Method, device and system for detecting grooves in tread and sidewall surfaces

Abstract

The invention relates to the technical field of tire detection, in particular to a method, a device and a system for detecting grooves in tread and sidewall surfaces. The method comprises the following steps: acquiring a first image of a tire by adopting a first image sensor; performing abnormal area identification on the first image, and if an identification result shows that the first image is abnormal, acquiring a second image by adopting a second image sensor after a preset time length; performing weighted stacking on the first image and the second image to obtain a stacked image; converting the pixel value of each pixel point in the superposed image into a frequency value; calculating a frequency difference value between the frequency value and a reference frequency; and determining a groove area of the superposed image based on the difference value maximum value and the difference value minimum value of the frequency difference values. The method can improve the detection precision and reduce the calculation amount.

Description

Technical Field

[0001] The present invention belongs to the technical field of tire detection, and in particular relates to a method, a device and a system for detecting grooves on a tread and a sidewall surface. Background Art

[0002] With the continuous development of vehicle safety technology, tire wear detection technology has become an important means to improve driving safety. However, the existing tire wear detection technology still has some shortcomings in detection accuracy, real-time performance, and installation and maintenance convenience, which affects the effectiveness of the detection system and user experience.

[0003] After searching, a tire wear detection system and vehicle for vehicles with a publication number of CN113942347B was disclosed, and the publication date is September 9, 2022. This patent embeds a filling component including a transparent rubber part and a reflective part in the groove of the tire, and uses a transmitting device and a receiving device to detect the reflection of light to achieve the detection of tire wear. However, this technical solution has the following problems:

[0004] Inconvenient installation and maintenance: The system requires the filling components to be embedded in the grooves of the tire. This installation method is not only complicated but also easily affected by the external environment. If the embedding is not firm or the rubber parts are damaged, the test results will be inaccurate.

[0005] Limited detection accuracy: The detection component relies on light reflection from the transmitter and receiver. This detection method may be interfered with under complex working conditions (such as rainy days or at night), resulting in reduced detection accuracy.

[0006] High cost: It is necessary to embed a filling component in the groove of each tire and install a transmitting device and a receiving device on the vehicle body, which places high demands on the system cost and maintenance cost.

[0007] In addition, with the continuous development of image processing technology, cameras are also used to capture image information of the tire surface, and the image is analyzed to detect the grooves on the tire surface. However, the accuracy of image processing is closely related to its clarity. If high-definition images are to be obtained, the computing requirements will be significantly increased, especially in complex working conditions such as vehicle driving. The increase in computing requirements will lead to a significant increase in the complexity and cost of the entire detection system.

[0008] Therefore, the existing technology has obvious deficiencies in installation and maintenance, detection accuracy and cost control, and a new detection method and structural design are urgently needed. Summary of the invention

[0009] In order to solve the above technical problems, the present application is proposed. The embodiments of the present application provide a method, device and system for detecting grooves on the tread and sidewall surfaces.

[0010] According to one aspect of the present application, a method for detecting grooves on a tread and sidewall surface is provided, comprising: acquiring a first image of a tire using a first image sensor; identifying an abnormal area of ​​the first image to obtain an identification result; wherein the identification result indicates whether the first image is abnormal; if the identification result indicates that the first image is abnormal, acquiring a second image of the tire using a second image sensor after a preset time; wherein the first image sensor and the second image sensor are arranged on one side of the tire, and the second image sensor is arranged downstream of the first image sensor along the moving direction of the tire, and the preset time is determined according to the distance between the first image sensor and the second image sensor and the moving speed of the tire; weightedly superimposing the first image and the second image to obtain a superimposed image; wherein the weight of the first image is equal to the ratio of the minimum pixel difference to the maximum pixel difference between the first image and the second image; converting the pixel value of each pixel point in the superimposed image into a frequency value; wherein the conversion formula is:

[0011]

[0012] P(u,v) is the value at the frequency domain point (u,v), g(x,y) is the pixel value of the pixel point (x,y), M is the number of horizontal pixels in the first image, N is the number of vertical pixels in the first image, and i is an imaginary unit; calculate the frequency difference between the frequency value and the reference frequency; wherein the reference frequency is the frequency average of all pixels in the superimposed image; calculate the maximum difference and the minimum difference of the frequency difference in the same column or row; determine the groove area of ​​the superimposed image based on the maximum difference and the minimum difference.

[0013] A light emitter is arranged on a side of the tire away from the first image sensor and the second image sensor, and the light emitter emits a plurality of parallel line light beams to the tire; wherein, the abnormal area of ​​the first image is identified to obtain the identification result, including: calculating the brightness value of all pixels of the tire image in the first image; if the brightness value is greater than a reference brightness, determining that the first image is abnormal; wherein the reference brightness is the brightness value of the groove-free area of ​​the tire, and the reference brightness is updated regularly.

[0014] The abnormal area of ​​the first image is identified to obtain the identification result, which includes: binarizing the first image to obtain a binary image; segmenting the binary image to obtain a plurality of segmented areas; if there is a closed segmented area located in the middle of the first image among the plurality of segmented areas, and the pixel value of the closed segmented area is greater than the pixel value of the segmented area outside the closed segmented area, then the first image is determined to be abnormal.

[0015] The first image and the second image are weightedly superimposed to obtain a superimposed image, which includes: aligning the first image and the second image based on the mark points of the tire; weightedly superimposing the closed segmented area in the first image and the corresponding area in the second image to obtain a superimposed closed area; enhancing the superimposed closed area to obtain a target superimposed area; weightedly superimposing the external segmented area in the first image and the corresponding area in the second image to obtain a superimposed external area; and combining the target superimposed area and the superimposed external area to obtain the superimposed image.

[0016] Determining the groove area of ​​the superimposed image based on the maximum difference and the minimum difference includes: if the maximum difference and the minimum difference in the same row or the same column are adjacent, determining the corresponding pixel point as the boundary pixel point of the groove area; and fitting the groove area based on multiple boundary pixel points.

[0017] The first image includes an unloaded image of the tire when it is unloaded and a loaded image of the tire when it is loaded; abnormal areas are identified on the first image, and the identification results include: comparing the unloaded boundary position of the tire in the unloaded image with the loaded boundary position of the tire in the loaded image; if the difference between the unloaded boundary position and the loaded boundary position is greater than a preset difference, determining that the first image is abnormal.

[0018] Identifying abnormal areas of the first image to obtain an identification result includes: inputting the first image into an image recognition model to obtain image feature information of the first image; if the image feature information includes a crack feature, determining that the first image is abnormal.

[0019] Performing abnormal area identification on the first image to obtain an identification result includes: calculating the variance of all pixels between the first image and a standard image; if the variance is greater than a preset value, determining that the first image is abnormal.

[0020] According to another aspect of the present application, a device for detecting grooves on the tread and sidewall surface is provided, comprising: a first image acquisition module, used to acquire a first image of a tire using a first image sensor; an abnormal area recognition module, used to identify the abnormal area of ​​the first image and obtain an identification result; wherein the identification result indicates whether the first image is abnormal; a second image acquisition module, used to acquire a second image of the tire using a second image sensor after a preset time if the identification result indicates that the first image is abnormal; wherein the first image sensor and the second image sensor are arranged on one side of the tire, and the second image sensor is arranged downstream of the first image sensor along the movement direction of the tire, and the preset time is determined according to the distance between the first image sensor and the second image sensor and the movement speed of the tire; an image weighted superposition module, used to perform weighted superposition on the first image and the second image to obtain a superimposed image; wherein the weight of the first image is equal to the ratio of the minimum pixel difference to the maximum pixel difference between the first image and the second image; a pixel frequency calculation module, used to convert the pixel value of each pixel point in the superimposed image into a frequency value; wherein the conversion formula is:

[0021]

[0022] P(u,v) is the value at the frequency domain point (u,v), g(x,y) is the pixel value of the pixel point (x,y), M is the number of horizontal pixels in the first image, N is the number of vertical pixels in the first image, and i is an imaginary unit; a frequency difference calculation module is used to calculate the frequency difference between the frequency value and the reference frequency; wherein the reference frequency is the frequency average of all pixels in the superimposed image; a frequency change calculation module is used to calculate the maximum difference and the minimum difference of the frequency difference in the same column or the same row; a groove area determination module is used to determine the groove area of ​​the superimposed image based on the maximum difference and the minimum difference.

[0023] According to another aspect of the present application, a system for detecting grooves on the tread and sidewall surfaces is provided, comprising a dual image sensor and the above-mentioned device for detecting grooves on the tread and sidewall surfaces.

[0024] The method, device and system for detecting grooves on the tread and sidewall surface provided by the present application adopt a first image sensor to obtain a first image of the tire; identify abnormal areas in the first image to obtain an identification result; if the identification result indicates that the first image is abnormal, adopt a second image sensor to obtain a second image of the tire after a preset time; wherein the first image sensor and the second image sensor are arranged on one side of the tire, and the second image sensor is arranged downstream of the first image sensor along the movement direction of the tire, and the preset time is determined according to the distance between the first image sensor and the second image sensor and the movement speed of the tire; weightedly superimpose the first image and the second image to obtain a superimposed image; wherein the weight of the first image is equal to the ratio of the minimum pixel difference to the maximum pixel difference between the first image and the second image; convert the pixel value of each pixel point in the superimposed image into a frequency value; calculate the frequency between the frequency value and the reference frequency difference; wherein the reference frequency is the frequency average value of all pixels in the superimposed image; the maximum difference value and the minimum difference value of the frequency difference values ​​in the same column or the same row are calculated; the groove area in the superimposed image is determined based on the maximum difference value and the minimum difference value; that is, firstly a first image of the tire is acquired by a first image sensor and an abnormality is identified for the first image, if the first image is abnormal, a second image of the tire is acquired by a second image sensor and the first image and the second image are weightedly superimposed, the superimposed image is converted into a frequency value and the maximum and minimum values ​​of the difference between the frequency value and the reference frequency are calculated, and the groove area in the superimposed image is determined based on the maximum difference value and the minimum difference value, not only can the image be acquired only by the first image sensor when the tire is normal to reduce the amount of calculation, but also a more accurate groove area of ​​the tire can be obtained by using the dual image sensors when the tire is abnormal, thereby improving the detection accuracy while reducing the amount of calculation as much as possible. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0026] Figure 1 It is a schematic flow chart of a method for detecting grooves on the tread and sidewall surfaces provided by an exemplary embodiment of the present application.

[0027] Figure 2 It is a schematic diagram of the structure of a device for detecting grooves on the tread and sidewall surfaces provided by an exemplary embodiment of the present application.

[0028] Figure 3 It is a schematic diagram of the structure of a system for detecting grooves on the tread and sidewall surfaces provided by an exemplary embodiment of the present application.

[0029] Figure 4 It is a schematic diagram of a tire image and multiple parallel line light beams provided by an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0030] The present invention provides a method, device and system for detecting grooves on the tread and sidewall surface. The method acquires an image of the tire through a first image sensor and a second image sensor, and identifies the groove area on the tire surface through image processing technology, thereby improving the detection accuracy while reducing the amount of calculation as much as possible. This specific implementation will describe the technical solution of the present invention in detail in conjunction with the accompanying drawings.

[0031] Figure 1 The following is a schematic diagram showing a method for detecting grooves on the tread and sidewall surfaces provided by an exemplary embodiment of the present application. Figure 1 As shown, the method includes the following steps:

[0032] A first image of the tire is acquired using a first image sensor:

[0033] In this step, the first image sensor ( Figure 3 101) is installed on one side of the tire production line to obtain tires ( Figure 3 The first image sensor may be a high-resolution industrial camera, and its installation position and angle should ensure that the tread and sidewall areas of the tire surface can be clearly captured. The first image acquired by the first image sensor should include detailed information on the tread and sidewall surfaces of the tire. The first image may be a color image or a grayscale image, and the specific selection depends on the actual application requirements and the efficiency of the image processing algorithm.

[0034] The abnormal area of ​​the first image is identified to obtain the identification result:

[0035] In this step, the first image is subjected to abnormal area recognition through image processing technology to determine whether there are grooves or other abnormal conditions on the tire surface. Specific recognition methods may include the following:

[0036] Brightness value recognition method:

[0037] Calculate the brightness values ​​of all pixels of the tire image in the first image. The reference brightness value may be the brightness value of the non-groove area, and the reference brightness value needs to be updated regularly to adapt to changes in different lighting conditions. If the brightness value of the tire image in the first image is greater than the reference brightness value, the first image is determined to be abnormal. For example, assuming that the reference brightness value is 120 and the calculated brightness value is 150, the image is determined to be abnormal.

[0038] Binarization and segmentation methods:

[0039] The first image is binarized to convert it into a black and white image. Then, the binarized image is segmented to obtain a plurality of segmented regions. If there is a closed segmented region located in the middle of the first image among the plurality of segmented regions, and the pixel value of the closed segmented region is greater than the pixel value outside the closed segmented region, the first image is determined to be abnormal. For example, assuming that the pixel value of the closed segmented region is 255 and the pixel value of the outer region is 0, the image is determined to be abnormal.

[0040] No-load and loaded image comparison method:

[0041] The first image may include an unloaded image when the tire is unloaded and a loaded image when the tire is loaded. By comparing the unloaded boundary position of the tire in the unloaded image with the loaded boundary position of the tire in the loaded image, if the difference between the two is greater than a preset difference, the first image is determined to be abnormal. The value of the preset difference can be set according to the size and load condition of the actual tire. For example, assuming that the preset difference is 10 pixels, and the calculated boundary position difference is 15 pixels, the image is determined to be abnormal.

[0042] Image recognition model method:

[0043] The first image is input into a pre-trained image recognition model to obtain image feature information of the first image. If the image feature information includes a crack feature, the first image is determined to be abnormal. The image recognition model may be a deep learning model, such as a convolutional neural network (CNN), and its training data may come from a previous tire defect image library.

[0044] If the recognition result indicates that the first image is abnormal, a second image of the tire is acquired using a second image sensor after a preset time period:

[0045] If the first image is judged to be abnormal, the second image sensor ( Figure 3 The first image sensor and the second image sensor are disposed on one side of the tire, and the second image sensor is disposed downstream of the first image sensor along the moving direction of the tire. The preset time length is based on the distance between the first image sensor and the second image sensor ( Figure 3 104) and the speed of the tire ( Figure 3 For example, assuming that the distance between the first image sensor and the second image sensor is 1 meter and the moving speed of the tire is 0.5 m / s, the preset time length is 2 seconds.

[0046] Perform weighted superposition of the first image and the second image to obtain a superimposed image:

[0047] In order to more accurately identify the groove area on the tire surface, this step performs weighted superposition of the first image and the second image. The specific steps are as follows:

[0048] Alignment Operation:

[0049] Based on the landmarks on the tire, the first image and the second image are aligned to ensure that the two images are superimposed in the same coordinate system. The alignment operation can be achieved by an image registration algorithm, such as a registration algorithm based on feature points.

[0050] Weighted overlay:

[0051] The closed segmented area in the first image and the corresponding area in the second image are weightedly superimposed to obtain the superimposed closed area. The weight is determined by calculating the ratio of the minimum pixel difference and the maximum pixel difference between the first image and the second image. For example, assuming that the minimum pixel difference between the first image and the second image is 10 and the maximum pixel difference is 100, the weight of the first image is 0.1.

[0052] Enhanced processing:

[0053] The superimposed closed area is enhanced to highlight the features of the groove area. The enhancement method may include histogram equalization, edge enhancement, etc. For example, the contrast of the image may be enhanced by histogram equalization, making the groove area more obvious.

[0054] Combine to get the superimposed image:

[0055] The external segmented area in the first image and the corresponding area in the second image are weightedly superimposed to obtain a superimposed external area. Then, the superimposed closed area and the superimposed external area are combined to obtain a final superimposed image.

[0056] Convert the pixel value of each pixel in the overlay image to a frequency value:

[0057] This step converts the pixel value of each pixel in the overlay image into a frequency value for further analysis. The specific conversion formula is:

[0058]

[0059] Among them, P(u,v) is the value at the frequency domain point (u,v), g(x,y) is the pixel value of the pixel point (x,y), M is the number of horizontal pixels in the first image, N is the number of vertical pixels in the first image, and i is an imaginary unit. Through this formula, the superimposed image can be converted from the spatial domain to the frequency domain, so as to better analyze the frequency characteristics of the image.

[0060] Calculate the frequency difference between the frequency value and the reference frequency:

[0061] In this step, the frequency difference between the frequency value of each pixel in the superimposed image and the reference frequency is calculated. The reference frequency is the average frequency of all pixels in the superimposed image. The specific calculation method is as follows:

[0062]

[0063] Among them, ΔP(u,v) is the frequency difference, and Pˉ is the reference frequency. By calculating the frequency difference, the frequency characteristics of the groove area can be further highlighted.

[0064] Calculate the maximum and minimum differences in frequency differences in the same column or row:

[0065] In this step, the maximum and minimum frequency differences in the same column or row are calculated. The specific method is as follows:

[0066] For the frequency difference ΔP(u,v) of the same column (u,v), calculate the maximum difference ΔPmax(u) and the minimum difference ΔPmin(u).

[0067] For the frequency difference ΔP(u,v) of the same row (u,v), the maximum difference ΔPmax(v) and the minimum difference ΔPmin(v) are calculated.

[0068] Determine the groove area of ​​the superimposed image based on the maximum and minimum difference values:

[0069] In this step, if the maximum difference value and the minimum difference value in the same row or column are adjacent, the corresponding pixel point is determined to be the boundary pixel point of the groove area. The groove area is fitted based on multiple boundary pixel points. The specific method is as follows:

[0070] If ΔPmax(u) and ΔPmin(u) are adjacent in the same column, or ΔPmax(v) and ΔPmin(v) are adjacent in the same row, the corresponding pixel point is determined to be a boundary pixel point of the groove area.

[0071] Based on multiple boundary pixels, the groove area is determined by a fitting algorithm. The fitting algorithm may be a polynomial fitting, a linear fitting, etc. For example, a contour curve of the groove area may be obtained by polynomial fitting.

[0072] Figure 2 FIG. 1 is a schematic diagram showing a device structure for detecting grooves on the tread and sidewall surface provided by an exemplary embodiment of the present application. Figure 2 As shown, the device includes the following modules:

[0073] The first image acquisition module ( Figure 2 401): used to acquire a first image of a tire using a first image sensor.

[0074] Abnormal area recognition module ( Figure 2 402): used to identify abnormal areas of the first image and obtain identification results.

[0075] The second image acquisition module ( Figure 2 403): used to obtain a second image of the tire using a second image sensor after a preset time period.

[0076] Image weighted overlay module ( Figure 2 404): used to perform weighted superposition on the first image and the second image to obtain a superimposed image.

[0077] Pixel frequency calculation module ( Figure 2 405): used to convert the pixel value of each pixel in the superimposed image into a frequency value.

[0078] Frequency difference calculation module ( Figure 2 406): used to calculate the frequency difference between the frequency value and the reference frequency.

[0079] Frequency change calculation module ( Figure 2 407): used to calculate the maximum and minimum frequency differences in the same column or row.

[0080] Groove area determination module ( Figure 2 408): used to determine the groove area in the superimposed image based on the maximum difference value and the minimum difference value.

[0081] Figure 3 FIG. 1 is a schematic diagram showing a system structure for detecting grooves on the tread and sidewall surfaces provided by an exemplary embodiment of the present application. Figure 3 As shown, the system includes a dual image sensor (a first image sensor 101 and a second image sensor 103) and the above-mentioned device for detecting the grooves on the tread and sidewall surface ( Figure 3 106). Dual image sensors are installed on the tire production line, and are used to obtain a first image and a second image of the tire respectively. The distance 104 between the first image sensor 101 and the second image sensor 103 and the movement speed 105 of the tire are used to determine the preset time. Device 106 identifies the groove area on the tire surface through image processing technology.

[0082] Figure 4 FIG. 1 shows a tire image and a schematic diagram of multiple parallel line beams provided by an exemplary embodiment of the present application. Figure 4 As shown, a light emitter ( Figure 4 501), the light emitter emits multiple parallel line beams to the tire ( Figure 4502). These parallel line beams can enhance the contrast between the groove area and the normal area on the tire surface, thereby improving the accuracy of image recognition. The light emitter can be a laser emitter or an LED light source, and the specific selection depends on the actual application requirements and equipment conditions.

[0083] The specific implementation of the present invention can be applied in a tire production line. Through the above method and device, the groove area on the tire surface can be detected in real time, and the defects of the tire can be found in time, thereby improving the quality control level of the tire. The method can not only obtain images only through the first image sensor when the tire is normal to reduce the amount of calculation, but also use the dual image sensors to comprehensively obtain a more accurate groove area of ​​the tire when the tire is abnormal, thereby improving the detection accuracy while reducing the amount of calculation as much as possible.

[0084] The above description shows and describes several preferred embodiments of the present invention, but as mentioned above, it should be understood that the present invention is not limited to the form disclosed herein, and should not be regarded as excluding other embodiments, but can be used in various other combinations, modifications and environments, and can be modified within the scope of the invention concept described herein through the above teachings or the technology or knowledge of the relevant field. Changes and variations made by those skilled in the art do not depart from the spirit and scope of the present invention, and should be within the scope of protection of the claims attached to the present invention.

Claims

1. A method for detecting grooves on the tread and sidewall surfaces, characterized in that: include: Using a first image sensor (101) to acquire a first image of a tire (102); Performing abnormal region recognition on the first image to obtain a recognition result; wherein the recognition result indicates whether the first image has an abnormality; If the recognition result indicates that the first image is abnormal, a second image of the tire is acquired using a second image sensor (103) after a preset time period; wherein the first image sensor and the second image sensor are arranged on one side of the tire, and the second image sensor is arranged downstream of the first image sensor along the moving direction of the tire, and the preset time period is determined according to the distance (104) between the first image sensor and the second image sensor and the moving speed (105) of the tire; Performing weighted superposition on the first image and the second image to obtain a superimposed image; wherein the weight of the first image is equal to the ratio of the minimum pixel difference to the maximum pixel difference between the first image and the second image; The pixel value of each pixel in the superimposed image is converted into a frequency value; wherein the conversion formula is: Wherein, P(u,v) is the value at the frequency domain point (u,v), g(x,y) is the pixel value of the pixel point (x,y), M is the number of horizontal pixels in the first image, N is the number of vertical pixels in the first image, and i is an imaginary unit; Calculating a frequency difference between the frequency value and a reference frequency; wherein the reference frequency is the frequency average value of all pixels in the superimposed image; Calculate the maximum value and the minimum value of the frequency difference in the same column or row; Determining a groove area of ​​the superimposed image based on the maximum difference value and the minimum difference value; A light emitter (501) is arranged on a side of the tire away from the first image sensor and the second image sensor, and the light emitter emits a plurality of parallel line beams (502) toward the tire; wherein the abnormal area recognition is performed on the first image to obtain the recognition result, including: calculating the brightness value of all pixels of the tire image in the first image; if the brightness value is greater than a reference brightness, determining that the first image is abnormal; wherein the reference brightness is the brightness value of the non-groove area of ​​the tire, and the reference brightness is updated regularly; Identifying an abnormal region of the first image to obtain an identification result includes: binarizing the first image to obtain a binary image; segmenting the binary image to obtain a plurality of segmented regions; if a closed segmented region located in the middle of the first image exists among the plurality of segmented regions, and a pixel value of the closed segmented region is greater than a pixel value of a segmented region outside the closed segmented region, determining that the first image is abnormal; The first image and the second image are weightedly superimposed to obtain a superimposed image, comprising: aligning the first image (202) and the second image (203) based on the mark point (201) on the tire; weighted superimposing the closed segmented area in the first image and the corresponding area in the second image to obtain a superimposed closed area (303); enhancing the superimposed closed area to obtain a target superimposed area; weighted superimposing the external segmented area in the first image and the corresponding area in the second image to obtain a superimposed external area; and combining the target superimposed area and the superimposed external area to obtain the superimposed image; Determining the groove area of ​​the superimposed image based on the maximum difference value and the minimum difference value includes: if the maximum difference value and the minimum difference value in the same row or the same column are adjacent, determining the corresponding pixel point as the boundary pixel point of the groove area; fitting the groove area according to the plurality of boundary pixel points; The first image includes an unloaded image of the tire when it is unloaded and a loaded image of the tire when it is loaded; performing abnormal area recognition on the first image to obtain a recognition result includes: comparing an unloaded boundary position of the tire in the unloaded image with a loaded boundary position of the tire in the loaded image; if the difference between the unloaded boundary position and the loaded boundary position is greater than a preset difference, determining that the first image is abnormal; Identifying an abnormal area of ​​the first image to obtain an identification result includes: inputting the first image into an image recognition model to obtain image feature information of the first image; if the image feature information includes a crack feature, determining that the first image is abnormal; Performing abnormal area identification on the first image to obtain an identification result includes: calculating the variance of all pixels between the first image and a standard image; if the variance is greater than a preset value, determining that the first image is abnormal.

2. The method for detecting grooves on the tread and sidewall surfaces according to claim 1, characterized in that: The first image includes an unloaded image of the tire when it is unloaded and a loaded image of the tire when it is loaded; The abnormal region is identified on the first image, and the identification result obtained includes: comparing an unloaded boundary position of the tire in the unloaded image with a loaded boundary position of the tire in the loaded image; If the difference between the unloaded boundary position and the loaded boundary position is greater than a preset difference, it is determined that the first image is abnormal.

3. The method for detecting grooves on the tread and sidewall surfaces according to claim 1, characterized in that: The abnormal region is identified on the first image, and the identification result obtained includes: Inputting the first image into an image recognition model to obtain image feature information of the first image; If the image feature information includes a crack feature, it is determined that the first image is abnormal.

4. The method for detecting grooves on the tread and sidewall surfaces according to claim 1, characterized in that: The abnormal region is identified on the first image, and the identification result obtained includes: Calculating the variance of all pixels between the first image and the standard image; If the variance is greater than a preset value, it is determined that the first image is abnormal.

5. A device for detecting grooves on the tread and sidewall surfaces, characterized in that: include: A first image acquisition module (401), configured to acquire a first image of a tire using a first image sensor; An abnormal region identification module (402) is used to identify abnormal regions in the first image to obtain an identification result; wherein the identification result indicates whether the first image has an abnormality; a second image acquisition module (403), configured to acquire a second image of the tire using a second image sensor after a preset time period if the recognition result indicates that the first image is abnormal; wherein the first image sensor and the second image sensor are arranged on one side of the tire, and the second image sensor is arranged downstream of the first image sensor along the moving direction of the tire, and the preset time period is determined according to the distance between the first image sensor and the second image sensor and the moving speed of the tire; An image weighted superposition module (404) is used to perform weighted superposition on the first image and the second image to obtain a superposition image; wherein the weight of the first image is equal to the ratio of the minimum pixel difference to the maximum pixel difference between the first image and the second image; A pixel frequency calculation module (405), used for converting the pixel value of each pixel point in the superimposed image into a frequency value; A frequency difference calculation module (406), used to calculate the frequency difference between the frequency value and a reference frequency; wherein the reference frequency is the frequency average value of all pixels in the superimposed image; A frequency change calculation module (407), used for calculating the maximum value and the minimum value of the frequency difference in the same column or the same row; A groove region determination module (408), configured to determine the groove region of the superimposed image based on the maximum difference value and the minimum difference value; A light emitter is disposed on a side of the tire away from the first image sensor and the second image sensor, and the light emitter emits a plurality of parallel line beams to the tire; wherein the abnormal area recognition module is further configured to: calculate the brightness value of all pixels of the tire image in the first image; if the brightness value is greater than a reference brightness, then determine that the first image is abnormal; wherein the reference brightness is the brightness value of the non-groove area of ​​the tire, and the reference brightness is updated regularly; The abnormal region identification module is further configured to: perform binarization processing on the first image to obtain a binarized image; segment the binarized image to obtain a plurality of segmented regions; if there is a closed segmented region located in the middle of the first image among the plurality of segmented regions, and the pixel value of the closed segmented region is greater than the pixel value of the segmented region outside the closed segmented region, then determine that the first image is abnormal; The image weighted superposition module is further configured to: align the first image and the second image based on the mark points on the tire; weightedly superimpose the closed segmented area in the first image and the corresponding area in the second image to obtain a superimposed closed area; enhance the superimposed closed area to obtain a target superimposed area; weightedly superimpose the external segmented area in the first image and the corresponding area in the second image to obtain a superimposed external area; and combine the target superimposed area and the superimposed external area to obtain the superimposed image; The groove area determination module is further configured as follows: if the maximum difference value and the minimum difference value in the same row or column are adjacent, the corresponding pixel point is determined to be a boundary pixel point of the groove area; and the groove area is fitted based on multiple boundary pixel points.

6. A system for detecting grooves on the tread and sidewall surfaces, characterized in that: include: A dual image sensor (101, 103) and a device (106) for detecting grooves on the tread and sidewall surfaces as claimed in claim 5.

7. The method for detecting grooves on the tread and sidewall surfaces according to claim 1, characterized in that: The weight of the first image is equal to the ratio of the minimum pixel difference to the maximum pixel difference between the first image and the second image.

8. The method for detecting grooves on the tread and sidewall surfaces according to claim 1, characterized in that: The reference frequency is the frequency average of all pixels in the superimposed image.

9. The method for detecting grooves on the tread and sidewall surfaces according to claim 1, characterized in that: The performing abnormal region recognition on the first image to obtain a recognition result includes: Calculating the variance of all pixels between the first image and the standard image; If the variance is greater than a preset value, it is determined that the first image is abnormal.

10. The method for detecting grooves on the tread and sidewall surfaces according to claim 1, characterized in that: A light emitter is disposed on a side of the tire away from the first image sensor and the second image sensor, and the light emitter emits a plurality of parallel line light beams toward the tire.

Images