Wheel state identification method, device, water spray control method and device

Abstract

The present invention provides a wheel state recognition method, device, and water spray control method and device. The wheel state recognition method comprises: acquiring a vehicle image; detecting a front image of a wheel in the vehicle image; extracting a wheel profile in the front image; calculating a mud area within the wheel profile; and determining a wheel cleaning state according to the size of the mud area. Through the present invention, cleaning control can be performed to clean the wheel while reducing the waste of water resources.

Description

Technical Field

[0001] The present invention relates to the field of image recognition technology, and in particular to a wheel state recognition method and device, and a water spray control method and device. Background Art

[0002] At present, domestic air pollution is serious, among which construction site dust is one of the main causes of air pollution. Construction site dust pollution is unorganized particulate pollution generated during construction, including primary dust caused by various construction links inside the construction site, as well as secondary traffic dust caused by construction site trucks carrying mud on the road and construction site external roads.

[0003] In order to solve the above-mentioned secondary traffic dust, vehicle washing stations have been installed on construction sites in many cities. However, the problem of vehicles going on the road with mud cannot be avoided. On the one hand, the reason is that there is not enough time for vehicle washing. On the other hand, the reason is that supervision is not in place and vehicles go on the road directly without being washed.

[0004] In order to further solve the above problems, physical sensors are currently used to sense water spraying, that is, water spraying sensors are installed at the entrance and exit of the construction site. When a vehicle passes by, it will generate a certain weight, and the water spraying sensor will sense it and automatically spray water. However, different vehicles carry different mud, and the time of automatic water spraying is difficult to control. If a shorter water spraying time is uniformly set, some vehicles cannot be washed clean; if a longer water spraying time is uniformly set, it will lead to a waste of water resources.

[0005] Therefore, how to perform cleaning control to rinse the wheels clean while reducing the waste of water resources has become a technical problem that urgently needs to be solved in the field. Summary of the invention

[0006] The purpose of the present invention is to provide a wheel status identification method and device, and a water spray control method and device to solve the technical problems in the prior art.

[0007] On the one hand, to achieve the above objectives, the present invention provides a wheel state identification method.

[0008] The wheel state recognition method comprises: acquiring a vehicle image; detecting a front image of a wheel in the vehicle image; extracting a wheel contour in the front image; calculating a mud area within the wheel contour; and determining a wheel cleaning state according to the size of the mud area.

[0009] Furthermore, the step of detecting the front image of the wheel in the vehicle image includes: detecting the wheel image surrounding the wheel in the vehicle image; when the wheel image is larger than a preset image threshold and the aspect ratio of the wheel image satisfies a preset aspect ratio range, determining that the wheel image is the front image.

[0010] Furthermore, the step of extracting the wheel contour in the front image includes: detecting a circle in the front image by using a circle detection algorithm; and determining the wheel contour according to the circle when the size and center position of the circle meet tire parameters.

[0011] Furthermore, the step of calculating the soil area within the wheel contour includes: calculating the characteristic value distribution of the image characteristics of the wheel contour; and determining the soil area according to the characteristic value distribution and the image feature range corresponding to the soil.

[0012] Furthermore, the image features include HSV distribution and RGB values, and the step of determining the soil area according to the feature value distribution and the image feature range corresponding to the soil includes: determining the soil area according to the HSV value range and RGB value range corresponding to the soil, and the HSV distribution and RGB value of the wheel profile.

[0013] On the other hand, to achieve the above objective, the present invention provides a water spray control method.

[0014] The water spray control method comprises: using any one of the wheel state recognition methods provided by the present invention to identify the cleaning state of the wheel; and controlling a water spray switch for cleaning the wheel according to the cleaning state.

[0015] On the other hand, to achieve the above-mentioned purpose, the present invention provides a wheel status identification device.

[0016] The wheel state recognition device includes: an acquisition module for acquiring a vehicle image; a detection module for detecting a front image of a wheel in the vehicle image; an extraction module for extracting a wheel contour in the front image; a calculation module for calculating a soil area within the wheel contour; and a determination module for determining a cleaning state of the wheel according to the size of the soil area.

[0017] On the other hand, to achieve the above-mentioned purpose, the present invention provides a water spray control device.

[0018] The water spray control device comprises: an identification module, which is used to identify the cleaning state of the wheel by adopting any one of the wheel state identification methods provided by the present invention; and a control module, which is used to control the water spray switch for cleaning the wheel according to the cleaning state.

[0019] To achieve the above objectives, the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0020] To achieve the above object, the present invention also provides a computer-readable storage medium on which a computer program is stored, and the computer program implements the steps of the above method when executed by a processor.

[0021] The wheel state recognition method, device, water spray control method and device provided by the present invention, in the wheel cleaning control, obtain the vehicle image through the camera device, and detect the front image of the wheel therein, extract the wheel contour in the front image, and calculate the soil area within the wheel contour, and finally determine the wheel cleaning state according to the size of the soil area, and then determine whether to continue to clean the wheel according to the wheel cleaning state, thereby avoiding the waste of water resources while cleaning the wheel, and improving the accuracy of water spray control. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0023] Figure 1 A flowchart of a wheel state identification method provided in Embodiment 1 of the present invention;

[0024] Figure 2 A schematic effect diagram of a front view of a wheel provided in the first embodiment of the present invention;

[0025] Figure 3 This is a schematic effect diagram of the front image of a wheel provided in the first embodiment of the present invention.

[0026] Figure 4 A flow chart of a water spray control method provided in Embodiment 2 of the present invention;

[0027] Figure 5 A block diagram of a wheel state recognition device provided in Embodiment 3 of the present invention;

[0028] Figure 6 A block diagram of a water spray control device provided in Embodiment 4 of the present invention;

[0029] Figure 7 This is a hardware structure diagram of a computer device provided in Embodiment 5 of the present invention. DETAILED DESCRIPTION

[0030] In order to make the purpose, technical scheme and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0031] For vehicles leaving the construction site, in order to improve the accuracy of water spray control, so as to clean the wheels and avoid the waste of water resources, the present invention provides a wheel state recognition method, device, water spray control method and device, as well as computer equipment and readable storage medium. In the wheel state recognition method provided by the present invention, after obtaining the vehicle image, the front image of the wheel in the vehicle image is detected, and then the wheel contour in the front image is extracted, and the soil area within the wheel contour is calculated. Finally, the wheel cleaning state is determined according to the size of the soil area, and then the water spray switch for cleaning the wheel can be controlled according to the cleaning state, and water continues to be sprayed on the wheels that have not been cleaned, and water is stopped for the wheels that have been cleaned.

[0032] Specific embodiments of the wheel state identification method and device, water spray control method and device, computer equipment and readable storage medium provided by the present invention will be described in detail below.

[0033] Embodiment 1

[0034] Embodiment 1 of the present invention provides a wheel state recognition method, through which the wheel cleaning state can be automatically recognized, and then the water spray switch for cleaning the wheel can be controlled according to the recognized cleaning state. Specifically, Figure 1 This is a flow chart of a wheel status recognition method provided in Embodiment 1 of the present invention, as shown in FIG. Figure 1 As shown, the wheel state recognition method provided by this embodiment includes the following steps S101 to S105.

[0035] Step S101: Acquire a vehicle image.

[0036] Optionally, when the wheels are washed, the vehicle is parked at a fixed position, and a camera is set at the position to take pictures during the wheel washing process to obtain the vehicle image. Alternatively, a video of the vehicle can be shot in real time during the wheel washing process, and frame images therein can be extracted to obtain the vehicle image.

[0037] Step S102: Detect the front image of the wheel in the vehicle image.

[0038] Optionally, when taking a photo of a vehicle, the vehicle is parked at a fixed position each time, and the relative position relationship with the camera is fixed. In the obtained vehicle image, for the same vehicle type, the position and size of the front image of the wheel in the vehicle image are also fixed. Therefore, the position and size of the front image of the wheel corresponding to each vehicle type can be calculated in advance and stored corresponding to the vehicle type. When detecting the front image of the wheel in the vehicle image, first identify the vehicle type in the vehicle image, then obtain the position and size of the front image of the wheel corresponding to the vehicle type, and finally obtain the position and size of the front image of the wheel in the vehicle image. Figure 2 The schematic diagram of the camera setting position provided in the first embodiment of the present invention is as follows: Figure 2 As shown, in order to obtain a side image of the vehicle and further obtain a relatively complete and clear front image of the wheels, cameras are deployed on both sides of the front end of the car wash tank and on both sides of the rear end of the car wash tank.

[0039] Optionally, by performing feature analysis on the image, a portion of the vehicle image that meets the features of the front image of the wheel is extracted to obtain the front image of the wheel.

[0040] Optionally, a wheel detection algorithm can also be obtained through a machine learning model to detect the front image of the wheel. For example, a wheel detection algorithm is implemented using a yolov5 network to detect the front image of the wheel. Specifically, Figure 3 This is a schematic effect diagram of the front image of the wheel provided in the first embodiment of the present invention, such as Figure 3 As shown, the figure shows a front view of the wheel.

[0041] Step S103: extracting the wheel contour in the front image.

[0042] The extracted front image includes both the wheel part and the background part. Through this embodiment, the background part is distinguished from the wheel part, and the wheel contour is extracted therefrom. Optionally, a certain amount of vehicle images can be collected, and after the front image of the wheel in the vehicle image is detected, manual annotation is performed in the front image to annotate the wheel contour part, forming a training sample, and the neural network model is trained to obtain a neural network model that can extract the wheel contour from the front image. In the process of wheel state recognition, after the front image is input into the trained neural network model, the wheel contour can be extracted therefrom.

[0043] Optionally, the front image may be detected by using a Huffman circle detection algorithm to detect the best circle in the front image as the tire contour.

[0044] Step S104: Calculate the soil area within the wheel contour.

[0045] Optionally, a semantic segmentation network is used to calculate the soil area in the wheel contour. For example, the soil area in the wheel contour can be identified based on a UNET network.

[0046] Step S105: determining the wheel cleaning status according to the size of the mud area.

[0047] After obtaining the mud area, the ratio of the mud area to the wheel contour can be calculated to obtain the proportion of the mud. By comparing the proportion of the mud with the proportion threshold, the cleaning state of the wheel can be determined. For example, when the proportion of the mud is greater than the preset proportion threshold, the wheel is in an unclean state. When the proportion of the mud is less than or equal to the proportion threshold, the wheel is in a clean state. It should be noted that the wheel includes a tire part and a non-tire part (such as a wheel hub, etc.). In some scenes, the mud on the tire and the non-tire part show the same characteristics in the image. Therefore, the identified mud area includes the mud part on the tire and the non-tire part. For the non-tire part, its proportion in the wheel area is fixed. Therefore, the proportion threshold can be determined according to the proportion of the non-tire part. When the proportion of the mud is greater than the proportion threshold, it indicates that the mud area detected in the wheel area includes the non-tire part and the mud part, and the wheel is not cleaned. When the proportion of the mud is less than or equal to the above proportion threshold, it indicates that the mud area detected in the wheel area only includes the wheel part and the wheel has been cleaned.

[0048] Optionally, a camera can be installed at the water spraying position. During the wheel cleaning process, the camera captures the vehicle image every certain period of time, and the wheel cleaning status is determined after processing. If it is determined to be clean, the cleaning process of the current vehicle wheel is ended and the vehicle is released. If it is determined to be not clean, the water spray device can continue to be controlled to spray water until it is clean, and an alarm event is generated. Alternatively, the camera can be installed at the exit of the workplace to determine the cleaning status of the vehicle. If it is determined to be not clean, an alarm can be issued to prevent the vehicle from taking mud on the road and polluting the environment.

[0049] By adopting the wheel state recognition method provided in this embodiment, in the wheel cleaning control, the vehicle image is obtained by a camera device, and the front image of the wheel is detected, the wheel contour is extracted from the front image, and the soil area within the wheel contour is calculated. Finally, the cleaning state of the wheel can be determined according to the size of the soil area, and then it can be determined whether to continue cleaning the wheel according to the cleaning state of the wheel. At the same time, the wheel can be cleaned and the waste of water resources can be avoided, thereby improving the accuracy of water spray control.

[0050] Optionally, in one embodiment, the step of detecting the front image of the wheel in the vehicle image includes: detecting the wheel image surrounding the wheel in the vehicle image; when the wheel image is larger than a preset image threshold and the aspect ratio of the wheel image satisfies a preset aspect ratio range, determining that the wheel image is the front image.

[0051] Specifically, a large number of vehicle images can be obtained at one time. When detecting the front image of the wheel in the vehicle image, the wheel image surrounding the wheel, that is, the bounding box of the wheel, is first detected in the vehicle image, and then the detected wheel image is filtered to filter out wheel images that are too small (that is, the wheel image is less than or equal to a preset image threshold) and wheel images with a large difference in length and width (determined by the relationship between the aspect ratio of the wheel image and a preset aspect ratio range). The remaining wheel images with suitable size and moderate length and width difference are the front images of the wheel.

[0052] The wheel status recognition method provided in this embodiment is used to filter the detected wheel images, filter out wheel images that are too small or have large differences in length and width, and use front images with appropriate size, length and width for processing, thereby improving the accuracy of wheel contour extraction and thus improving the accuracy of wheel cleaning status recognition.

[0053] Optionally, in one embodiment, the step of extracting the wheel contour in the front image includes: detecting a circle in the front image by using a circle detection algorithm; when the size and center position of the circle meet tire parameters, determining the wheel contour based on the circle.

[0054] Specifically, in the front image, the wheel outline is basically a circle. At the same time, other structures on the wheel, such as the wheel hub or the pattern of the wheel tire, are also basically circles. Therefore, through the circle detection algorithm, the circles representing the wheel outline and other structures on the wheel can be detected, and these circles are identified by the size and center position of the circle. The circle that meets the size and center position of the circle represented by the wheel outline is extracted to determine the wheel outline. Further optionally, the wheel outline can be found through Hoffman circle detection. Hoffman circle detection may detect multiple circles, and the most suitable circle is screened out by the radius length and center position to determine the wheel outline.

[0055] The wheel state recognition method provided in this embodiment is used to detect circles in the front image through a circle detection algorithm, and the size and center position of the circle are set as conditions based on the characteristics of the wheel contour. The detected circles are screened, and the circle that represents the wheel contour is found to determine the wheel contour, thereby improving the accuracy of wheel contour extraction and thus improving the accuracy of wheel cleaning state recognition.

[0056] Optionally, in one embodiment, the step of calculating the soil area within the wheel profile includes: calculating the characteristic value distribution of the image features of the wheel profile; and determining the soil area according to the characteristic value distribution and the image feature range corresponding to the soil.

[0057] Specifically, when calculating the soil area within the wheel contour, the wheel contour is subjected to feature analysis, and image features that can distinguish between soil and non-soil within the wheel contour are calculated to obtain the eigenvalue distribution corresponding to the wheel contour. In the eigenvalue distribution, the image feature range corresponding to the soil is found, and the area distributed in this range is also the soil area.

[0058] The wheel state recognition method provided in this embodiment is used to quickly calculate the soil area by analyzing the distribution of the characteristic values ​​of the wheel profile, with less calculation. At the same time, based on the changes in the soil image features, different image feature ranges can be used to determine the soil area, which can meet different construction scenarios. Different sites only need to modify the image feature range corresponding to the soil, and the modification method is simple.

[0059] Optionally, in one embodiment, the image features include HSV distribution and RGB values, and the step of determining the soil area according to the feature value distribution and the image feature range corresponding to the soil includes: determining the soil area according to the HSV value range and RGB value range corresponding to the soil, and the HSV distribution and RGB value of the wheel profile.

[0060] Specifically, when calculating the characteristic value distribution of the image features of the wheel profile, the selected image features include (H, S, V, R, G, B). By analyzing the characteristic value range of the soil, the HSV value range and RGB value range corresponding to the soil are designed to determine the soil area and then judge the cleaning status of the wheel. For example, after analysis, the characteristic value range of a certain soil is V mean>150 and R mean greater than 100, while the characteristic value range of clean tire rubber is V mean<150 and R mean less than 50.

[0061] By adopting the wheel status recognition method provided in this embodiment, the HSV value range and RGB value range corresponding to the soil are determined through H, S, V, R, G, and B, so as to accurately determine the soil area, thereby improving the accuracy of wheel cleaning status recognition.

[0062] Embodiment 2

[0063] Embodiment 2 of the present invention provides a water spray control method, through which the wheel cleaning state can be automatically identified, and then the water spray switch for cleaning the wheel can be controlled according to the identified cleaning state. Specifically, Figure 4 This is a flow chart of a water spray control method provided in Embodiment 2 of the present invention, such as Figure 4As shown, the wheel state recognition method provided by this embodiment includes the following steps S201 to S202.

[0064] Step S201: Identify the cleaning status of the wheel.

[0065] Specifically, any one of the wheel status recognition methods provided in the first embodiment may be used for recognition, which will not be described in detail in this embodiment.

[0066] Step S202: Controlling a water spray switch for cleaning the wheel according to the cleaning state.

[0067] Specifically, the water spray switch can be controlled to spray water at predetermined time intervals, and in each interval when the water spraying is stopped, the above step S201 is used to identify the cleaning status of the wheel. When the cleaning status is that the wheel has been cleaned, the cleaning process is ended. When the cleaning status is that the wheel has not been cleaned, the water spraying cleaning continues.

[0068] Embodiment 3

[0069] Corresponding to the above-mentioned embodiment 1, embodiment 3 of the present invention provides a wheel state recognition device. The corresponding technical feature details and corresponding technical effects can be referred to the above-mentioned embodiment 1, and will not be repeated in this embodiment. Figure 5 A block diagram of a wheel state recognition device provided in Embodiment 3 of the present invention, such as Figure 5 As shown, the device includes an acquisition module 301 , a detection module 302 , an extraction module 303 , a calculation module 304 and a determination module 305 .

[0070] Among them, the acquisition module 301 is used to acquire the vehicle image; the detection module 302 is used to detect the front image of the wheel in the vehicle image; the extraction module 303 is used to extract the wheel contour in the front image; the calculation module 304 is used to calculate the soil area within the wheel contour; the determination module 305 is used to determine the cleaning status of the wheel according to the size of the soil area.

[0071] Optionally, in one embodiment, the detection module 302 includes: a first detection unit, used to detect a wheel image surrounding the wheel in the vehicle image; and a first determination unit, used to determine that the wheel image is the front image when the wheel image is larger than a preset image threshold and the aspect ratio of the wheel image satisfies a preset aspect ratio range.

[0072] Optionally, in one embodiment, the extraction module 303 includes: a second detection unit, used to detect a circle in the front image through a circle detection algorithm; and a second determination unit, used to determine the wheel profile according to the circle when the size and center position of the circle meet the tire parameters.

[0073] Optionally, in one embodiment, the calculation module 304 includes: a first calculation unit, used to calculate the characteristic value distribution of the image characteristics of the wheel profile; and a third determination unit, used to determine the soil area according to the characteristic value distribution and the image feature range corresponding to the soil.

[0074] Optionally, in one embodiment, the image features include HSV distribution and RGB values. When the third determination unit determines the soil area based on the feature value distribution and the image feature range corresponding to the soil, the specific steps performed include: determining the soil area based on the HSV value range and RGB value range corresponding to the soil, and the HSV distribution and RGB value of the wheel profile.

[0075] Embodiment 4

[0076] Corresponding to the above-mentioned embodiment 2, embodiment 4 of the present invention provides a water spray control device. The corresponding technical feature details and corresponding technical effects can be referred to the above-mentioned embodiment 2, and will not be repeated in this embodiment. Figure 6 A block diagram of a water spray control device provided in Embodiment 4 of the present invention, such as Figure 6 As shown, the device includes an identification module 401 and a control module 402 .

[0077] The identification module 401 is used to identify the wheel cleaning state; and the control module 402 is used to control the water spray switch for cleaning the wheel according to the cleaning state. Specifically, the identification module 401 is used to perform identification using the steps provided by any one of the wheel state identification methods provided in the first embodiment above, which will not be described in detail in this embodiment.

[0078] Embodiment 5

[0079] This fifth embodiment also provides a computer device, such as a smart phone, tablet computer, laptop computer, desktop computer, rack server, blade server, tower server or cabinet server (including an independent server or a server cluster composed of multiple servers) that can execute programs. Figure 7 As shown, the computer device 01 of this embodiment includes at least but is not limited to: a memory 011 and a processor 012 which can be interconnected through a system bus. Figure 7 It should be pointed out that Figure 7 Only a computer device 01 having components memory 011 and processor 012 is shown, but it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0080] In this embodiment, the memory 011 (i.e., readable storage medium) includes flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 011 can be an internal storage unit of the computer device 01, such as a hard disk or memory of the computer device 01. In other embodiments, the memory 011 can also be an external storage device of the computer device 01, such as a plug-in hard disk equipped on the computer device 01, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card, etc. Of course, the memory 011 can also include both the internal storage unit of the computer device 01 and its external storage device. In this embodiment, the memory 011 is generally used to store the operating system and various application software installed on the computer device 01, such as the wheel state recognition device of the third embodiment, or the program code of the water spray control device of the fourth embodiment. In addition, the memory 011 can also be used to temporarily store various types of data that have been output or are to be output.

[0081] In some embodiments, the processor 012 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips. The processor 012 is generally used to control the overall operation of the computer device 01. In this embodiment, the processor 012 is used to run the program code stored in the memory 011 or process data, such as the wheel state recognition method, the water spray control method, etc.

[0082] Embodiment 6

[0083] This embodiment six also provides a computer-readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory (for example, an SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a disk, an optical disk, a server, an App application store, etc., on which a computer program is stored, and when the program is executed by a processor, a corresponding function is realized. The computer-readable storage medium of this embodiment is used to store a wheel state recognition device and a water spray control device, and when executed by a processor, the wheel state recognition method of the first embodiment or the water spray control method of the second embodiment is realized.

[0084] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0085] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0086] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method.

[0087] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A wheel state recognition method, characterized in that: include: Acquire vehicle images; Detecting a front image of a wheel in the vehicle image; extracting a wheel contour in the front image; calculating the dirt area within the wheel profile; The cleaning status of the wheel is determined according to the size of the mud area, wherein after obtaining the mud area, the ratio of the mud area to the wheel contour is calculated to obtain the proportion of the mud, the wheel includes a tire part and a non-tire part, and a preset proportion threshold is determined according to the proportion of the non-tire part. When the proportion of the mud is greater than the preset proportion threshold, it indicates that the mud area includes the non-tire part and the mud part, and the wheel is not cleaned; when the proportion of the mud is less than or equal to the preset proportion threshold, it indicates that the mud area only includes the non-tire part, and the wheel has been cleaned.

2. The wheel state recognition method according to claim 1, characterized in that: The step of detecting the front image of the wheel in the vehicle image comprises: Detecting a wheel image surrounding a wheel in the vehicle image; When the wheel image is larger than a preset image threshold and the aspect ratio of the wheel image satisfies a preset aspect ratio range, it is determined that the wheel image is the front image.

3. The wheel state recognition method according to claim 1, characterized in that: The step of extracting the wheel contour in the front image comprises: Detecting a circle in the front image by a circle detection algorithm; When the size and center position of the circle meet the tire parameters, the wheel profile is determined according to the circle.

4. The wheel state recognition method according to claim 1, characterized in that: The step of calculating the soil area within the wheel profile comprises: Calculate the characteristic value distribution of the image features of the wheel profile; The soil area is determined according to the characteristic value distribution and the image feature range corresponding to the soil.

5. The wheel state recognition method according to claim 4, characterized in that: The image features include HSV distribution and RGB values, and the step of determining the soil area according to the feature value distribution and the image feature range corresponding to the soil includes: The soil area is determined according to the HSV value range and RGB value range corresponding to the soil, and the HSV distribution and RGB value of the wheel profile.

6. A water spray control method, characterized in that: include: Using the wheel state recognition method according to any one of claims 1 to 5 to recognize the cleaning state of the wheel; as well as A water spray switch for washing the wheels is controlled according to the washing state.

7. A wheel state recognition device, characterized in that: include: An acquisition module, used for acquiring vehicle images; A detection module, used for detecting a front image of a wheel in the vehicle image; An extraction module, used for extracting the wheel outline in the front image; A calculation module, used for calculating the soil area within the wheel profile; A determination module is used to determine the cleaning status of the wheel according to the size of the mud area, wherein after obtaining the mud area, the ratio of the mud area to the wheel contour is calculated to obtain the proportion of mud, the wheel includes a tire part and a non-tire part, and a preset proportion threshold is determined according to the proportion of the non-tire part. When the proportion of the mud is greater than the preset proportion threshold, it indicates that the mud area includes the non-tire part and the mud part, and the wheel is not cleaned; when the proportion of the mud is less than or equal to the preset proportion threshold, it indicates that the mud area only includes the non-tire part and the wheel is cleaned.

8. A water spray control device, characterized in that: include: An identification module, used to identify the cleaning state of the wheel using the wheel state identification method according to any one of claims 1 to 5; as well as A control module is used to control a water spray switch for cleaning the wheels according to the cleaning state.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images