Tire surface damage detection method and system and electronic equipment
By installing shooting and laser emitting devices on the lift, a three-dimensional image model of the tire is constructed, and a machine learning model is used to detect tire surface damage, which solves the problems of low efficiency, poor accuracy and small range of tire pattern depth measurement in the prior art. A rapid and accurate assessment of tire damage is achieved.
Patent Information
- Application Number
- CN202410986383.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-23
- Publication Date
- 2024-12-06
AI Technical Summary
The prior art has problems such as low efficiency, poor accuracy, high cost and small measurement range when measuring tire pattern depth, and it is impossible to accurately detect the pattern depth of the entire tire.
The lift is equipped with a shooting device and a laser emitting device. By obtaining laser lines on the bottom and sides of the tire, a three-dimensional image model is constructed, and a machine learning model is used to predict tire surface damage data, including detection of pattern wear, cracks and bulges.
It realizes rapid and accurate detection of tire surface damage, can collect full-view data of the tire, improves detection efficiency and accuracy, and ensures a more complete damage assessment.
Smart Images

Figure CN119090799A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of vehicle technology, and in particular to a tire surface damage detection method. Background Art
[0002] In recent years, with the substantial improvement of computer computing power and the continuous maturity of neural network technology, the field of artificial intelligence has made breakthrough progress, thus bringing new development opportunities to all walks of life. Among them, computer vision technology is one of the representative technologies of artificial intelligence and has been applied to all aspects of life. At present, the tread depth is usually measured by calipers, which has the disadvantages of low efficiency, poor accuracy and high cost. In addition, customers need to measure it by themselves, which has large measurement errors and high labor costs. There is also a method of laser measurement, but the measurement range is small and the tread depth of the entire tire cannot be measured, resulting in inaccurate measurement. Summary of the invention
[0003] Based on this, it is necessary to provide a tire surface damage detection method to address the problem that the current measurement accuracy of tire tread depth is not high enough.
[0004] To achieve the above objectives, on the one hand, an embodiment of the present application provides a tire surface damage detection method, characterized in that it includes:
[0005] Raise at least one tire of the vehicle using a lift;
[0006] At least one first shooting device and at least one first laser emitting device installed on the lifting machine, used to obtain a first laser line image projected by laser onto the bottom surface of the tire to be tested and at least one second laser line image projected by laser onto the bottom surface of the tire to be tested after the tire to be tested rotates;
[0007] Build a machine learning model for tire surface detection;
[0008] Inputting a first laser line image and a second laser line image of the tested tire into a machine learning model;
[0009] The machine learning model calculates the surface damage data of the tested tire.
[0010] Preferably, the lift is also equipped with at least one second shooting device and at least one second laser emitting device, wherein the second shooting device and the second laser emitting device are used to obtain a third laser line image projected by the laser onto the side of the tire being measured and at least one fourth laser line image projected by the laser onto the side of the tire being measured after the tire being measured rotates.
[0011] Preferably, the method of constructing the tire surface detection machine learning model includes:
[0012] S31: constructing the first laser line image and the third laser line image into a first local three-dimensional image model of the tested tire, and constructing the at least one second laser line image and the at least one fourth laser line image into at least one second local three-dimensional image model of the tested tire;
[0013] S32: fitting the first local three-dimensional image model and the at least one second local three-dimensional image model to obtain a three-dimensional image of the tested tire;
[0014] S33 inputs the three-dimensional image model of the tested tire into the machine learning model;
[0015] S34 machine learning model predicts the surface damage data of the tested tire;
[0016] S115 repeats steps S31-S34.
[0017] Preferably, the method for predicting the surface damage data of the tested tire by a machine learning model includes:
[0018] Predicting the location of damage in the three-dimensional image model of the tested tire and calculating the location coordinates;
[0019] The position coordinates are returned to the model, and a damage position image in the three-dimensional image model of the tested tire is obtained through the coordinates;
[0020] Perform Gaussian blur processing on the damage location image to reduce image noise and detail levels;
[0021] Present the image through the green channel;
[0022] Perform grayscale processing on the image to obtain a grayscale image;
[0023] Binarizing the grayscale image to obtain a binary image;
[0024] Perform morphological operations on the binary image to obtain a set of white line points;
[0025] Perform straight line fitting on the white line point set to find the damage spacing.
[0026] Calculate the damage degree of the tested tire.
[0027] Preferably, the measured tire surface damage data includes: tire tread wear degree, tire cracks and tire bulges.
[0028] In another aspect, the present invention further provides a tire surface damage detection system, comprising: a lifter for lifting at least one tire of a vehicle;
[0029] The first shooting device and at least one first laser emitting device are used to obtain a first laser line image of the bottom surface of the tire and at least one second laser line image projected onto the bottom surface of the tire after the tire is rotated.
[0030] The machine learning model is used to perform machine learning on images and predict the surface damage of the tested tire.
[0031] On the other hand, the present invention also provides an electronic device for detecting tire surface damage, the electronic device comprising a processor and a memory, the memory storing at least one instruction, at least one program, a code set or an instruction set, the at least one instruction, the at least one program, the code set or the instruction set being loaded by the processor and executing the above-mentioned tire surface damage detection method.
[0032] Compared with the prior art, the advantages of this application are:
[0033] (1) The present application installs a shooting device and a laser emitting device on a lift, so that the wheels can rotate when the vehicle is lifted. During the rotation of the wheels, data on the tire surface can be collected, and the overall picture of the tested tire can be collected, including not only the wear condition of the tire pattern but also the crack condition of the tire.
[0034] (2) By setting up a second shooting device and a second laser emission device, when the first shooting device and the first laser emission device shoot an image of the bottom surface of the tire, the second shooting device and the second laser emission device can synchronously shoot an image of the side surface of the tire corresponding to the bottom surface of the tire, and a three-dimensional image of the tire under test can be fitted based on the image of the bottom surface of the tire and the image of the side surface of the tire.
[0035] (3) The three-dimensional image of the tested tire is trained with a machine learning model to quickly obtain tire damage data including the bottom and side surfaces. Not only can the tire tread wear data be obtained, but also the tire crack data and tire side bulge data can be obtained. The data on tire surface damage has a more complete detection conclusion, further ensuring the safety of the ride. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] The present application is further described below in conjunction with the accompanying drawings and embodiments:
[0037] Figure 1 A schematic diagram of an application environment of a tire surface damage detection method of the present application;
[0038] Figure 2 A schematic diagram of a tire surface damage detection method in Embodiment 1 of the present application;
[0039] Figure 3A schematic diagram of constructing a tire surface detection machine learning model in a tire surface damage detection method of the present application;
[0040] Figure 4 This is a schematic diagram of a tire surface damage detection method in Embodiment 2 of the present application;
[0041] Figure 5 This is a schematic diagram of constructing a tire surface detection machine learning model in Example 2 of a tire surface damage detection method of the present application.
[0042] Among them, 1. a lift, 2. a first shooting device, 3. a first laser emitting device. DETAILED DESCRIPTION
[0043] In order to make the purpose, technical scheme and advantages of the present application clearer, the embodiments of the present application will be further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiment is only one embodiment of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.
[0044] "Embodiment" referred to herein refers to a specific feature, structure or characteristic that may be included in at least one implementation of the present application. In the description of the embodiment of the present application, it should be understood that the terms "first", "second" and "third" etc. are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features. Thus, the features defined as "first", "second" and "third" etc. may include one or more of the features explicitly or implicitly. Moreover, the terms "first", "second" and "third" etc. are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiment of the present application described here can be implemented in an order other than illustrated or described here. In addition, the terms "including" and "for" and any of their variations are intended to cover non-exclusive inclusions.
[0045] Embodiment 1
[0046] like Figure 1 As shown, it is a schematic diagram of an application environment of a tire surface damage detection method provided in an embodiment of the present application, including a lift 1, a first shooting device 2 and a first laser emitting device 3. The first shooting device 2 and the first laser emitting device 3 are installed on the lift 1 as a group of shooting systems, and a laser is emitted to the tire under test through the laser emitting device 3, and then a photo of the bottom surface of the tire under test is taken through the first shooting device 2.
[0047] like Figure 2As shown, in this embodiment, the steps of the tire surface damage detection method are:
[0048] S1: Lifting at least one tire of the vehicle using a lift;
[0049] Specifically, the vehicle is lifted by the lift 1. In this embodiment, the lift 1 lifts the entire vehicle so that the tire to be tested can rotate.
[0050] S2: obtaining, by means of at least one first photographing device 2 and at least one first laser emitting device 3 installed on the lift 1, a first laser line image projected by laser onto the bottom surface of the tire to be tested and at least one second laser line image projected by laser onto the bottom surface of the tire to be tested after the tire to be tested rotates;
[0051] Specifically, the first laser emitting device 3 emits a laser to the tire under test, and at the same time, the first shooting device 2 takes a picture of the position where the laser is emitted to the bottom surface of the tire under test, and the captured image is recorded as a first image, which is then stored in a memory. Subsequently, after the tire under test is rotated, the first shooting device 2 takes a picture again of the position where the laser is emitted to the bottom surface of the tire under test, and the captured image is recorded as a second image, which is stored in the memory. The above operation is repeated until all images of the bottom surface of the tire are captured and stored in the memory.
[0052] S3: Build a machine learning model for tire surface detection;
[0053] Specifically, Figure 3 As shown, building a tire surface detection machine learning model includes the following steps:
[0054] S31: fitting the image of the tire bottom surface around one circle to obtain the contour image of the tire bottom surface around one circle;
[0055] S32: inputting the images of the bottom surface of the tested tire around one circumference into the machine learning model;
[0056] S33: Machine learning model predicts the surface damage data of the tested tire;
[0057] S34: Repeat steps S31-S33.
[0058] S4: Inputting the profile image of the bottom surface of the tested tire into the machine learning model;
[0059] Specifically, the image of the bottom surface of the tire is fitted to obtain a contour image of the bottom surface of the tested tire, and the contour image of the bottom surface of the tire is input into the machine learning model.
[0060] S5: The machine learning model calculates the surface damage data of the tested tire.
[0061] Specifically, the machine learning model recognizes the input contour image of the bottom surface of the tire being tested and predicts and calculates the damage data on the surface of the tire being tested.
[0062] Embodiment 2:
[0063] like Figure 4 As shown, it is a schematic diagram of another application environment of a tire surface damage detection method provided in an embodiment of the present application, including a lift 1, a first shooting device 2 and a first laser emitting device 3, wherein the first shooting device 2 and the first laser emitting device 3 are installed on the lift 1 as a shooting system, and also includes a second shooting device and a second laser emitting device, wherein the second shooting device and the second laser emitting device are installed on the lift 1 as a shooting system for capturing images of the tire side.
[0064] In another embodiment of the present application, the steps of the tire surface damage detection method are as follows:
[0065] S11: lifting at least one tire of the vehicle using a lift;
[0066] S12: photographing a first image of the bottom surface of the tire by a first photographing device 2 and a first laser emitting device 3 installed on the lift 1, and photographing a first image of the side surface of the tire by at least one second photographing device and at least one second laser emitting device installed on the lift 1;
[0067] S13: After the tested tire is rotated, the first photographing device 2 and the first laser emitting device 3 photograph a second image of the bottom surface of the tire, and the second photographing device and the second laser emitting device photograph a second image of the side surface of the tire.
[0068] Specifically, after the tire rotates, the first camera 2 and the second camera simultaneously photograph the bottom surface and the side surface of the tire, respectively, to obtain a second image of the bottom surface of the tire and a second image of the side surface of the tire, and then the tire continues to rotate, and the first camera 2 and the second camera continue to photograph the second image of the bottom surface of the tire and the second image of the side surface of the tire, until the tire rotates one circle, the first camera 2 and the second camera respectively obtain the images of the bottom surface of the tire and the images of the side surface of the tire, and then merge the images of the bottom surface of the tire and the images of the side surface of the tire to fit a three-dimensional image of the tire.
[0069] S14: Building a tire surface detection machine learning model;
[0070] Specifically, Figure 5 As shown, building a tire surface detection machine learning model includes the following steps:
[0071] S141: merging the image of the bottom surface of the tested tire and the image of the side surface of the tested tire to fit a three-dimensional image of the tested tire;
[0072] S142: Inputting the three-dimensional image of the tested tire into the machine learning model;
[0073] S143: Machine learning model predicts the surface damage data of the tested tire;
[0074] S144: Repeat steps S141-S143.
[0075] S15: inputting the three-dimensional image of the tested tire into the machine learning model;
[0076] Specifically, the images of the bottom surface of the tested tire and the images of the side surface of the tested tire are combined to fit a three-dimensional image of the tested tire, and the three-dimensional contour image of the tested tire is input into the machine learning model.
[0077] S16: The machine learning model calculates the surface damage data of the tested tire.
[0078] Specifically, predicting the location of damage in the three-dimensional image model of the tested tire and calculating the location coordinates;
[0079] The position coordinates are returned to the model, and a damage position image in the three-dimensional image model of the tested tire is obtained through the coordinates;
[0080] Perform Gaussian blur processing on the damage location image to reduce image noise and detail levels;
[0081] Present the image through the green channel;
[0082] Perform grayscale processing on the image to obtain a grayscale image;
[0083] Binarizing the grayscale image to obtain a binary image;
[0084] Perform morphological operations on the binary image to obtain a set of white line points;
[0085] Perform straight line fitting on the white line point set to find the damage spacing.
[0086] Calculate the damage degree of the tested tire.
[0087] It should be understood that although Figure 2-5 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 2At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.
[0088] In another aspect, the present invention further provides a tire surface damage detection system, comprising: a lifter for lifting at least one tire of a vehicle;
[0089] The first shooting device and at least one first laser emitting device are used to obtain a first laser line image of the bottom surface of the tire and at least one second laser line image projected onto the bottom surface of the tire after the tire is rotated.
[0090] The machine learning model is used to perform machine learning on images and predict the surface damage of the tested tire.
[0091] On the other hand, the present invention also provides an electronic device for detecting tire surface damage, the electronic device comprising a processor and a memory, the memory storing at least one instruction, at least one program, a code set or an instruction set, the at least one instruction, the at least one program, the code set or the instruction set being loaded by the processor and executing the above-mentioned tire surface damage detection method.
[0092] When the processor executes the computer program, the following steps are implemented:
[0093] Raise at least one tire of the vehicle using a lift;
[0094] At least one first shooting device and at least one first laser emitting device installed on the lifting machine, acquiring a first laser line image projected by laser onto the bottom surface of the tire to be tested and at least one second laser line image projected by laser onto the bottom surface of the tire to be tested after the tire to be tested rotates;
[0095] Build a machine learning model for tire surface detection;
[0096] Inputting a first laser line image and a second laser line image of the tested tire into a machine learning model;
[0097] The machine learning model calculates the surface damage data of the tested tire.
[0098] The above embodiments are only for illustrating the technical concept and features of the present application, and their purpose is to enable people familiar with this technology to understand the content of the present application and implement it accordingly, and they cannot be used to limit the scope of protection of the present application. For those skilled in the art, it is obvious that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the spirit or basic features of the present application. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present application is limited by the attached claims rather than the above description, and it is intended to include all changes within the meaning and scope of the equivalent elements of the claims in the present application.
Claims
1. A tire surface damage detection method, It is characterized in that include: Raise at least one tire of the vehicle using a lift; At least one first shooting device and at least one first laser emitting device installed on the lifting machine, acquiring a first laser line image projected by laser onto the bottom surface of the tire to be tested and at least one second laser line image projected by laser onto the bottom surface of the tire to be tested after the tire to be tested rotates; Build a machine learning model for tire surface detection; Inputting a first laser line image and a second laser line image of the tested tire into a machine learning model; The machine learning model calculates the surface damage data of the tested tire.
2. A tire surface damage detection method according to claim 1, It is characterized in that The lift is also equipped with at least one second shooting device and at least one second laser emitting device, wherein the second shooting device and the second laser emitting device are used to obtain a third laser line image projected by the laser onto the side of the tire being tested and at least one fourth laser line image projected by the laser onto the side of the tire being tested after the tire being tested rotates.
3. A tire surface damage detection method according to claim 2, It is characterized in that The method of constructing a tire surface detection machine learning model includes: S31: constructing the first laser line image and the third laser line image into a first local three-dimensional image model of the tested tire, and constructing the at least one second laser line image and the at least one fourth laser line image into at least one second local three-dimensional image model of the tested tire; S32: fitting the first local three-dimensional image model and the at least one second local three-dimensional image model to obtain a three-dimensional image of the tested tire; S33 inputs the three-dimensional image model of the tested tire into the machine learning model; S34 machine learning model predicts the surface damage data of the tested tire; S115 repeats steps S31-S34.
4. A tire surface damage detection method according to claim 3, It is characterized in that The method of predicting the surface damage data of the tested tire by the machine learning model includes: Predicting the location of damage in the three-dimensional image model of the tested tire and calculating the location coordinates; The position coordinates are returned to the model, and a damage position image in the three-dimensional image model of the tested tire is obtained through the coordinates; Perform Gaussian blur processing on the damage location image to reduce image noise and detail levels; Present the image through the green channel; Perform grayscale processing on the image to obtain a grayscale image; Binarizing the grayscale image to obtain a binary image; Perform morphological operations on the binary image to obtain a set of white line points; Perform straight line fitting on the white line point set to find the damage spacing. Calculate the damage degree of the tested tire.
5. A tire surface damage detection method according to any one of claims 1 to 4, It is characterized in that The measured tire surface damage data includes: tire tread wear degree, tire cracks and tire bulges.
6. A tire surface damage detection system, include: a lift for lifting at least one tire of the vehicle; The first shooting device and at least one first laser emitting device are used to obtain a first laser line image of the bottom surface of the tire and at least one second laser line image projected onto the bottom surface of the tire after the tire is rotated. The machine learning model is used to perform machine learning on images and predict the surface damage of the tested tire.
