Tread depth estimation system and method

A computerized tire inspection system using angled imaging and lighting captures tire images to segment and estimate tread depth, addressing manual inspection inefficiencies and inaccuracies with enhanced precision and efficiency.

JP7593603B2Active Publication Date: 2024-12-03UVEYE LTD
View PDF 10 Cites 0 Cited by

Patent Information

Application Number
JP2023519295
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Priority Date
2020-09-30
Filing Date
2021-09-12
Publication Date
2024-12-03
Estimated Expiration
2041-09-12

AI Technical Summary

Technical Problem

Current tire inspection methods for tread depth are manual, expensive, time-consuming, and prone to errors, lacking accuracy and efficiency.

Method used

A computerized system using an imaging device and lighting device positioned at specific angles to capture tire images, performing image segmentation and estimating tread depth based on illuminated and shadowed areas, with optional machine learning for enhanced precision.

Benefits of technology

Automatically provides accurate tire tread depth measurements, reducing human error and costs while improving inspection efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007593603000001
    Figure 0007593603000001
  • Figure 0007593603000002
    Figure 0007593603000002
  • Figure 0007593603000003
    Figure 0007593603000003
Patent Text Reader

Abstract

A method and system for estimating tread depth of a tire is provided, comprising: acquiring an image of the tire providing information about the tread and grooves embedded therein, the image being acquired by an imaging device from a first angle relative to a horizontal direction perpendicular to the tread surface, and the tire being illuminated by an illumination device from a second angle relative to the horizontal direction, producing shadowed and illuminated portions on the bottoms and / or sidewalls of the grooves, the first angle being less than the second angle such that the image captures at least a portion of the illuminated and shadowed portions; performing segmentation on the image to obtain image segments corresponding to at least a portion of the illuminated and shadowed portions; and estimating tread depth based on the image segments, the groove width, and the second angle.
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The subject matter of this disclosure relates generally to the field of tire inspection, and more specifically, to methods and systems for tread depth estimation. [Background technology]

[0002] Tires are a critical component of a vehicle because they are the only part of the vehicle that comes into direct contact with the road. Tires can affect the handling and safety of a vehicle due to their functions of supporting the vehicle load, transmitting traction and braking forces to the road surface, absorbing road shocks, and changing and maintaining direction of travel. For optimal performance, tires must have the correct inflation pressure, tread depth, balance, etc., and the vehicle's wheels must be properly installed and maintained. Thus, for at least safety and economic reasons, tires must be inspected periodically.

[0003] The tread of a tire refers to the rubber on its circumference that comes into contact with the road or ground. The tread is a critical part of the tire and its importance ranges from safety to economy. It gives the tire the ability to grip the road and helps maximize fuel economy.

[0004] As a tire is used, the tread gradually wears down, limiting its effectiveness in providing traction. Thus, over time, the tire becomes less effective at gripping the road. In some cases, if the tread wears excessively, it can become a significant safety hazard. Tire grooves are designed to evacuate water from under the tire and prevent hydroplaning. Shallow tread grooves also make it more difficult to control the vehicle in rainy weather, increasing the likelihood of hydroplaning.

[0005] Current inspection of tires for wear and damage is typically performed manually at an inspection station. For example, tread depth, which is the vertical measurement from the top of the tire's rubber to the bottom of the tire's groove, can be obtained as an important indicator of the condition of the tire. Tire tread depth gauges are often used to measure tread depth by inserting a probe bar into the groove and pressing the shoulder flush with the tread. The depth measurement can be read from the top of the gauge. However, such manual inspection is not only expensive and time consuming, but is also prone to inspection errors and variability caused by the particular personnel performing the inspection.

[0006] Although certain aspects of tire inspection have been partially automated with advances in computer technology, there remains a need for inspection systems that can automatically provide accurate information regarding the condition of the tread. Summary of the Invention

[0007] According to certain aspects of the subject matter of the present disclosure, there is provided a computerized system for estimating tread depth of a tire, the system including processing and memory circuitry. a processing and memory circuitry (PMC) configured to: acquire from an imaging device an image of a tire positioned on an inspection lane, the image providing information of the tire's tread and one or more grooves embedded therein; the imaging device being positioned on at least one side of the inspection lane; the image being acquired by the imaging device from a first angle relative to a horizontal direction perpendicular to a surface of the tread; the tire being illuminated by an illumination device from a second angle relative to the horizontal direction resulting in shadowed and illuminated portions at a bottom and / or sidewall of at least one groove, the imaging device and illumination device being positioned to have a first angle less than the second angle such that the image captures at least a portion of the illuminated and shadowed portions; perform segmentation on the image to acquire at least a first image segment corresponding to the illuminated portion and a second image segment corresponding to at least a portion of the shadowed portion; acquire a groove width of the at least one groove; and estimate a tread depth based on at least the first image segment, the groove width, and the second angle.

[0008] In addition to the features described above, systems according to this aspect of the disclosed subject matter may include one or more of the features (i)-(xi) listed below, in any desired combination or permutation that is technically possible. (i) the first image segment indicates that the illuminated portion is completely on a sidewall of at least one groove, and the estimating includes determining a range of tread depth based on the groove width and the second angle. (ii) the first image segment includes a first sub-segment corresponding to a first sub-section of the illuminated portion located at a bottom of the at least one groove and a second sub-segment corresponding to a second sub-section of the illuminated portion located on a sidewall of the at least one groove, and the estimating includes measuring a width of the first sub-segment, calculating a width of the shadow portion using the width of the first sub-segment and the groove width, and estimating a tread depth of the tire using the width of the shadow portion and the second angle. (iii) The system further comprises an imaging device and an illumination device disposed adjacent to each other on at least one side of the inspection lane, where at least the imaging device is operably connected to the PMC. (iv) the second angle is configured to accommodate different tire characteristics, including different groove widths and / or tire positions on the inspection lane, to provide an estimate of tread depth within a predetermined depth range for different tires. (v) The PMC is further configured to compare the tread depth with a predetermined standard to determine whether the tire should be replaced. (vi) Segmentation is performed using a segmentation learning model trained to segment tire images according to different illumination levels. (vii) the image provides information of one or more tread wear bars, and the PMC is further configured to estimate a depth of at least one of the tread wear bars. (viii) the images provide information of one or more tires, and the PMC is configured to extract one or more sub-images corresponding to the one or more tires and perform segmentation and estimation for each of the one or more sub-images. (ix) the tire is a rotating tire on a moving vehicle, and the PMC is configured to acquire a series of images of the tire during relative motion between the tire and the imaging device, and perform segmentation and estimation on at least some of the series of images to obtain an estimated tread depth covering at least a portion of a circumference of the tire. (x) the image is segmented into a plurality of image patches corresponding to a plurality of measurement locations on at least one groove, and the PMC is configured to perform segmentation and estimation for a first image patch that is in a horizontal plane relative to the illumination device, the imaging device, and the center of the tire using a second angle, and for at least a second image patch that is above or below the horizontal plane, the PMC is configured to obtain a 3D second angle corresponding to the measurement location in the second image patch and perform segmentation and estimation for the second image patch using the 3D second angle. (xi) A 3D second angle is obtained by performing a correction to the second angle based on the relative position of the measurement position to the horizontal plane and the radius of the tire.

[0009] According to another aspect of the subject matter of the present disclosure, there is provided a computerized method of estimating tread depth of a tire, the method being executed by a processing and memory circuit (PMC) and comprising acquiring, from an imaging device, an image of a tire positioned on an inspection lane, the image providing information of the tire's tread and one or more grooves embedded therein, the imaging device being positioned on at least one side of the inspection lane, the image being acquired by the imaging device from a first angle relative to a horizontal direction perpendicular to a surface of the tread, the tire being illuminated by an illumination device from a second angle relative to the horizontal direction, and an image of a bottom of the at least one groove being captured by the imaging device. and / or a sidewall, the imaging device and the illumination device are positioned to have a first angle smaller than the second angle such that the image captures at least a portion of the illuminated and shadowed portions; performing segmentation on the image to obtain at least a first image segment corresponding to the illuminated portions and a second image segment corresponding to at least a portion of the shadowed portions; obtaining a groove width of at least one groove; and estimating a tread depth based on at least the first image segment, the groove width, and the second angle.

[0010] This aspect of the disclosed subject matter may suitably include one or more of the above system features (i)-(xi) in any desired combination or permutation that is technically possible, mutatis mutandis.

[0011] According to another aspect of the subject matter of the present disclosure, there is provided a non-transitory computer readable storage medium tangibly embodying a program of instructions that, when executed by a computer, causes the computer to perform a method of estimating tread depth of a tire, the method comprising: acquiring, from an imaging device, an image of a tire positioned on an inspection lane, the image providing information of the tire's tread and one or more grooves embedded therein, the imaging device being positioned on at least one side of the inspection lane, the image being acquired by the imaging device from a first angle relative to a horizontal direction perpendicular to a surface of the tread, and the tire being illuminated by an illumination device from a second angle relative to the horizontal direction. a first angle that is less than a second angle, the imaging device and the illumination device being positioned to have a first angle that produces shadow and illuminated portions on a bottom and / or sidewall of at least one groove, such that the image captures at least a portion of the illuminated and shadowed portions; performing segmentation on the image to obtain at least a first image segment that corresponds to the illuminated portions and a second image segment that corresponds to at least a portion of the shadowed portions; obtaining a groove width of the at least one groove; and estimating a tread depth based on at least the first image segment, the groove width, and the second angle.

[0012] This aspect of the disclosed subject matter may suitably include one or more of the above system features (i)-(xi) in any desired combination or permutation that is technically possible, mutatis mutandis. [Brief description of the drawings]

[0013] In order to understand the present disclosure and how it may be carried out in practice, embodiments will now be described, by way of non-limiting example only, with reference to the accompanying drawings, in which: [Figure 1A] 1 illustrates generally a functional block diagram of a tire inspection system in accordance with certain embodiments of the presently disclosed subject matter. [Figure 1B] 1 illustrates generally a generalized block diagram of a computerized system for tread depth estimation in accordance with certain embodiments of the subject matter of the present disclosure. [Diagram 2] 1 illustrates a generalized flow chart of tread depth estimation according to certain embodiments of the presently disclosed subject matter. [Diagram 3] 1 illustrates a generalized flowchart of tread depth estimation when the illuminated portion hits both the bottom and sidewall of the groove, according to certain embodiments of the disclosed subject matter. [Figure 4] 1 is a schematic diagram of a system configuration of an imaging device and an illumination device relative to a tire, in accordance with certain embodiments of the subject matter of this disclosure. [Diagram 5] 1 shows two example tire images according to certain embodiments of the subject matter of this disclosure. [Figure 6A] 1A-1C are diagrams illustrating example image patches from a tire image showing shadow and illuminated areas, in accordance with certain embodiments of the disclosed subject matter. [Figure 6B] 1 illustrates an example of a segmented tire image in accordance with certain embodiments of the subject matter of this disclosure. [Figure 7] 1 illustrates generally one example of how to estimate tread depth in accordance with certain embodiments of the subject matter of the present disclosure. [Figure 8] 1 shows a table illustrating the correlation between different groove widths and estimated tread depth according to certain embodiments of the subject matter of the present disclosure. [Figure 9] FIG. 2 illustrates a tire having tread wear bars spaced through the grooves in accordance with certain embodiments of the subject matter of this disclosure. [Figure 10A] 1 illustrates examples of image patches extracted from different locations of a tire image, according to certain embodiments of the subject matter of this disclosure. [Figure 10B] 1 illustrates an example tire having tread and grooves in a direction that is not parallel to the circumference of the tire, according to certain embodiments of the subject matter of this disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure. However, it will be understood by those skilled in the art that the subject matter of the present disclosure may be practiced without these specific details. In other instances, well-known methods, procedures, components, and circuits have not been described in detail so as not to obscure the subject matter of the present disclosure.

[0015] Unless otherwise indicated, and as will be apparent from the following description, throughout the specification, descriptions using terms such as "obtain," "capture," "perform," "estimate," "segment," "measure," "calculate," "compare," "extract," "inspect," "select," "use," and the like refer to computer operations and / or processes that manipulate and / or transform data into other data, where the data is represented as physical quantities, e.g., electronic quantities, and / or the data represents physical objects. The term "computer" should be interpreted broadly to cover any kind of hardware-based electronic device with data processing capabilities, including, as non-limiting examples, the tire inspection system, tread depth estimation system and portions thereof disclosed in this application.

[0016] Operations according to the teachings herein can be performed by a specially constructed computer for the desired purpose, or by a general-purpose computer specially configured for the desired purpose by a computer program stored on a non-transitory computer-readable storage medium.

[0017] As used herein, the terms “non-transitory memory,” “non-transitory storage medium,” and “non-transitory computer-readable storage medium” should be interpreted broadly to include any volatile or non-volatile computer memory suitable for the presently disclosed subject matter.

[0018] Embodiments of the presently disclosed subject matter are not described with reference to any particular programming language, it will be appreciated that a variety of programming languages ​​can be used to implement the teachings of the presently disclosed subject matter as described herein.

[0019] As used herein, phrases such as "for example," "such as," "for example," and variations thereof describe non-limiting embodiments of the subject matter of the present disclosure. References herein to "one instance," "several instances," "other instances," or variations thereof mean that a particular feature, structure, or characteristic described in connection with an embodiment is included in at least one embodiment of the subject matter of the present disclosure. Thus, appearances of the phrases "one instance," "several instances," "other instances," or variations thereof do not necessarily refer to the same embodiment.

[0020] It should be understood that certain features of the presently disclosed subject matter that are described in the context of separate embodiments can also be provided in combination in a single embodiment, unless otherwise specified. Conversely, various features of the presently disclosed subject matter that are described in the context of a single embodiment can also be provided separately or in any suitable subcombination. In the following detailed description, numerous specific details are set forth in order to provide a thorough understanding of the methods and apparatus.

[0021] In embodiments of the presently disclosed subject matter, one or more of the steps illustrated in the figures may be performed in a different order and / or one or more groups of the steps may be performed simultaneously, or vice versa.

[0022] With this in mind, attention is directed to FIG. 1A, which illustrates generally a functional block diagram of a tire inspection system in accordance with certain embodiments of the presently disclosed subject matter.

[0023] 1A is a computer-based tire inspection system for automatically inspecting one or more tires of a vehicle (also referred to herein as the tire being inspected). Tires are used on many types of vehicles, including, but not limited to, automobiles, bicycles, motorcycles, buses, trucks, heavy equipment, and aircraft, and the present disclosure is not limited to inspecting tires of any particular type of vehicle.

[0024] The system 100 comprises a computerized system 101 configured for automatic tread depth estimation and at least one set of an image acquisition device 130 (also referred to herein as an imaging device) and an illumination device 132. In particular, the system 101 can be configured to acquire one or more images of at least one tire 112 positioned on an inspection lane 110 from the imaging device 130, and automatically estimate the tread depth of the tire based on the captured images. In some cases, the tire to be inspected can be associated with a vehicle 114 positioned on or passing through the inspection lane. In some other cases, the tire to be inspected can be a stand-alone tire.

[0025] As mentioned above, the tread of a tire (also called tire tread or simply tread) refers to the rubber on the circumference of the tire that contacts the ground. Grooves embedded or molded into the rubber form the tread pattern. The grooves are designed to evacuate water from under the tire and prevent hydroplaning. As a tire is used, the tread wears, limiting its effectiveness in providing traction and the vehicle may experience extended braking distances. Shallow tread grooves also make it more difficult to control the vehicle in wet weather, increasing the likelihood of hydroplaning. To assess tread wear condition, tread depth can be estimated and provided as a direct indication of the condition of the tire.

[0026] As used herein, the term "tread depth" refers to the depth of the grooves (pattern) on a tire tread. Tread depth is the vertical measurement from the top of the tire's rubber (i.e., the surface of the tread) to the bottom of the tire's grooves. Tread depth can be measured at several locations along the width of the tire. New tires typically have an average tread depth of 8 to 9 millimeters (10 / 32 to 11 / 32 inches). Different countries may have different legal limitations and requirements for tread depth. For example, most states and tire manufacturers in the United States consider a tire to be worn down when one or more of the tire's grooves have worn down to 1.6 millimeters (2 / 32 inches) and the tire must be replaced. For safety reasons, in some cases, it is recommended that summer tires have a minimum tread depth of 3 millimeters and winter tires have at least 4 millimeters (5 / 32 inches).

[0027] Continuing with FIG. 1A , the imaging device 130 can be located (e.g., mounted or otherwise positioned) on at least one side of the tire 112 (e.g., on at least one side of the inspection lane 110) and can be configured to capture one or more images of the tire. According to certain embodiments, the imaging device 130 is positioned / oriented to face the tire from a first angle relative to a horizontal direction perpendicular to a surface of the tire tread, and one or more images are captured by the imaging device from the first angle. The images captured by the imaging device 130 can provide information of the tire tread and one or more grooves embedded therein, as described above. The imaging device 130 can be operatively connected to the system 101, and the captured images can be transmitted to the system 101 for processing via wired or wireless communication.

[0028] It should be noted that an imaging device as used herein may refer to any type of image capture device or general-purpose device with image capture capabilities that can be used to capture tire images at a particular resolution and / or frequency, such as, for example, a digital camera with image and / or video recording capabilities.

[0029] The illumination device 132 is positioned proximate to the imaging device 130 (e.g., on the same side of the tire as the imaging device) and is configured to provide illumination that covers the field of view (FOV) of the imaging device to enable images to be captured with relatively high resolution and quality. In some cases, the imaging device and / or the illumination device can be mounted to a support structure, such as a pole located on at least one side of the inspection lane. The imaging device and / or the illumination device can be mounted to the support structure at an appropriate height and / or angle relative to the tire being inspected.

[0030] Specifically, in some embodiments, the imaging device 130 is positioned / oriented to face the tire from a first angle (also referred to as an imaging angle) relative to the horizontal direction perpendicular to the surface of the tire tread, and the illumination device is positioned / oriented to illuminate the tire from a second angle (also referred to as an illumination angle) relative to the horizontal direction, resulting in shadowed and illuminated portions at the bottom and / or sidewall of at least one groove. The imaging device and illumination device are positioned to have a first angle that is smaller than the second angle, such that the image captures at least a portion of the illuminated and shadowed portions, as described in more detail below with reference to FIG.

[0031] In some embodiments, there may be a set of imaging and lighting devices located on both sides of the inspection lane (as illustrated in FIG. 1A ) so that tire images from both sides of the vehicle can be acquired and processed simultaneously. In some cases, the vehicle 114 may be a moving vehicle passing through the inspection lane and the tire being inspected is a rotating tire of the moving vehicle. In some other cases, the tire being inspected is a stationary tire, either freestanding on the inspection lane or associated with a stationary vehicle. If the tire being inspected is a rotating tire of a moving vehicle, image acquisition and / or lighting may be triggered by an external sensing device that can detect the presence / approach of the vehicle (e.g., road loop, Infra-red (IR) beam, VMD, etc.).

[0032] The system 101 may be operatively connected to an imaging device 130, and possibly also to a lighting device, which may be used to control the devices (e.g., synchronize image capture and lighting operations), calibrate the system during a set-up phase, and process captured images of the tire to estimate tread depth at run-time. In some cases, the system 101 may be operatively connected to one or more external data repositories 138.

[0033] Referring now to FIG. 1B, there is shown generally a generalized block diagram of a computerized system for tread depth estimation having certain embodiments of the subject matter of the present disclosure.

[0034] The system 101 may comprise a processing and memory circuit (PMC) 102 operatively connected to a hardware-based I / O interface 126 and a storage unit 122. The PMC 102 is configured to provide the necessary processing for the operating system 101, which will be described in further detail with reference to FIGS. 2-3. The PMC 102 comprises a processor (not shown separately) and a memory (not shown separately). The processor of the PMC 102 may be configured to execute several functional modules according to computer-readable instructions implemented on a non-transitory computer-readable memory included in the PMC. Such functional modules are hereinafter referred to as being included in the PMC. It should be noted that the term processor referred to herein should be expansively interpreted to encompass any processing circuit having data processing capabilities, and the present disclosure is not limited to its type or platform, or the number of processing cores included therein.

[0035] According to a particular embodiment, the functional modules included in the PMC 102 may include a segmentation module 104 and a depth estimation module 106 operatively connected to each other. The PMC is configured to acquire an image of the tire to be inspected from an imaging device 130 (e.g., via a hardware-based I / O interface 126). The image provides information of the tire's tread and one or more grooves embedded therein. As described above, the imaging device and the illumination device are arranged in a specific relative position such that the image acquired by the imaging device captures at least a portion of the illuminated and shaded portions at the bottom and / or sidewall of at least one groove. The segmentation module 104 may be configured to perform segmentation on the image to acquire at least a first image segment corresponding to the illuminated portion and a second image segment corresponding to at least a portion of the shaded portion. The depth estimation module 106 may be configured to acquire a groove width of at least one groove and to estimate the tread depth based on at least the first image segment, the groove width, and the second angle. Details of the processing by these functional modules are described below with reference to Figures 2 and 3.

[0036] The storage unit 122 may include an image database 123 that may be configured to store acquired images of one or more tires to be inspected. In some cases, these images may be pre-acquired from the imaging device 130 and stored in the image database 123 for retrieval and processing by the PMC. The storage unit 122 may also be configured to store any of the intermediate processing results, such as, for example, image segments, measurements, etc. Optionally, the image database 123 may reside outside the system 101, for example, in one of the external data repositories or in an external system or provider, and the images may be retrieved via the I / O interface 126.

[0037] The I / O interface 126 may be configured to take as input images acquired from an imaging device and / or an image database, and to provide as output an estimated tread depth. Optionally, the system 101 may further comprise a graphical user interface (GUI) 124 configured to render a representation of the inputs and / or outputs to a user. Optionally, the GUI may be configured to allow user-specified inputs for the operating system 101.

[0038] In some cases, the system 101 may be operatively connected to one or more external data repositories 138, which may be local or remote (e.g., cloud-based). Acquired images and / or results of run-time image processing may be stored in the storage unit 122 and / or the external data repositories 138.

[0039] It should also be noted that the system shown in Figure 1A and / or Figure 1B can be implemented in a distributed computing environment. As an example, some of the functional modules shown in Figure 1B can be distributed across several local and / or remote devices and linked through a communication network. As another example, the system 101 can be located at a different location than the imaging device.

[0040] Those skilled in the art will readily understand that the teachings of the subject matter of the present disclosure are not bound by the systems shown in Figures 1A and 1B. Equivalent and / or modified functions may be integrated or divided in other forms and implemented in appropriate combinations of software, firmware and / or hardware. The systems in Figures 1A and 1B may be standalone network entities or may be fully or partially integrated with other network entities. Those skilled in the art will also readily understand that the data repository or storage units therein may be shared with other systems or provided by other systems, including third-party equipment.

[0041] Although not necessarily, the process of operation of the system 101 may correspond to some or all of the steps of the method described with respect to Figures 2 and 3. Similarly, the methods described with respect to Figures 2 and 3 and their possible implementations may be implemented by the system 101. It should thus be noted that the embodiments discussed in relation to the methods described with respect to Figures 2 and 3 may also be implemented mutatis mutandis as various embodiments of the system 101, and vice versa.

[0042] Referring now to FIG. 2, a generalized flow chart of tread depth estimation in accordance with certain embodiments of the subject matter of this disclosure is shown.

[0043] At least one image of a tire (i.e., a tire to be inspected positioned on an inspection lane) may be acquired (202) by an imaging device (e.g., by PMC 102 via I / O interface 126 or from storage unit 122, as shown in FIG. 1B).

[0044] At least one image as used herein can refer to either i) one or more original / raw images captured by any kind of image capture device in any suitable format, or ii) one or more processed images generated after performing certain image processing procedures on the original images. In some cases, the original image captured by the imaging device can capture a larger portion of the vehicle, including not only the tire but also other components of the vehicle. In such cases, the original image may need to be segmented and / or cropped to obtain a processed tire image including the tire. As an example, if the tire is a rotating tire of a moving vehicle, the segmentation can be performed by estimating the pixel movement between two consecutive frames and separating pixels of circular movement (i.e., wheel pixels) from pixels of horizontal movement.

[0045] According to certain embodiments, multiple tires of a vehicle are inspected. In such cases, one or more images may be captured for each of the tires. If the vehicle is a moving vehicle, by way of example, the imaging device may capture multiple images of the tires at a given capture rate (e.g., 100-250 frames per second) as the vehicle passes through the inspection lane. In some cases, at least one image of the multiple captured images may be selected and used directly for further processing. In some other cases, multiple images with overlapping fields of view may be combined to form a single stitched image of the tire. Such stitched images typically have a relatively high resolution and may be used for further processing.

[0046] For simplicity and illustrative purposes, certain embodiments of the present disclosure are described with reference to tread depth estimation based on one image of a tire, however, this is not intended to limit the present disclosure in any way and the estimation methods disclosed herein may be similarly applied to multiple images of a tire, or one or more images of one or more tires on a vehicle.

[0047] As described above, the acquired images capture the tire being inspected and provide information of the tire's tread and one or more grooves embedded therein. Figure 5 shows two examples of tire images according to certain embodiments of the subject matter of this disclosure. As shown, 502 is an original image acquired by an imaging device that includes an image representation of three tires of a vehicle, and 504 is a processed tire image that has been scaled and / or cropped based on the original image and includes an image patch that represents a portion / slice of the tire. As shown, images 502 and 504 provide information of the tire's tread and one or more grooves embedded therein.

[0048] The tire images are acquired with a particular system configuration of the imaging device and the lighting device as described above with reference to FIG. 1A. Specifically, the imaging device is positioned on at least one side of the inspection lane and the images are acquired by the imaging device from a first angle relative to the horizontal direction perpendicular to the surface of the tread. The tire is illuminated by the lighting device from a second angle relative to the horizontal direction, producing shadowed and illuminated portions at the bottom and / or sidewall of at least one groove. The imaging device and the lighting device are positioned in a particular relative position to have the first angle smaller than the second angle such that the image can capture at least a portion of the illuminated and shadowed portions.

[0049] Referring now to FIG. 4, there is shown a schematic diagram of a system configuration of imaging and illumination devices relative to a tire, in accordance with certain embodiments of the subject matter of this disclosure.

[0050] Continuing with the example of FIG. 1A, the vehicle 114 is positioned on the inspection lane 110, and two tires 402 and 404 of the vehicle to be inspected are shown. As mentioned above, the vehicle 114 can be a moving vehicle passing through the inspection lane, or a stationary vehicle parked in the inspection lane. The imaging device 130 and the lighting device 132 are positioned close to each other on one side of the inspection lane. Taking the tire 404 as an example, the imaging device 130 is oriented to capture an image from a first angle 406 with respect to a horizontal direction 410 perpendicular to the surface of the tire tread. The horizontal direction 410 refers to being horizontal to the ground of the inspection lane. In this particular example, the direction 410 can also be understood to be parallel to the vehicle's direction of travel or parallel to the vehicle's longitudinal axis. Similarly, the lighting device 132 is oriented to illuminate the tire 404 from a second angle 408 with respect to the horizontal direction 410. As shown, it is specifically designed by the present disclosure that the first angle 406 is smaller than the second angle 408, i.e., the imaging device 130 is positioned relatively closer to the tire / inspection lane compared to the illumination device 132.

[0051] Because the lighting device 132 shines light from the side of the tire and the tread blocks some of the light, shadowed and illuminated areas naturally occur at the bottom and / or sidewalls of the tire grooves. Because the imaging device is positioned at a smaller angle to the tire compared to the lighting device, the captured image is able to capture the entire illuminated area and at least a portion of the shadowed area.

[0052] 6A shows an example image patch from a tire image showing shadow and illuminated areas according to certain embodiments of the subject matter of this disclosure. In this example of image 600, illuminated area 603 hits both the bottom and sidewall of the groove. The groove sidewall refers to the vertical area on the side of the groove between the surface of the tread and the bottom of the groove. The shadow area 601 captured in image 600 is a portion of the shadow actually cast by the lighting device at the bottom of the groove due to the relative position of the lighting device and the tire.

[0053] Continuing with the description of FIG. 2, image segmentation may be performed (204) on the image (e.g., by segmentation module 104 of PMC 102) to obtain an image segment including at least a first image segment (also referred to as an illumination segment) corresponding to the illumination portion and a second image segment (also referred to as a shadow segment) corresponding to at least a portion of the shadow portion.

[0054] Image segmentation as referred to herein can be performed in a variety of ways using different segmentation methods, such as, for example, thresholding, clustering, edge detection, blob analysis, classification, or any other suitable segmentation method, and the disclosure is not limited by the particular segmentation method used herein. In some embodiments, image segmentation can be performed using machine learning. By way of example, segmentation can be implemented using a segmentation learning model, such as, for example, a deep learning neural network (also referred to as a deep neural network or DNN). The segmentation deep learning model can be considered to be included in the segmentation module 104 of the PMC 102.

[0055] A DNN as used herein may refer to a supervised or unsupervised DNN that includes multiple layers organized according to a respective DNN architecture. As non-limiting examples, the layers of a DNN may be organized according to a Convolutional Neural Network (CNN) architecture, a Recurrent Neural Network architecture, a Recurrent Neural Network architecture, a GAN architecture, etc. Optionally, at least some of the layers may be organized into multiple DNN sub-networks. Each layer of a DNN may include multiple basic computational elements (CEs), commonly referred to in the art as dimensions, neurons, or nodes.

[0056] In some embodiments, a segmentation deep learning model (e.g., a segmentation DNN) can be trained using a training dataset that includes a set of training tire images, each segmented and labeled according to different parts having different illumination levels, such as illuminated parts, shadow parts, tread surface parts, etc. The training images and labels corresponding to the segments are provided to the segmentation DNN for training. The training process is to optimize the model so that it can correctly predict the segmentation labels (e.g., pixel-wise segmentation labels) of tire images. In some cases, different training datasets covering images of various types of tires (e.g., tires of different types of vehicles) need to be provided to train the model so that it can segment different types of input tire images at runtime.

[0057] It should be noted that the teachings of the presently disclosed subject matter are not bound by any particular segmentation method, or by any particular type or structure of machine learning model used to perform the segmentation.

[0058] According to certain embodiments, the division of the tire image into different segments may vary, for example, a certain segment may be further divided into sub-segments. As an example, if the illumination portion hits both the bottom and the sidewall of the groove, a first image segment corresponding to the illumination portion may be further divided into two sub-segments. The first sub-segment corresponds to a first subsection of the illumination portion that hits the bottom of at least one groove (also called bottom illumination portion), and the second sub-segment corresponds to a second subsection of the illumination portion that hits the sidewall of at least one groove (also called sidewall illumination portion). The two sub-segments are separated by a corner line between the bottom and the sidewall of the groove. Such a sub-segmentation may result from a segmentation performed by a segmentation DNN, i.e., the output of the segmentation DNN includes the shadow segment and two sub-segments in the illumination segment. Alternatively, the sub-segmentation may be performed separately on the output of the DNN including the shadow segment and the illumination segment. As an example, it can be performed based on the difference between the grayscale levels of the two subsections resulting from different light reflections of the bottom and sidewalls with respect to the illumination angle. As another example, it can be performed by detecting a corner line separating the two subsections. In some further cases, the sub-segmentation can be performed in any other segmentation method as described above.

[0059] 6B, an example of a segmented tire image according to certain embodiments of the subject matter of the present disclosure is shown. As shown, segmented tire image 620 corresponds to tire image 600 as shown in FIG. 6A. Tire image 600 is segmented into a number of image segments 602, 604, 606, 608, and 610 as shown. Segmentation is performed such that the image segments represent different portions of the tire image. As an example, image segments 604, 606, and 608 respectively correspond to shadow portion 601, a first subsection of illuminated portion 603 that hits the bottom of the groove, and a second subsection of illuminated portion 603 that hits the sidewall of the groove. Image segments 606 and 608 are separated by a corner line between the bottom and sidewall of the groove, and are the two subsegments that correspond to illuminated portion 603. In addition, image segmentation also results in image segments 602 and 610 that represent tread portions adjacent to the groove.

[0060] Continuing with the description of FIG. 2, a width of the at least one groove (also referred to as groove width) may be obtained (206), and a tread depth may be estimated (208) based on at least the first image segment, the groove width, and the second angle (e.g., by the depth estimation module 106 of the PMC 102).

[0061] According to certain embodiments of the subject matter of the present disclosure, it is proposed by the present disclosure to use measurements of the shadowed and illuminated areas to estimate the tread depth. Specifically, once the width W of the shadowed area is obtained, as described with reference to FIG. 7, e.g., D=W shadow / tan(θ) determines the width of the shadow area W shadowand the second angle θ (i.e., the illumination angle), the tread depth D can be estimated. However, it should be understood that the imaging device can capture the entire shadow portion, the width of which can then be obtained from the image, only if the imaging device is positioned directly along the horizontal / travel direction, as shown in FIG. 4, and thus faces the tire from a vertical direction. However, in many cases, it is inconvenient or nearly impossible to position the imaging device in such an orientation (without making modifications to the equipment, such as digging an inspection lane and installing the imaging device underground), especially when the tire being inspected is on a moving vehicle.

[0062] In the present disclosure, by positioning the imaging device and the illumination device to the side of the inspection lane and arranging them in a specific relative position as described above, the image acquired can capture at least a portion of the shadowed portion, thereby ensuring that the entire illuminated portion is captured in the image. In this way, the width of the illuminated portion can be obtained, and the width of the shadowed portion can be estimated by subtracting the width of the illuminated portion from the total width of the groove.

[0063] Depending on the location of the illuminated portion on the tire, there are different scenarios for estimating tread depth, which may vary due to factors such as different tire types, tread width, tire age, illumination angle, position of the tire on the inspection lane relative to the lighting device / imaging device, etc.

[0064] In some embodiments, as described above, when the illuminated portion hits both the bottom and the sidewall of the groove, the first image segment corresponding to the illuminated portion actually includes a first sub-segment corresponding to a first sub-section of the illuminated portion that hits the bottom of the at least one groove and a second sub-segment corresponding to a second sub-section of the illuminated portion that hits the sidewall of the at least one groove. Figure 3 shows a generalized flowchart of tread depth estimation in such a case, i.e., when the illuminated portion hits both the bottom and the sidewall of the groove, according to certain embodiments of the present disclosure in such a case.

[0065] A width of the first sub-segment (corresponding to a first sub-section of the bottom illuminated portion) can be measured from the image 302. A width of the shadow portion can be calculated using the width of the first sub-segment and the groove width 304. The width of the shadow portion and the second angle can be used to estimate the tread depth of the tire 306.

[0066] With reference to FIG. 7, an example of how to estimate tread depth in the above scenario according to certain embodiments of the subject matter of the present disclosure is shown generally.

[0067] 7 shows a cross-sectional view of a portion of a tire tread 700 and a groove 702 embedded therein. Light is illuminated into the tire from a second angle 408 as described above (relative to a horizontal direction 410, note that the horizontal direction 410 appears vertical in this view due to the different perspectives and cross-sectional views of the view). As shown, the illuminated portion hits both the bottom of the groove and the sidewalls 408 of the groove.

[0068] According to the method described with reference to FIG. 3, after image segmentation, a subsegment 706 can be obtained, which corresponds to a first subsection of the illuminated portion that hits the bottom of the groove, and the width of the subsegment 706 can be measured from the image. The groove width can be obtained, for example, by measuring the top width 708 of the groove 702 from the image. By way of example, the top width can be measured as the total width of the image segments of segments 604, 606, and 608. Alternatively, in some cases, the groove width may be obtained as part of the tire information provided by the tire manufacturer. The tire model and manufacturer tire information can be recognized by reading the tire markings from the side of the tire using the side camera 420, as shown in FIG. 4. The width W of the shadowed portion 704 can be obtained by measuring the top width W of the shadowed portion 704 from the image. shadow can be obtained by subtracting the width of the subsegment 706 from the top width 708 (assuming the top and bottom widths of the groove 702 are substantially the same). Thus, the tread depth D, which is the vertical distance between the surface of the tread 710 and the bottom of the groove, is given by D=W shadow / tan(second angle 408).

[0069] Or, the width W of the side wall lighting part sidewall (e.g., the width of segment 608 as shown in FIG. 6) can be measured, and the tread depth D can be calculated by W sidewall and the first angle (i.e., the imaging angle), for example, D=W sidewall / sin(first angle).

[0070] It should be noted that measurements described in this disclosure, such as the widths of different portions, refer to widths in units of length, e.g., millimeters, centimeters, etc. In some cases, the original measurements obtained from the image may be in units of pixels, and these measurements can be converted to measurements in units of length by using a calibration factor that converts from pixels to millimeters.

[0071] In some embodiments, the illuminated portion may only hit the sidewall of the groove in some cases (e.g., if the groove is very narrow and / or deep). In such cases, the tread depth cannot be estimated using the methods described above because there is no illuminated portion at the bottom of the groove. However, the range of the tread depth can still be determined based on the groove width and the second angle (310).

[0072] Referring now to FIG. 8, a table illustrating the correlation between different groove widths and estimated tread depths is shown, in accordance with certain embodiments of the subject matter of the present disclosure.

[0073] Table 800 shows the width of the illuminated portion at the bottom of the groove for different tires having different groove widths (e.g., 4-10 mm as shown) and different tread depths (e.g., 1-12 mm) at a given illumination angle. As an example, for a tire having a groove width of 10 mm (see last column of the table), the estimation method described with reference to FIG. 3 can be used to establish a correlation between the width of the bottom illuminated portion and the tread depth. For example, if the width of the bottom illuminated portion is measured to be 9.3 mm, the tread depth is estimated to be 1 mm, and if the width of the bottom illuminated portion is measured to be 2.1 mm, the tread depth is estimated to be 12 mm. As shown, for a tire having a fixed groove width, the smaller the bottom illuminated portion, the deeper the tread.

[0074] From another perspective, as the groove width decreases (i.e., the groove becomes narrower), the size of the illuminated portion visible at the bottom of the groove is also limited. As an example, for a tire with a groove width of 4 mm (see the second column of the table), when the width of the bottom illuminated portion is measured as 3.3 mm, the tread depth is estimated as 1 mm, but when the bottom illuminated portion is 0.1 mm or disappears from the image (i.e., 0 mm), the tread depth is estimated as 6 mm or 7 mm or more. This means that for tires with relatively narrow groove widths, in some cases, when the tread depth exceeds a certain threshold, the light is only illuminated on the sidewalls and the entire groove bottom is not illuminated and is in shadow. In such cases, it is not possible to estimate the tread depth value using the method described above with reference to FIG. 3, but the depth range can still be derived using table 800. For example, for a tire with a groove width of 4 mm, if the illuminated portion is on the entire sidewall of the groove, the tread depth can be determined to be 7 mm or more. Similarly, in a tire with a 6mm groove width, if the illuminated portion is located on the entire sidewall, the tread depth can be determined to be 10mm or more.

[0075] It should be understood that table 800 is derived for a particular lighting angle. For different lighting angles configured with different system settings, respective tables can be similarly derived using the estimation methods described above.

[0076] Thus, if the illuminated portion is only on the sidewall of the groove, the tread depth range (e.g., minimum tread depth) can be determined using such a correlation table based on the tire groove width and the illumination angle.

[0077] According to certain embodiments, the second angle can be specifically configured to accommodate different tire characteristics, including different groove widths and / or tire positions on the inspection lane, so as to be able to provide an estimate of the tread depth within a predetermined depth range for different tires. The tire position refers to the position of the tire relative to the inspection lane, e.g., center, left, or right. The predetermined depth range can be determined differently, for example, according to different legal requirements and / or recommendations. For example, as mentioned above, the US legal limit for tire tread depth is about 1.6 millimeters (2 / 32 inches). In some locations, it is recommended to have a minimum tread depth of 3 millimeters for summer tires and at least 4 millimeters (5 / 32 inches) for winter tires. Thus, for safety reasons, a critical depth range of 3 to 5 mm can be pre-determined, and the illumination angle can be specifically set to be able to always estimate the tread depth within the critical range for various tires. For example, it can be seen that for the particular illumination angle used to derive table 800, for different tires having various groove widths ranging from 4 to 10 mm, the method described with reference to FIG. 3 can be used to consistently estimate / calculate tread depths within the critical range of 3 to 5 mm.

[0078] In some cases, once the configuration of the system 100 (e.g., the layout of the imaging device and the lighting device, and the first and second angles as nominally configured, etc.) is specifically defined, the actual position of the tire being inspected is still variable. This is due to the fact that the vehicle passing through the system is not positioned perfectly on the inspection lane (e.g., in the center of the inspection lane) in some cases. Furthermore, the vehicles may have different vehicle widths. Thus, even if the vehicle is located in the center of the lane, the relative position and distance between the vehicle and the imaging device will still be different. Such variations in tire position may result in the actual first and second angles being different from the nominal configuration angles. The actual angles can be inferred from the position of the tire in the image. For example, a tire at the center of the image can be inferred to have a nominal angle, and a tire at the far side of the image can be inferred to have a larger angle, and vice versa. A calibration can be made between the different positions of the tire in the image and their corresponding respective angles. Thus, for example, the actual angle in the image can be obtained by measuring the position of the tire in the image and performing a correction to the nominal angle based on the calibration.

[0079] Once the tread depth is estimated (208) as described above, the estimated tread depth may be compared to predetermined criteria, such as, for example, legal limits, predetermined ranges, etc., and a decision may be made whether to replace the tire based on the results of the comparison.

[0080] In some embodiments, the captured image may provide information of one or more tires (such as image 502 shown in FIG. 5). The PMC may be further configured to extract one or more sub-images corresponding to the one or more tires and perform segmentation and tread depth estimation as described above with reference to FIG. 2 for each of the one or more sub-images.

[0081] In some embodiments, the captured image (such as image 502 or 504) can be divided into multiple measurement locations of a given groove (e.g., different locations along the curved surface of the tire tread / groove) and / or multiple image patches (such as image patch 600) corresponding to different grooves, and image segmentation and estimation as described above can be performed for each image patch to obtain depth estimates for different locations of the tread.

[0082] It should be noted that the first and second angles used herein in some embodiments are defined on a horizontal plane where the tire center, the lighting device, and the imaging device are. FIG. 10A shows an example of an image patch 1001 extracted from a tire image along a horizontal plane relative to the lighting device, the imaging device, and the tire center. However, on the curved surface of the tire tread, there are multiple three-dimensional (3D) angles (because these angles are defined in the 3D space between the measurement point and the device, not on a horizontal plane). These additional angles can provide additional measurement locations / points to improve the measurement. For example, image patches can be extracted at different locations of the tire image and used for tread depth estimation. In some cases, when moving to the lower (or upper) part of the tire relative to the horizontal plane, there is always a position where the shadow portion extends further due to the 3D incidence angle until the width of the bottom illumination portion is reduced to 0, as exemplified by the bottom image patch 1002 in FIG. 10A. Such measurement points (and additional measurement points) can be used for robust measurement of tread depth. For example, measurements from different measurement points should be substantially consistent and match one another. The 3D angle can be calculated by applying a correction to the first and second angles based, for example, on the relative position of the measurement point with respect to the horizontal plane and the tire radius.

[0083] For example, for at least a second image patch that is above or below the horizontal plane, the PMC can be configured to obtain a 3D second angle corresponding to the measurement location in the second image patch and perform segmentation and estimation on the second image patch using the 3D second angle. The 3D second angle can be obtained by performing a correction to the second angle based on, for example, the relative position of the measurement location to the horizontal plane and the radius of the tire, as described above.

[0084] In some embodiments, the above-mentioned 3D angles can be used to measure the tread depth of a tire in which at least a portion of the tread and grooves are oriented non-parallel to the circumference of the tire, as illustrated in FIG. 10B in accordance with certain embodiments of the subject matter of the present disclosure. As illustrated, the tread 1004 (and adjacent grooves) has an orientation non-parallel to the circumference of the tire. The illumination angle used to estimate the tread depth of such a tread can be estimated as a 3D angle relative to the direction of the tread and illumination device.

[0085] In some embodiments, when the tire is a rotating tire on a moving vehicle, the PMC can be configured to acquire a series of images of the tire during relative motion between the tire and the imaging device, and segmentation and estimation can be performed on at least some of the series of images to obtain an estimated tread depth that covers a circumferential range (or at least a portion thereof) of the tire. By way of example, the series of images can be sampled based on a given frequency such that the sampled images can cover a circumferential range of the tire.

[0086] According to certain embodiments, the tread wear condition can also be estimated using tread wear indicators or wear bars. Wear bars look like flat rubber bars evenly spaced through the major grooves in the tire tread. When the wear bars are flush with the level of the tread surface, it indicates that the tire should be replaced. Figure 9 shows a tire with tread wear bars 900 spaced through the grooves according to certain embodiments of the subject matter of the present disclosure.

[0087] Wear bars are usually inspected manually to check whether they are flush with the level of the tread surface. According to certain embodiments of the present disclosure, the depth estimation method as described with reference to Figs. 2 and 3 can be similarly applied to automatically estimate the depth of the wear bars. In particular, the tire image providing the information of the tread wear bars can be segmented using image segmentation as described above, and the estimation method can be similarly applied in the case where the bottom of the groove should be replaced by the surface of the wear bar. For example, using the diagram of Fig. 7 as an example, assuming there is a wear bar embedded in the groove 702, the shaded portion 704 and the illuminated portion 706 fall on the surface of the wear bar, and the remaining estimation can be similarly applied according to Fig. 3 to derive the depth of the wear bar, thereby providing an indication of the tread wear condition.

[0088] It should be noted that for purposes of estimating tread wear condition, in some embodiments the estimating of the tread wear bar depth described above may be performed in addition to estimating the tread depth, while in some other embodiments the estimating of the tread wear bar depth may be performed separately from and instead of estimating the tread depth.

[0089] It is understood that the examples and embodiments illustrated herein with reference to tread depth estimation systems are by no means inclusive of all possible alternatives, but are intended to represent non-limiting examples only.

[0090] It is to be understood that the present disclosure is not limited in its application to the details shown in the description contained herein or in the drawings. The present disclosure is capable of other embodiments and can be practiced and carried out in various ways. It is therefore to be understood that the phraseology and terminology used herein are for the purpose of description and should not be regarded as limiting. As such, those skilled in the art will appreciate that the conception on which the present disclosure is based can be readily utilized as a basis for the designing of other structures, methods and systems for carrying out some of the purposes of the subject matter of the present disclosure.

[0091] It will also be appreciated that the system according to the present disclosure may be implemented, at least in part, on a suitably programmed computer. Similarly, the present disclosure contemplates a computer program readable by a computer for performing the methods of the present disclosure. The present disclosure further contemplates a non-transitory computer readable memory or storage medium tangibly embodying a program of instructions executable by a computer to perform the methods of the present disclosure.

[0092] A non-transitory computer-readable storage medium that enables a processor to perform aspects of the present disclosure can be a tangible device that can hold and store instructions for use by an instruction execution device. The computer-readable storage medium can be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing.

[0093] Those skilled in the art will readily appreciate that various modifications and changes can be made to the embodiments of the present disclosure, as described above, without departing from the scope thereof as defined by and in the appended claims.

Claims

1. 1. A computerized system for estimating tread depth of a tire, the system comprising a processing and memory circuit (PMC), the processing and memory circuit (PMC) comprising: acquiring from an imaging device an image of a tire positioned on an inspection lane, the image providing information of the tire's tread and one or more grooves embedded therein, the imaging device being positioned on at least one side of the inspection lane, the image being acquired by the imaging device from a first angle relative to a horizontal direction perpendicular to a surface of the tread, the tire being illuminated by an illumination device from a second angle relative to the horizontal direction to produce shadowed and illuminated portions on a bottom and / or sidewall of at least one of the grooves, the imaging device and the illumination device being positioned such that the first angle is less than the second angle such that the image captures at least a portion of the illuminated and shadowed portions; performing a segmentation on the image to obtain at least a first image segment corresponding to the illuminated portion and a second image segment corresponding to at least a portion of the shadow portion; Obtaining a groove width of the at least one groove; a computerized system configured to estimate the tread depth based on at least the first image segment, the groove width, and the second angle.

2. 2. The computerized system of claim 1, wherein the first image segment indicates that the illuminated portion is entirely on the sidewall of the at least one groove, and the estimating includes determining the tread depth range based on the groove width and the second angle.

3. the first image segment includes a first sub-segment corresponding to a first sub-section of the illuminated portion hitting a bottom of the at least one groove and a second sub-segment corresponding to a second sub-section of the illuminated portion hitting a sidewall of the at least one groove, and the estimating comprises: Measuring a width of the first subsegment; calculating a width of the shadow portion using the width of the first sub-segment and the groove width; and estimating a tread depth of the tire using the width of the shaded area and the second angle.

4. 2. The computerized system of claim 1, further comprising the imaging device and the lighting device positioned proximate to one another on the at least one side of the inspection lane, wherein at least the imaging device is operably connected to the PMC.

5. 2. The computerized system of claim 1, wherein the second angle is configured to accommodate different tire characteristics including different groove widths and / or tire positions on the inspection lane to provide tread depth estimates within a predetermined depth range for different tires.

6. 2. The computerized system of claim 1, wherein the PMC is further configured to compare the tread depth to a predetermined standard and determine whether the tire should be replaced.

7. 2. The computerized system of claim 1, wherein the segmentation is performed using a segmentation learning model trained to segment tire images according to different illumination levels.

8. 2. The computerized system of claim 1, wherein the image further provides information of one or more tread wear bars, and the PMC is further configured to estimate a depth of at least one of the tread wear bars.

9. 2. The computerized system of claim 1, wherein the images provide information of one or more tires, and the PMC is configured to extract one or more sub-images corresponding to the one or more tires and perform the segmentation and the estimation for each of the one or more sub-images.

10. 2. The computerized system of claim 1, wherein the tire is a rotating tire on a moving vehicle, and the PMC is configured to acquire a series of images of the tire during relative motion between the tire and the imaging device, and perform the segmentation and estimation on at least some of the series of images to obtain an estimated tread depth covering at least a portion of a circumference of the tire.

11. 2. The computerized system of claim 1, wherein the image is divided into a plurality of image patches corresponding to a plurality of measurement locations on the at least one groove, and the PMC is configured to perform the segmentation and estimation using the second angle for a first image patch along a horizontal plane relative to the illumination device, the imaging device, and the center of the tire, and for at least a second image patch that is above or below the horizontal plane, the PMC is configured to obtain a 3D second angle corresponding to a measurement location in the second image patch and perform the segmentation and estimation for the second image patch using the 3D second angle.

12. 12. The computerized system of claim 11, wherein the 3D second angle is obtained by performing a correction on the second angle based on a relative position of the measurement position to the horizontal plane and a radius of the tire.

13. 1. A computerized method for estimating tread depth of a tire, the method being performed by a processing and memory circuit (PMC), the method comprising: acquiring from an imaging device an image of a tire positioned on an inspection lane, the image providing information of the tire's tread and one or more grooves embedded therein, the imaging device being positioned on at least one side of the inspection lane, the image being acquired by the imaging device from a first angle relative to a horizontal direction perpendicular to a surface of the tread, the tire being illuminated by an illumination device from a second angle relative to the horizontal direction to produce shadowed and illuminated portions on a bottom and / or sidewall of at least one of the grooves, the imaging device and the illumination device being positioned to have the first angle less than the second angle such that the image captures at least a portion of the illuminated and shadowed portions; performing a segmentation on the image to obtain at least a first image segment corresponding to the illuminated portion and a second image segment corresponding to at least a part of the shadow portion; obtaining a groove width of the at least one groove; and estimating the tread depth based on at least the first image segment, the groove width, and the second angle.

14. 14. The computerized method of claim 13, wherein the first image segment indicates that the illuminated portion is entirely on the sidewall of the at least one groove, and the estimating includes determining the tread depth range based on the groove width and the second angle.

15. the first image segment includes a first sub-segment corresponding to a first sub-section of the illuminated portion hitting a bottom of the at least one groove and a second sub-segment corresponding to a second sub-section of the illuminated portion hitting a sidewall of the at least one groove, and the estimating comprises: Measuring a width of the first subsegment; calculating a width of the shadow portion using the width of the first sub-segment and the groove width; and estimating a tread depth of the tire using the width of the shaded area and the second angle.

16. 14. The computerized method of claim 13, wherein the second angle is configured to accommodate different tire characteristics including different groove widths and / or tire positions on the inspection lane to provide tread depth estimates within a predetermined depth range for different tires.

17. 14. The computerized method of claim 13, wherein the image further provides information of one or more tread wear bars, the method including estimating a depth of at least one of the tread wear bars.

18. 14. The computerized method of claim 13, wherein the image provides information of one or more tires, the method comprising extracting one or more sub-images corresponding to the one or more tires and performing the segmentation and the estimation for each of the one or more sub-images.

19. 14. The computerized method of claim 13, wherein the tire is a rotating tire on a moving vehicle, the method comprising acquiring a series of images of the tire during relative motion between the tire and the imaging device, and performing the segmentation and the estimation on at least some of the series of images to obtain an estimated tread depth that covers at least a portion of a circumference of the tire.

20. A non-transitory computer readable storage medium tangibly embodying a program of instructions that, when executed by a computer, causes the computer to perform a method for estimating tread depth of a tire, the method comprising: acquiring from an imaging device an image of a tire positioned on an inspection lane, the image providing information of the tire's tread and one or more grooves embedded therein, the imaging device being positioned on at least one side of the inspection lane, the image being acquired by the imaging device from a first angle relative to a horizontal direction perpendicular to a surface of the tread, the tire being illuminated by an illumination device from a second angle relative to the horizontal direction to produce shadowed and illuminated portions on a bottom and / or sidewall of at least one of the grooves, the imaging device and the illumination device being positioned to have the first angle less than the second angle such that the image captures at least a portion of the illuminated and shadowed portions; performing a segmentation on the image to obtain at least a first image segment corresponding to the illuminated portion and a second image segment corresponding to at least a part of the shadow portion; obtaining a groove width of the at least one groove; and estimating the tread depth based on at least the first image segment, the groove width, and the second angle.

Citation Information

Patent Citations

  • Bump inspection device

    JP1998089927A

  • Groove depth measuring method and measuring device

    JP2001201323A

  • Flaw detector and flaw detection method

    JP2008139126A

  • Method and apparatus for measuring the tread depth of a vehicle tire.

    JP2012523547A

  • Method and apparatus for analyzing the condition of tires

    JP2017500540A