance systems are known. The parking assistance system includes a marker with information and an in-vehicle parking assistance device. The marker with information is installed in the parking space. The marker with information holds parking space information and parking operable space information. Parking space information is information which shows the parking space on the basis of the position of the marker with information which holds it. The vehicle-mounted parking assistance device acquires parking space information and parking operable space information from the marker with information (see Patent Document 1).

JP 2010-186257 A

  In the technique described in Patent Document 1, the parking space is a space determined based on the installation position of the marker with information. For this reason, the degree of freedom in setting the position of the parking space is not necessarily high. The present disclosure provides a parking assistance device having a high degree of freedom regarding setting of a target parking position.

  One aspect of the present disclosure includes an image acquisition unit that acquires a captured image obtained by imaging the periphery of a vehicle, a storage unit that stores a positional relationship between the marker position and a target parking position, and the imaging In the image, a recognition unit for recognizing a marker having a form corresponding to the form stored in the storage unit, a position of the marker recognized by the recognition unit, and the positional relationship stored in the storage unit And a parking position calculation unit that calculates the target parking position.

  The parking assist device according to one aspect of the present disclosure stores the positional relationship between the marker position and the target parking position (hereinafter referred to as the positional relationship X) in the storage unit. And the parking assistance apparatus of 1 aspect of this indication calculates a target parking position based on the position of the marker recognized by the recognition unit, and the positional relationship X. FIG. Therefore, the target parking position can be changed by changing the positional relationship X stored in the storage unit. Therefore, according to the parking assistance device of one aspect of the present disclosure, the degree of freedom regarding the setting of the target parking position is high.

1 is a block diagram illustrating a configuration of a parking assistance device 1. FIG. 2 is a block diagram illustrating a functional configuration of the parking assist device 1. FIG. It is a flowchart showing the target parking position calculation process which the parking assistance apparatus 1 performs. It is a flowchart showing the marker recognition process which the parking assistance apparatus 1 performs. 5A is a plan view showing the configuration of the marker 49, and FIG. 5B is a cross-sectional view taken along the VB-VB cross section in FIG. 5A. 5 is a plan view showing an image search range 59. FIG. 7A to 7C are explanatory diagrams showing the positional relationship X between the marker 49 and the target parking position 61, respectively. 8A to 8C are explanatory diagrams showing the positional relationship X between the marker 49 and the target parking position 61, respectively. It is explanatory drawing showing the effect when the form of the two markers 49 differs from each other. It is a flowchart showing storage processing, such as an obstacle, which the parking assistance apparatus 1 performs. It is explanatory drawing showing the obstruction 67, the movement locus | trajectory 69, the marker 49, and the target parking position 61. FIG. It is a flowchart showing the target parking position calculation process which the parking assistance apparatus 1 performs. It is explanatory drawing showing the positional relationship X of one marker 49 and the target parking position 61. FIG. 4 is a plan view illustrating a configuration of a marker 49. FIG. 5 is a plan view showing an image search range 59. FIG. 5 is a plan view showing an image search range 59. FIG.

An embodiment of the present disclosure will be described with reference to the drawings.
<First Embodiment>
1. Configuration of Parking Support Device 1 The configuration of the parking support device 1 will be described with reference to FIGS. The parking assistance device 1 is an in-vehicle device mounted on a vehicle. Below, the vehicle carrying the parking assistance apparatus 1 is set as the own vehicle.

  The parking assistance device 1 is configured around a known microcomputer having a CPU 3 and a semiconductor memory (hereinafter referred to as a memory 5) such as a RAM, a ROM, and a flash memory. Various functions of the parking assistance device 1 are realized by the CPU 3 executing a program stored in a non-transitional physical recording medium. In this example, the memory 5 corresponds to a non-transitional tangible recording medium that stores a program. Also, by executing this program, a method corresponding to the program is executed. Note that the number of microcomputers constituting the parking assistance apparatus 1 may be one or plural.

  As shown in FIG. 2, the parking assist device 1 has a function configuration realized by the CPU 3 executing a program, as shown in FIG. 2, an image acquisition unit 7, a recognition unit 9, a parking position calculation unit 11, and an image conversion unit. 13, a predicted position calculation unit 15, a vehicle position acquisition unit 17, an input unit 19, a light projection instruction unit 21, an obstacle detection unit 23, a notification unit 25, and a movement locus calculation unit 27. .

  The method for realizing these elements constituting the parking assistance apparatus 1 is not limited to software, and some or all of the elements may be realized using one or a plurality of hardware. For example, when the above function is realized by an electronic circuit that is hardware, the electronic circuit may be realized by a digital circuit including a large number of logic circuits, an analog circuit, or a combination thereof.

  As shown in FIG. 1, the parking assistance device 1 is connected to other devices and the like via an in-vehicle network 29. The parking assistance apparatus 1 can acquire steering information, vehicle speed information, shift information, and the like from the in-vehicle network 29.

  In addition to the parking assist device 1, the own vehicle includes a camera 31, a sonar 33, a wireless transceiver 35, an input device 37, a GPS 39, and a lighting device 41. The camera 31 captures the surroundings of the vehicle and generates a captured image. The number of cameras 31 may be singular or plural.

  The sonar 33 detects an obstacle existing around the vehicle. The number of sonars 33 may be singular or plural. The wireless transceiver 35 performs wireless communication with the home lighting device 43. The home lighting device 43 is a lighting device installed outside the vehicle. The home lighting device 43 projects light around it. The home lighting device 43 corresponds to a light projecting device.

  The input device 37 receives an input operation of the driver of the own vehicle. The input device 37 includes a push button, and pressing the button corresponds to an input operation. The driver corresponds to the user. The GPS 39 acquires GPS information indicating the position of the own vehicle. The illuminating device 41 is attached to the own vehicle and projects light around the own vehicle. The illumination device 41 corresponds to a light projecting device. The display 45 and the speaker 47 are provided in the passenger compartment of the own vehicle.

2. Target parking position calculation process executed by the parking support apparatus 1 The target parking position calculation process executed by the parking support apparatus 1 will be described with reference to FIGS. In step 1 of FIG. 3, the vehicle position acquisition unit 17 acquires GPS information using the GPS 39.

In step 2, the vehicle position P ₁ represented by the acquired GPS information in the step 1 determines whether the home position P ₂ is within a predetermined range. Position P ₁ of the vehicle is, if the home position P ₂ is within a predetermined range the process proceeds to step 3, otherwise return to step 1. Position P ₂ of the home corresponding to the reference position. Position P ₂ of the home are stored in advance in the memory 5. The memory 5 corresponds to a storage unit.

  In step 3, the light projection instruction unit 21 instructs the home lighting device 43 to project light using the wireless transceiver 35. The home lighting device 43 performs projection according to the projection instruction and also performs answer back. The light projection instruction unit 21 also instructs the illumination device 41 to project light. The illuminating device 41 performs projection according to the projection instruction and also performs answer back.

  In step 4, the light projection instruction unit 21 determines whether or not there is an answer back from the home lighting device 43 and the lighting device 41. If there is an answer back from at least one of the home lighting device 43 and the lighting device 41, the process proceeds to step 5, and otherwise returns to step 3.

  In step 5, the image acquisition unit 7, the recognition unit 9, the image conversion unit 13, and the predicted position calculation unit 15 perform a marker recognition process for recognizing the first marker. As shown in FIGS. 5A and 5B, the marker 49 recognized by the marker recognition process is attached to the road surface 51.

  As shown in FIG. 5A, the marker 49 has a circular shape in plan view. The marker 49 includes an inner peripheral portion 53 that is black and an outer edge portion 55 that is white. The shape of the inner peripheral part 53 is circular. The diameter of the inner peripheral portion 53 is smaller than the diameter of the entire marker 49. The center of the inner peripheral portion 53 substantially coincides with the center of the entire marker 49. That is, in plan view, the outer periphery of the inner peripheral portion 53 and the outer periphery of the outer edge portion 55 form a concentric circle.

  As shown in FIG. 5B, the marker 49 projects upward from the road surface 51. The upper surface of the marker 49 is a protruding surface 52. A plane to which the protruding surface 52 belongs is referred to as a protruding plane 57. The protruding plane 57 is parallel to the road surface 51 and is above the road surface 51.

Two markers 49 are provided on the road surface 51. The distance R between the two markers 49 is constant, and the distance R is stored in the memory 5 in advance.
The marker recognition process will be described with reference to FIG. In step 11 of FIG. 4, the image acquisition unit 7 acquires a captured image using the camera 31. This captured image is an image of the surroundings of the vehicle.

In step 12, the image conversion unit 13 converts the captured image acquired in step 11 into a bird's-eye view image. This bird's-eye view image is a bird's-eye view image on the protruding plane 57.
In step 13, the recognition unit 9 extracts a marker from the bird's-eye view image converted in the previous step 12 (hereinafter referred to as the current frame). The marker is extracted as follows. The memory 5 stores a marker form in advance. The recognition unit 9 searches the entire current frame, and extracts a marker 49 corresponding to the marker form stored in the memory 5.

In step 14, the position of the marker 49 extracted from the bird's-eye image converted in the previous step 12 (hereinafter referred to as a past frame) is read from the memory 5.
In step 15, the predicted position calculation unit 15 calculates the amount and direction of movement of the vehicle from the time when the past frame is acquired to the time when the current frame is acquired. The predicted position calculation unit 15 uses the steering information, vehicle speed information, and the like acquired from the in-vehicle network 29 to calculate the amount and direction of movement of the host vehicle.

  In step 16, the predicted position calculation unit 15 calculates the predicted position of the marker. The predicted marker position is the predicted position of the marker 49 extracted in the past frame in the current frame. The predicted position calculation unit 15 calculates the predicted position of the marker from the position of the marker 49 read in step 14 and the movement amount and movement direction of the own vehicle calculated in step 15.

  In step 17, the recognition unit 9 determines whether or not the marker 49 extracted from the current frame in step 13 is within a predetermined range from the predicted position of the marker calculated in step 16. The predetermined range is a range in which the distance from the predicted position of the marker is within a predetermined threshold.

If the marker 49 extracted from the current frame is within a predetermined range from the predicted position of the marker, the process proceeds to step 18; otherwise, the process returns to step 11.
In step 18, the recognition unit 9 recognizes the marker 49 extracted in step 13 as the marker 49.

  Returning to FIG. 3, in step 6, the recognition unit 9 determines whether or not the marker 49 has been recognized in step 5. If the marker 49 can be recognized, the process proceeds to step 7; otherwise, the process returns to step 5.

  In step 7, the recognition unit 9 limits the range in which the second marker 49 is searched (hereinafter referred to as the image search range 59) in step 8 described later. As shown in FIG. 6, the image search range 59 is a band-shaped range having a width W and provided along the circumference of the distance R with the marker 49 recognized in the process of step 5 as the center. The image search range 59 corresponds to an area where other markers 49 are searched preferentially.

  In step 8, the image acquisition unit 7, the recognition unit 9, the image conversion unit 13, and the predicted position calculation unit 15 perform marker recognition processing for recognizing the second marker 49. The process of step 8 is basically the same as the process of step 5 described above. However, in the process of step 13, the second marker 49 is searched and extracted in the image search range 59 set in step 7.

  In step 9, the recognition unit 9 determines whether or not the second marker 49 has been recognized in step 8. If the second marker 49 can be recognized, the process proceeds to step 10; otherwise, the process returns to step 5.

In step 10, the parking position calculation unit 11 calculates the target parking position using the positions of the two markers 49 recognized in the processing of steps 5 and 8.
The positional relationship between the positions of the two markers 49 and the target parking position (hereinafter referred to as positional relationship X) is stored in the memory 5 in advance. The positional relationship X can be set as appropriate. Examples of the positional relationship X include those shown in FIGS. 7A to 7C and FIGS. 8A to 8C. In addition, 61 is a target parking position. 63 is the own vehicle.

The parking position calculation unit 11 calculates the target parking position 61 based on the positions of the two markers 49 recognized in the processing of steps 5 and 8 and the positional relationship X.
That is, two markers included in the positional relationship X with respect to the two markers 49 recognized in the processing of Steps 5 and 8 above are identified in the positional relationship between the markers and the form of each marker. . And the target parking position 61 matched with the position of two specified markers and the positional relationship X is calculated.

  The two markers 49 are preferably different in form. In this case, as shown in FIG. 9, the target parking position 61 is uniquely determined based on the position of the two markers 49 recognized in the processing of steps 5 and 8 and the positional relationship X, and the erroneous target parking position is determined. It can suppress calculating 65.

  In step 10, the position of the marker 49 can be determined as follows. First, the center of the inner peripheral portion 53 and the center of the entire marker 49 are calculated. Next, an internal dividing point between the center of the inner peripheral portion 53 and the center of the entire marker 49 is set as the position of the marker 49.

  In addition, the parking assistance apparatus 1 can assist the parking to the target parking position 61 by displaying the target parking position 61 on the display 45. In addition, a driving support device (not shown) mounted on the host vehicle can support parking at the target parking position 61.

3. Obstacle storage process executed by the parking support apparatus 1 The obstacle storage process executed by the parking support apparatus 1 will be described with reference to FIGS. This process is executed when the host vehicle parks at the target parking position.

  In step 21 of FIG. 10, the input unit 19 determines whether or not an input operation has been performed on the input device 37. The input operation is an operation of pressing a push button of the input device 37. If there is an input operation, the process proceeds to step 22; otherwise, the process returns to step 21.

In step 22, the obstacle detection unit 23 receives the detection coordinates of the sonar 33. The detection coordinates are coordinates representing the position of the obstacle detected by the sonar 33.
Steps 23 to 27 are the same as steps 5 to 9 described above.

  In step 28, the obstacle detection unit 23 determines whether or not the detection coordinates received in step 22 indicate the presence of an obstacle. If the detected coordinates indicate the presence of an obstacle, the process proceeds to step 29. Otherwise, the process proceeds to step 30.

  In step 29, the positional relationship between the marker and the obstacle is stored in the memory 5 based on the detection coordinates received in step 22 and the marker position recognized in steps 23 and 26.

  In step 30, the movement trajectory calculation unit 27 determines whether or not the own vehicle has moved from time T when the processing of step 30 was executed last time to the present time. If the host vehicle is moving, the process proceeds to step 31; otherwise, the process proceeds to step 33.

  In step 31, the movement trajectory calculation unit 27 calculates the movement trajectory of the host vehicle from the time T to the present time. If a movement locus before time T already exists, the movement locus newly calculated in step 31 is added to update the movement locus.

In step 32, the movement locus calculation unit 27 stores the movement locus calculated in step 31 in the memory 5.
In step 33, the vehicle position acquisition unit 17 determines whether or not parking at the target parking position 61 is completed. If the parking at the target parking position 61 is completed, the present process is terminated. Otherwise, the process returns to step 22.

  As a result of the above processing, the positional relationship between the marker 49 and the obstacle 67 (hereinafter referred to as the obstacle positional relationship) as shown in FIG. Further, the positional relationship between the marker 49 and the movement locus 69 of the host vehicle 63 until the parking is completed (hereinafter referred to as a movement locus position relationship) is stored in the memory 5. The parking assistance apparatus 1 can perform parking assistance using these.

  After performing the above processing, when the own vehicle 63 is parked at the target parking position 61, the sonar 33 is used to newly detect an obstacle (hereinafter referred to as a new detection processing). . The detection result of the new detection process may be different from the obstacle position relationship stored in the memory 5. In this case, the notification unit 25 performs notification using the display 45 and the speaker 47.

  As a case where the detection result of the new detection process is different from the obstacle positional relationship stored in the memory 5, there are a first case and a second case. The first case is a case where there is no obstacle at the position where the obstacle is newly detected by the new detection process in the obstacle position relationship stored in the memory 5. The second case is a case where an obstacle exists in the position of the obstacle stored in the memory 5 at a position where no obstacle has been detected in the new detection process.

  The notification unit 25 changes the notification mode in the first case and the second case. The notification mode in the first case is a mode that is more emphasized than the notification mode in the second case. As an emphasized aspect, it is possible to display a larger warning, a noticeable color warning, or the like on the display 45. Moreover, as an emphasized aspect, the aspect which makes the sound of the speaker 47 still louder is mentioned.

4). Effects of Parking Support Device 1 (1A) The parking support device 1 stores the positional relationship X in the memory 5. And the parking assistance apparatus 1 calculates the target parking position 61 based on the position of the marker 49 recognized by the recognition unit 9 and the positional relationship X. Therefore, if the positional relationship X stored in the memory 5 is changed, the target parking position 61 can be changed. Therefore, according to the parking assistance apparatus 1, the freedom degree regarding the setting of the target parking position 61 is high.

(1B) The parking assistance apparatus 1 recognizes the marker 49 in the bird's-eye view image. Therefore, the marker 49 can be recognized more accurately.
(1C) The marker 49 includes a projecting surface 52 that projects upward from the road surface 51. The bird's-eye image used for recognizing the marker 49 is a bird's-eye image on the protruding plane 57 to which the protruding surface 52 belongs. The parking assistance apparatus 1 calculates the predicted position of the marker 49 in the current frame from the position of the marker 49 in the past frame and the amount and direction of movement of the host vehicle. The recognition unit 9 recognizes the marker 49 in a range in which the distance from the predicted position is within a predetermined threshold in the bird's-eye view image.

  Therefore, it can be suppressed that noise is recognized as the marker 49. The reason is as follows. The noise on the road surface 51 moves irregularly with the passage of time in the bird's-eye view image on the protruding plane 57. For this reason, the noise is unlikely to exist in a range where the distance from the predicted position is within a predetermined threshold. As a result, it can be suppressed that noise is recognized as the marker 49.

  (1D) The parking assistance apparatus 1 stores the positional relationship X between the positions of the two markers 49 and the target parking position 61. The parking assistance device 1 calculates the target parking position 61 based on the recognized positions of the two markers 49 and the positional relationship X. Therefore, the target parking position 61 can be calculated more accurately.

  (1E) The parking support apparatus 1 is two markers included in the positional relationship X with respect to the two markers 49 recognized in the processing of Steps 5 and 8, and the positional relationship between the markers and the form of each marker Identify matches in. And the target parking position 61 matched with the position of two specified markers and the positional relationship X is calculated. Therefore, the target parking position 61 can be calculated more accurately.

  (1F) The parking assistance apparatus 1 stores the distance R between the two markers 49 in the memory 5. When the first marker 49 is recognized in step 5, the parking assistance device 1 sets the image search range 59 based on the distance R. The parking assistance device 1 searches for the second marker 49 in the image search range 59. Therefore, the second marker 49 can be searched efficiently.

(1G) the parking assist apparatus 1, on condition that the position P ₁ of the vehicle is within a predetermined range from the position P ₂ of the home, it recognizes the marker 49. Therefore, the marker 49 can be recognized only when the necessity is high.

  (1H) The parking assist device 1 can instruct the home lighting device 43 and the lighting device 41 to project light when shooting using the camera 31. As a result, an image with high brightness and contrast can be obtained.

  (1I) The parking assistance apparatus 1 can detect an obstacle 67 existing around the host vehicle 63. And the parking assistance apparatus 1 can memorize | store the positional relationship of the position of the marker 49 and the position of the obstruction 67. FIG. Thereby, parking assistance corresponding to the position of the obstacle 67 can be performed.

  (1J) The parking assistance apparatus 1 performs notification when the detection result of the new detection process is different from the obstacle positional relationship stored in the memory 5. As a result, it is possible to alert the driver to the obstacle 67 that has changed compared to the past.

  (1K) The parking assistance apparatus 1 varies the notification mode in the first case and the second case. As a result, the driver can understand the situation regarding the obstacle from the notification mode.

  (1L) The mode of notification performed by the parking assistance device 1 in the first case is a mode that is more emphasized than the mode of notification performed in the second case. The first case is more dangerous than the second case. The parking assistance apparatus 1 can perform an enhanced mode notification when the degree of danger is high.

(1M) The parking assistance apparatus 1 calculates the movement locus 69 of the own vehicle. And the parking assistance apparatus 1 memorize | stores the positional relationship of the position of the marker 49 and the movement locus | trajectory 69. FIG. As a result, parking assistance using the movement locus 69 can also be performed.
Second Embodiment
1. Differences from the First Embodiment Since the basic configuration of the second embodiment is the same as that of the first embodiment, the differences will be described below. Note that the same reference numerals as those in the first embodiment indicate the same configuration, and the preceding description is referred to.

In the first embodiment described above, the target parking position calculation process, the condition that the position P ₁ of the vehicle is within a predetermined range from the position P ₂ of the home to execute the subsequent processing. On the other hand, in the second embodiment, as shown in FIG. 12, the subsequent processing is executed on condition that an input operation has been performed on the input device 37. The process of steps 42 to 49 in FIG. 12 is the same as the process of steps 3 to 10 in the first embodiment.

2. Effects exhibited by the parking assist device 1 According to the second embodiment described in detail above, the effects (1A) to (1F) and (1H) to (1M) of the first embodiment described above are achieved, and the following effects are further achieved. Play.

(2A) The parking assist device 1 recognizes the marker 49 on the condition that the input device 37 has been input. Therefore, the marker 49 can be recognized only when the necessity is high.
<Other embodiments>
As mentioned above, although embodiment of this indication was described, this indication is not limited to the above-mentioned embodiment, and can carry out various modifications.

  (1) As shown in FIG. 13, the parking assist device 1 may recognize one marker 49. In this case, the positional relationship X is a positional relationship between the position of one marker 49 and the target parking position 61. The number of markers 49 recognized by the parking assistance device 1 and the number of markers 49 defined in the positional relationship X may be three or more.

  (2) As shown in FIG. 14, the marker 49 may have a form capable of identifying a specific direction. The inner peripheral portion 53 includes a convex portion 71 protruding to one side. The form of the marker 49 can identify a specific direction 73 based on the protruding direction of the convex portion 71.

  When the marker 49 has a form in which a specific direction 73 can be identified, when the image search range 59 is set in step 7, the image search range 59 can be set based on the specific direction 73. it can.

  For example, an image search range 59 shown in FIG. 15 can be set. The image search range 59 is a band-shaped range including the marker 49 and parallel to the specific direction 73. Note that the memory 5 stores in advance that the second marker 49 exists in a specific direction 73.

  Further, an image search range 59 shown in FIG. 16 can be set. The image search range 59 is a range centering on a point that exists in a specific direction 73 as viewed from the marker 49 and that has a distance R from the marker 49. Note that the memory 5 stores in advance that the second marker 49 exists in the position of the distance R from the marker 49 in the specific direction 73.

  (3) The marker 49 may be a road surface pattern. Examples of the road surface pattern include white lines, characters such as “stop”, and rhombuses indicating that a pedestrian crossing exists.

(4) The reason for executing the target parking position calculation process is that there is a condition that “the position P _{1 of the} vehicle is within a predetermined range from the position P _{2 of} the home” and “an input operation to the input device 37 has been performed. One of the above conditions may be satisfied. Alternatively, the trigger for executing the target parking position calculation process may be that both of the two conditions are satisfied.

  (5) A plurality of functions of one constituent element in the above embodiment may be realized by a plurality of constituent elements, or a single function of one constituent element may be realized by a plurality of constituent elements. . Further, a plurality of functions possessed by a plurality of constituent elements may be realized by one constituent element, or one function realized by a plurality of constituent elements may be realized by one constituent element. Moreover, you may abbreviate | omit a part of structure of the said embodiment. In addition, at least a part of the configuration of the above embodiment may be added to or replaced with the configuration of the other embodiment. In addition, all the aspects included in the technical idea specified from the wording described in the claims are embodiments of the present disclosure.

  (6) In addition to the parking assistance device described above, a system including the parking assistance device as a constituent element, a program for causing a computer to function as the parking assistance device, and a non-transitional actual record such as a semiconductor memory in which the program is recorded The present disclosure can also be realized in various forms such as a medium and a parking assistance device method.

DESCRIPTION OF SYMBOLS 1 ... Parking assistance apparatus, 3 ... CPU, 5 ... Memory, 7 ... Image acquisition unit, 9 ... Recognition unit, 11 ... Parking position calculation unit, 13 ... Image conversion unit, 15 ... Predicted position calculation unit, 17 ... Vehicle position acquisition Unit: 19 ... Input unit, 21 ... Light projection instruction unit, 23 ... Obstacle detection unit, 25 ... Notification unit, 27 ... Movement trajectory calculation unit, 29 ... In-vehicle network, 31 ... Camera, 33 ... Sonar, 35 ... Wireless transmission / reception 37, input device, 39 ... GPS, 41 ... lighting device, 43 ... home lighting device, 45 ... display, 47 ... speaker, 49 ... marker, 51 ... road surface, 52 ... projecting surface, 53 ... inner periphery, 55 ... outer edge part, 57 ... projecting plane, 59 ... image search range, 63 ... own vehicle, 67 ... obstacle, 69 ... movement trajectory, 71 ... convex part, 73 ... specific direction

Claims (15)

An image acquisition unit for acquiring captured images of the surroundings of the vehicle;
A storage unit storing the form of the marker and the positional relationship between the position of the marker and the target parking position;
A recognition unit for recognizing a marker having a form corresponding to the form stored in the storage unit in the captured image;
A parking position calculation unit that calculates the target parking position based on the position of the marker recognized by the recognition unit and the positional relationship stored in the storage unit;
A parking assistance device comprising: The parking assistance device according to claim 1,
An image conversion unit that converts the captured image into a bird's-eye view image;
The recognition unit is a parking assistance device configured to recognize a marker having a form corresponding to the form stored in the storage unit in the bird's-eye view image. The parking assistance device according to claim 2,
The marker includes a protruding surface protruding upward from the road surface,
The image conversion unit is configured to convert the captured image into the bird's-eye view image on a plane to which the protruding surface belongs,
A prediction position calculation unit that calculates a predicted position of the marker at the present time from the position of the marker in the past bird's-eye view image and the movement amount and movement direction of the vehicle;
The recognition unit is a parking assistance device configured to recognize the marker in a range in which the distance from the predicted position is within a predetermined threshold in the bird's-eye view image. It is the parking assistance device according to any one of claims 1 to 3,
The storage unit stores the positional relationship between two or more marker positions and the target parking position,
The parking position calculation unit is configured to calculate the target parking position based on the positions of the two or more markers recognized by the recognition unit and the positional relationship stored in the storage unit. apparatus. The parking assistance device according to claim 4,
The parking position calculation unit identifies two or more markers stored in the storage unit that match in the positional relationship between the markers and the form of each marker for the two or more markers recognized by the recognition unit. And the parking assistance apparatus comprised so that the said target parking position matched with the position of two or more specified said markers and the said positional relationship might be calculated. It is a parking assistance device according to claim 4 or 5,
Of the two or more markers in the positional relationship stored in the storage unit, at least some of the markers have a form capable of identifying a specific direction,
When the recognition unit recognizes the marker having a form capable of identifying the specific direction, an area for preferentially searching for the other marker among the two or more markers based on the specific direction. A parking assistance device configured to set. The parking assistance device according to any one of claims 4 to 6,
The storage unit further stores a distance between the two or more markers in the positional relationship,
When the recognition unit recognizes a part of the two or more markers in the positional relationship, the other unit of the two or more of the markers is based on the distance stored in the storage unit. The parking assistance apparatus comprised so that the area | region which preferentially searches for may be set. The parking assistance device according to any one of claims 1 to 7,
A vehicle position acquisition unit for acquiring the position of the vehicle;
The storage unit further stores a reference position of the vehicle;
The parking assist device configured to recognize the marker on a condition that the position of the vehicle acquired by the vehicle position acquisition unit is within a predetermined range from the reference position. The parking assistance device according to any one of claims 1 to 7,
An input unit that accepts user input is further provided.
The parking assist device configured to recognize the marker on condition that the input unit has the input. The parking assist device according to any one of claims 1 to 9,
The parking assistance apparatus further provided with the light projection instruction | indication unit which instruct | indicates light projection when acquiring the said picked-up image with respect to the light projection apparatus which projects around the said vehicle. It is the parking assistance device according to any one of claims 1 to 10,
An obstacle detection unit for detecting an obstacle present around the vehicle;
The storage unit further stores a positional relationship between the position of the marker and the position of the obstacle. The parking assistance device according to claim 11,
The parking assistance apparatus further provided with the alerting | reporting unit which alert | reports when the detection result of the obstacle by the said obstacle detection unit differs from the memory | storage of the said obstacle memorize | stored in the said memory | storage unit. The parking assist device according to claim 12,
In the first case where the obstacle is not stored in the position where the obstacle is detected by the obstacle detection unit, and in the position where the obstacle detection unit does not detect the obstacle, the storage unit is faulty. The parking assistance apparatus in which the mode of notification by the notification unit is different from that in the second case in which an object is stored. The parking assist device according to claim 13,
The parking assistance device according to the first aspect, wherein the notification mode is emphasized over the notification mode in the second case. The parking assistance device according to any one of claims 1 to 14,
A movement locus calculating unit for calculating a movement locus of the vehicle;
The storage unit is a parking assistance device that further stores a positional relationship between the position of the marker and the movement locus.

Images