Estimation device

Abstract

To estimate the depth of a tire groove easily in comparison with a case where information on a vehicle is required.SOLUTION: An estimation device includes: an acquisition part which acquires an image of a tread of a tire attached to a vehicle; and an estimation part which estimates the depth of a tire groove on the basis of the image of the tread of the tire.SELECTED DRAWING: Figure 4

Description

Technical Field

[0001] This disclosure relates to an estimation device.

Background Art

[0002] Patent Document 1 discloses a device for estimating the wear state of a tire mounted on a vehicle. This device includes a slope calculation unit that calculates the slope of the slip ratio with respect to the driving force based on a large number of data sets of the slip ratio and the driving force, as a regression coefficient representing the linear relationship between the slip ratio calculated based on the sequentially acquired rotational speed of the tire and the driving force of the vehicle. Further, this device includes a slope correction unit that corrects the calculated slope based on an index representing the temperature dependence of the slope and the temperature outside the vehicle at the time of correction, and an estimation unit that estimates the wear state of the tire based on the corrected slope.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] The device disclosed in Patent Document 1 has a problem that the depth of the tire groove cannot be estimated without information about the vehicle.

[0005] This disclosure has been made in consideration of the above facts, and an object thereof is to provide an estimation device that can easily estimate the depth of a tire groove as compared with the case where information about a vehicle is required.

Means for Solving the Problems

[0006] The estimation device according to the first aspect is an acquisition unit that acquires an image of the tread of a tire mounted on a vehicle and the driving history of the aforementioned vehicle and, based on the image, estimates the depth of the groove of the tire At the same time, the depth of the groove is estimated based on the aforementioned driving history. The estimation unit, If the difference between the groove depth estimated based on the aforementioned image and the groove depth estimated based on the aforementioned driving history is greater than or equal to a predetermined difference, the output unit outputs a command to measure the groove depth. It is equipped with.

[0007] In the estimation device according to the first embodiment, the acquisition unit acquires an image of the tread of a tire mounted on a vehicle, and the estimation unit estimates the depth of the tire groove based on the image. According to the estimation device according to the first embodiment, the depth of the tire groove can be estimated more easily than when information about the vehicle is required.

[0008] Also, The 1 The estimation device relating to the embodiment ,before The data acquisition unit further acquires the vehicle's driving history, the estimation unit further estimates the groove depth based on the driving history, and the output unit further outputs a command to measure the groove depth if the difference between the groove depth estimated based on the image and the groove depth estimated based on the driving history is greater than or equal to a predetermined difference.

[0009] This The actual depth of the tire grooves can be determined if the difference between the groove depth estimated based on the image and the groove depth estimated based on the driving history exceeds a predetermined difference.

[0010] The 2 The estimation device relating to the embodiment is the 1 In an estimation device according to the embodiment, the estimation unit estimates the depth of the groove by inputting the acquired image into a depth estimation model that has been trained using pairs of the image and the groove depth as training data, and the acquisition unit acquires the measured value of the groove depth and trains the depth estimation model using the pair of the image and the measured value as training data. It will also be equipped with a learning section.

[0011] The 2 According to the estimation device described above, when the difference between the groove depth estimated based on the image and the groove depth estimated based on the driving history is greater than a predetermined difference, the estimation accuracy of the depth estimation model can be improved compared to when the depth estimation model is not trained using the acquired measured values.

[0012] The 3 estimation device according to the aspect further includes an output unit that outputs to replace the tire when the depth of the groove estimated based on the image is less than a predetermined depth, in the estimation device according to any one of the first to third aspects.

[0013] The 3 estimation device according to the aspect enables understanding that the tire must be replaced when the depth of the groove is less than a predetermined depth. and further includes an output unit that outputs to replace the tire.

[0014] The 4 estimation device according to the aspect, in the estimation device according to any one of the first to fourth aspects, the estimation unit estimates whether damage has occurred to the tire based on the image, and when it is estimated that damage has occurred to the tire, further includes an output unit that outputs to replace the tire.

[0015] The 4 estimation device according to the aspect enables understanding that damage has occurred to the tire.

Effect of the Invention

[0016] According to the present disclosure, the depth of the groove of the tire can be estimated more simply than when information about the vehicle is required.

Brief Description of the Drawings

[0017] [Figure 1] It is a diagram showing an example of the schematic configuration of the estimation system according to the embodiment. [Figure 2] It is a block diagram showing an example of the hardware configuration of the user terminal according to the embodiment. [Figure 3] It is a block diagram showing an example of the hardware configuration of the center server according to the embodiment. [Figure 4]It is a block diagram showing an example of the functional configuration of the CPU in the center server according to the embodiment. [Figure 5] It is a flowchart showing an example of the flow of the estimation process according to the embodiment.

Mode for Carrying Out the Invention

[0018] As shown in FIG. 1, the estimation system 100 of the present embodiment includes a user terminal 10, a vehicle 12, and a center server 30. The center server 30 is an example of an estimation device. Note that the number of user terminals 10 and vehicles 12 included in the estimation system 100 is not limited to the number shown in FIG. 1. The user terminal 10, the vehicle 12, and the center server 30 are mutually connected via a network CN1.

[0019] As shown in FIG. 1, the vehicle 12 of the present embodiment is equipped with tires 14A to 14D. Hereinafter, when the tires 14A to 14D are not distinguished, these are simply referred to as "tire 14". In the present embodiment, a four-wheeled vehicle is applied as the vehicle 12, and the vehicle 12 is equipped with four tires 14. However, it is not limited to this example. A two-wheeled vehicle may be applied as the vehicle 12. In this case, the vehicle 12 is equipped with two tires 14.

[0020] The user terminal 10 is an information processing terminal owned by the user. The user terminal 10 is, for example, a portable information processing terminal such as a smartphone.

[0021] As shown in Figure 2, the user terminal 10 is composed of a CPU (Central Processing Unit) 10A, ROM (Read Only Memory) 10B, RAM (Random Access Memory) 10C, storage 10D, imaging unit 10E, display unit 10F, communication interface 10G, and position acquisition unit 10H. The CPU 10A, ROM 10B, RAM 10C, storage 10D, imaging unit 10E, display unit 10F, communication interface 10G, and position acquisition unit 10H are interconnected via a bus 10I so that they can communicate with each other.

[0022] The CPU 10A is a central processing unit that executes various programs and controls various components. Specifically, the CPU 10A reads programs from ROM 10B or storage 10D and executes them using RAM 10C as a workspace. The CPU 10A controls the above components and performs various calculations according to the programs stored in ROM 10B or storage 10D.

[0023] ROM10B stores various programs and data. RAM10C temporarily stores programs or data as a working area. Storage10D consists of an HDD (Hard Disk Drive) or SSD (Solid State Drive) and stores various programs, including the operating system, and various data.

[0024] The camera unit 10E is a camera for capturing images of the tread of the tire 14 mounted on the vehicle 12 (hereinafter also referred to as "tread image").

[0025] Communication I / F10G is an interface for connecting to network CN1.

[0026] The display unit 10F is, for example, a liquid crystal display and displays various information. The display unit 10F may also function as an input unit by employing a touch panel system.

[0027] The position acquisition unit 10H acquires the shooting location where the tread image was taken. The position acquisition unit 10H is equipped with an antenna (not shown) that receives radio signals from GPS (Global Positioning System) satellites and quasi-zenith satellite systems (e.g., "Michibiki").

[0028] As shown in Figure 3, the center server 30 is configured to include a CPU 30A, ROM 30B, RAM 30C, storage 30D, and communication I / F 30G. The CPU 30A, ROM 30B, RAM 30C, storage 30D, and communication I / F 30G are interconnected via an internal bus 30H so that they can communicate with each other.

[0029] The CPU 30A is a central processing unit that executes various programs and controls each component. Specifically, the CPU 30A reads a program from the ROM 30B or storage 30D and executes the program using the RAM 30C as a working area. The CPU 30A controls each of the above components and performs various calculations according to the program stored in the ROM 30B or storage 30D. In this embodiment, the ROM 30B or storage 30D stores an estimation program, a depth estimation model, a depth estimation formula, and a damage estimation model.

[0030] ROM30B stores various programs and data. RAM30C temporarily stores programs or data as a working area. Storage30D consists of an HDD or SSD and stores various programs, including the operating system, and various data.

[0031] The estimated program is a program that implements each of the functions that the center server 30 possesses.

[0032] The depth estimation model is a model that estimates the groove depth of the tire 14 based on tread images. Specifically, the depth estimation model is a supervised model that has been trained using pairs of tread images and the groove depth of the tire 14 as training data.

[0033] The depth estimation formula is a formula that estimates the groove depth of the tire 14 based on the driving history of the vehicle 12. Specifically, the depth estimation formula is determined based on the measured value of the groove depth of the tire 14. Furthermore, it is set so that the groove depth of the tire 14 becomes shallower as the driving distance of the vehicle 12 increases. Note that the depth estimation formula may differ for each type of tire 14 and tread pattern.

[0034] The damage estimation model is a model that estimates whether or not damage has occurred to the tire 14 based on the tread image. In this embodiment, damage refers to scratches, cracks, fissures, or uneven wear of the tire 14. Specifically, the damage estimation model is a supervised model that has been trained using the tread image and the presence or absence of damage to the tire 14 as training data.

[0035] Communication I / F30G is an interface for connecting to network CN1.

[0036] Figure 4 is a block diagram showing an example of the functional configuration of the CPU 30A. As shown in Figure 4, the CPU 30A has an acquisition unit 300, an estimation unit 310, an output unit 320, and a learning unit 330. Each functional configuration is realized by the CPU 30A reading an estimation program stored in the ROM 30B or storage 30D and executing it.

[0037] The acquisition unit 300 has the function of acquiring tread images. In this embodiment, the acquisition unit 300 acquires tread images from the user terminal 10 via the communication interface 30G.

[0038] Furthermore, the acquisition unit 300 has a function to acquire the shooting location where the tread image was captured. In this embodiment, the acquisition unit 300 acquires the shooting location from the user terminal 10 via the communication I / F 30G.

[0039] Furthermore, the acquisition unit 300 has a function to acquire the measured value of the groove depth of the tire 14. In this embodiment, when the output unit 320, which will be described later, outputs to measure the groove depth of the tire 14, the acquisition unit 300 acquires the measured value of the groove depth of the tire 14 from the user terminal 10 via the communication I / F 30G.

[0040] Furthermore, the acquisition unit 300 has a function to acquire the driving history of the vehicle 12. In this embodiment, the acquisition unit 300 acquires the mileage traveled by the vehicle 12 since the tire 14 was mounted on the vehicle 12 (hereinafter also simply referred to as "mileage") from the vehicle 12 via the communication I / F 30G. However, it is not limited to this example. For example, the acquisition unit 300 may acquire a driving history from the vehicle 12 that includes the date and time of the vehicle 12's driving and the associated driving speed. The acquisition unit 300 may also acquire at least one of the following from the vehicle 12: the type of tire 14 (e.g., summer tire, studless tire, or all-season tire, or radial tire or bias tire, etc.) and the tread pattern (e.g., rib type, lug type, rib-lug type, or block type, etc.). Alternatively, instead of acquiring at least one of the type of tire 14 and the tread pattern, the acquisition unit 300 may acquire at least one of the size and brand of the tire 14.

[0041] The estimation unit 310 has the function of estimating the groove depth of the tire 14 based on the tread image acquired by the acquisition unit 300. In this embodiment, the estimation unit 310 estimates the groove depth of the tire 14 by inputting the tread image acquired by the acquisition unit 300 into a depth estimation model.

[0042] However, this is not the only example. For example, the estimation unit 310 calculates LBP (Local Binary Pattern) features from the tread image. Then, the calculated LBP features can be input into a supervised model that has been trained using pairs of LBP features and the depth of the tire grooves 14 as training data to estimate the depth of the tire grooves 14.

[0043] Furthermore, the estimation unit 310 may estimate the groove depth of the tire 14 based on whether or not a wear indicator is visible in the tread image. For example, the estimation unit 310 estimates whether or not a wear indicator is visible in the tread image by inputting the tread image acquired by the acquisition unit 300 into a supervised model that has been trained using pairs of tread images and whether or not a wear indicator is visible in the tread image as training data. If the estimation unit 310 determines that there is a wear indicator on the tire 14, it may estimate that the groove depth of the tire 14 is 1.6 mm or less, and if it determines that there is no wear indicator on the tire 14, it may estimate that the groove depth of the tire 14 is greater than 1.6 mm.

[0044] Furthermore, the estimation unit 310 has a function to further estimate the groove depth of the tire 14 based on the driving history of the vehicle 12. In this embodiment, the estimation unit 310 estimates the groove depth of the tire 14 by inputting the driving distance acquired by the acquisition unit 300 into the depth estimation formula. If the depth estimation formula differs for each type of tire 14, the estimation unit 310 may estimate the groove depth of the tire 14 by inputting the driving distance acquired by the acquisition unit 300 into the depth estimation formula for the type of tire 14 acquired by the acquisition unit 300. Also, if the depth estimation formula differs for each tread pattern, the estimation unit 310 may estimate the groove depth of the tire 14 by inputting the driving distance acquired by the acquisition unit 300 into the depth estimation formula for the tread pattern acquired by the acquisition unit 300.

[0045] Furthermore, the estimation unit 310 has the function of estimating whether or not damage has occurred to the tire 14 based on the tread image. In this embodiment, the estimation unit 310 inputs the tread image acquired by the acquisition unit 300 into the damage estimation model and estimates whether or not damage has occurred to the tire 14. However, it is not limited to this example. For example, the estimation unit 310 may group the acquired tread images by inputting them into an unsupervised model and estimate that the tread image belonging to the smallest group is the tread image of the tire 14 that has been damaged. This is because it is assumed that there are fewer damaged tires 14 than undamaged tires 14.

[0046] Furthermore, the estimation unit 310 estimates which tire 14 corresponds to the tread image acquired by the acquisition unit 300 from among the tires 14A to 14D mounted on the vehicle 12. In this embodiment, the estimation unit 310 estimates which tire 14 corresponds to the tread image based on the shooting position acquired by the acquisition unit 300. Specifically, the estimation unit 310 estimates that the image with the largest distance from the shooting position to one predetermined reference tire (for example, tire 14A corresponding to the left front wheel) is the tread image of a tire (for example, tire 14D corresponding to the right rear wheel) that has a different front-rear position and left-right position from the reference tire. The estimation unit 310 also estimates that the image with the smallest distance from the reference tire to the shooting position is the tread image of a tire (for example, tire 14B corresponding to the right front wheel) that has the same front-rear position as the reference tire but a different left-right position. The estimation unit 310 also estimates that the image with the second largest distance from the reference tire to the shooting position is the tread image of a tire (for example, tire 14C corresponding to the left rear wheel) that has a different front-rear position but the same left-right position from the reference tire. The standard tire is predetermined, for example, by the user terminal 10.

[0047] The output unit 320 has a function to output a message to replace the tire 14 if the groove depth estimated based on the tread image is less than a predetermined depth. In this embodiment, the predetermined depth is predetermined by the administrator of the center server 30, etc. However, it is not limited to this example. The predetermined depth may be set for each type of tire 14 on the vehicle 12. For example, the predetermined depth may be set to 4 mm if the tire 14 is a summer tire, and to 50% of the groove depth when new if it is a studless tire. The output unit 320 may also output which of the tires 14A to 14D mounted on the vehicle 12 is the tire 14 with a groove depth less than the predetermined depth.

[0048] Furthermore, in this embodiment, if the groove depth estimated based on the tread image is less than a predetermined depth, the output unit 320 outputs a message to the user terminal 10 instructing it to replace the tire 14. However, this is not the only example. For example, if the groove depth is less than a predetermined depth, the output unit 320 may output a message to the vehicle 12 or a terminal owned by the dealership that sold the vehicle 12 instructing it to replace the tire 14.

[0049] Furthermore, the output unit 320 may output the estimated groove depth regardless of whether the groove depth estimated based on the tread image is less than a predetermined depth.

[0050] Furthermore, in this embodiment, the output unit 320 has a function to output a command to measure the groove depth of the tire 14 if the difference between the groove depth estimated based on the tread image and the groove depth estimated based on the driving history is greater than or equal to a predetermined difference. The predetermined difference is predetermined by the administrator of the center server 30, etc. However, this is not the only example. For example, the predetermined difference may be determined based on the mileage of the vehicle 12. Specifically, the predetermined difference may be set to increase as the mileage of the vehicle 12 increases.

[0051] Furthermore, in this embodiment, if the difference between the groove depth estimated based on the tread image and the groove depth estimated based on the driving history is greater than or equal to a predetermined difference, the output unit 320 outputs to the user terminal 10 to measure the groove depth of the tire 14. However, this is not the only example. For example, if the above difference is greater than or equal to a predetermined difference, the output unit 320 may output to the vehicle 12 or a terminal owned by the dealership that sold the vehicle 12 to replace the tire 14.

[0052] Furthermore, in this embodiment, the output unit 320 has a function to output a command to replace the tire 14 if it is estimated that damage has occurred to the tire 14. In this embodiment, the output unit 320 outputs a command to replace the tire 14 if it is estimated that damage has occurred to the tire 14, regardless of the groove depth estimated based on the tread image and the groove depth estimated based on the driving history. However, it is not limited to this example. For example, the output unit 320 may output a command to replace the tire 14 if at least one of the groove depth estimated based on the tread image and the groove depth estimated based on the driving history is less than a predetermined depth and it is estimated that damage has occurred to the tire 14. The output unit 320 may also output which of the tires 14A to 14D mounted on the vehicle 12 is the tire 14 that is estimated to be damaged.

[0053] Furthermore, in this embodiment, if the output unit 320 estimates that the tire 14 is damaged, it outputs a message to the user terminal 10 instructing it to replace the tire 14. However, this is not the only example. For example, if the output unit 320 estimates that the tire 14 is damaged, it may output a message to the vehicle 12 or a terminal owned by the dealership that sold the vehicle 12 instructing it to replace the tire 14.

[0054] The learning unit 330 has a function to retrain the depth estimation model using the pair of the tread image acquired by the acquisition unit 300 and the measured value of the groove depth of the tire 14 as training data. Specifically, when the acquisition unit 300 outputs the tread image and the output unit 320 to measure the groove depth of the tire 14, the learning unit 330 retrains the depth estimation model using the pair of the tread image acquired by the acquisition unit 300 and the measured value of the groove depth of the tire 14 as training data. The learning unit 330 then stores the retrained depth estimation model in the ROM 30B or storage 30D.

[0055] The learning unit 330 may pre-train the depth estimation model and the damage estimation model. Specifically, the learning unit 330 may train the depth estimation model using pre-acquired tread images and the depth of the tire grooves 14 as training data and store it in the ROM 30B or storage 30D. The learning unit 330 may also train the damage estimation model using pre-acquired tread images and whether or not the tire 14 is damaged as training data and store it in the ROM 30B or storage 30D. Furthermore, the depth estimation model and the damage estimation model may be pre-trained by a device other than the center server 30.

[0056] Next, the flow of the estimation process will be explained using Figure 5. The estimation process is performed when the CPU 30A reads the estimation program from the ROM 30B or storage 30D, loads it into the RAM 30C, and executes it.

[0057] In step S100 of Figure 5, the CPU 30A waits until it obtains the tread image and the location where the tread image was taken from the user terminal 10. Once the CPU 30A obtains the tread image and the location where the tread image was taken (step S100: YES), it proceeds to step S102. The CPU 30A may obtain the tread image and the location where the tread image was taken at different times.

[0058] In step S102, the CPU 30A estimates which of the tires 14A to 14D mounted on the vehicle 12 corresponds to the tire 14 related to the tread image acquired in step S100.

[0059] In step S104, the CPU 30A inputs the tread image acquired in step S100 into the damage estimation model and estimates whether or not damage has occurred to the tire 14.

[0060] In step S106, the CPU 30A inputs the tread image acquired in step S100 into the depth estimation model to estimate the groove depth of the tire 14.

[0061] In step S108, the CPU 30A determines whether or not it is presumed that the tire 14 is damaged. If the CPU 30A determines that the tire 14 is damaged (step S108: YES), it proceeds to step S112. On the other hand, if the CPU 30A determines that the tire 14 is not damaged (step S108: NO), it proceeds to step S110.

[0062] In step S110, the CPU 30A determines whether the groove depth of the tire 14 estimated based on the tread image in step S108 is less than a predetermined depth. If the groove depth of the tire 14 estimated based on the tread image is less than the predetermined depth (step S110: YES), the CPU 30A proceeds to step S112. On the other hand, if the groove depth of the tire 14 estimated based on the tread image is greater than or equal to the predetermined depth (step S110: NO), the CPU 30A proceeds to step S114.

[0063] In step S112, the CPU 30A outputs a message to the user terminal 10 instructing it to replace the tire 14.

[0064] In step S114, the CPU 30A waits until it obtains the mileage of the vehicle 12. Once the CPU 30A obtains the mileage of the vehicle 12 (step S114: YES), it proceeds to step S116.

[0065] In step S116, the CPU 30A inputs the mileage obtained in step S114 into the depth estimation formula to estimate the depth of the tire groove 14.

[0066] In step S118, the CPU 30A determines whether the difference between the groove depth estimated based on the tread image in step S106 and the groove depth estimated based on the mileage in step S116 is greater than or equal to a predetermined difference. If the difference between the groove depth estimated based on the tread image and the groove depth estimated based on the mileage is greater than or equal to a predetermined difference (step S118: YES), the CPU 30A proceeds to step S120. On the other hand, if the difference between the groove depth estimated based on the tread image and the groove depth estimated based on the mileage is less than a predetermined difference (step S118: NO), the CPU 30A terminates this estimation process.

[0067] In step S120, the CPU 30A outputs a message to the user terminal 10 instructing it to measure the depth of the tire grooves 14.

[0068] In step S122, the CPU 30A waits until it obtains the measured value of the groove depth of the tire 14 from the user terminal 10. Once the CPU 30A obtains the measured value of the groove depth of the tire 14 from the user terminal 10 (step S122: YES), it proceeds to step S124.

[0069] In step S124, the CPU 30A retrains the depth estimation model using the pair of tread images acquired in step S100 and measured groove depths acquired in step S122 as training data, and then terminates this estimation process.

[0070] [remarks] In the above embodiment, a center server 30, configured separately from the user terminal 10, was used as the estimation device. However, this is not the only example. A device built into the user terminal 10 may be used as the estimation device. Alternatively, a device built into the vehicle 12 may be used as the estimation device.

[0071] Furthermore, in the above embodiment, the estimation unit 310 further estimated the groove depth of the tire 14 based on the driving history of the vehicle 12. However, it is not limited to this example. For example, the estimation unit 310 may further estimate the groove depth based on the rotation speed of the tire 14, etc. In this case, if the difference between the groove depth estimated based on the tread image and the groove depth estimated based on the rotation speed of the tire 14, etc. is greater than or equal to a predetermined difference, the output unit 320 outputs to the user terminal 10 to measure the groove depth of the tire 14.

[0072] Furthermore, the processing that the CPU reads and executes in the above embodiment may be executed by various processors other than the CPU. Examples of such processors include PLDs (Programmable Logic Devices) such as FPGAs (Field-Programmable Gate Arrays) whose circuit configuration can be changed after manufacturing, and dedicated electrical circuits such as ASICs (Application Specific Integrated Circuits) which have a circuit configuration specifically designed to execute a particular process. The above processing may be executed by one of these various processors, or by a combination of two or more processors of the same or different types (for example, multiple FPGAs, and a combination of a CPU and an FPGA). More specifically, the hardware structure of these various processors is an electrical circuit that combines circuit elements such as semiconductor elements.

[0073] Furthermore, although the above embodiments describe a configuration in which each program is pre-stored (installed) in ROM or storage, the invention is not limited to this. Programs may be provided in the form of recordings on recording media such as CD-ROM (Compact Disc Read Only Memory), DVD-ROM (Digital Versatile Disc Read Only Memory), and USB (Universal Serial Bus) memory. Programs may also be provided in the form of downloads from external devices via a network.

[0074] The processing flow described in the above embodiment is just one example, and unnecessary steps may be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0075] Furthermore, the configurations of the user terminal 10, the vehicle 12, and the center server 30 described in the above embodiment are examples and may be modified as needed without departing from the main purpose. [Explanation of symbols]

[0076] 12 vehicles 14 tires 30. Center Server (Estimated Device) 300 Acquisition Department 310 Estimation Department 320 Output section 330 Learning Department

Claims

1. An acquisition unit that acquires images of the tire treads mounted on the vehicle and the vehicle's driving history, An estimation unit that estimates the depth of the tire grooves based on the aforementioned image, and also estimates the depth of the grooves based on the aforementioned driving history, If the difference between the groove depth estimated based on the aforementioned image and the groove depth estimated based on the aforementioned driving history is greater than or equal to a predetermined difference, the output unit outputs a command to measure the groove depth. An estimation device equipped with this device.

2. The estimation unit estimates the depth of the groove by inputting the acquired image into a depth estimation model that has been trained using the pair of the image and the groove depth as training data. The acquisition unit acquires the measured value of the groove depth, The estimation device according to claim 1, further comprising a learning unit that retrains the depth estimation model using the pair of the image and the measured value as training data.

3. The estimation device according to claim 1, further comprising an output unit that outputs a command to replace the tire if the groove depth estimated based on the aforementioned image is less than a predetermined depth.

4. The estimation unit estimates whether or not damage has occurred to the tire based on the image. The estimation device according to claim 1, further comprising an output unit that outputs a command to replace the tire if it is estimated that damage has occurred to the tire.

Images