Patent Application
20250045897
The present invention relates to a tire inspection support apparatus, a method, and a program, and in particular, to a tire inspection support apparatus, a method, and a program for supporting an inspection of a tire.
Regarding a determination as to whether a tire requires maintenance work or not, the criterion based on which the determination is made varies according to the driver or the mechanic, so it has been desired to introduce an objective indicator. Patent Literature 1 discloses a technology for detecting a crack in a tire by extracting an area where grooves are formed in the tire from a depth map or the like of the tire and binarizing a photographed image of that area, and for then evaluating the deterioration of the tire from the size of the crack.
Patent Literature 1: Japanese Unexamined Patent Application Publication No. 2015-161575
Note that to determine the deterioration of a tire, it is necessary to take the degree of cracks into consideration. Further, there is room for improvement in the accuracy of the technology for detecting a cracked part in a tire from a photographed image of the tire. Note that in the technology disclosed in Patent Literature 1, cracks formed in areas other than the area where grooves are formed are not detected.
In view of the above-described problem, an object of the present disclosure is to provide a tire inspection support apparatus, a method, and a program for improving the accuracy of the detection of a cracked part in a tire from a photographed image of the tire.
A tire inspection support apparatus according to a first aspect of the present disclosure includes:
In a tire inspection support method according to a second aspect of the present disclosure, a computer:
A non-transitory computer readable medium storing an inspection support program according to a third aspect of the present disclosure causes a computer to perform:
According to the present disclosure, it is possible to provide a tire inspection support apparatus, a method, and a program for improving the accuracy of the detection of a cracked part in a tire from a photographed image of the tire.
An example embodiment according to the present disclosure will be described in detail hereinafter with reference to the drawings. The same or corresponding elements are assigned the same reference numerals (or symbols) throughout the drawings, and redundant descriptions thereof will be omitted as appropriate for clarifying the explanation.
The first detection unit 11 detects a first area including a cracked part candidate in a tire through first image processing performed on a photographed image of the tire. The generation unit 12 generates an image to be processed obtained by extracting a partial image corresponding to the first area from the photographed image. The second detection unit 13 detects a second area showing the cracked part from the first area through second image processing performed on the image to be processed. The calculation unit 14 calculates an index value for the cracked part in the tire based on the second area.
As described above, the tire inspection support apparatus 1 according to this example embodiment detects a first area including a cracked part candidate with a certain level of accuracy (first accuracy) from the photographed image of the tire through the first image processing. Then, the tire inspection support apparatus 1 performs second image processing on a partial image corresponding to the first area in the photographed image. That is, in the second image processing, image data from which the cracked part will be detected has already been narrowed down. Therefore, the tire inspection support apparatus 1 can detect the cracked part (second area) through the second image processing with second accuracy higher than the first accuracy. Further, the tire inspection support apparatus 1 calculates an index value from the second area showing the cracked part with increased accuracy by using a predetermined criterion, and thereby can provide an objective determination index in regard to whether the tire requires maintenance work or not to a user such as a mechanic. Therefore, the accuracy of the detection of a cracked part from the photographed image of the tire is improved, thus making it possible to support the inspection of the tire.
Note that the tire inspection support apparatus 1 includes, as a configuration not shown in the drawing, a processor, a memory, and a storage device. Further, in the storage device, a computer program(s) programed for implementing processes of a tire inspection support method according to this example embodiment is stored. Further, the processor loads a computer program and the like from the storage device onto the memory, and executes the loaded computer program. In this way, the processor implements the functions of the first detection unit 11, the generation unit 12, the second detection unit 13, and the calculation unit 14.
Alternatively, each component of the tire inspection support apparatus 1 may be implemented by dedicated hardware. Further, some or all of the components of apparatuses may be implemented by a general-purpose or dedicated circuitry, processor or the like, or a combination thereof. They may be configured by a single chip or by a plurality of chips connected through a bus. Some or all of the components of apparatuses may be implemented by a combination of the above-described circuitry or the like and the program. Further, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an FPGA (Field-Programmable Gate Array), a quantum processor (quantum computer control chip) or the like may be used as a processor.
A second example embodiment is a specific example of the above-described first example embodiment. A problem to be solved by this example embodiment will be described hereinafter in detail. Firstly, the exhaustion of a tire includes exhaustion due to wear and that due to a crack(s). Regarding the exhaustion level due to wear, there is a specific index value in regard to the depth of grooves of a tire. Further, when the depth of grooves of a tire does not meet a threshold, the car or the like using this tire will not pass a car inspection. Therefore, a mechanic or the like can determine whether the tire requires maintenance work or not based on the objective index in regard to the depth of grooves. In contrast, the exhaustion due to a crack(s) is caused by, for example, the effect of ultraviolet rays irrespective of the distance that the car or the like has travelled using the tire, so it is difficult for at least an ordinary driver to predict such exhaustion. Further, there is no clear maintenance criterion in regard to the exhaustion level due to a crack(s). Therefore, the criterion based on which it is determined whether or not maintenance work is required because of the exhaustion due to a crack(s) in the tire differs from one mechanic to another.
Therefore, as an example, an AI (Artificial Intelligence) model is used to determine the degree of a crack in a tire by using a photographed image of the tire as its input. When doing so, the AI model is machine-trained through deep learning or the like by using photographed images of tires and results of determinations on exhaustion levels made by mechanics or the like as learning data, and then an image of a cracked part candidate can be extracted from input data of a photographed image of a tire by using the trained model.
However, there are cases where in such a trained model, an area larger than the actual cracked part is determined (detected) as an area of a cracked part. As a result, there is a problem that the accurate size and shape of the cracked part cannot be extracted (detected) when only the trained model is used. Therefore, in each of the below-described example embodiments, a technology for improving the accuracy of the detection of a cracked part in a tire from a photographed image of the tire will be described.
The camera 200 is a photographing apparatus by which the mechanic U photographs the tire 100 to be inspected. The camera 200 transmits a photographed image of the tire 100 to the tire inspection support apparatus 300 in response to, for example, an operation performed by the mechanic U.
The tire inspection support apparatus 300 is an example of the above-described tire inspection support apparatus 1. The tire inspection support apparatus 300 may be configured in a redundant manner over a plurality of servers, and each functional block thereof may be implemented by a plurality of computers.
The tire inspection support apparatus 300 detects a cracked part from the photographed image of the tire 100 taken by the camera 200 in two stages, and calculates an index value for the cracked part. Further, the tire inspection support apparatus 300 may determine the deterioration level of the tire from the index value. Further, the tire inspection support apparatus 300 may generate a display image by adding, to the photographed image, display information for displaying a position corresponding to the cracked part in the photographed image in such a manner that the position can be distinguished. Further, the tire inspection support apparatus 300 may output at least one of the index value, the result of the determination on the deterioration level, and the display image to the display device 400.
The display device 400 displays, on a screen, information received from the tire inspection support apparatus 300, e.g., displays at least one of the index value, the result of the determination on the deterioration level, and the display image. In this way, the mechanic U can easily determine whether the tire 100 requires maintenance work or not through the screen of the display device 400.
The memory 320 is a volatile storage device such as a RAM (Random Access Memory) and provides a storage area for temporarily holding information when the control unit 340 operates. The IF unit 330 is a communication interface between the components or the like inside the tire inspection support apparatus 300, and the camera 200 and the display device 400.
The control unit 340 is a processor, i.e., a control apparatus that controls each component of the tire inspection support apparatus 300. The control unit 340 loads the tire inspection support program 311 and the first image processing model 312 from the storage unit 310 onto the memory 320, and executes the loaded tire inspection support program 311 and the first image processing model 312. In this way, the control unit 340 implements functions of an acquisition unit 341, a preprocessing unit 342, a first detection unit 343, a generation unit 344, a second detection unit 345, a calculation unit 346, a specifying unit 347, a determination unit 348, and an output unit 349.
The acquisition unit 341 acquires the photographed image of the tire 100 from the camera 200. That is, the acquisition unit 341 receives the photographed image as an input to the tire inspection support program 311.
The preprocessing unit 342 converts the size (the number of pixels or the like) of the photographed image to a first size, and divides the converted image into a plurality of divided photographed images each having a second size.
The first detection unit 343 is an example of the above-described first detection unit 11. The first detection unit 343 performs first image processing on the photographed image of the tire. Specifically, the first detection unit 343 performs the first image processing on the photographed image (divided photographed image) input to the tire inspection support program 311 by using the first image processing model 312, and acquires a detection result. The detection result is information indicating a first area including a cracked part candidate in the tire. The detection result is, for example, drawing data of an area determined to be a cracked part candidate or a first binary image in which a cracked part candidate is black and the other parts are white.
The generation unit 344 is an example of the above-described generation unit 12. The generation unit 344 generates an image to be processed which is a partial image corresponding to the first area, extracted from the photographed image. Specifically, the generation unit 344 generates an image to be processed by masking the areas other than the first area in the photographed image and thereby extracting a partial image. Further, the generation unit 344 may also generate a display image which is an image obtained by adding, to the photographed image, display information of a position specified by the specifying unit 347 described later. Note that the display information of the specified position is an enclosing line by which the area of interest is enclosed in the photographed image, or information or the like highlighted so that the area of interest can be distinguished.
The second detection unit 345 is an example of the above-described second detection unit 13. The second detection unit 345 performs second image processing on the image to be processed. Specifically, the second detection unit 345 performs binarization processing on the image to be processed and thereby generates a second binary image. Note that the second image processing is not limited to the binarization processing. For example, the second image processing may be a process for extracting a cracked part by using an AI model different from the one used for the first image processing, in particular, a trained model. Further, the second detection unit 345 may divide the image to be processed into a plurality of first unit areas and perform second image processing for each of the first unit areas, and by doing so, detect a second area for each of the first unit areas.
The calculation unit 346 is an example of the above-described calculation unit 14. The calculation unit 346 calculates an index value for a crack in the tire 100 based on the second area. For example, the calculation unit 346 may set a part of the image to be processed as a second unit area, slide the part by a distance shorter than the size of the second unit area, thereby setting a plurality of second unit areas in the image to be processed, and calculate an index value for each of the second unit areas. The size of the second unit area is, for example, the vertical length or the horizontal length of the second unit area. Further, the distance shorter than the size of the second unit area may be called a slide width. That is, the calculation unit 346 successively slides the second unit area, starting from an initial setting position thereof, by the slide width in the image to be processed, and thereby sets a plurality of second unit areas so that they cover the entire area in the image to be processed. Therefore, the plurality of second unit areas may overlap one another. Then, the calculation unit 346 may calculate, as an index value, a crack rate based on a ratio between the second unit area and a second area detected in the second unit area.
The specifying unit 347 is an example of the first specifying means. The specifying unit 347 specifies a second unit area corresponding to, among the index values calculated for the respective second unit areas, an index value that satisfies a predetermined condition. The predetermined condition is, for example, a condition that the index value is equal to or larger than a first predetermined value, a condition that the index value is the maximum value among the index values calculated for the respective second unit areas, or a condition that the index value is included in a predetermined number of highest ones among the index values calculated for the respective second unit areas. Further, the specifying unit 347 specifies a position in the photographed image corresponding to the specified second unit area.
The determination unit 348 determines the deterioration level of the tire 100 based on the index value. For example, the determination unit 348 determines the deterioration level based on the crack rate. Examples of the deterioration level include, but are not limited to, a multi-level value such as a value indicating large, medium, or small, a numerical value, and a percentage. Note that the determination unit 348 may determine a deterioration level for each of the second unit areas.
The output unit 349 outputs the deterioration level determined by the determination unit 348 to the display device 400. Further, the output unit 349 may output a deterioration level of each of the second unit areas. Further, the output unit 349 outputs an index value. Specifically, the output unit 349 outputs the crack rate calculated by the calculation unit 346. Further, the output unit 349 may output a crack rate in each of the second unit areas. The output unit 349 may add, to the photographed image, display information for displaying the position specified by the specifying unit 347 so that the position can be distinguished, and output the photographed image including the display information. Alternatively, the output unit 349 may output the display image generated by the generation unit 344. Alternatively, the output unit 349 may output the deterioration level and the index value while associating them with each other. Alternatively, the output unit 349 may output the deterioration level and the display information while associating them with each other. Alternatively, the output unit 349 may output the index value and the display information while associating them with each other. Alternatively, the output unit 349 may output the deterioration level, the index value, and the display information while associating them with each other.
Next, the tire inspection support apparatus 300 converts the photographed image into an image having a first size, and divides the converted image into a plurality of divided photographed images each having a second size (S102). For example, the preprocessing unit 342 converts the size of the photographed image to 3,000 pixels. Then, the preprocessing unit 342 divides the converted image into images each having 500×500 pixels. However, the conversion to the first size does not necessarily have to be carried out.
Next, the tire inspection support apparatus 300 inputs each of the divided photographed images to the first image processing model 312, and thereby acquires a detection result (first binary image) of a cracked part candidate (S103).
Then, the tire inspection support apparatus 300 generates an image to be processed 53 from the divided photographed image 51 and the detection result 52 (S104). For example, the generation unit 344 superimposes the divided photographed image 51 and the detection result 52 on each other, and converts the color of pixels in the divided photographed image 51 which correspond to white pixels in the detection result 52 to white. That is, while the pixel values of the pixels in the divided photographed image 51 which correspond to black pixels in the detection result 52 are unchanged, the other pixels in the divided photographed image 51 are masked to white (i.e., their color is changed to white). Note that in the above-described process, the conversion of the color of pixels in the divided photographed image 51 to white is just an example, and any of other types of conversion may be performed, provided that the converted pixels can be distinguished, in the image to be processed 53, as an area outside the area on which the second image processing will be performed. For example, the generation unit 344 may convert the opacity of the area in the divided photographed image 51, located outside the area on which the second image processing will be performed to zero, i.e., convert the opacity of the area so that the area becomes transparent.
Then, the tire inspection support apparatus 300 divides the image to be processed 53 into a plurality of first unit areas (S105). For example, the second detection unit 345 divides the image to be processed 53 into a grid pattern (lattice or cell) of 500×500 pixels. That is, the second detection unit 345 divides the image to be processed 53 into a plurality of first unit areas.
Then, the tire inspection support apparatus 300 performs binarization processing for each of the first unit areas, and thereby detects a cracked part in each of them (S106). That is, the tire inspection support apparatus 300 acquires a second binary image obtained by performing binarization processing on the image to be processed 53. Specifically, the second detection unit 345 performs predetermined binarization processing for each of the first unit areas. For example, the second detection unit 345 converts, for each pixel in the first unit area 531, the color of the pixel to black when its pixel value is equal to or higher than a threshold, and converts it to white when its pixel value is lower than the threshold. Note that in the predetermined binarization processing, the threshold may be changed for each of the first unit areas.
After that, the tire inspection support apparatus 300 calculates a crack rate in each of the second unit areas (S107). Note that the size of the second unit area in the step S107 may be different from the size of the first unit area in the above-described step S105. Further, the tire inspection support apparatus 300 may calculate a crack rate in each of the second unit areas, each of which has a predetermined size, on the second binary image 54 while shifting the second unit area by a distance equivalent to a predetermined number of pixels. The second unit area, which is set while being shifted by a distance equivalent to a predetermined number of pixels in the step S107 as described above, is called a slide window or simply a window.
For example, the calculation unit 346 sets the slide window 541 by using the upper left corner of the second binary image 54 as the origin. Then, the calculation unit 346 calculates a crack rate in the slide window 541. Specifically, the calculation unit 346 calculates the crack rate by dividing the number of black pixels in the slide window 541 by the size of the slide window 541. Next, the calculation unit 346 sets the slide window 542 by sliding the left end of the slide window 541 to the right by 200 pixels. Therefore, a right-end area of the slide window 541 having a width of 400 pixels overlaps with a left-end area of the slide window 542 having a width of 400 pixels. Then, the calculation unit 346 calculates a crack rate in the slide window 542. Next, the calculation unit 346 sets the slide window 543 by sliding the left end of the slide window 542 to the right by 200 pixels. Therefore, a right-end area of the slide window 541 having a width of 200 pixels overlaps with a left-end area of the slide window 543 having a width of 200 pixels. Further, a right-end area of the slide window 542 having a width of 400 pixels overlaps with a left-end area of the slide window 543 having a width of 400 pixels. Then, the calculation unit 346 calculates a crack rate in the slide window 543.
As described above, the calculation unit 346 slides, from the left end of the uppermost row of the second binary image 54 to the right end thereof, the slide window by a slide width shorter than the crosswise length of the slide window at a time, and thereby successively sets slide windows, and calculates a crack rate in each of the slide windows. Next, the calculation unit 346 slides the slide window from the uppermost row of the second binary image 54 by a slide width shorter than the lengthwise length of the slide window, and thereby sets a slide window. For example, the calculation unit 346 slides the slide window downward from the slide window 541 by 200 pixels and thereby sets the leftmost slide window in the second row, and calculates a crack rate in this slide window. After that, the calculation unit 346 calculates a crack rate in each of slide windows one after another from the leftmost slide window to the rightmost slide window in the second row of the second binary image 54, and eventually calculates crack rates up to the rightmost slide window in the lowermost row. Note that the size of the slide window, the order of slide windows, the slide width, and the like are not limited to the above-described examples.
After that, the tire inspection support apparatus 300 specifies the maximum value among the calculated crack rates (S108). Specifically, for example, the specifying unit 347 specifies the maximum crack rate among the crack rates of all the slide windows including the slide window 541 and the like.
Then, the tire inspection support apparatus 300 determines a deterioration level from the specified crack rate (S109). Specifically, the determination unit 348 determines (i.e., selects) one of a plurality of multi-level values according to the crack rate, and defines the result of the determination as the deterioration level. For example, the determination unit 348 determines the deterioration level as “Low” when the crack rate is lower than 2.5%, determines the deterioration level as “Medium” when the crack rate is not lower than 2.5% and lower than 4.2%, and determines the deterioration level as “High” when the crack rate is 4.2% or higher.
Further, the tire inspection support apparatus 300 specifies, independently of the step S109, a unit area corresponding to the specified crack rate (S110). That is, the specifying unit 347 specifies a slide window corresponding to the maximum crack rate. Then, the tire inspection support apparatus 300 specifies a position in the photographed image corresponding to the specified unit area (S111). Then, the tire inspection support apparatus 300 generates a display image obtained by adding display information of the specified position to the photographed image (S112). For example, the generation unit 344 uses a red enclosing line by which the area corresponding to the specified position is enclosed in the divided photographed image 51 as display information. Then, the generation unit 344 generates a display image by adding the display information to the area of interest on the divided photographed image 51.
After the steps S109 and S112, the tire inspection support apparatus 300 outputs the maximum value of the crack rate, the determined deterioration level, and the display image to the display device 400 (S113). Note that the tire inspection support apparatus 300 may further output a support message corresponding to the deterioration level. In response to this, the display device 400 displays, on a screen, the maximum value of the crack rate, the determined deterioration level, and the display image received from the tire inspection support apparatus 300.
As described above, when an index value is calculated from a second binary image, the second binary image is scanned (i.e., successively defined and checked) while shifting the slide window having a predetermined size by a slide width shorter than the window width. In this way, it is possible to determine the position of the maximum crack rate with increased accuracy than in the case where the second binary image is simply divided into a grid pattern (into first unit areas) and the index value is calculated for each cell (or lattice) of the grid pattern (i.e., for each unit area). For example, as shown as the display information 554 in
Further, the first detection unit 343 detects a candidate area (first area) of a cracked part from a photographed image of a tire by using first image processing model 312 that has already been trained through deep learning. However, regarding the candidate area of the cracked part detected by using the first image processing model 312, the cracked part tends to be detected thicker than the actual cracked part. Therefore, in this example embodiment, the generation unit 344 masks the area other than the first area in the divided photographed image 51 and thereby generates the image to be processed 53 in which the partial image of the first area remains. Then, the second detection unit 345 can narrow down the actual cracked part in the partial image by performing binarization processing on the image to be processed 53. That is, in this example embodiment, the process for detecting a cracked part is performed in two stages, so that the shape of a crack(s) can be detected in a detailed manner.
Further, there is unevenness in the brightness of the image to be processed 53 obtained by performing the masking in the photographed image of the tire. Therefore, if the whole image is binarized in a collective manner, there is a limit on the improvement of the accuracy of the narrowing-down of the cracked part. Therefore, in this example embodiment, the image to be processed 53 is divided into a plurality of unit areas and binarization is performed for each of the unit areas, so that the analysis can be performed in a detailed manner and hence the accuracy of the detection can be improved. In particular, by adjusting the threshold used in the binarization for each of the unit areas, it is possible improve the accuracy of the detection while taking the unevenness in the brightness into consideration. Note that the second detection unit 345 may perform second image processing other than the binarization processing.
Further, in this example embodiment, an area corresponding to the maximum value of the crack rate is specified, and is indicated and displayed in the photographed image. Therefore, a mechanic U can visually and easily recognize a part of the tire 100 to be inspected which has deteriorated more than any of the other parts of the tire 100, and thereby can easily determine whether maintenance work is necessary or not. This is because a tire is one integrated component, so that if there is a large crack even in only one place, the tire itself needs to be replaced.
Note that although the binarization processing is performed and a crack rate is calculated after the image to be processed 53 is divided into a plurality of unit areas in the above-described second example embodiment, the present disclosure is not limited to this example. For example, the second detection unit 345 may detect a second area by performing binarization processing on the whole image to be processed 53 without dividing the image to be processed 53. In such a case, the calculation unit 346 preferably calculates a crack rate as an index value based on a ratio between the photographed image (divided photographed image 51) and the second area (i.e., number of pixels belonging to the second area).
Further, although display information is added to the unit area corresponding to the maximum value of the crack rate in the above-described second example embodiment, the present disclosure is not limited to this example. For example, the specifying unit 347 may specify two or more positions in the photographed image corresponding respective second areas. In such a case, the output unit 349 preferably adds, in the photographed image, a plurality of pieces of display information for displaying a plurality of specified positions, respectively, so that these positions can be distinguished, and output the photographed image including these pieces of display information. Further, although the above-described example embodiments have been described by using a crack in a tire as an object to be detected, the technology according to the present disclosure may be applied to a crack in an article or a structure other than the tire (such as a road, a bridge, and a building).
In the above-described examples, the program includes a set of instructions (or software codes) that, when being loaded into a computer, causes the computer to perform one or more of the functions described in the example embodiments. The program may be stored in a non-transitory computer readable medium or in a physical storage medium. By way of example rather than limitation, a computer readable medium or a physical storage medium may include a random-access memory (RAM), a read-only memory (ROM), a flash memory, a solid-state drive (SSD), or other memory technology, a CD-ROM, a digital versatile disc (DVD), a Blu-ray (registered trademark) disc or other optical disc storages, a magnetic cassette, magnetic tape, and a magnetic disc storage or other magnetic storage devices. The program may be transmitted on a transitory computer readable medium or a communication medium. By way of example rather than limitation, the transitory computer readable medium or the communication medium may include electrical, optical, acoustic, or other forms of propagating signals.
Note that the present disclosure is not limited to the above-described example embodiments and various changes may be made therein without departing from the spirit and scope of the present disclosure. Further, the present disclosure may be implemented by combining example embodiments with one another.
The whole or part of the example embodiments disclosed above can be described as, but not limited to, the following Supplementary note.
A tire inspection support apparatus comprising:
The tire inspection support apparatus described in Supplementary note A1, wherein the second detection means performs binarization processing on the image to be processed as the second image processing.
The tire inspection support apparatus described in Supplementary note A1 or A2, further comprising:
The tire inspection support apparatus described in any one of Supplementary notes A1 to A3, further comprising second output means for outputting the index value.
The tire inspection support apparatus described in any one of Supplementary notes A1 to A4, wherein the generation means generates the image to be processed by masking an area other than the first area in the photographed image and thereby extracting the partial image.
The tire inspection support apparatus described in any one of Supplementary notes A1 to A5, wherein
The tire inspection support apparatus described in Supplementary note A6, further comprising:
The tire inspection support apparatus described in Supplementary note A7, wherein the predetermined condition is a condition that the index value be a maximum value among the index values calculated for the respective second unit areas.
The tire inspection support apparatus described in any one of Supplementary notes A6 to A8, wherein the calculation means calculates a crack rate as the index value based on a ratio between the second unit area and the second area detected in the second unit area.
The tire inspection support apparatus described in any one of Supplementary notes A1 to A5, wherein the calculation means calculates a crack rate as the index value based on a ratio between the photographed image and the second area.
The tire inspection support apparatus described in any one of Supplementary notes A1 to A5 and A10, further comprising:
A tire inspection support method, in which a computer:
A non-transitory computer readable medium storing an inspection support program for causing a computer to perform:
Although the present invention has been described with reference to example embodiments (and examples), the present invention is not limited to the above-described example embodiments (and examples). The configuration and details of the present invention may be modified within the scope of the present invention in various ways that can be understood by those skilled in the art.
| Filing Document | Filing Date | Country | Kind |
|---|---|---|---|
| PCT/JP2021/048385 | 12/24/2021 | WO |
