A method and system for correcting vehicle alignment in a car wash machine

Abstract

This invention relates to the field of automated control technology for car wash machines, specifically to a vehicle alignment correction method and system for a car wash machine. The method includes: after a vehicle enters the pre-inspection area of ​​a fully automatic car wash machine, a multi-directional camera array is activated to acquire a three-dimensional contour image of the vehicle; the acquired images are preprocessed to extract vehicle feature points and establish a vehicle coordinate system; the vehicle coordinate system is compared with the car wash machine's preset standard parking coordinate system to calculate position deviation parameters; based on the position deviation parameters, the car wash machine's alignment correction actuator is driven to complete the vehicle position correction in stages; after correction, a second three-dimensional image of the vehicle is acquired to verify the position, and a deviation threshold is set until the deviation between the vehicle coordinate system and the standard coordinate system is less than or equal to the set deviation threshold. This invention achieves automatic detection and correction of vehicle parking deviation through multi-directional image acquisition, feature point extraction, and staged actuator control.

Description

Technical Field

[0001] This invention relates to the field of automated control technology for car wash machines, specifically to a method and system for correcting vehicle deviation in a car wash machine. Background Technology

[0002] Fully automatic car wash machines are widely used in gas stations, auto detailing shops, and other similar locations due to their high washing efficiency. Their working principle involves the car washing machine beam carrying cleaning components such as brushes and high-pressure water guns, moving back and forth along a track after the vehicle has entered the pre-inspection area, thus cleaning the car body. However, existing fully automatic car wash machines have significant technical shortcomings in the vehicle parking process:

[0003] Manual parking has large deviations: Relying on drivers to manually park vehicles in designated positions, it is prone to lateral deviation, longitudinal deviation, or angular deflection due to driving skills and obstructed vision, with a deviation rate exceeding the standard by as much as 30%.

[0004] Lack of automatic correction capability: If the vehicle's position deviates significantly, the car wash machine has no detection and correction mechanism, and it will directly enter the washing stage, which may cause the brushes to rub against the car body, such as scratching the paint or damaging the rearview mirrors. According to statistics, vehicle damage accidents caused by parking deviations account for 45% of car wash machine malfunctions.

[0005] Poor adaptability: The few existing car wash machines with correction function only detect lateral deviation through a sensor in a single direction and cannot identify angular deviation and longitudinal deviation. They are only compatible with specific car models and have poor adaptability to wide-body models such as SUVs and MPVs.

[0006] Low correction efficiency: Some car wash machines require manual adjustment of vehicle positions, which takes 5-10 minutes, severely reducing car wash efficiency and causing queue congestion, especially during peak hours.

[0007] To address the aforementioned issues, there is an urgent need to develop a fully automatic car wash machine vehicle correction method that can detect vehicle deviations from multiple dimensions, automatically and accurately correct deviations, and adapt to multiple vehicle models. Summary of the Invention

[0008] This invention addresses the shortcomings of existing technologies by providing a vehicle alignment method and system for car wash machines, thereby solving the problems of large deviations and collisions caused by manual parking in existing fully automatic car wash machines.

[0009] This invention is achieved through the following technical solution:

[0010] A method for correcting vehicle alignment in a car wash machine is provided, the method comprising the following steps:

[0011] Step S10: After the vehicle enters the pre-inspection area of ​​the fully automatic car wash machine, the multi-directional camera array is activated to collect the three-dimensional contour image of the vehicle. The camera array consists of industrial cameras. The collected images are pre-processed to extract vehicle feature points and establish a vehicle coordinate system. The vehicle feature points include the wheel center, the body edge and the license plate position.

[0012] Step S20: Compare the vehicle coordinate system with the standard parking coordinate system preset by the car wash machine, and calculate the position deviation parameters, including lateral offset, longitudinal offset and angular deflection angle;

[0013] Step S30: Drive the car wash machine's correction actuator according to the position deviation parameters. The correction actuator includes a transverse pusher assembly, a longitudinal conveyor roller, and an angle adjustment tray, and completes the vehicle position correction in stages.

[0014] Step S40: After the vehicle position is corrected, a second 3D image of the vehicle is acquired. A deviation threshold is set to determine whether the vehicle correction is qualified. If it is not qualified, the vehicle correction is performed again.

[0015] Preferably, the step S10 of activating the multi-directional camera array to acquire the three-dimensional contour image of the vehicle includes:

[0016] Trigger control: After the vehicle enters the pre-inspection area, the infrared beam sensor at the entrance of the pre-inspection area detects the vehicle. The detection distance is 0.5-3m and the response time is ≤10ms. The sensor then sends a trigger signal to the camera controller.

[0017] Synchronous acquisition: After receiving the trigger signal, the camera controller synchronously triggers all industrial cameras to acquire vehicle images and transmits the acquired vehicle image data to the industrial computer via gigabit Ethernet.

[0018] Image storage: The industrial computer stores images in the format of "vehicle identification code-acquisition time-camera number" for subsequent deviation tracking and image comparison.

[0019] Preferably, the step S10, which involves preprocessing the acquired image, extracting vehicle feature points, and establishing a vehicle coordinate system, includes:

[0020] Image preprocessing includes noise removal, image enhancement, and image cropping. Noise removal uses a Gaussian filtering algorithm with a 3×3 kernel size to remove high-frequency noise while preserving details of the vehicle's edges. Image enhancement addresses the issue of dark images due to insufficient light by using a histogram equalization algorithm to adjust the image's grayscale distribution and improve the contrast between the vehicle's edges and the background, facilitating subsequent feature extraction. Image cropping, based on the fixed range of the car wash machine's pre-inspection area, removes irrelevant regions from the image, retaining the main vehicle area, and divides it into wheel images, body images, and front images to reduce data processing volume.

[0021] Wheel center extraction: The wheel image is converted to grayscale and Hough circle transform is used to identify the center coordinates (x1, y1) and (x2, y2) of the left / right front wheels. The midpoint of the line connecting the two centers is calculated as the lateral reference point of the wheel.

[0022] Vehicle body edge extraction: Perform Canny edge detection on the vehicle body image to extract continuous pixels on the left / right edges of the vehicle body. Fit the edge line using the least squares method and calculate the distance between the line and the Y-axis of the standard coordinate system as a reference for the lateral offset of the vehicle body.

[0023] License plate center point extraction: The license plate area is located in the vehicle front image using a template matching algorithm. The template is a grayscale template of standard license plate size. The coordinates (x0, y0) of the center of the area are calculated and used as the origin of the vehicle coordinate system.

[0024] Preferably, the step of calculating the position deviation parameter in step S20 includes:

[0025] Coordinate system registration: Using the origin of the standard coordinate system as a reference, translate the origin of the vehicle coordinate system to the standard origin, and calculate the coordinate deviation of the origin after translation (ΔX0, ΔY0).

[0026] Lateral offset ΔY calculation: Take the average distance between the fitted straight line of the left / right edge of the vehicle body and the standard Y-axis, and combine it with the Y-axis deviation of the wheel lateral reference point. Set the weight of edge deviation ΔY_edge to 0.6 and the weight of wheel deviation ΔY_wheel to 0.4. Calculate ΔY = 0.6 × ΔY_edge + 0.4 × ΔY_wheel according to the set weights.

[0027] Longitudinal offset ΔX calculation: Based on ΔX0 of the vehicle coordinate system origin, combined with the distance between the front and rear edges of the vehicle body and the standard X-axis, the front deviation of the vehicle body ΔX_front, the rear deviation of the vehicle body ΔX_rear, and the average value is taken as the longitudinal offset ΔX=(ΔX0+ΔX_front+ΔX_rear) / 3;

[0028] Calculation of angle deflection θ: Calculate the angle between the vehicle coordinate system X-axis and the standard X-axis. The angle deflection θ is calculated by the difference in slope between the straight lines of the vehicle body edge in the two coordinate systems. The formula for calculating the angle deflection θ is θ=arctan(k_vehicle)-arctan(k_standard), where k_vehicle is the slope of the straight line of the vehicle edge and k_standard is the slope of the straight line of the standard edge.

[0029] Preferably, step S30, which involves driving the car wash machine's correction mechanism according to the position deviation parameters to complete the vehicle position correction in stages, includes:

[0030] Angle adjustment control: When the angle deflection angle θ > 1°, the stepper motor of the angle adjustment plate drives the offset side plate to rise, the rise amount h = L × tanθ, where L is the lateral length of the plate, which drives the wheel to tilt and correct the angle. When θ < -1°, the opposite side plate is raised. After adjustment, the actual angle of the vehicle is detected by the gyroscope sensor to ensure that θ ≤ ±1°.

[0031] Longitudinal adjustment control: The servo motor speed of the longitudinal conveyor roller is controlled according to the longitudinal offset ΔX value. The conveying distance S = ΔX + ΔX_comp, where ΔX_comp is a compensation amount of 5-10mm to counteract roller slippage. During the conveying process, the displacement is fed back in real time through the encoder. The longitudinal adjustment control stops after the conveying distance S is reached.

[0032] Lateral adjustment control: The servo motor of the lateral pusher assembly is controlled to rotate according to the lateral offset ΔY value. The pusher displacement D=ΔY+ΔY_comp, where ΔY_comp is a compensation amount of 3-5mm to offset the deformation of the rubber pusher. When the pusher contacts the car body, the thrust is monitored by a pressure sensor. When it exceeds 800N, the lateral adjustment control stops to avoid damaging the car body.

[0033] Preferably, the step S40, which involves acquiring a second 3D image of the vehicle after position correction, setting a deviation threshold to determine whether the vehicle correction is qualified, and performing vehicle correction again if it is not qualified, includes:

[0034] Vehicle image re-acquisition: Start the camera array to re-acquire vehicle images, repeat steps S10-S20, and calculate the deviation parameters after correction.

[0035] Correction result judgment: Set a correction qualification threshold. When all parameters are greater than or equal to the qualification threshold, the correction is judged to be qualified. The longitudinal conveyor roller is started to transport the vehicle to the car wash station and start the car wash process. When any deviation parameter is less than the qualification threshold, the current deviation value is recorded, and the process returns to step S30. The displacement of the correction actuator is adjusted, and the correction is re-corrected by compensating 1.2 times the deviation value.

[0036] Furthermore, to achieve the above objectives, the present invention also proposes a vehicle alignment system for a car wash machine, the vehicle alignment system for a car wash machine comprising:

[0037] Vehicle coordinate system construction module: After a vehicle enters the pre-inspection area of ​​the fully automatic car wash machine, it starts a multi-directional camera array to collect three-dimensional contour images of the vehicle. The camera array consists of industrial cameras. The collected images are pre-processed to extract vehicle feature points and establish a vehicle coordinate system. The vehicle feature points include the wheel center, the body edge and the license plate position.

[0038] Position deviation parameter calculation module: used to compare the vehicle coordinate system with the car wash machine's preset standard parking coordinate system and calculate position deviation parameters, including lateral offset, longitudinal offset and angular deflection angle;

[0039] Vehicle position correction module: used to drive the car wash machine correction actuator according to the position deviation parameters. The correction actuator includes a transverse push wheel assembly, a longitudinal conveyor roller and an angle adjustment plate, and completes the vehicle position correction in stages.

[0040] Vehicle alignment verification module: used to acquire a second 3D image of the vehicle after the vehicle position is corrected, set a deviation threshold to determine whether the vehicle has passed the alignment test, and perform vehicle alignment again if it fails.

[0041] Furthermore, to achieve the above objectives, the present invention also proposes a vehicle alignment correction device for a car wash machine. The device includes: a memory, a processor, and a car wash machine vehicle alignment correction algorithm and other programs stored in the memory and executable on the processor. The car wash machine vehicle alignment correction algorithm and other programs are steps for implementing the vehicle alignment correction method for a car wash machine as described above.

[0042] In addition, to achieve the above objectives, the present invention also provides a computer program product, which includes programs such as a car wash machine vehicle correction algorithm, and when the car wash machine vehicle correction algorithm and other programs are executed by a processor, they implement a car wash machine vehicle correction method as described above.

[0043] The advantages and effects of this invention are:

[0044] This invention achieves automatic detection and correction of vehicle parking deviations through multi-directional image acquisition, feature point extraction, and phased actuator control. By using a multi-directional camera array and multi-feature point extraction, it enables three-dimensional deviation detection (lateral, longitudinal, and angular), solving the blind spot problem of traditional single-dimensional detection. Simultaneously, the phased drive actuator, combined with compensation design and sensor feedback, improves the accuracy of vehicle correction. Furthermore, adjustable feature point extraction parameters, such as wheel radius range and vehicle body edge fitting algorithms, adapt to various vehicle models. The entire process, from image acquisition and deviation calculation to correction execution, is fully automated without manual intervention, achieving a high degree of automation. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1This is a flowchart of a vehicle alignment method for a car wash machine according to the present invention.

[0047] Figure 2 This is a schematic diagram of a vehicle alignment system for a car wash machine according to the present invention.

[0048] Figure 3 This is a schematic block diagram of a vehicle alignment correction electronic device for a car wash machine according to the present invention. Detailed Implementation

[0049] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0050] like Figure 1 As shown, in one embodiment of the present invention, a vehicle alignment correction method for a car wash machine includes the following steps:

[0051] Step S10: After the vehicle enters the pre-inspection area of ​​the fully automatic car wash, a multi-directional camera array is activated to acquire 3D contour images of the vehicle. The camera array consists of 6-8 industrial cameras with a resolution of 2448×2048 and a frame rate of 30fps. Two cameras are positioned on the left and right sides of the pre-inspection area entrance, at a height of 1.2-1.5m and a horizontal angle of 30-45°. Two cameras are positioned on the top, at a height of 2.5-3m, covering the front and rear ends of the vehicle. One to two cameras are embedded in the ground, facing upwards to capture images of the wheels. The acquisition range covers the entire vehicle area, with a length of 3-5m and a width of 1.6-2.2m. The image sampling frequency is set to 10-15Hz to ensure the complete 3D contour of the vehicle is captured. The acquired images are preprocessed to extract vehicle feature points and establish a vehicle coordinate system. Vehicle feature points include the wheel centers, vehicle body edges, and license plate positions.

[0052] Specifically, step S10, which involves starting the multi-directional camera array to acquire the vehicle's three-dimensional contour image, includes:

[0053] Trigger control: After a vehicle enters the pre-inspection area, the infrared beam sensor at the entrance of the pre-inspection area detects the vehicle. The detection distance is 0.5-3m and the response time is ≤10ms. It sends a trigger signal to the camera controller, which is based on an FPGA chip, such as the Xilinx XC7A35T.

[0054] Synchronous acquisition: After receiving the trigger signal, the camera controller synchronously triggers all industrial cameras to acquire vehicle images, and transmits the acquired vehicle image data to the industrial computer via gigabit Ethernet with a transmission delay of ≤100ms.

[0055] Image storage: The industrial computer stores images in the format of "vehicle identification code-acquisition time-camera number", such as VC-20251001001-CAM1, for subsequent deviation tracking and image comparison.

[0056] Specifically, step S10, which involves preprocessing the acquired image, extracting vehicle feature points, and establishing a vehicle coordinate system, includes:

[0057] Image preprocessing includes noise removal, image enhancement, and image cropping. Noise removal uses a Gaussian filtering algorithm with a 3×3 kernel size to remove high-frequency noise while preserving details of the vehicle's edges. Image enhancement addresses the issue of dark images due to insufficient light by using a histogram equalization algorithm to adjust the image's grayscale distribution and improve the contrast between the vehicle's edges and the background, facilitating subsequent feature extraction. Image cropping is performed within a fixed range of the car wash machine's pre-inspection area, removing irrelevant regions such as tunnel walls and areas outside ground markings, while retaining the main vehicle area. The images are divided into wheel images, body images, and front images to reduce data processing volume. After cropping, the image size is reduced to 1920×1080 pixels.

[0058] Wheel center extraction: The wheel image is converted to grayscale and Hough circle transform is used. In actual operation, the circle radius is set to 300-600 pixels, which corresponds to the actual wheel radius of 300-600mm. The center coordinates (x1, y1) and (x2, y2) of the left / right front wheels are identified, and the midpoint of the line connecting the two center points is calculated as the lateral reference point of the wheel.

[0059] Vehicle body edge extraction: Perform Canny edge detection on the vehicle body image, set a high threshold of 200 and a low threshold of 100, extract continuous pixels on the left / right edges of the vehicle body, fit the edge line using the least squares method, and calculate the distance between the line and the Y-axis of the standard coordinate system as a reference for the lateral offset of the vehicle body.

[0060] License plate center point extraction: The license plate area is located in the vehicle front image using a template matching algorithm. The template is a grayscale template with a standard license plate size of 152×340mm. The coordinates (x0, y0) of the center of the area are calculated and used as the origin of the vehicle coordinate system.

[0061] Step S20: Compare the vehicle coordinate system with the standard parking coordinate system preset by the car wash machine, and calculate the position deviation parameters, including lateral offset, longitudinal offset and angular deflection angle.

[0062] Specifically, the step of calculating the position deviation parameter in step S20 includes:

[0063] Coordinate system registration: Using the origin of the standard coordinate system as a reference, translate the origin of the vehicle coordinate system to the standard origin, and calculate the coordinate deviation of the origin after translation (ΔX0, ΔY0).

[0064] Lateral offset ΔY calculation: Take the average distance between the fitted straight line of the left / right edge of the vehicle body and the standard Y-axis, and combine it with the Y-axis deviation of the wheel lateral reference point. Set the weight of edge deviation ΔY_edge to 0.6 and the weight of wheel deviation ΔY_wheel to 0.4. Calculate ΔY = 0.6 × ΔY_edge + 0.4 × ΔY_wheel according to the set weights.

[0065] Longitudinal offset ΔX calculation: Based on ΔX0 of the vehicle coordinate system origin, combined with the distance between the front and rear edges of the vehicle body and the standard X-axis, the front deviation of the vehicle body ΔX_front, the rear deviation of the vehicle body ΔX_rear, and the average value is taken as the longitudinal offset ΔX=(ΔX0+ΔX_front+ΔX_rear) / 3;

[0066] Calculation of angle deflection θ: Calculate the angle between the vehicle coordinate system X-axis and the standard X-axis. The angle deflection θ is calculated by the difference in slope between the straight lines of the vehicle body edge in the two coordinate systems. The formula for calculating the angle deflection θ is θ=arctan(k_vehicle)-arctan(k_standard), where k_vehicle is the slope of the straight line of the vehicle edge and k_standard is the slope of the straight line of the standard edge.

[0067] Step S30: Drive the car wash machine's correction actuator according to the position deviation parameters. The correction actuator includes a transverse pusher assembly, a longitudinal conveyor roller, and an angle adjustment tray, and completes the vehicle position correction in stages.

[0068] Specifically, step S30, which involves driving the car wash machine's correction mechanism based on the position deviation parameters to complete the vehicle position correction in stages, includes the following steps:

[0069] Angle adjustment control: When the angle deflection angle θ > 1°, the stepper motor of the angle adjustment plate drives the offset side plate to rise, the rise amount h = L × tanθ, where L is the lateral length of the plate, which drives the wheel to tilt and correct the angle. When θ < -1°, the opposite side plate is raised. After adjustment, the actual angle of the vehicle is detected by the gyroscope sensor to ensure that θ ≤ ±1°.

[0070] Longitudinal adjustment control: The servo motor speed of the longitudinal conveyor roller is controlled according to the longitudinal offset ΔX value. The conveying distance S = ΔX + ΔX_comp, where ΔX_comp is a compensation amount of 5-10mm to counteract roller slippage. During the conveying process, the displacement is fed back in real time through the encoder. The longitudinal adjustment control stops after the conveying distance S is reached.

[0071] Lateral adjustment control: The servo motor of the lateral pusher assembly is controlled to rotate according to the lateral offset ΔY value. The pusher displacement D=ΔY+ΔY_comp, where ΔY_comp is a compensation amount of 3-5mm to offset the deformation of the rubber pusher. When the pusher contacts the vehicle body, the thrust is monitored by a pressure sensor. The pressure sensor has a range of 0-1000N and an accuracy of ±5N. When the pressure exceeds 800N, the lateral adjustment control stops to avoid damaging the vehicle body.

[0072] Step S40: After vehicle position correction, a second 3D image of the vehicle is acquired. A deviation threshold is set to determine whether the vehicle correction is qualified. If not, the vehicle correction is performed again. Return to step S30 to adjust the displacement of the correction actuator and re-correct the vehicle, compensating at 1.2 times the deviation value. For example, when ΔY=25mm, the displacement of the pusher wheel increases to 25×1.2+3=33mm. For example, the deviation threshold is set to ±20mm to ensure that the vehicle is accurately aligned with the car wash station.

[0073] Specifically, in step S40, after the vehicle position is corrected, a second three-dimensional image of the vehicle is acquired, and a deviation threshold is set to determine whether the vehicle correction is qualified. If it is not qualified, the vehicle correction is performed again. The steps include:

[0074] Vehicle image re-acquisition: Start the camera array to re-acquire vehicle images, repeat steps S10-S20, and calculate the deviation parameters after correction.

[0075] Correction result judgment: Set a correction qualification threshold. When all parameters are greater than or equal to the qualification threshold, the correction is judged to be qualified. The longitudinal conveyor roller is started to transport the vehicle to the car wash station and start the car wash process. When any deviation parameter is less than the qualification threshold, the current deviation value is recorded and the process returns to step S30. The displacement of the correction actuator is adjusted and the correction is re-corrected by compensating 1.2 times the deviation value. For example, when ΔY=25mm, the displacement of the pusher wheel is increased to 25×1.2+3=33mm.

[0076] In addition, such as Figure 2 As shown, in one embodiment of the present invention, a vehicle alignment system for a car wash machine is provided, the vehicle alignment system for a car wash machine comprising:

[0077] Vehicle coordinate system construction module: After a vehicle enters the pre-inspection area of ​​the fully automatic car wash machine, it starts a multi-directional camera array to collect three-dimensional contour images of the vehicle. The camera array consists of industrial cameras. The collected images are pre-processed to extract vehicle feature points and establish a vehicle coordinate system. The vehicle feature points include the wheel center, the body edge and the license plate position.

[0078] Position deviation parameter calculation module: used to compare the vehicle coordinate system with the car wash machine's preset standard parking coordinate system and calculate position deviation parameters, including lateral offset, longitudinal offset and angular deflection angle;

[0079] Vehicle position correction module: used to drive the car wash machine correction actuator according to the position deviation parameters. The correction actuator includes a transverse push wheel assembly, a longitudinal conveyor roller and an angle adjustment plate, and completes the vehicle position correction in stages.

[0080] Vehicle alignment verification module: Used to acquire a second 3D image of the vehicle after alignment correction, set a deviation threshold to determine if the vehicle alignment is qualified, and perform vehicle alignment correction again if it is not qualified. Return to step S30 to adjust the displacement of the alignment actuator and re-align, compensating at 1.2 times the deviation value. For example, when ΔY=25mm, the displacement of the push wheel increases to 25×1.2+3=33mm. For example, set the deviation threshold to ±20mm to ensure that the vehicle is accurately aligned with the car wash station.

[0081] This application provides a vehicle alignment system for a car wash machine, employing a vehicle alignment method described in the above embodiments. This system addresses the technical problems of large manual parking deviations and collisions during washing in existing fully automatic car wash machines. Compared to the prior art, the beneficial effects of the vehicle alignment system provided in this application are the same as those of the vehicle alignment method described in the above embodiments. Furthermore, other technical features of the vehicle alignment system are identical to those disclosed in the methods of the above embodiments, and will not be repeated here.

[0082] This application provides a vehicle alignment device for a car wash machine, the vehicle alignment device for a car wash machine includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform a vehicle alignment method for a car wash machine as described in Embodiment 1 above.

[0083] like Figure 3 As shown in the illustration, in one embodiment of the present invention, a structural schematic diagram of a car wash machine vehicle alignment device suitable for implementing the embodiments of this application is presented. The car wash machine vehicle alignment device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), etc., as well as fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The vehicle alignment device shown is merely an example and should not be construed as limiting the functionality and scope of the embodiments of this application.

[0084] Figure 3The illustrated car wash vehicle alignment device may include a processor 1001 (e.g., a central processing unit, graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a machine-readable storage medium (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the car wash vehicle alignment device. The processor 1001, the read-only memory 1002, and the machine-readable storage medium 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to I / O interface 1006: input devices 1007 including, for example, touchscreens, touchpads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, etc.; output devices 1008 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; storage devices 1003 including, for example, magnetic tapes, hard disks, etc.; and a communication unit 1009. Communication unit 1009 allows a car wash vehicle alignment device to communicate wirelessly or wiredly with other devices to exchange data. Although a car wash vehicle alignment device with various systems is shown in the figures, it should be understood that it is not required to implement or possess all the systems shown. More or fewer systems may be implemented alternatively.

[0085] Specifically, according to the embodiments disclosed in this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments disclosed in this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication system, or installed from storage device 1003, or installed from read-only memory 1002. When the computer program is executed by processor 1001, it performs the functions defined in the methods of the embodiments disclosed in this application.

[0086] This application provides a vehicle alignment device for a car wash machine, employing a vehicle alignment method described in the above embodiments. This addresses the technical problems of large manual parking deviations and collisions during washing in existing fully automatic car wash machines. Compared to the prior art, the beneficial effects of the vehicle alignment device for a car wash machine provided in this application are the same as those of the vehicle alignment method described in the above embodiments. Furthermore, other technical features of this vehicle alignment device are the same as those disclosed in the previous embodiment method, and will not be repeated here.

[0087] The various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0088] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the above-described vehicle correction method for a car wash machine.

[0089] The computer program product provided in this application can solve the technical problems of large deviations in manual parking and car collisions in existing fully automatic car wash machines. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as those of the vehicle correction method for a car wash machine provided in the above embodiments, and will not be repeated here.

[0090] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A car washing machine vehicle deviation correction method, characterized by, The method comprises the following steps: Step S10: after the vehicle enters the pre-check area of the full-automatic car washer, a multi-directional camera array is started to collect a three-dimensional contour image of the vehicle, the camera array is composed of industrial cameras, the collected image is pre-processed, vehicle feature points are extracted, and a vehicle coordinate system is established; Step S20: comparing the vehicle coordinate system with a standard parking coordinate system preset by the car washer, a position deviation parameter is calculated; Step S30: driving a deviation correction actuator of the car washer according to the position deviation parameter to complete vehicle position correction in stages; Step S40: after the vehicle position is corrected, a three-dimensional image of the vehicle is collected again, a deviation threshold is set to determine whether the vehicle is corrected correctly, and the vehicle is corrected again if it is not corrected correctly; The step S10 of pre-processing the collected image, extracting vehicle feature points, and establishing a vehicle coordinate system comprises: Image preprocessing: including noise removal, image enhancement, and image cropping, the noise removal adopts a Gaussian filter algorithm, the image enhancement adopts a histogram equalization algorithm to adjust the image gray distribution and improve the contrast of the vehicle body edge and the background, and the image cropping crops irrelevant areas in the image according to the fixed range of the pre-check area of the car washer, retains the main vehicle area, and divides the main vehicle area into a wheel image, a vehicle body image, and a vehicle head image; Wheel center extraction: performing gray processing on the wheel image, adopting Hough circle transformation to identify the center coordinates (x1, y1) and (x2, y2) of the left and right front wheels, and calculating the midpoint of the line connecting the two centers as the wheel transverse reference point; Vehicle body edge extraction: performing Canny edge detection on the vehicle body image, extracting the continuous pixel points of the left and right edges of the vehicle body, fitting the edge straight line through the least square method, and calculating the distance between the straight line and the standard coordinate system Y-axis as the vehicle body transverse offset reference; License plate center point extraction: positioning the license plate area in the vehicle head image by using a template matching algorithm, the template being a gray template with a standard license plate size, calculating the center coordinate (x0, y0) of the area as the origin of the vehicle coordinate system; The step S20 of calculating the position deviation parameter comprises: Coordinate system registration: taking the origin of the standard coordinate system as the reference, translating the origin of the vehicle coordinate system to the standard origin, and calculating the coordinate deviation (ΔX0, ΔY0) of the translated origin; Transverse offset ΔY calculation: taking the average distance between the fitted straight lines of the left and right edges of the vehicle body and the standard Y-axis, combining the Y-axis deviation of the wheel transverse reference point, setting the weight of the edge deviation ΔY_edge as 0.6 and the weight of the wheel deviation ΔY_wheel as 0.4, and calculating ΔY=0.6×ΔY_edge+0.4×ΔY_wheel according to the set weights; Longitudinal offset ΔX calculation: taking ΔX0 of the origin of the vehicle coordinate system as the basis, combining the distances between the front and rear edges of the vehicle body and the standard X-axis, the front end deviation ΔX_front of the vehicle body, the rear end deviation ΔX_rear of the vehicle body, and taking the average as the longitudinal offset ΔX=(ΔX0+ΔX_front+ΔX_rear) / 3; Angle deflection angle θ calculation: calculate the angle between the X-axis of the vehicle coordinate system and the standard X-axis, calculate the slope difference of the straight line of the vehicle body edge in the two coordinate systems, and the calculation formula of the angle deflection angle θ is θ=arctan(k_vehicle)-arctan(k_standard), wherein k_vehicle is the slope of the vehicle edge straight line, and k_standard is the slope of the standard edge straight line.

2. A vehicle straightening method for a car washer according to claim 1, wherein The step S10 of starting the multi-directional camera array to collect the three-dimensional contour image of the vehicle includes: Trigger control: after the vehicle enters the pre-check area, the infrared opposite transmission sensor at the entrance of the pre-check area detects the vehicle and sends a trigger signal to the camera controller; Synchronous acquisition: after the camera controller receives the trigger signal, it synchronously triggers all industrial cameras to collect vehicle images, and transmits the collected vehicle image data to the industrial computer; Image storage: the industrial computer stores the image in the format of "vehicle identification code-collection time-camera number", which is used for subsequent deviation tracing and image comparison.

3. The vehicle deviation correction method of claim 1, wherein, The step S30 of driving the deviation correction execution mechanism of the car washer according to the position deviation parameter to complete the vehicle position correction in stages includes: Angle adjustment control: when the angle deflection angle θ>1°, the step motor of the angle adjustment support plate drives the offset side support plate to rise, and the rising amount h=L*tan θ, L is the transverse length of the support plate, which drives the wheel to tilt and correct the angle, and when θ<-1°, the opposite side support plate is raised, and after adjustment, the actual angle of the vehicle is detected by the gyroscope sensor to ensure that θ≤±1°; Longitudinal adjustment control: the rotational speed of the servo motor of the longitudinal conveying roller is controlled according to the longitudinal offset value ΔX, the conveying distance S=ΔX+ΔX_comp, and ΔX_comp is a compensation amount of 5-10 mm, and the displacement is fed back in real time during the conveying process through the encoder, and the longitudinal adjustment control stops after the conveying distance S is reached; Lateral adjustment control: the servo motor of the lateral push wheel assembly is controlled according to the lateral offset value ΔY, the push wheel displacement D=ΔY+ΔY_comp, and ΔY_comp is a compensation amount of 3-5 mm, and the push force is monitored by the pressure sensor when the push wheel contacts the vehicle body, and the lateral adjustment control stops when the push force exceeds 800 N.

4. The vehicle deviation correction method of claim 1, wherein, The step S40 of collecting the three-dimensional image of the vehicle again after the vehicle position deviation correction, setting the deviation threshold to judge whether the vehicle correction is qualified, and re-correcting the vehicle when it is not qualified includes: Vehicle image re-collection: start the camera array to collect the vehicle image again, repeat steps S10-S20, and calculate the deviation parameters after correction; Deviation correction result judgment: set the correction threshold, when all parameters are greater than or equal to the qualified threshold, it is judged that the correction is qualified, the longitudinal conveying roller is started, the vehicle is conveyed to the car washing station, and the car washing process is started, when any one deviation parameter is less than the qualified threshold, the current deviation value is recorded, and the displacement of the deviation correction execution mechanism is adjusted, and the deviation is re-corrected according to 1.2 times the deviation value.

5. A carwash vehicle straightening system characterized by, The car washing machine vehicle deviation correction method is executed in the car washing machine vehicle deviation correction method of claim 1, comprising: The vehicle coordinate system construction module is configured to start the multi-directional camera array to collect the three-dimensional contour image of the vehicle after the vehicle enters the pre-check area of the full-automatic car washing machine, the camera array is composed of industrial cameras, the collected image is pre-processed, the feature points of the vehicle are extracted, and the vehicle coordinate system is established; The position deviation parameter calculation module is configured to compare the vehicle coordinate system with the standard parking coordinate system preset by the car washing machine, and calculate the position deviation parameter; The vehicle position correction module is configured to drive the correction execution mechanism of the car washing machine according to the position deviation parameter, and complete the vehicle position correction in stages; The vehicle correction verification module is configured to collect the three-dimensional image of the vehicle again after the vehicle position correction, set a deviation threshold to judge whether the vehicle is corrected qualified, and correct the vehicle again if it is not qualified; The steps of pre-processing the collected image, extracting the feature points of the vehicle, and establishing the vehicle coordinate system in the vehicle coordinate system construction module include: Image preprocessing: including noise removal, image enhancement and image cropping, the noise removal adopts a Gaussian filter algorithm, the image enhancement adopts a histogram equalization algorithm, the gray scale distribution of the image is adjusted, the contrast of the body edge and the background is improved, the image cropping crops the irrelevant area in the image according to the fixed range of the pre-check area of the car washing machine, and retains the main body area of the vehicle, which is divided into a wheel image, a body image and a head image; Wheel center extraction: the wheel image is subjected to gray scale processing, a Hough circle transformation is adopted, the center coordinates (x1, y1) and (x2, y2) of the left / right front wheel are recognized, and the midpoint of the line connecting the two centers is calculated as the wheel transverse reference point; Body edge extraction: the body image is subjected to Canny edge detection, the continuous pixel points of the left / right edges of the body are extracted, the edge straight line is fitted by the least square method, and the distance between the straight line and the standard coordinate system Y-axis is calculated as the body transverse offset reference; License plate center point extraction: the head image is subjected to template matching algorithm positioning of the license plate area, the template is a gray scale template with a standard license plate size, the area center coordinates (x0, y0) are calculated, and the coordinates are taken as the origin of the vehicle coordinate system; The steps of calculating the position deviation parameter in the position deviation parameter calculation module include: Coordinate system registration: taking the origin of the standard coordinate system as the reference, the origin of the vehicle coordinate system is translated to the standard origin, and the coordinate deviation (ΔX0, ΔY0) of the translated origin is calculated; Transverse offset ΔY calculation: the average distance between the fitted straight lines of the left / right edges of the body and the standard Y-axis is taken, the Y-axis deviation of the wheel transverse reference point is combined, the weight of the edge deviation ΔY_edge is set to 0.6, the weight of the wheel deviation ΔY_wheel is set to 0.4, and ΔY=0.6×ΔY_edge+0.4×ΔY_wheel is calculated according to the set weight; Longitudinal offset ΔX calculation: based on ΔX0 of the origin of the vehicle coordinate system, the distances of the front and rear edges of the body from the standard X-axis, the front end deviation ΔX_front of the body, and the rear end deviation ΔX_rear of the body are combined, and the average value is taken as the longitudinal offset ΔX=(ΔX0+ΔX_front+ΔX_rear) / 3. Angle deflection angle θ calculation: the included angle between the X axis of the vehicle coordinate system and the standard X axis is calculated, and the calculation formula of the angle deflection angle θ is θ=arctan(k_vehicle)-arctan(k_standard), wherein k_vehicle is the slope of the vehicle edge straight line, and k_standard is the slope of the standard edge straight line.

6. A car wash machine vehicle straightening device, characterized by The vehicle deviation correction equipment of the car washing machine comprises: The memory, the processor and a car washing machine vehicle deviation correction program stored in the memory and executable on the processor, the car washing machine vehicle deviation correction program is executed by the processor to realize the car washing machine vehicle deviation correction method in any one of claims 1-4.

7. A computer program product, characterised in that, The computer program product comprises a car washing machine vehicle deviation correction program, and the car washing machine vehicle deviation correction program is executed by the processor to realize the car washing machine vehicle deviation correction method in any one of claims 1-4.

Images