A method, system and apparatus for measuring tread depth

Abstract

The application provides a kind of tread depth measurement method, system and device.The kind of tread depth measurement method includes the following steps:S1, laser projects line structured light to the tire section needing to detect tread depth, to generate laser stripe, camera is photographed to the laser stripe, generates tread image;S2, tread image preprocessing, to the tread image camera is deformed and is handled with denoising;S3, tread feature identification, to the tread image multiple round scanning and calculation analysis, gradually output each item of the tread image the contained tread feature, to form effective tread groove group data;S4, tread depth calculation, the application can quickly and conveniently obtain tire tread depth numerical value, the calculation result is accurate, and repeatability is good, using the interface ability provided by measurement system, the calculation result is sent into external information unit, satisfies the demand of information processing, improves the precision of tire tread depth calculation result.

Description

Technical Field

[0001] This invention relates to the technical field of tire tread depth measurement, and in particular to a tire tread depth measurement method, system and device. Background Technology

[0002] Tires are one of the most important components of a car. As the only medium of contact between the car and the ground, they bear important responsibilities such as load-bearing, braking, and driving safety. Among the vehicle's safety technical indicators, tire tread depth is a crucial one. Many countries' automotive safety regulations set requirements for tire tread depth, using it as an important indicator of tire wear.

[0003] Traditional methods for measuring tire tread depth use a tread depth gauge. This method is relatively inefficient, the measurement results are easily affected by the operating method and vary greatly, the measurement scenarios are limited, the measurement data needs to be recorded manually, and it is difficult to meet the needs of rapid information processing.

[0004] Therefore, there is an urgent need to redesign a new method, system, and device for measuring tire tread depth to solve the above problems. Summary of the Invention

[0005] This invention provides a method, system, and apparatus for measuring tire tread depth to solve the technical problems mentioned in the background section.

[0006] This invention provides a method, system, and apparatus for measuring tire tread depth. The method includes the following steps: S1, a laser projects structured light onto the tire cross-section where the tread depth needs to be detected to generate laser stripes, and a camera captures the laser stripes to generate a tread image; S2, tread image preprocessing, performing camera distortion correction and noise reduction on the tread image; S3, tread feature recognition, performing multiple scans and calculations on the tread image, and gradually outputting the various tread features contained in the tread image to form effective tread groove group data; S4, tread depth calculation, using a pre-stored homography transformation matrix, converting the tread groove group data in the image coordinate system into laser plane coordinate data, and calculating the tread depth by the distance from the groove to the adjacent tread.

[0007] Optionally, the tread groove group data includes tread segment T, groove segment G, falling edge D from tread to groove, and rising edge U from groove to tread.

[0008] Optionally, the specific steps for performing multi-round scanning and calculation analysis on the tire tread image in step S3 are as follows: S31, extract the center points of the laser stripes in the tire tread image, and construct a continuous list of laser stripe center point data by identifying the center points of the laser stripes. Each data list consists of the horizontal position of the image point, the vertical position of the image point, and the gray value; S32, scan the list of laser stripe center point data from the beginning according to the set gradient change range, and divide the list of laser stripe center point data into several continuous different intervals. Data points in the same interval have approximately the same gradient change, while different intervals have different gradient changes; S33, identify candidate segments that can be used as falling edges and rising edges, traverse each interval, and according to the set falling edge... S34. Select candidate segments for falling and rising edges based on the gradient change rate range of the rising edge; S35. Identify invalid data segments, continue to traverse each interval segment, analyze the gradient change rate and interrelationship between each interval segment and its adjacent interval segments, and filter out abnormal data and mark them as invalid data segments; S36. Traverse each interval segment, merge adjacent interval segments with gradient changes within the set range, and merged interval segments have similar gradient change relationships; S37. Traverse the candidate segments for falling and rising edges, and identify adjacent ordinary data segments of falling and rising edges as tread and groove data segments respectively; S38. Starting from the leftmost tread data segment, check its subsequent consecutive interval segments, and identify consecutive data segments that meet the conditions for valid tread and groove groups.

[0009] Optionally, the center point of the laser stripe in step S31 refers to the data point with the largest gray value in each column of image points, and the falling edge in step S33 refers to the transition section from the tread to the groove, and the rising edge refers to the transition section from the groove to the tread.

[0010] Optionally, the step of calculating the distance from the groove to the adjacent tread in step S4 is as follows: S41, in the tread data adjacent to the left side of the groove, select several data points sequentially from right to left as the tread point on the left side of the groove (X). Li ,Y Li Sort the y-coordinates of these tire tread points from largest to smallest, and select the top n from the sorted list. L There are n data points. L The range is 5 to 9, and the average value is used to obtain the left tread point (X). L ,Y L The formula is as follows: S42. In the tread data adjacent to the right side of the groove, select several data points sequentially from left to right as the tread points on the right side of the groove (X). Ri ,Y Ri Sort the y-coordinates of these tire tread points from largest to smallest, and select the top n from the sorted list.R There are n data points. R The range is 5 to 9, and the average value is used to obtain the right tread point (X). R ,Y R ), expressed by the formula as follows: and S43, from the left tread point (X) L ,Y L ) and right tread point (X) R ,Y R A tread line can be determined. Let the equation of this line be ax + by + c = 0. Then the coefficients of the equation can be calculated using the following formula: a = Y R -Y L b = X L -X R c = X R ×Y L -X L ×Y R S44. Calculate each data point (x) on the trench. i ,y i The distance d from the above tread line i (i = 1, 2, ..., k), the maximum value among them is the tread depth d from the groove to the adjacent tread, and the calculation formula is as follows: d = max(d i ), (i = 1, 2, ..., k).

[0011] Optionally, the specific steps for preprocessing the tire tread image in step S2 are as follows: S21, read the pre-stored camera intrinsic parameter matrix and distortion coefficients, and perform distortion correction on the tire tread image captured by the camera; S22, perform conventional filtering operations on the distortion-corrected tire tread image to complete the denoising process of the tire tread image.

[0012] Optionally, the present invention also discloses a tire tread depth measurement system, which includes an external information unit, a system main unit, and a system platform unit. The system main unit includes a tire tread image acquisition module, a tire tread image preprocessing module, a tire tread feature recognition module, a tire tread depth calculation module, and an information unit interface module. The tire tread image acquisition module is used to acquire tire tread images. The tire tread image preprocessing module is used to perform distortion and noise reduction processing on the tire tread images. The tire tread feature recognition module is used to generate tire tread groove group data. The tire tread depth calculation module is used to calculate the tire tread depth. The information unit interface module is used for human-computer interaction interface functions.

[0013] Optionally, the tire tread image acquisition module includes a line structured light laser and a camera. The line structured light laser projects line structured light onto the tire cross-section, and the camera takes pictures of the laser stripe patterns generated by the line structured light on the tire surface and grooves.

[0014] Optionally, the present invention also discloses a tire tread depth measuring device, the tire tread depth measuring device comprising: a tire tread image acquisition module for acquiring tire tread images; a tire tread image preprocessing module for performing distortion and noise reduction processing on the tire tread images; a tire tread feature recognition module for generating tire tread groove group data; a tire tread depth calculation module for calculating the tire tread depth; and an information unit interface module for human-computer interaction interface functions.

[0015] The beneficial effects of this invention are as follows:

[0016] The tire tread depth measurement method includes the following steps: S1, a laser projects structured light onto the tire cross-section where the tread depth needs to be detected to generate laser stripes, and a camera captures the laser stripes to generate a tire tread image; S2, tire tread image preprocessing, performing camera distortion correction and noise reduction on the tire tread image; S3, tire tread feature recognition, performing multiple scans and calculations on the tire tread image, and gradually outputting the various tire tread features contained in the tire tread image to form effective tread groove group data; S4, tire tread depth calculation, using a pre-stored homography transformation matrix, converting the tread groove group data in the image coordinate system into laser plane coordinate data, and calculating the tire tread depth by the distance from the groove to the adjacent tread. This invention can quickly and conveniently obtain tire tread depth values, with accurate calculation results and good repeatability. Utilizing the interface capabilities provided by the measurement system, the calculation results can be sent to an external information unit to meet the needs of information processing. Simultaneously, upgrading the hardware equipment such as the camera and laser used for acquisition further improves the accuracy of the tire tread depth calculation results. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of the structure of the tire tread depth measurement system provided by the present invention;

[0019] Figure 2 This is a flowchart illustrating the tire tread depth measurement method provided by the present invention;

[0020] Figure 3 This is a schematic diagram of a digital image of laser stripes captured by the camera provided by the present invention;

[0021] Figure 4 This is a schematic diagram of the process for acquiring tire tread images provided by the present invention;

[0022] Figure 5 This is a schematic diagram of the tire tread image recognition process provided by the present invention;

[0023] Figure 6 This is a schematic diagram of the effective tread groove group identified by the tread image recognition module provided by the present invention;

[0024] Figure 7 This is a schematic diagram of the tread depth calculated by the tread depth calculation module provided by the present invention.

[0025] Figure 8 This is a schematic diagram of the process for calculating tire tread depth according to an embodiment of the present invention. Detailed Implementation

[0026] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. It is understood that the specific embodiments described herein are only for explaining the present invention and not for limiting the present invention. Furthermore, it should be noted that, for ease of description, only the parts related to the present invention are shown in the drawings, not all structures. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0027] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0028] Please see Figures 1 to 8 The present invention provides a method for measuring tire tread depth, comprising the following steps: S1, a laser projects structured light onto the tire cross-section to be tested for tread depth to generate laser stripes, and a camera captures the laser stripes to generate a tread image; S2, tread image preprocessing, performing camera distortion correction and noise reduction on the tread image; S3, tread feature recognition, performing multiple scans and calculations on the tread image, and gradually outputting the various tread features contained in the tread image to form effective tread groove group data; S4, tread depth calculation, using a pre-stored homography transformation matrix, converting the tread groove group data in the image coordinate system into laser plane coordinate data, and calculating the tread depth by the distance from the groove to the adjacent tread.

[0029] The tread groove group data includes tread segment T, groove segment G, the falling edge D from the tread to the groove, and the rising edge U from the groove to the tread. (See Appendix) Figure 6 It can be seen that the appendix Figure 6 From left to right, the order is TDGUT, which constitutes two effective tread groove groups.

[0030] In this embodiment, the specific steps of performing multi-round scanning and calculation analysis on the tire tread image in step S3 are as follows: S31, extract the center points of the laser stripes in the tire tread image, and construct a continuous list of laser stripe center point data by identifying the center points of the laser stripes. Each data list consists of the horizontal position of the image point, the vertical position of the image point, and the gray value; S32, scan the list of laser stripe center point data from the beginning according to the set gradient change range, and divide the list of laser stripe center point data into several continuous different intervals. Data points in the same interval have approximately the same gradient change, while different intervals have different gradient changes; S33, identify candidate segments that can be used as falling edges and rising edges, traverse each interval, and perform multi-round scanning and calculation analysis according to the set gradient change range. S34. Select candidate segments for falling and rising edges based on the gradient change rate range; S35. Identify invalid data segments by traversing each interval segment and analyzing the gradient change rate and interrelationship between each interval segment and its adjacent interval segments, filtering out abnormal data and marking them as invalid data segments; S36. Traverse each interval segment and merge adjacent interval segments with gradient changes within the set range, merging interval segments with similar gradient change relationships; S37. Traverse the candidate segments for falling and rising edges, identifying adjacent ordinary data segments of falling and rising edges as tread and groove data segments respectively; S38. Starting from the leftmost tread data segment, check its subsequent consecutive interval segments, identifying consecutive data segments that meet the conditions for valid tread and groove groups.

[0031] In step S31, the center point of the laser stripe refers to the data point with the largest gray value in each column of image points. In step S33, the falling edge refers to the transition section from the tread to the groove, and the rising edge refers to the transition section from the groove to the tread.

[0032] The step S4, which calculates the distance from the groove to the adjacent tread, is as follows: S41, in the tread data adjacent to the left side of the groove, select several data points sequentially from right to left as the tread point (X) on the left side of the groove. Li ,Y Li Sort the y-coordinates of these tire tread points from largest to smallest, and select the top n from the sorted list. L There are n data points. L The range is 5 to 9, and the average value is used to obtain the left tread point (X). L ,Y L The formula is as follows: S42. In the tread data adjacent to the right side of the groove, select several data points sequentially from left to right as the tread points on the right side of the groove (X). Ri ,Y Ri Sort the y-coordinates of these tire tread points from largest to smallest, and select the top n from the sorted list. R There are n data points. R The range is 5 to 9, and the average value is used to obtain the right tread point (X). R ,Y R ), expressed by the formula as follows: and S43, from the left tread point (X) L ,Y L ) and right tread point (X) R ,Y R A tread line can be determined. Let the equation of this line be ax + by + c = 0. Then the coefficients of the equation can be calculated using the following formula: a = Y R -Y L b = X L -X R c = X R ×Y L -X L ×Y R S44. Calculate each data point (x) on the trench. i ,y i The distance d from the above tread line i (i = 1, 2, ..., k), the maximum value among them is the tread depth d from the groove to the adjacent tread, and the calculation formula is as follows: d = max(d i ), (i = 1, 2, ..., k).

[0033] The specific steps for preprocessing the tire tread image in step S2 are as follows: S21, read the pre-stored camera intrinsic parameter matrix and distortion coefficients, and perform distortion correction on the tire tread image captured by the camera; S22, perform conventional filtering operations on the distortion-corrected tire tread image to complete the denoising process of the tire tread image.

[0034] This invention also discloses a tire tread depth measurement system, which includes an external information unit, a system main unit, and a system platform unit. The system main unit includes a tire tread image acquisition module, a tire tread image preprocessing module, a tire tread feature recognition module, a tire tread depth calculation module, and an information unit interface module. The tire tread image acquisition module is used to acquire tire tread images. The tire tread image preprocessing module is used to perform distortion and noise reduction processing on the tire tread images. The tire tread feature recognition module is used to generate tire tread groove group data. The tire tread depth calculation module is used to calculate the tire tread depth. The information unit interface module is used for human-computer interaction interface functions.

[0035] The tire tread image preprocessing module receives the tire tread image from the tire tread image acquisition module, performs camera distortion correction and noise reduction on the image, and then sends the preprocessed image to the tire tread feature recognition module. This module utilizes various gradient analysis techniques to perform multiple scans and calculations on the tire tread image, gradually outputting various tire tread features, including the tread surface, grooves, the descending edge from the tread surface to the groove, and the ascending edge from the groove to the tread surface. These local features ultimately form valid tread groove group data. The tire tread depth calculation module receives this data and uses a pre-stored homography transformation matrix to convert the image coordinate system data into laser plane coordinate data. The tire tread depth can then be calculated from the distance from the groove to the adjacent tread surface. The information unit interface module is responsible for human-computer interaction functions such as the user interface and data display. It also provides an information interface to external information units for further information processing.

[0036] The tire tread image acquisition module includes a line structured light laser and a camera. The line structured light laser projects line structured light onto the tire cross-section, and the camera takes pictures of the laser stripe patterns generated by the line structured light on the tire surface and grooves.

[0037] The present invention also discloses a tire tread depth measuring device, which includes: a tire tread image acquisition module for acquiring tire tread images; a tire tread image preprocessing module for performing distortion and noise reduction processing on the tire tread images; a tire tread feature recognition module for generating tire tread groove group data; a tire tread depth calculation module for calculating the tire tread depth; and an information unit interface module for human-computer interaction interface functions.

[0038] The tire tread depth measurement method includes the following steps: S1, a laser projects structured light onto the tire cross-section where the tread depth needs to be detected to generate laser stripes, and a camera captures the laser stripes to generate a tire tread image; S2, tire tread image preprocessing, performing camera distortion correction and noise reduction on the tire tread image; S3, tire tread feature recognition, performing multiple scans and calculations on the tire tread image, and gradually outputting the various tire tread features contained in the tire tread image to form effective tread groove group data; S4, tire tread depth calculation, using a pre-stored homography transformation matrix, converting the tread groove group data in the image coordinate system into laser plane coordinate data, and calculating the tire tread depth by the distance from the groove to the adjacent tread. This invention can quickly and conveniently obtain tire tread depth values, with accurate calculation results and good repeatability. Utilizing the interface capabilities provided by the measurement system, the calculation results can be sent to an external information unit to meet the needs of information processing. Simultaneously, upgrading the hardware equipment such as the camera and laser used for acquisition further improves the accuracy of the tire tread depth calculation results.

[0039] The above description is merely an embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. A method for measuring tire tread depth, characterized in that, Includes the following steps: S1. A laser projects structured light onto the tire cross-section where the tread depth needs to be detected to generate laser stripes. A camera captures the laser stripes to generate a tread image. S2. Tire tread image preprocessing: performing camera distortion correction and noise reduction processing on the tire tread image; S3. Tread feature recognition: The tread image is scanned and analyzed in multiple rounds, and the various tread features contained in the tread image are output step by step to form effective tread groove group data. The tread groove group data includes tread segment T, groove segment G, tread to groove descending edge D, and groove to tread ascending edge U. S4. Tread depth calculation: Using the pre-stored homography transformation matrix, the tread groove group data in the image coordinate system is converted into laser plane coordinate data, and the tread depth is calculated by the distance from the groove to the adjacent tread. The specific steps for performing multi-round scanning and calculation analysis on the tire tread image in step S3 are as follows: S31. Extract the center point of the laser stripe in the tire tread image. By identifying the center point of the laser stripe, construct a continuous list of laser stripe center point data. Each data list consists of the horizontal position of the image point, the vertical position of the image point, and the gray value. The center point of the laser stripe refers to the data point with the largest gray value in each column of image points. S32. According to the set gradient change range, scan the laser stripe center point data list from the beginning, divide the laser stripe center point data list into several consecutive different intervals, the data points in the same interval have approximately the same gradient change, and the gradient changes in different intervals are different. S33. Identify candidate segments that can serve as falling edges and rising edges, traverse each interval segment, and select candidate segments that can serve as falling edges and rising edges according to the set gradient change rate range of falling edges and rising edges. The falling edge refers to the transition interval segment from the tread to the groove, and the rising edge refers to the transition interval segment from the groove to the tread. S34. Identify invalid data segments. Continue to traverse each interval segment, analyze the gradient change rate and interrelationship between each interval segment and its adjacent interval segments, and filter out abnormal data and mark them as invalid data segments. S35. Traverse each interval segment and merge adjacent interval segments whose gradient changes are within the set range. The merged interval segments have similar gradient change relationships. S36. Traverse the candidate segments of falling edge and rising edge, and identify the adjacent ordinary data segments of falling edge and rising edge as tread and groove data segments respectively. S37. Starting from the leftmost tread data segment, check its subsequent consecutive interval segments and identify the consecutive data segments that meet the conditions for a valid tread groove group. The step S4, which calculates the distance from the groove to the adjacent tread, is as follows: S41. In the tread data adjacent to the left side of the groove, select several data points sequentially from right to left as the left tread point (X). Li Y Li Sort the y-coordinates of these tire tread points from largest to smallest, and select the top n from the sorted list. L There are n data points. L The range is 5 to 9, and the average value is used to obtain the left tread point (X). L Y L The formula is as follows: S42. In the tread data adjacent to the right side of the groove, select several data points sequentially from left to right as the tread points on the right side of the groove (X). Ri Y Ri Sort the y-coordinates of these tire tread points from largest to smallest, and select the top n from the sorted list. R There are n data points. R The range is 5 to 9, and the average value is used to obtain the right tread point (X). R Y R The formula is as follows: S43, from the left tread point (X) L Y L ) and right tread point (X) R Y R A tread line can be determined. Let the equation of this line be ax + by + c = 0. Then the coefficients of the equation can be calculated using the following formula: a=Y R -AND L ; b=X L -X R ; c=X R ×Y L -X L ×Y R ; S44. Calculate each data point (x) on the trench. i y i The distance d from the above tread line i (i = 1, 2, ..., k), the maximum value among them is the tread depth d from the groove to the adjacent tread, and the calculation formula is as follows: d=max(d i ),(i=1,2,...,k)。 2. The method for measuring tire tread depth according to claim 1, characterized in that, In step S2, the tire tread pattern is... The specific steps of preprocessing are as follows: S21. Read the pre-stored camera intrinsic parameter matrix and distortion coefficients, and perform distortion correction on the tire tread image captured by the camera. S22. Perform a conventional filtering operation on the distorted tire tread image to complete the denoising process of the tire tread image.

3. A tire tread depth measurement system, characterized in that, The tire tread depth measurement system includes an external information unit, a main system unit, and a system platform unit. The main unit of the system includes a tire tread image acquisition module, a tire tread image preprocessing module, a tire tread feature recognition module, a tire tread depth calculation module, and an information unit interface module. The tire tread image acquisition module is used to acquire tire tread images. The tire tread image preprocessing module is used to perform distortion and noise reduction processing on the tire tread images. The tire tread feature recognition module is used to generate tire tread groove group data. The tire tread depth calculation module is used to calculate the tire tread depth. The information unit interface module is used for human-computer interaction interface functions. When the tire tread image acquisition module acquires tire tread images, it executes step S1: the laser projects line structured light onto the tire cross-section where the tire tread depth needs to be detected to generate laser stripes, and the camera captures the laser stripes to generate a tire tread image. When the tire tread image preprocessing module performs distortion correction and noise reduction on the tire tread image, it executes step S2: tire tread image preprocessing, which performs camera distortion correction and noise reduction on the tire tread image. When the tread feature recognition module generates tread groove group data, it executes step S3: tread feature recognition, performs multiple rounds of scanning and calculation analysis on the tread image, and gradually outputs the various tread features contained in the tread image to form effective tread groove group data. The tread groove group data includes tread segment T, groove segment G, falling edge D from tread to groove, and rising edge U from groove to tread. When the tire tread depth calculation module calculates the tire tread depth, it executes step S4: tire tread depth calculation. Using the pre-stored homography transformation matrix, the tire tread groove group data in the image coordinate system is converted into laser plane coordinate data, and the tire tread depth is calculated by the distance from the groove to the adjacent tire tread. The specific steps for performing multi-round scanning and calculation analysis on the tire tread image in step S3 are as follows: S31. Extract the center point of the laser stripe in the tire tread image. By identifying the center point of the laser stripe, construct a continuous list of laser stripe center point data. Each data list consists of the horizontal position of the image point, the vertical position of the image point, and the gray value. The center point of the laser stripe refers to the data point with the largest gray value in each column of image points. S32. According to the set gradient change range, scan the laser stripe center point data list from the beginning, divide the laser stripe center point data list into several consecutive different intervals, the data points in the same interval have approximately the same gradient change, and the gradient changes in different intervals are different. S33. Identify candidate segments that can serve as falling edges and rising edges, traverse each interval segment, and select candidate segments that can serve as falling edges and rising edges according to the set gradient change rate range of falling edges and rising edges. The falling edge refers to the transition interval segment from the tread to the groove, and the rising edge refers to the transition interval segment from the groove to the tread. S34. Identify invalid data segments. Continue to traverse each interval segment, analyze the gradient change rate and interrelationship between each interval segment and its adjacent interval segments, and filter out abnormal data and mark them as invalid data segments. S35. Traverse each interval segment and merge adjacent interval segments whose gradient changes are within the set range. The merged interval segments have similar gradient change relationships. S36. Traverse the candidate segments of falling edge and rising edge, and identify the adjacent ordinary data segments of falling edge and rising edge as tread and groove data segments respectively. S37. Starting from the leftmost tread data segment, check its subsequent consecutive interval segments and identify the consecutive data segments that meet the conditions for a valid tread groove group.

4. The tire tread depth measurement system according to claim 3, characterized in that, The tire tread image acquisition module includes a line structured light laser and a camera. The line structured light laser projects line structured light onto the tire cross-section, and the camera takes pictures of the laser stripe patterns generated by the line structured light on the tire surface and grooves.

5. A tire tread depth measuring device, characterized in that, The tire tread depth measuring device includes: Tire tread image acquisition module, used to acquire tire tread images; The tire tread image preprocessing module is used to perform distortion correction and noise reduction on tire tread images; The tread feature recognition module is used to generate tread groove group data; The tread depth calculation module is used to calculate the tread depth. Information unit interface module, used for human-computer interaction interface functions; When the tire tread image acquisition module acquires tire tread images, it executes step S1: the laser projects line structured light onto the tire cross-section where the tire tread depth needs to be detected to generate laser stripes, and the camera captures the laser stripes to generate a tire tread image. When the tire tread image preprocessing module performs distortion correction and noise reduction on the tire tread image, it executes step S2: tire tread image preprocessing, which performs camera distortion correction and noise reduction on the tire tread image. When the tread feature recognition module generates tread groove group data, it executes step S3: tread feature recognition, performs multiple rounds of scanning and calculation analysis on the tread image, and gradually outputs the various tread features contained in the tread image to form effective tread groove group data. The tread groove group data includes tread segment T, groove segment G, falling edge D from tread to groove, and rising edge U from groove to tread. When the tire tread depth calculation module calculates the tire tread depth, it executes step S4: tire tread depth calculation. Using the pre-stored homography transformation matrix, the tire tread groove group data in the image coordinate system is converted into laser plane coordinate data, and the tire tread depth is calculated by the distance from the groove to the adjacent tire tread. The specific steps for performing multi-round scanning and calculation analysis on the tire tread image in step S3 are as follows: S31. Extract the center point of the laser stripe in the tire tread image. By identifying the center point of the laser stripe, construct a continuous list of laser stripe center point data. Each data list consists of the horizontal position of the image point, the vertical position of the image point, and the gray value. The center point of the laser stripe refers to the data point with the largest gray value in each column of image points. S32. According to the set gradient change range, scan the laser stripe center point data list from the beginning, divide the laser stripe center point data list into several consecutive different intervals, the data points in the same interval have approximately the same gradient change, and the gradient changes in different intervals are different. S33. Identify candidate segments that can serve as falling edges and rising edges, traverse each interval segment, and select candidate segments that can serve as falling edges and rising edges according to the set gradient change rate range of falling edges and rising edges. The falling edge refers to the transition interval segment from the tread to the groove, and the rising edge refers to the transition interval segment from the groove to the tread. S34. Identify invalid data segments. Continue to traverse each interval segment, analyze the gradient change rate and interrelationship between each interval segment and its adjacent interval segments, and filter out abnormal data and mark them as invalid data segments. S35. Traverse each interval segment and merge adjacent interval segments whose gradient changes are within the set range. The merged interval segments have similar gradient change relationships. S36. Traverse the candidate segments of falling edge and rising edge, and identify the adjacent ordinary data segments of falling edge and rising edge as tread and groove data segments respectively. S37. Starting from the leftmost tread data segment, check its subsequent consecutive interval segments and identify the consecutive data segments that meet the conditions for a valid tread groove group.

Images