Car wash machine

Abstract

To increase the processing speed of the car wash machine when guiding vehicles. [Solution] The car wash machine (2) comprises an imaging device (9) that captures an imaging area including a driving area on which a vehicle to be washed travels, and an information processing unit (70), wherein the information processing unit (70) includes a key point detection unit (72) that detects a plurality of object key points of an object in the image captured by the imaging device (9), and a reference line definition unit (74) that defines a reference line used to identify the position of the vehicle based on the plurality of detected object key points.

Description

[[Technical Field]]

[0001] The present disclosure relates to a car washer. [[Background Art]]

[0002] Patent Document 1 describes a car washing apparatus that detects positional deviation of a vehicle protruding from an appropriate stop range based on an image captured by a camera. In the car washing apparatus of Patent Document 1, contour extraction means extracts a contour of an object existing within a specific coordinate range in an image captured by the camera. Object identification means identifies, from among the contours extracted by the contour extraction means, the contour of a guide that functions as a position indicator when a vehicle to be washed approaches the appropriate stop range. Protrusion determination means determines left-right deviation of a vehicle stopping or traveling between rails (that is, protrusion from the appropriate stop range) based on whether the object identification means was able to identify the contour of the guide. [[Prior Art Literature]] [[Patent Literature]]

[0003] [[Patent Document 1]] Japanese Unexamined Patent Publication No. 2023-112770 [[Summary of the Invention]] [[Problem to be Solved by the Invention]]

[0004] However, in the car washing apparatus of Patent Document 1, it is necessary to perform processing for identifying the contour of the guide when guiding the vehicle. Therefore, it is conceivable that the processing speed of the car washing apparatus is reduced due to the large amount of information.

[0005] An object of an aspect of the present disclosure is to increase the processing speed of a car washer during vehicle guidance. [[Means for Solving the Problem]]

[0006] To solve the above problems, a car wash machine according to one aspect of the present disclosure comprises an imaging unit that images an imaging area including a driving area on which a vehicle to be washed travels, and an information processing unit, wherein the information processing unit includes a key point detection unit that detects a plurality of object key points of an object in the image captured by the imaging unit, and a reference line defining unit that defines a reference line used to identify the position of the vehicle based on the plurality of detected object key points. [Effects of the Invention]

[0007] According to one aspect of this disclosure, the processing speed of the car wash machine during vehicle guidance can be increased. [Brief explanation of the drawing]

[0008] [Figure 1] This diagram shows a schematic side view of the car wash machine body and remote panel, and a schematic front view of the car wash machine body, according to this embodiment. [Figure 2] This is a schematic diagram showing the main components of the car wash machine and a vehicle parked at the car wash position, as viewed from above. [Figure 3] This is a block diagram showing the main components of a car wash machine. [Figure 4] This figure shows exemplary images captured by the first and second imaging devices. [Figure 5] This figure shows exemplary images captured by the first and second imaging devices. [Figure 6] This figure shows exemplary images captured by the first and second imaging devices. [Figure 7] This flowchart shows an example of processing performed by the control unit. [Modes for carrying out the invention]

[0009] [Embodiment 1] A car wash machine according to one embodiment of this disclosure will be described in detail below.

[0010] <Overview of the car wash machine> This embodiment describes an exemplary car wash machine 2 that performs a car wash process to clean a vehicle. Figure 1 is a schematic diagram showing a schematic side view 2S of the car wash machine body 4 and remote panel 6, and a schematic front view 4F of the car wash machine body 4, which are included in the car wash machine 2 according to this embodiment. Figure 2 is a schematic diagram of the main parts of the car wash machine 2 and a vehicle X parked at the car wash position, which is the stopping position during car washing, as viewed from above. Figure 3 is a block diagram showing the main parts configuration of the car wash machine 2. Figures 4 to 6 show exemplary images IA and IB captured by the first imaging device 9L and the second imaging device 9R. For convenience of explanation, in the description of the car wash machine 2, the forward / backward direction, the up / down direction and the left / right direction are defined as indicated by the arrows in Figure 1, etc. The forward direction is the direction in which the vehicle X, which is the vehicle to be washed, is parked at the stopping position relative to the car wash machine body 4 which is located in the standby position.

[0011] As shown in Figure 1, the car wash machine 2 includes a car wash machine body 4 that travels in the forward and backward direction of the vehicle X, which is parked at a stopping position. The car wash machine 2 further includes a remote panel 6 that acquires the car wash conditions of the vehicle X by the car wash machine body 4. In the schematic side view 2S, the outline of the remote panel 6 is shown with a dotted line to indicate that the remote panel 6 is located further back from the vehicle X in the view of the paper.

[0012] As shown in the general front view 4F, the car wash machine body 4 comprises, for example, two frames 8 and a ceiling portion 10 connecting the upper ends of the two frames 8. The car wash machine body 4 has a structure that allows a vehicle X to pass through a space 4S enclosed by the frames 8 and the ceiling portion 10 along the vehicle X's entry direction DA, as shown in the general side view 2S. In this specification, the entry direction DA is the direction from the front 4A to the rear 4B of the car wash machine body 4, i.e., the front-to-rear direction. In this embodiment, the front 4A is, for example, the surface on which the operation panel 42, which will be described later, is provided.

[0013] As shown in Figure 2, an entry guide G is formed within the car wash area where the car wash machine body 4 is installed. The entry guide G is an example of an object on the ground. The entry guide G is formed on the ground within the car wash area and functions as a reference to indicate where and in which direction a vehicle X to be washed by the car wash machine body 4 should stop. In other words, the entry guide G serves as a guide for at least one of the direction or position of entry of the vehicle X to the car wash machine body 4. The entry guide G includes, for example, a right-side entry guide GR positioned to the right of the ideal stopping position of the vehicle X, and a left-side entry guide GL positioned to the left. In this embodiment, the entry guide G is composed of a plurality of road studs arranged at regular intervals in the front-rear direction. Figure 2 also shows the driving area Y1, which will be described later.

[0014] As shown in Figure 1, the car wash machine 2 may also be equipped with a first display device 45 that provides various instructions and / or displays to the driver. The first display device 45 may include, for example, a first display panel 45A installed on the car wash machine body 4 and a second display panel 45B installed behind the car wash machine body 4 and in a position visible to the driver of the vehicle X being washed. Alternatively, the car wash machine 2 may be equipped with either the first display panel 45A or the second display panel 45B. For example, the first display panel 45A may be installed on a movable part of the car wash machine body 4, such as the front of the top air blower nozzle 38. The car wash machine 2 may also be equipped with an audio output device 60 (see Figure 3) that outputs sound.

[0015] <Car wash machine body> The car wash machine body 4 travels in the longitudinal direction relative to the vehicle X. More specifically, the car wash machine body 4 has wheels 12 at the bottom of each of its frames 8, and rotates these wheels 12 by a drive unit (not shown), causing it to move relative to the vehicle X in the longitudinal direction along rails R arranged on the ground G. The rails R extend in the longitudinal direction. The direction of travel of the car wash machine body 4 is the longitudinal direction. While moving relative to the vehicle X, the car wash machine body 4 performs washing on the vehicle X in the space 4S.

[0016] The car washer body 4 comprises, as one of the cleaning parts, a plurality of brushes that slide on the vehicle X to perform brushing. For example, the brushes included in the car washer body 4 include a top brush 14, a side brush 16, and a rocker brush 18, each of which is rotated by a rotary motor (not shown). The top brush 14 slides along the top surface of the vehicle X to clean the top surface of the vehicle X. The side brush 16 and the rocker brush 18 clean both side surfaces of the vehicle X.

[0017] A tank storage portion 20 that stores a plurality of liquid storage tanks (not shown) storing various liquid agents including detergent, wax or the like is disposed on a side portion of the car washer body 4. Above the tank storage portion 20, a distribution piping portion 22 that distributes water including city water or the liquid agents from each liquid storage tank is provided. From the distribution piping portion 22, a plurality of nozzles detailed below are led out respectively via electromagnetic valves (not shown).

[0018] The plurality of nozzles include a first nozzle that injects a liquid containing city water or a cleaning liquid onto the vehicle X to clean the vehicle X, and a second nozzle that injects a coating agent containing a water-repellent coating agent or wax onto the vehicle X to form a coating film on the surface of the vehicle X.

[0019] The first nozzle includes a first purified water nozzle 24, a second purified water nozzle 26, a first detergent nozzle 28, and a second detergent nozzle 30. The first purified water nozzle 24 and the second purified water nozzle 26 are respectively disposed on the front surface 4A side and the rear surface 4B side of each frame 8 of the car washer body 4, and inject water including city water toward the vehicle X. The first detergent nozzle 28 and the second detergent nozzle 30 are respectively disposed on the front surface 4A side and the rear surface 4B side of each frame 8, and inject a cleaning liquid containing shampoo or the like toward the vehicle X.

[0020] The second nozzle includes a water-repellent coating nozzle 32 and a wax nozzle 34. The water-repellent coating nozzle 32 and the wax nozzle 34 are disposed on the rear surface 4B of the car washer body 4. The water-repellent coating nozzle 32 injects a liquid agent of the water-repellent coating agent toward the vehicle X. The wax nozzle 34 injects wax toward the vehicle X.

[0021] Furthermore, the car wash machine body 4 is equipped with a blower 36 that generates airflow to dry the vehicle X. The blower 36 is connected to a top air blower nozzle 38 and side air blower nozzles 40. The top air blower nozzle 38 is located at the top center of the car wash machine body 4 and blows air toward the ceiling surface of the vehicle X. The side air blower nozzles 40 are located on both sides of the car wash machine body 4 and blow air toward the sides of the vehicle X. The car wash machine body 4 dries the vehicle X after washing by the air blown by the top air blower nozzle 38 and the side air blower nozzles 40.

[0022] As shown in Figure 2, the car wash machine body 4 is equipped with an imaging device 9 that images an area including at least a portion of the driving area Y1. The imaging device 9 is an example of an imaging unit according to this disclosure. Here, the driving area Y1 is the area in which a vehicle X travels from a specific position to a stopping position. The specific position may be, for example, the position of an entrance gate that permits entry to the car wash, or the position in front of the remote panel 6 that handles car wash registration where the vehicle X stops. The driving area Y1 is located in front of the car wash machine body 4 in the standby position and is the area located between the right-side entry guide GR and the left-side entry guide GL in the left-right direction. After registering for car wash, the driver drives the vehicle X within the driving area Y1 and stops the vehicle X at the designated stopping position.

[0023] The imaging device 9 includes a first imaging device 9L located on the upper left side of the car wash machine body 4, and a second imaging device 9R located on the upper right side. The first imaging device 9L images the travel area Y1 from the left, and the second imaging device 9R images the travel area Y1 from the right. Here, reference numeral 400 in Figure 4 indicates image IA captured by the first imaging device 9L, and reference numeral 401 in Figure 4 indicates image IB captured by the second imaging device 9R. Images IA and IB shown in Figure 4 are images of a vehicle X traveling in the travel area Y1. As shown by reference numeral 400 in Figure 4, the first imaging device 9L images the right side of the vehicle X traveling in the travel area Y1, and as shown by reference numeral 401 in Figure 4, the second imaging device 9R images the left side of the vehicle X traveling in the travel area Y1.

[0024] The imaging area of ​​each imaging device 9L and 9R includes the entry guide G. The imaging area of ​​each imaging device 9L and 9R may also include the rail R. It is preferable that the mounting position and angle of both imaging devices 9L and 9R on the car wash machine body 4 are adjusted so that the portion of the vehicle X in contact with the ground is imaged.

[0025] Images IA and IB captured by the first imaging device 9L and the second imaging device 9R may be moving images or still images. Furthermore, moving images captured by the first imaging device 9L and the second imaging device 9R may include images composed of still images taken in succession at predetermined intervals.

[0026] In Figures 1 and 2, for the sake of simplicity, the illustrations of the various devices for washing the vehicle X provided by the car wash machine body 4, as described above, may be omitted. Furthermore, the devices provided by the car wash machine body 4 shown in Figure 1 are merely examples, and the car wash machine body 4 may also be equipped with devices for washing the vehicle X, including conventionally known configurations, and devices to assist in said washing, on the frame 8 or ceiling 10, in addition to the devices described above.

[0027] An operation panel 42 is located on the front of one frame 8 of the car wash machine body 4. The operation panel 42 is equipped with operation buttons (not shown) for setting car wash conditions. For example, a driver who has gotten out of vehicle X, or another technician, may operate the operation buttons to set car wash conditions, etc.

[0028] <Control unit and remote panel> The car wash machine 2 includes a car wash machine body 4 and a control unit 7 that controls each part of the car wash machine 2. For example, the control unit 7 controls the washing of the vehicle X by the car wash machine body 4 by controlling the movement of the car wash machine body 4 along the rail R and the operation of each part of the cleaning unit. As shown in Figure 3, the control unit 7 includes an information processing unit 70. The control unit 7 may also include a notification unit 80. The information processing unit 70 will be described later.

[0029] The control unit 7 may be located on the car wash machine body 4, as shown in Figure 1, or it may be located outside the car wash machine body 4. The control unit 7 may transmit and receive information between the car wash machine body 4 or the remote panel 6 (described later) using a communication device (not shown) or the like, and control the car wash machine body 4. The control unit 7 is composed of a processor such as a CPU, and each control is realized by executing a control program stored in memory on the processor. The control unit 7 is, for example, a controller that controls the car wash machine 2.

[0030] The remote panel 6 is located, for example, on the front side of the car wash machine body 4 and is positioned roughly in line with the direction of movement of the car wash machine body 4. Furthermore, as shown in Figure 1, the front of the remote panel 6 is positioned to face the side of the vehicle X before it is washed by the car wash machine body 4, in other words, before it enters the interior of the car wash machine body 4.

[0031] As shown in Figure 1, the remote panel 6 comprises a housing 46 and support columns 48 erected on the ground G to support the housing 46. The remote panel 6 may also include a second display device 46A, such as a touch panel, provided on the housing 46. The remote panel 6 may acquire at least a portion of the car wash conditions for the vehicle X by the car wash machine body 4 by tapping a button displayed on the second display device 46A (see Figure 3) or by pressing a button (not shown) provided on the housing 46. The control unit 7 may control the car wash machine body 4 and wash the vehicle X based on at least a portion of the car wash conditions acquired by the remote panel 6.

[0032] (Information Processing Department) As shown in Figure 3, the control unit 7 of this embodiment includes an information processing unit 70. The information processing unit 70 can be, for example, a CPU (Central Processing Unit), a GPU (Graphic Processing Unit), a microprocessor, a digital signal processor, a microcontroller, a TPU (Tensor Processing Unit), or a combination thereof.

[0033] The information processing unit 70 includes a keypoint detection unit 72 and a reference line definition unit 74. The information processing unit 70 may further include at least one of an image acquisition unit 71, a storage unit 73, a reference line definition unit 74 position identification unit 75, a position identification unit 75, and an operation control unit 77. The information processing unit 70 may use the learned models M1 and M2 stored in the storage unit 73 to execute various steps included in the processing by the control unit 7, which will be described later.

[0034] The image acquisition unit 71 acquires images IA and IB from the first imaging device 9L and the second imaging device 9R, respectively. The image acquisition unit 71 acquires images IA and IB, which are captured by the first imaging device 9L and the second imaging device 9R, respectively, and which include at least a portion of the travel area Y1.

[0035] The keypoint detection unit 72 detects multiple object keypoints GP of the object in the respective images IA and IB captured by the first imaging device 9L and the second imaging device 9R. The keypoint detection unit 72 detects characteristic points of the object as object keypoints GP. In each image IA and IB, the keypoint detection unit 72 detects multiple object keypoints GP necessary to define the no-go line BL. In this embodiment, the keypoint detection unit 72 detects object keypoints GP of the entry guide G, which is an object on the ground. The characteristic points of the entry guide G (object) detected by the keypoint detection unit 72 as object keypoints GP may be characteristic points selected by the operator of the car wash machine 2.

[0036] As shown in Figure 4, in this embodiment, the characteristic points of the entry guide G are the corners located behind each road stud constituting the entry guide G, and the corners located on the rail R side in the left-right direction. The key point detection unit 72 detects the rear corners, which are located on the rail R side in the left-right direction, as the target key point GP of the entry guide G. The key point detection unit 72 may also detect the corners of the entry guide G located in front as the target key point GP, or the corners of the entry guide G located on the travel area Y1 side in the left-right direction as the target key point GP. Furthermore, the key point detection unit 72 may also detect the center (center of gravity) of the entry guide G as the target key point GP.

[0037] The key point detection unit 72 detects at least two object key points GP of objects on the ground in each image IA, IB, and preferably three or more. That is, in each image IA, IB, it is essential for the key point detection unit 72 to detect two or more object key points GP in order to define the no-crossing line BL, and it is desirable to detect three or more. Furthermore, the spacing between multiple object key points GP detected by the key point detection unit 72 is preferably 500 mm or more. Furthermore, the spacing between multiple object key points GP detected by the key point detection unit 72 may be equal. Furthermore, the spacing between multiple object key points GP detected by the key point detection unit 72 does not have to be equal. If the spacing between object key points GP is not equal, for example, the spacing between object key points GP may widen or narrow as the vehicle approaches the stopping position. In this embodiment, the spacing between object key points GP corresponds to the spacing in the front-rear direction of the road studs acting as entry guides G.

[0038] The keypoint detection unit 72 detects object keypoints GP in each image IA and IB using a trained model M1 constructed by machine learning. In this disclosure, machine learning refers to the general process of automatically constructing detection algorithms based on data. Deep learning is a typical example of machine learning, but machine learning in this disclosure is not limited to deep learning. For example, machine learning in this disclosure may be supervised learning other than deep learning, unsupervised learning, or reinforcement learning.

[0039] Furthermore, in this disclosure, "trained model" refers to a general detection algorithm constructed using machine learning. A typical example of a trained model is a CNN (Convolutional Neural Network). While a network is one example, the trained models in this disclosure are not limited to those built using a CNN.

[0040] For example, the trained model M1 relating to this disclosure can be generated by supervised learning using training data that associates image data representing an image including at least a portion of the driving area, captured by an imaging device, with labels indicating the target object key point GP of the entry guide in the image. The trained model M1 is a model that takes an image including the driving area, captured by an imaging device, as input and outputs information indicating the target object key point GP of the entry guide in the image. The training data used to generate the trained model M1 may include a label indicating that what is captured by the imaging device is an "entry guide".

[0041] The keypoint detection unit 72 may detect a first vehicle keypoint FP of vehicle X and a second vehicle keypoint RP of vehicle X located behind the first vehicle keypoint FP in the images IA and IB, respectively, captured by the first imaging device 9L and the second imaging device 9R. The first vehicle keypoint FP and the second vehicle keypoint RP are characteristic points of vehicle X and are indices used to calculate the distance between them and the no-crossing line BL.

[0042] The first vehicle keypoint FP detected in image IA captured by the first imaging device 9L and the first vehicle keypoint FP detected in image IB captured by the second imaging device 9R may be feature points located symmetrically on both sides of the vehicle X. Similarly, the second vehicle keypoint RP detected in image IA captured by the first imaging device 9L and the second vehicle keypoint RP detected in image IB captured by the second imaging device 9R may be feature points located symmetrically on both sides of the vehicle X. That is, the vehicle centerline, which is the center of the vehicle X in the vehicle width direction, may be located at the intermediate position between the first vehicle keypoint FP located on the right side of the vehicle X and the first vehicle keypoint FP located on the left side, and at the intermediate position between the second vehicle keypoint RP located on the right side of the vehicle X and the second vehicle keypoint RP located on the left side. Furthermore, it is preferable that the first vehicle keypoint FP and the second vehicle keypoint RP are feature points on the lower side of the vehicle X.

[0043] Furthermore, the keypoint detection unit 72 may use the trained model M2 to detect the first vehicle keypoint FP and the second vehicle keypoint RP (see Figure 5) in each image IA, IB. The trained model M2 according to this disclosure can be generated by supervised learning using training data that associates image data representing an image including a vehicle, captured by the imaging device, with labels indicating the first vehicle keypoint FP and the second vehicle keypoint RP of the vehicle in the image. The trained model M2 is a model that takes an image including a vehicle to be washed, captured by the imaging device, as input and outputs information indicating the first vehicle keypoint FP and the second vehicle keypoint RP of the vehicle body in the image. The training data used to generate the trained model M2 may include a label indicating that what is captured by the imaging device is a "car".

[0044] In this embodiment, the first vehicle key point FP detected by the key point detection unit 72 is a characteristic point of the front tire of vehicle X, and the second vehicle key point RP detected by the key point detection unit 72 is a characteristic point of the rear tire of vehicle X. More specifically, the key point detection unit 72 detects the rotation axis (center of rotation) of the front tire of vehicle X as the first vehicle key point FP, and detects the rotation axis (center of rotation) of the rear tire of vehicle X as the second vehicle key point RP. The key point detection unit 72 may also detect the contact point where the front tire of vehicle X contacts the ground as the first vehicle key point FP, or the contact point where the rear tire of vehicle X contacts the ground as the second vehicle key point RP.

[0045] Furthermore, the key points detected by the key point detection unit 72 are not limited to the characteristic points of the tires of the vehicle X. The key point detection unit 72 may also detect characteristic points of the front of the vehicle body (for example, the front corner FE shown in Figure 6) or the front lamps (including headlights, small lights, and turn signals) as the first vehicle key point FP. The key point detection unit 72 may also detect characteristic points of the rear of the vehicle body (for example, the rear corner RE shown in Figure 6) as the second vehicle key point RP.

[0046] Furthermore, as shown in Figure 6, the keypoint detection unit 72 may also detect the front corner FE located at the front of the vehicle X and the rear corner RE located at the rear of the vehicle X in the images IA and IB, respectively, captured by the first imaging device 9L and the second imaging device 9R when the vehicle X is stopped at the stopping position. Here, reference numeral 600 in Figure 6 indicates the image IA captured by the first imaging device 9L, and reference numeral 601 in Figure 6 indicates the image IB captured by the second imaging device 9R. The images IA and IB shown in Figure 6 are images of the vehicle X when it is stopped at the stopping position.

[0047] The front corner FE is the part where the front of vehicle X connects to the side of vehicle X. The rear corner RE is the part where the rear of vehicle X connects to the side of vehicle X. In this embodiment, the key point detection unit 72 detects the lower end of the part where the front of vehicle X connects to the side of vehicle X as the front corner FE, and the lower end of the part where the rear of vehicle X connects to the side of vehicle X as the rear corner RE.

[0048] In this embodiment, the front corner FE and rear corner RE detected by the key point detection unit 72 when the vehicle X is stopped at the stopping position are not indicators used to calculate the distance between the key point and the no-crossing line BL, but rather indicators used to determine whether or not the vehicle X has crossed the no-crossing line BL.

[0049] As shown in Figure 3, the memory unit 73 stores various types of information. The memory unit 73 stores the trained model M1. The memory unit 73 may also store the trained model M2. For example, the memory unit 73 can be a random access memory, flash memory, or a hard disk drive.

[0050] The reference line definition section 74 defines the no-crossing line BL used to identify the position of vehicle X based on the multiple object key points GP detected. The no-crossing line BL is an example of a reference line. The no-crossing line BL is a virtual reference line extending in the front-rear direction. The no-crossing line BL is a virtual line defined to avoid contact between vehicle X and the moving car wash machine body 4 during car washing. The no-crossing line BL is a reference line used to detect the positional deviation of vehicle X relative to the center position of the travel area Y1 in the left-right direction. The no-crossing line BL is also a reference line used to determine whether or not a part of vehicle X is protruding into the area in which the car wash machine body 4 travels during car washing.

[0051] The reference line definition unit 74 defines a virtual boundary line BL extending in the front-to-back direction in each of the images IA and IB captured by the first imaging device 9L and the second imaging device 9R. For example, the reference line definition unit 74 defines a boundary line BL as a line passing through each of the multiple object keypoints GP detected in images IA and IB. Alternatively, the reference line definition unit 74 may define an approximate line calculated based on the multiple object keypoints GP as the boundary line BL. This approximate line can be represented by a straight line or a curve. The boundary line BL represented by the approximate line may be a line that does not pass through some of the multiple object keypoints GP detected.

[0052] The position identification unit 75 identifies the position of vehicle X based on the no-crossing line BL in each image IA and IB. For example, as shown in Figure 5, the position identification unit 75 calculates first distance data Af and Bf, which indicate the distance between the first vehicle key point FP and the no-crossing line BL, and second distance data Ar and Br, which indicate the distance between the second vehicle key point RP and the no-crossing line BL, in each image IA and IB. That is, in the image IA captured by the first imaging device 9L, the position identification unit 75 calculates first distance data Af, which indicates the distance between the first vehicle key point FP and the no-crossing line BL, and second distance data Ar, which indicates the distance between the second vehicle key point RP and the no-crossing line BL. In the image IB captured by the second imaging device 9R, the position identification unit 75 calculates first distance data Bf, which indicates the distance between the first vehicle key point FP and the no-crossing line BL, and second distance data Br, which indicates the distance between the second vehicle key point RP and the no-crossing line BL. Each distance data calculated by the positioning unit 75 is the distance in the left-right direction, that is, the direction perpendicular to the reference line BL. Each distance data calculated by the positioning unit 75 is measured, for example, by performing pixel processing on each image IA, IB. In this case, the distance between two points can be measured in pixels.

[0053] In this embodiment, the position identification unit 75 calculates the positional deviation degree Cf of the first vehicle key point FP and the positional deviation degree Cr of the second vehicle key point RP based on the calculated first distance data Af, Bf and second distance data Ar, Br. The positional deviation degree Cf is an index that indicates which side of the driving area Y1 the front of the vehicle X is closer to, left or right, within the driving area Y1, and the positional deviation degree Cr is an index that indicates which side of the driving area Y1 the rear of the vehicle X is closer to, left or right, within the driving area Y1. In this embodiment, the position identification unit 75 calculates the positional deviation degree Cf and the positional deviation degree Cr, respectively, based on the following equations 1 and 2. [Equation 1]...Positional deviation Cf = (First distance data Bf - First distance data Af) / (First distance data Bf + First distance data Af) [Equation 2]...Positional displacement Cr = (Second distance data Br - Second distance data Ar) / (Second distance data Br + Second distance data Ar)

[0054] The position identification unit 75 may determine whether or not the vehicle X has stopped at the stopping position. The position identification unit 75 may also determine, in the images IA and IB captured by the first imaging device 9L and the second imaging device 9R, respectively, whether or not at least one of the front corner FE and rear corner RE of the vehicle X, which is stopped at the stopping position as detected by the keypoint detection unit 72, exceeds the no-crossing line BL. When at least one of the front corner FE and rear corner RE exceeds the no-crossing line BL, a part of the vehicle X is located on the rail R side of the no-crossing line BL, that is, it is overflowing the running area Y1.

[0055] The operation control unit 77 controls the operation of the car wash machine 2. When the vehicle X is stopped at the stopping position, if at least one of the front corner FE and rear corner RE of the vehicle X, as detected by the key point detection unit 72, exceeds the no-go line BL, the operation control unit 77 controls the car wash machine body 4 not to move.

[0056] The notification unit 80 guides the vehicle X traveling in the driving area Y1 based on the first distance data Af, Bf between the first vehicle key point FP and the no-crossing line BL, and the second distance data Ar, Br between the second vehicle key point RP and the no-crossing line BL, which are calculated in the images IA, IB captured by the first imaging device 9L and the second imaging device 9R, respectively. The notification unit 80 notifies the driver of the vehicle X of at least one of the following: an instruction to correct the bias of the vehicle X in the driving area Y1, and an instruction to correct the tilt of the vehicle X. The bias of the vehicle X is the bias of the vehicle X in the left-right direction in the driving area Y1. The tilt of the vehicle X is the tilt of the vehicle X in the longitudinal direction relative to the longitudinal direction.

[0057] In this embodiment, the notification unit 80 guides the vehicle X so that the absolute values ​​of the position deviation degree Cf and the position deviation degree Cr calculated by the position identification unit 75 are minimized. Based on the position deviation degree Cf and the position deviation degree Cr, the notification unit 80 guides the vehicle X by displaying an instruction to correct the bias and / or tilt of the vehicle X on at least one of the first display device 45 and the second display device 46A. Alternatively, the notification unit 80 may guide the vehicle X by outputting an instruction to correct the bias and / or tilt of the vehicle X as an audio output from the audio output device 60.

[0058] Furthermore, if the operation of the car wash machine 2 is stopped by the operation control unit 77, the notification unit 80 may notify the manager of the car wash machine 2 that the operation of the car wash machine 2 has stopped.

[0059] (Processing flow by the control unit) The following describes the flow of various processes performed by the control unit 7 of the car wash machine 2, using Figure 7 as an example. Figure 7 is a flowchart showing an example of the processes performed by the control unit 7.

[0060] The control unit 7 initiates the car wash as requested by the remote panel 6 and stops the vehicle X at the designated stop. When a request to stop the vehicle at a designated location is received, the following process begins.

[0061] As shown in Figure 7, in step S1, the image acquisition unit 71 starts acquiring image data from the first imaging device 9L and the second imaging device 9R, respectively. Image data acquisition by the image acquisition unit 71 may be performed intermittently multiple times while the vehicle X is traveling in the travel area Y1. The interval between image data acquisitions can be set arbitrarily, and the processing in steps S4 to S8 described below may be performed for each image data acquired.

[0062] In step S2, the keypoint detection unit 72 detects multiple object keypoints GP in each image IA and IB. More specifically, in step S2, the keypoint detection unit 72 detects object keypoints GP of each road stud constituting the left-side entry guide GL in image IA, and detects object keypoints GP of each road stud constituting the right-side entry guide GR in image IB (see Figure 4).

[0063] In step S3, the reference line definition unit 74 defines the no-crossing line BL based on the multiple object key points GP detected in each image IA and IB. More specifically, in step S3, the reference line definition unit 74 defines the no-crossing line BL in image IA as the line passing through the object key point GP of each road stud that constitutes the left-side entry guide GL (see Figure 4, etc.). In addition, the reference line definition unit 74 defines the no-crossing line BL in image IB as the line passing through the object key point GP of each road stud that constitutes the right-side entry guide GR (see Figure 4, etc.).

[0064] In step S4, the keypoint detection unit 72 detects a first vehicle keypoint FP and a second vehicle keypoint RP of vehicle X in each image IA and IB. More specifically, in step S4, the keypoint detection unit 72 detects the rotation axis of the right front tire of vehicle X as the first vehicle keypoint FP and the rotation axis of the right rear tire of vehicle X as the second vehicle keypoint RP in image IA captured by the first imaging device 9L (see Figure 5). In step S4, the keypoint detection unit 72 detects the rotation axis of the left front tire of vehicle X as the first vehicle keypoint FP and the rotation axis of the left rear tire of vehicle X as the second vehicle keypoint RP in image IB captured by the second imaging device 9R (see Figure 5).

[0065] In step S5, the position identification unit 75 calculates first distance data Af and Bf, which indicate the distance between the first vehicle key point FP and the no-crossing line BL, and second distance data Ar and Br, which indicate the distance between the second vehicle key point RP and the no-crossing line BL, for each image IA and IB (see Figure 5).

[0066] In step S6, the position identification unit 75 calculates the position deviation degree Cf of the first vehicle key point FP and the position deviation degree Cr of the second vehicle key point RP based on the first distance data Af, Bf and second distance data Ar, Br calculated in step S5.

[0067] In step S7, the notification unit 80 guides the vehicle X. In step S7, the notification unit 80 guides the vehicle X so that the absolute values ​​of the positional deviation Cf and positional deviation Cr calculated in step S6 are minimized. In step S7, the notification unit 80 may display at least one of the following on at least one of the first display device 45 and the second display device 46A: an instruction to correct the bias of the vehicle X in the driving area Y1, and an instruction to correct the tilt of the vehicle X, or it may be output as an audio signal from the audio output device 60.

[0068] In step S8, the position identification unit 75 determines whether or not the vehicle X has stopped at the stopping position. If the position identification unit 75 determines in step S8 that the vehicle X has stopped at the stopping position (S8:YES), step S9 is executed. If the position identification unit 75 determines in step S8 that the vehicle X has not stopped at the stopping position (S8:NO), step S4 is executed again.

[0069] In step S9, the keypoint detection unit 72 detects the front corner FE and rear corner RE of the vehicle X in the images IA and IB, respectively, captured by the first imaging device 9L and the second imaging device 9R (see Figure 6).

[0070] In step S10, the position identification unit 75 determines whether at least one of the front corner FE and rear corner RE of the vehicle X detected in step S9 exceeds the no-crossing line BL in the respective images IA and IB captured by the first imaging device 9L and the second imaging device 9R. If the position identification unit 75 determines in step S10 that at least one of the front corner FE and rear corner RE of the vehicle X does not exceed the no-crossing line BL (S10: NO), then step S11 is executed. If the position identification unit 75 determines in step S10 that at least one of the front corner FE and rear corner RE of the vehicle X exceeds the no-crossing line BL (S10: YES), then step S12 is executed.

[0071] In step S11, the operation control unit 77 controls the operation of the car wash machine body 4 based on at least some of the car wash conditions acquired by the remote panel 6, and performs the washing of the vehicle X. After the execution of step S11 is completed, the series of processes shown in Figure 7 are terminated.

[0072] In step S12, the operation control unit 77 controls the car wash machine body 4 so that it does not move. More specifically, the operation control unit 77 controls a drive unit (not shown) that rotates the wheels 12 so that the car wash machine body 4 does not move.

[0073] In step S13, the notification unit 80 notifies the operator of the car wash machine 2 that the operation of the car wash machine 2 has stopped. In step S13, the notification unit 80 may display an indication that the operation of the car wash machine 2 has stopped on at least one of the first display device 45 and the second display device 46A, or it may output an audio message from the audio output device 60 indicating that the operation of the car wash machine 2 has stopped. After the execution of step 13 is completed, the series of processes shown in Figure 7 are terminated.

[0074] According to the car wash machine 2 described above, the no-go line BL is defined based on the target key point GP of the ground-based entry guide G. Therefore, it is possible to reduce the amount of information required to identify the position of vehicle X. This makes it possible to speed up the processing of the car wash machine 2 when guiding vehicle X.

[0075] (Other aspects) In the embodiment described above, the entry guide G is composed of multiple road studs, but it is not limited to this configuration. The entry guide G may be composed of a rail extending in the front-rear direction. In this case, the key point detection unit 72 detects multiple characteristic points of the rail as the entry guide G, which are then used as the object key point GP. If it is difficult to detect the object key point GP of the rail, a marker or the like may be attached to the rail. Alternatively, the entry guide G may be a marker attached to the ground, in which case the key point detection unit 72 may detect multiple characteristic points of the marker attached to the ground, which are then used as the object key point GP.

[0076] Furthermore, in the embodiment described above, the object on the ground that is the target of detection of the target key point GP by the key point detection unit 72 was the entry guide G, but the object is not limited to the entry guide G. The object may be, for example, a rail R installed on the ground. Moreover, the object is not limited to objects on the ground, but may be any object placed at a distance from the ground within the car wash area and included in the imaging area of ​​the imaging device 9.

[0077] Furthermore, although the above-described embodiment defines the first and second reference lines as the no-crossing line BL, the configuration is not limited to this. The first and second reference lines may be different reference lines. For example, the second reference line may be a reference line defined on the rail R side of the first reference line in the left-right direction.

[0078] Furthermore, although the above-described embodiment shows an example in which the car wash machine body 4 is equipped with a first imaging device 9L and a second imaging device 9R, the invention is not limited to this example. The first imaging device 9L and the second imaging device 9R may be installed independently of the car wash machine body 4, as long as they are in a position that can capture a desired imaging area. For example, the first imaging device 9L and the second imaging device 9R may be attached to each of a pair of support columns installed on both sides of the car wash machine body 4. The pair of support columns to which the first imaging device 9L and the second imaging device 9R are attached may be installed on the front side of the travel area Y1, that is, on the side of the remote panel 6. In this case, the first imaging device 9L may capture the travel area Y1 from the front left, that is, from the rear side of the vehicle X traveling in the travel area Y1, capturing the right side of the vehicle X. The second imaging device 9R may capture the travel area Y1 from the front right, that is, from the rear side of the vehicle X traveling in the travel area Y1, capturing the left side of the vehicle X. In this case, the key point detection unit 72 may also detect characteristic points of the rear lamps (including taillights, brake lights, reverse lights, and rear fog lights) as the second vehicle key point RP.

[0079] Furthermore, although the car wash machine 2 is configured to include multiple imaging devices 9 (first imaging device 9L and second imaging device 9R), it is not limited to this configuration. The car wash machine 2 may also be configured to include only one imaging device 9. In this case, the single imaging device 9 will image an area that includes at least a portion of the driving area Y1.

[0080] This disclosure is not limited to the embodiments described above, and various modifications are possible within the scope of the claims. Embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of this disclosure. [Explanation of symbols]

[0081] 2 car wash machine 4 Car wash machine body 7 Control Unit 9L First Imaging Device (First Imaging Unit) 9R Second Imaging Device (Second Imaging Unit) 70 Information Processing 72 Keypoint detection unit 74 Reference Line Regulation Section Y1 Driving Area

Claims

[Claim 1] A car wash machine comprising an imaging unit that captures an imaging area including the driving area in which the vehicle to be washed travels, and an information processing unit, The aforementioned information processing unit, The image captured by the imaging unit includes a keypoint detection unit that detects multiple keypoints of the object, A car wash machine having a reference line defining section that defines a reference line used to determine the position of the vehicle based on a plurality of object key points detected.

Images