Non-contact measurement device, non-contact measurement method, and program

Abstract

A non-contact measurement device (10) comprises: an acquisition unit (131) that acquires three-dimensional coordinate data of an object having a groove; and a measurement unit (132) that, by using a trained model, specifies a measurement region including the groove in the three-dimensional coordinate data, and measures the remaining groove amount of the object in a non-contact manner from three-dimensional coordinate data of the measurement region.

Description

Non-contact measurement device, non-contact measurement method, and program

[0001] The present disclosure relates to a non-contact measurement device, a non-contact measurement method, and a program.

[0002] Conventionally, there are known techniques for measuring the degree of wear of an object without contact. For example, Patent Literature 1 discloses a technique for identifying a tread surface region of interest in a tread surface image of a tire, where a tread surface slip sign is captured, and estimating the degree of wear of the tire based on the output when the image of the tread surface region of interest is input into a trained machine learning model.

[0003] Japanese Patent Application Laid-Open No. 2021-63703

[0004] However, in the technology disclosed in Patent Document 1, the tread surface region of interest (46) is identified based on the position of the side slip sign (36) shown in the side 2D image (34), and then an estimated value of the degree of wear is output based on the 3D image data of the tread surface region of interest (46), so it is not possible to directly identify the groove portion to be measured, and this is time-consuming.

[0005] In view of the above circumstances, the purpose of the present disclosure is to provide a non-contact measurement device, a non-contact measurement method, and a program that can directly identify the measurement area of ​​an object and measure the remaining groove depth easily and with high accuracy.

[0006] The gist of the present disclosure for solving the above problems is as follows.

[0007] (1) A non-contact measurement device comprising: an acquisition unit that acquires three-dimensional coordinate data of an object having a groove; and a measurement unit that uses a trained model to identify a measurement area in the three-dimensional coordinate data that includes the groove, and non-contactly measure the remaining groove amount of the object from the three-dimensional coordinate data of the measurement area.

[0008] (2) The non-contact measuring device according to (1), wherein the measuring unit approximates a plane that closes the groove portion and measures the normal distance from the plane to the bottom of the groove portion as the remaining groove amount.

[0009] (3) A non-contact measuring device as described in (1) or (2), wherein the measuring unit uses a trained model that has learned the groove shape of the groove portion of the object to identify an area in the three-dimensional coordinate data that has the groove shape as the measurement area.

[0010] (4) A non-contact measuring device as described in (1) or (2), wherein the measuring unit uses a trained model that has learned a pattern pitch, which is the smallest unit of a pattern applied to an object, to identify an area in the three-dimensional coordinate data that has the pattern pitch as the measurement area.

[0011] (5) The non-contact measuring device according to (4), wherein the measuring unit identifies an area of ​​a predetermined proportion of the pattern pitch as the measurement area.

[0012] (6) A non-contact measuring device as described in (1) or (2), wherein the object has a processed portion on the land portion that has been processed for measurement, and the measuring unit uses a trained model that has learned the shape of the processed portion to identify an area defined by multiple processed portions in the three-dimensional coordinate data as the measurement area.

[0013] (7) The non-contact measuring device according to (6), wherein the processed portion has a recess and has a circular shape when viewed from the front.

[0014] (8) A non-contact measuring device according to any one of (1) to (7), wherein the measuring unit corrects the size of the measurement area so that the larger the size of the object or the groove portion, the larger the size of the measurement area.

[0015] (9) The non-contact measurement device according to any one of (1) to (8), wherein the object includes a tire and a rubber crawler.

[0016] (10) A non-contact measuring device according to any one of (1) to (9), wherein the three-dimensional coordinate data is acquired by a 3D camera or photogrammetry.

[0017] (11) A non-contact measurement method in which a non-contact measurement device acquires three-dimensional coordinate data of an object having a groove, uses a trained model to identify a measurement area in the three-dimensional coordinate data that includes the groove, and non-contactly measures the remaining groove amount of the object from the three-dimensional coordinate data of the measurement area.

[0018] (12) A program for causing a computer to function as the non-contact measuring device according to any one of (1) to (10).

[0019] According to the present disclosure, it is possible to directly identify a measurement area of ​​an object and measure the remaining groove depth easily and with high accuracy.

[0020] FIG. 1 is a diagram showing an example of the configuration of a non-contact measurement system according to an embodiment. FIG. 2 is a block diagram showing an example of the configuration of a non-contact measurement device according to an embodiment. FIG. 3 is a schematic diagram showing an example of a measurement area identified using a first trained model. FIG. 4 is a schematic diagram showing an example of a measurement area identified using a second trained model. FIG. 5 is a schematic diagram showing an example of identifying a further partial area from the area shown in FIG. 4. FIG. 6 is a schematic diagram showing an example of a measurement area identified using a third trained model. FIG. 7 is a diagram for explaining an example of measuring the remaining groove depth. FIG. 8 is a flowchart showing an example of the procedure of a non-contact measurement method according to an embodiment.

[0021] Hereinafter, one embodiment will be described in detail with reference to the drawings.

[0022] Fig. 1 shows an example of the configuration of a non-contact measurement system according to one embodiment. The non-contact measurement system 1 shown in Fig. 1 includes a non-contact measurement device 10 and a camera 20. The non-contact measurement system 1 is a system that uses the camera 20 to capture an image of an object 30 having a groove, and uses the non-contact measurement device 10 to measure the remaining groove depth of the object 30 in a non-contact manner. In this specification, "groove" refers to the "main groove" that is the subject of measurement of the remaining groove depth.

[0023] The object 30 may be, for example, a tire or a rubber crawler, but is not limited to this as long as it is a part that receives force from the ground and transmits braking / driving force to the main body. The tire is not particularly limited, and may be an OR (Off The Road) tire mounted on a construction vehicle, a mining vehicle, a truck / bus tire, an airplane tire, a passenger car tire, etc. The remaining tread amount may be the remaining tread depth (RTD) or the remaining tread volume.

[0024] The camera 20 is a 3D camera such as a stereo camera or a ToF (Time of Flight) camera, and acquires three-dimensional coordinate data of the object 30. In the stereo camera, the camera 20 has two cameras and calculates the distance (depth) to the object 30 based on the principle of triangulation. In the ToF camera, the camera 20 has a light source and calculates the distance to the object 30 by irradiating the object 30 with infrared light and measuring the time it takes for the reflected light to return.

[0025] The camera 20 may be a monocular camera, or the three-dimensional coordinate data may be acquired by photogrammetry. In this case, the camera 20 photographs the object 30 from multiple directions and calculates the distance to the object 30 based on the principle of triangulation. By using a 3D camera, photogrammetry, or the like, the three-dimensional coordinate data of the object 30 can be acquired with high accuracy.

[0026] The non-contact measuring device 10 is a device that measures the remaining groove depth of an object 30 having a groove in a non-contact manner. The non-contact measuring device 10 may have a built-in camera 20. The non-contact measuring device 10 may be a smart device such as a smartphone or a tablet.

[0027] Fig. 2 shows an example of the configuration of a non-contact measuring device 10 according to one embodiment. The non-contact measuring device 10 shown in Fig. 2 includes an input I / F (interface) 11, a camera I / F 12, a control unit 13, a storage unit 14, and an output I / F 15. The non-contact measuring device 10 may further include a communication I / F such as a LAN (Local Area Network) I / F to enable communication with an external device.

[0028] The input I / F 11 is an interface between the non-contact measuring device 10 and an input device, and the non-contact measuring device 10 is connected to the input device via the input I / F 11. The input device is a keyboard, a pointing device, etc. The input I / F 11 receives user instructions and inputs various data from the input device.

[0029] The camera I / F 12 is an interface between the non-contact measuring device 10 and the camera 20, and the non-contact measuring device 10 is connected to the camera 20 via the camera I / F 12. The camera I / F 12 acquires three-dimensional coordinate data of the object 30 photographed by the camera 20. The camera I / F 12 outputs the three-dimensional coordinate data to the storage unit 14.

[0030] The storage unit 14 includes one or more memories, and may include, for example, a semiconductor memory, a magnetic memory, an optical memory, etc. Each memory included in the storage unit 14 may function, for example, as a main storage device, an auxiliary storage device, or a cache memory. The storage unit 14 stores any information used in the operation of the non-contact measuring device 10. A part of the storage unit 14 may be provided outside the non-contact measuring device 10.

[0031] The output I / F 15 outputs the processing results of the control unit 13 to a display device such as a display. The display device may be integrated with an input device such as a touch screen.

[0032] The control unit 13 performs various controls of the non-contact measurement device 10. The control unit 13 includes an acquisition unit 131 and a measurement unit 132. The control unit 13 may be configured with dedicated hardware such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field-Programmable Gate Array), or may be configured with a processor, or may be configured with both.

[0033] The acquisition unit 131 acquires three-dimensional coordinate data obtained by the camera 20 capturing an image of the object 30 having a groove.

[0034] The measuring unit 132 uses the trained model to identify a measurement area including a groove portion in the three-dimensional coordinate data acquired by the acquiring unit 131, and non-contactly measures the remaining groove amount of the object 30 from the three-dimensional coordinate data of the measurement area. The trained model is a model that has learned the measurement area including the groove portion in the three-dimensional coordinate data through supervised learning. Note that the learning may be machine learning or deep learning. The trained model may be stored in the memory unit 14. Three examples of trained models are shown below.

[0035] The first trained model is a model that has learned the groove shape of the groove portion of the object 30. Using the first trained model, the measurement unit 132 can automatically and with high accuracy identify an area having a groove shape in the three-dimensional coordinate data as a measurement area, and can measure the remaining groove amount from the three-dimensional coordinate data of the measurement area.

[0036] FIG. 3 shows an example of measurement areas identified using the first trained model. The object 30 is a schematic diagram of a tire, with the vertical direction being the circumferential direction and the horizontal direction being the width direction. The same applies to FIGS. 4 to 6. In this example, measurement areas 41 to 48, each having a groove shape, on the object 30 are shown by bounding boxes (rectangles). Each of the measurement areas 41 to 48 has one groove portion 31. The measurement unit 132 measures the remaining groove depth of each groove portion 31 from the three-dimensional coordinate data of the measurement areas 41 to 48.

[0037] The second trained model is a model that has learned the pattern pitch, which is the smallest unit of a pattern applied to the object 30. The pattern pitch is the smallest unit when the same pattern is repeated. If the object 30 is a tire or a rubber crawler, the same pattern is repeated along the circumferential direction. Using the second trained model, the measurement unit 132 can automatically and accurately identify an area having the pattern pitch in the three-dimensional coordinate data as a measurement area, and can measure the remaining groove depth from the three-dimensional coordinate data of the measurement area.

[0038] 4 shows an example of measurement areas identified using the second trained model. In this example, measurement areas 51 to 54 having a pattern pitch on the object 30 are indicated by bounding boxes. The measurement unit 132 measures one remaining groove depth for each of the measurement areas 51 to 54 from the three-dimensional coordinate data.

[0039] 4, one pattern pitch has one groove portion 31 on each side. When one pattern pitch includes multiple groove portions 31, the measurement unit 132 can specify, as the measurement region, an area of ​​the pattern pitch that has only one groove portion 31. In other words, the measurement unit 132 may specify, as the measurement region, an area that accounts for a predetermined proportion of the pattern pitch, and measure the remaining groove amount from the three-dimensional coordinate data of the measurement region.

[0040] FIG. 5 shows an example of further identifying a region from the region shown in FIG. 4 . In this example, the measurement unit 132 identifies a predetermined region 511 or 512 (hatched region) as the measurement region from region 51 having a pattern pitch. For example, measurement region 511 is A% of region 51 on the left side, and measurement region 512 is B% of region 51 on the right side. The values ​​of A and B may be predetermined values ​​or may be values ​​specified by the user. Similarly, the measurement unit 132 identifies measurement region 521 or 522 from region 52, measurement region 531 or 532 from region 53, and measurement region 541 or 542 from region 54.

[0041] The third trained model can be used when the object 30 has a processed portion processed for measurement on the land portion (the portion of the tread surface excluding the grooves). The processed portion may have a recess. This allows it to serve as a marker that remains even when the object 30 wears. The processed portion may also have a circular shape when viewed from the front. This makes it easy to distinguish the processed portion from scratches on the land portion and makes it less susceptible to damage from external forces. The third trained model is a model that has learned the shape of the processed portion. Using the third trained model, the measurement unit 132 can automatically and accurately identify an area defined by multiple processed portions in the three-dimensional coordinate data as a measurement area, and can measure the remaining groove depth from the three-dimensional coordinate data of the measurement area.

[0042] 6 shows an example of a measurement area identified using the third trained model. In this example, a measurement area 71 defined by processing portions 61, 62, and 63 and a measurement area 72 defined by processing portions 64, 65, and 66 on the object 30 are shown by bounding boxes. The measurement unit 132 measures one remaining groove depth from the three-dimensional coordinate data of each of the measurement areas 71 and 72.

[0043] If the object 30 is a tire or rubber crawler, wear indicators (slip signs) for determining the degree of wear are provided at the bottom of some of the grooves. For management purposes, the remaining groove depth of the groove portion where the wear indicator is provided may be measured. Therefore, the trained model may be a model that has trained on the groove portion where the wear indicator is provided (hereinafter referred to as the "measurement target groove portion"). In this case, the measurement unit 132 can measure the remaining groove depth of the measurement target groove portion.

[0044] That is, the measuring unit 132 may use a first trained model that has learned the groove shape of the measurement target groove of the object 30 to identify an area of ​​the three-dimensional coordinate data that has the groove shape of the measurement target groove as the measurement area, and measure the remaining groove depth from the three-dimensional coordinate data of the measurement area. Similarly, the measuring unit 132 may use a second trained model that has learned the pattern pitch of the object 30 that includes the measurement target groove to identify an area of ​​the three-dimensional coordinate data that is the pattern pitch and includes the measurement target groove as the measurement area, and measure the remaining groove depth from the three-dimensional coordinate data of the measurement area. Similarly, the measuring unit 132 may use a third trained model that has learned the shape of the processed portions provided around the measurement target groove to identify an area of ​​the three-dimensional coordinate data that is defined by the processed portions provided around the measurement target groove as the measurement area, and measure the remaining groove depth from the three-dimensional coordinate data of the measurement area.

[0045] The measuring unit 132 may also use a combination of the first trained model and the second trained model. That is, the measuring unit 132 may identify a first measurement area using the first trained model, identify a second measurement area using the second trained model, and further identify a third measurement area included in both or either of the first measurement area and the second measurement area, and measure the remaining groove depth from the three-dimensional coordinate data of the third measurement area. Similarly, the measuring unit 132 may use a combination of the second trained model and the third trained model, or a combination of the first trained model and the third trained model, or a combination of the first trained model, the second trained model, and the third trained model.

[0046] FIG. 7 is a diagram illustrating an example of measuring the remaining groove depth, showing an example of a cross-section of a groove. In this example, the measurement unit 132 uses the three-dimensional coordinate data of the measurement area identified by the trained model to approximate a plane P that closes the groove 31, and measures the normal distance L from the plane P to the bottom Q of the groove 31 as the remaining groove depth. The measurement unit 132 may also determine the longest distance among multiple normals extending from the plane P toward the bottom Q of the groove 31 as the remaining groove depth. In this way, the remaining groove depth can be defined and measured even when the heights of the land portions 32 on both sides of the groove 31 are different. The plane P can be approximated from the three-dimensional coordinate data of the land portions 32 near the groove 31. Note that when the three-dimensional coordinate data of the cross section of the groove 31 is used, the plane P becomes a straight line. That is, when using three-dimensional coordinate data of the cross section of the groove portion 31, the measuring unit 132 may approximate a straight line P that blocks the cross section of the groove portion 31 and measure the normal distance L from the straight line P to the bottom Q of the groove portion 31 as the remaining groove amount.

[0047] The size of the measurement area is not limited, but the measurement unit 132 may correct the size of the measurement area so that it increases as the size of the object 30 or the groove 31 increases. By determining the size of the measurement area taking the size of the object 30 or the groove 31 into consideration, the remaining groove depth can be measured with higher accuracy. For example, if the object 30 is a tire, the measurement unit 132 may set the size of the measurement area to a size proportional to the square of the diameter or radius of the tire. More specifically, if the radius of the object is r and the width of the groove 31 is w, the measurement unit 132 uses the coefficients a, b, and c to determine that the area of ​​the measurement area is a × r ２ More than b x r ２ or less, and the length of the long side of the measurement area may be corrected to be c×w or more.

[0048] <Non-contact measurement method> Next, a non-contact measurement method according to an embodiment will be described. Fig. 8 is a flowchart showing an example of the procedure of the non-contact measurement method.

[0049] In step S101, the camera 20 captures an image of the object 30 having a groove.

[0050] In step S102 , the acquisition unit 131 of the non-contact measuring device 10 acquires three-dimensional coordinate data obtained by photographing the object 30 with the camera 20 .

[0051] In step S103, the measurement unit 132 of the non-contact measurement device 10 uses the trained model to identify a measurement region that includes a groove portion in the three-dimensional coordinate data.

[0052] In step S104, the measurement unit 132 of the non-contact measuring device 10 non-contactly measures the remaining groove amount of the object 30 from the three-dimensional coordinate data of the measurement area.

[0053] As described above, the non-contact measuring device 10 uses the trained model to determine a measurement area including a groove portion in the three-dimensional coordinate data, and then measures the remaining groove depth of the object 30 from the three-dimensional coordinate data of the measurement area. Therefore, according to this embodiment, it is possible to directly identify the measurement area of ​​the object 30 and measure the remaining groove depth easily and with high accuracy. It is also possible to diagnose the lifespan, replacement time, safety, etc. of the object 30.

[0054] <Program> A computer capable of executing program instructions can be used to function as the non-contact measurement device 10. Here, the computer may be a general-purpose computer, a dedicated computer, a workstation, a personal computer (PC), an electronic notepad, a mobile terminal such as a smartphone, etc. The program instructions may be program code, code segments, etc. for performing the necessary tasks.

[0055] The computer includes a processor, a storage unit, an input unit, and an output unit. The processor may be a CPU (Central Processing Unit), an MPU (Micro Processing Unit), a GPU (Graphics Processing Unit), a DSP (Digital Signal Processor), or a SoC (System on a Chip), and may be composed of multiple processors of the same or different types. The processor reads and executes programs from the storage unit to control the above components and perform various arithmetic processing. Note that at least a portion of these processing contents may be implemented by hardware. The input unit is an input interface that accepts user input operations and acquires information based on the user operations, and may be a pointing device, keyboard, microphone, or the like. The output unit is an output interface that outputs information, and may be a display, speaker, or the like.

[0056] The program may be recorded on a computer-readable recording medium. Using such a recording medium, the program can be installed on a computer. Here, the recording medium on which the program is recorded may be a non-transitory recording medium. The non-transitory recording medium is not particularly limited, and may be, for example, a CD-ROM, a DVD-ROM, or a USB (Universal Serial Bus) memory. Furthermore, the program may be downloaded from an external device via a network.

[0057] Although the above-described embodiments have been described as typical examples, it will be apparent to those skilled in the art that many modifications and substitutions are possible within the spirit and scope of the present disclosure. Therefore, the present disclosure should not be interpreted as being limited by the above-described embodiments, and various modifications and alterations are possible without departing from the scope of the claims. For example, multiple building blocks shown in the block diagrams of the embodiments may be integrated, or a single building block may be divided. Furthermore, multiple steps shown in the flowcharts of the embodiments may be integrated into one, or a single step may be divided. Contributing to the United Nations-led Sustainable Development Goals (SDGs)

[0058] The SDGs have been proposed to realize a sustainable society. One embodiment of the present invention is thought to be a technology that can contribute to goals such as "No. 9 - Build infrastructure for industry and technological innovation," "No. 12 - Responsible consumption and production," and "No. 13 - Take concrete action against climate change."

[0059] 1 Non-contact measurement system 10 Non-contact measurement device 11 Input I / F 12 Camera I / F 13 Control unit 14 Memory unit 15 Output I / F 20 Camera 30 Object 31 Groove portion 32 Land portion 61 to 66 Processing unit 131 Acquisition unit 132 Measurement unit 41 to 48, 51 to 54, 71, 72, 511, 512, 521, 522, 531, 532, 541, 542 Measurement area

Claims

1. A non-contact measurement device comprising: an acquisition unit that acquires three-dimensional coordinate data of an object having a groove; and a measurement unit that uses a trained model to identify a measurement area in the three-dimensional coordinate data that includes the groove, and non-contactly measures the remaining groove volume of the object from the three-dimensional coordinate data of the measurement area.

2. The non-contact measuring device according to claim 1, wherein the measuring unit approximates a plane that closes the groove and measures the normal distance from the plane to the bottom of the groove as the remaining groove amount.

3. A non-contact measuring device as described in claim 1 or 2, wherein the measurement unit uses a learned model that has learned the groove shape of a groove portion of an object to identify an area in the three-dimensional coordinate data that has the groove shape as the measurement area.

4. A non-contact measuring device as described in claim 1 or 2, wherein the measurement unit uses a trained model that has learned a pattern pitch, which is the smallest unit of a pattern applied to an object, to identify an area in the three-dimensional coordinate data that has the pattern pitch as the measurement area.

5. The non-contact measuring device according to claim 4, wherein the measuring section identifies an area of ​​a predetermined percentage of the pattern pitch as the measurement area.

6. A non-contact measuring device as described in claim 1 or 2, wherein the object has a processed portion on a land portion that has been processed for measurement, and the measuring unit uses a trained model that has learned the shape of the processed portion to identify an area defined by a plurality of the processed portions in the three-dimensional coordinate data as the measurement area.

7. The non-contact measuring device according to claim 6, wherein the processed portion has a recess and is circular in shape when viewed from the front.

8. A non-contact measuring device according to claim 1 or 2, wherein the measuring section corrects the size of the measurement area so that the larger the size of the object or the groove portion, the larger the size of the measurement area becomes.

9. The non-contact measuring device according to claim 1 or 2, wherein the object includes a tire and a rubber crawler.

10. A non-contact measuring device as described in claim 1 or 2, wherein the three-dimensional coordinate data is acquired by a 3D camera or photogrammetry.

11. A non-contact measurement method in which a non-contact measuring device performs the following steps: acquires three-dimensional coordinate data of an object having a groove; identifies a measurement area including the groove in the three-dimensional coordinate data using a trained model; and non-contactly measures the remaining groove volume of the object from the three-dimensional coordinate data of the measurement area.

12. A program for causing a computer to function as the non-contact measuring device according to claim 1 or 2.

Images