WO2022054385A1 - 管理装置、管理方法及び照合用データ生成方法 - Google Patents
管理装置、管理方法及び照合用データ生成方法 Download PDFInfo
- Publication number
- WO2022054385A1 WO2022054385A1 PCT/JP2021/025676 JP2021025676W WO2022054385A1 WO 2022054385 A1 WO2022054385 A1 WO 2022054385A1 JP 2021025676 W JP2021025676 W JP 2021025676W WO 2022054385 A1 WO2022054385 A1 WO 2022054385A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- unit
- data
- collation
- long object
- management device
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65H—HANDLING THIN OR FILAMENTARY MATERIAL, e.g. SHEETS, WEBS, CABLES
- B65H63/00—Warning or safety devices, e.g. automatic fault detectors, stop-motions ; Quality control of the package
- B65H63/08—Warning or safety devices, e.g. automatic fault detectors, stop-motions ; Quality control of the package responsive to delivery of a measured length of material, completion of winding of a package, or filling of a receptacle
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65H—HANDLING THIN OR FILAMENTARY MATERIAL, e.g. SHEETS, WEBS, CABLES
- B65H55/00—Wound packages of filamentary material
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65H—HANDLING THIN OR FILAMENTARY MATERIAL, e.g. SHEETS, WEBS, CABLES
- B65H63/00—Warning or safety devices, e.g. automatic fault detectors, stop-motions ; Quality control of the package
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65H—HANDLING THIN OR FILAMENTARY MATERIAL, e.g. SHEETS, WEBS, CABLES
- B65H2511/00—Dimensions; Position; Numbers; Identification; Occurrences
- B65H2511/10—Size; Dimensions
- B65H2511/11—Length
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
- B65H—HANDLING THIN OR FILAMENTARY MATERIAL, e.g. SHEETS, WEBS, CABLES
- B65H2553/00—Sensing or detecting means
- B65H2553/40—Sensing or detecting means using optical, e.g. photographic, elements
- B65H2553/42—Cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30136—Metal
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Definitions
- the present invention relates to a management device, a management method, and a collation data generation method.
- Patent Document 1 describes attaching a management module to a drum around which a long object is wound.
- An object of the present invention is to simplify the management of long objects.
- the present invention for solving the above problems is a management device for managing a unit in which a long object is wound around a drum, and when the unit is continuously photographed while the long object is wound around the drum.
- FIG. 1 is an explanatory diagram of the relationship between the pattern of the unit and the winding amount (remaining amount) of a long object.
- FIG. 2 is an explanatory diagram of an example of the management system 100 of the present embodiment.
- FIG. 3 is an explanatory diagram of an example of the processing flow of the present embodiment.
- FIG. 4A is an explanatory diagram of an example of registered data.
- FIG. 4B is an explanatory diagram of another example of the registered data.
- FIG. 5 is an explanatory diagram of an example of unit basic data.
- FIG. 6 is an explanatory diagram showing a hardware configuration of the management device 20.
- FIG. 7 is a block diagram showing the functions of the management device 20.
- FIG. 8 is an explanatory diagram of the coordinate conversion process of the present embodiment.
- FIG. 1 is an explanatory diagram of the relationship between the pattern of the unit and the winding amount (remaining amount) of a long object.
- FIG. 2 is an explanatory diagram of an example of
- FIG. 9 is an explanatory diagram of an example of collation data 42.
- FIG. 10 is an explanatory diagram of an example of management data 44.
- FIG. 11A is an explanatory diagram of image data used for acquiring feature quantity information.
- FIG. 11B is a conceptual explanatory diagram of the collation process.
- FIG. 12 is an explanatory diagram of the management data 44 of the modified example.
- FIG. 13A is an explanatory diagram of the unit manufacturing apparatus 10 of the modified example.
- FIG. 13B is an explanatory diagram of the unit 1 of the modified example.
- 14A and 14B are explanatory views of the second embodiment.
- the remaining amount of the long object is determined based on the collation result of collating the collation data associated with the winding amount of the long object and the shooting result of the unit acquired from the user terminal.
- the management device characterized by doing so becomes clear. Such a management device simplifies the management of long objects.
- the collation data is associated with a unit ID that identifies the unit, the winding amount of the long object, and a shooting result, and the collation data and the shooting acquired from the user terminal are associated with each other. It is desirable to determine the unit ID based on the collation result collated with the result. This simplifies unit management.
- Information about the unit is associated with the unit ID, and after the unit ID is determined by collating the collation data with the shooting result acquired from the user terminal, the unit ID is used. It is desirable to send information about the associated unit to the user terminal. This simplifies unit management.
- collation data is associated with the winding amount of the long object and the feature amount extracted from the image data obtained by photographing the unit. This makes it possible to improve the accuracy of collation.
- the shooting result of the unit is acquired again from the user terminal, the winding amount larger than the remaining amount is excluded from the collation target, and the shooting result acquired from the user terminal is collated with the collation data. It is desirable to do. As a result, the collation processing time can be shortened.
- the collation data is a trained model generated by machine learning using the shooting result as input data and the winding amount as output data. This makes it possible to improve the accuracy of collation.
- a management method for determining the remaining amount of the long object becomes clear. According to such a management method, management of a long object becomes easy.
- a plurality of registration data including the shooting result and the winding amount of the long object wound around the drum at the time of shooting are acquired.
- a collation data generation method in which the imaging result of the unit is used as an input and the collation data is generated with the winding amount as an output becomes clear. According to such a collation data generation method, collation data that can easily manage the remaining amount of a long object can be generated.
- long object means a long member.
- the long object includes, for example, a linear member such as a cable (electric wire cable, optical cable, etc.), a thread, a wire, and a strip-shaped member such as a tape or a film.
- the "drum” means a member around which a long object is wound.
- the drum has a cylindrical body, and a long object is wound around the outer circumference of the body. Flange portions may be provided at both ends of the body portion of the drum.
- the drum also includes, for example, a member called a bobbin.
- the "unit” means an aggregate in which a long object is wound around a drum.
- the unit includes, for example, a cable wound around a drum, a thread wound around a bobbin, and the like.
- FIG. 1 is an explanatory diagram of the relationship between the pattern of the unit and the winding amount (remaining amount) of a long object.
- the length (winding amount) of the long object wound around the drum is 100 m, 500 m, and 1000 m in order from the left side in the figure.
- the long object wrapped around the drum will form a pattern on the surface of the unit.
- the pattern of the unit will be different depending on the winding amount, and it will be a unique pattern like a fingerprint.
- the unit is manufactured by stacking and winding a long object on the drum.
- the unit may be newly manufactured, or the unit may be manufactured by rewinding a long product of the manufactured unit to another drum.
- the pattern of the unit will change one after another as the long object is wrapped around it.
- a certain amount of wrapping pattern in the middle of production is hidden under a long object wrapped around it. For example, as shown on the upper side in the figure, the pattern when the winding amount is 100 m is not displayed when the winding amount is 500 m or 1000 m. Similarly, the pattern when the winding amount is 500 m is not displayed when the winding amount is 1000 m. However, the pattern according to the winding amount is held under the long object wound on it.
- the lower part of the figure shows how the long object is pulled out from the drum, reducing the remaining amount of the long object wound around the drum (corresponding to the winding amount).
- the remaining amount of the long object wound around the drum is 1000 m, 500 m, and 100 m in order from the right side in the figure.
- the pattern hidden under the pulled out long object appears.
- the exposed pattern becomes a pattern peculiar to the remaining amount (corresponding to the winding amount) of the long object wound around the drum at that time.
- the remaining amount of a long object is managed by utilizing the pattern property of such a unit. That is, by continuously photographing the unit while the long object is wound around the drum at the time of manufacturing the unit, collation data corresponding to the winding amount of the long object at the time of photographing and the photographing result is formed. Will be done. As a result, the pattern of the unit is registered. The user who is the user of the unit will shoot the unit after using the unit and send the shooting result. Then, the shooting result acquired from the user is collated with the collation data, and the remaining amount of the long object is determined based on the collation result.
- the remaining amount (winding amount) of the long object of the user's original unit is obtained. According to the management method of the present embodiment as described above, the remaining amount management of the long object is simplified.
- the pattern of the units will be different if the units are different. As a result, if the units are different, the patterns of the units will be different even if the winding amount is the same. In this way, the pattern of the unit is unique, like a fingerprint. It is also possible to manage not only the remaining amount of long objects but also the type of unit (unit ID) by utilizing the pattern property of such a unit.
- FIG. 2 is an explanatory diagram of an example of the management system 100 of the present embodiment.
- FIG. 3 is an explanatory diagram of an example of the processing flow of the present embodiment.
- the management system 100 is a system that manages the remaining amount of the long object 3 of the unit 1 under the user.
- the management system 100 includes a unit manufacturing device 10 installed in a unit manufacturing factory and a management device 20.
- the management system 100 can communicate with the user terminal 70 via the communication network 90.
- the communication network 90 is, for example, a telephone line network (public telephone line network, mobile telephone line network), a wireless communication network, the Internet, a LAN, a WAN, or the like, and the Internet is assumed here.
- the user terminal 70 is, for example, a smartphone equipped with a photographing device (camera), a mobile phone, or the like.
- the user terminal 70 does not have to be directly equipped with a shooting device (camera), and may be a terminal (for example, a mobile computer) capable of acquiring a shooting result from an external shooting device.
- the user terminal 70 can communicate with the management device 20 via the communication network 90, and can, for example, transmit a shooting result shot by the shooting device (camera) to the management device 20.
- the "shooting result” means the information obtained by shooting with the shooting device.
- the “shooting result” includes, for example, image data (raw data) output from the shooting device and image data (processed image data) obtained by processing the image data (raw data) output from the shooting device. And data acquired from image data (vector data such as feature amount) and the like are included.
- the shooting result at the time of manufacturing the unit 1 may be referred to as a "registered shooting result”
- the shooting result of the unit 1 acquired from the user terminal 70 may be referred to as a "user shooting result”.
- one of the shooting results of the unit 1 at the time of manufacture and the shooting result of the unit 1 acquired from the user terminal 70 is called a “first shooting result”
- the other shooting result is called a "second shooting result”.
- the unit manufacturing device 10 is a device for manufacturing the unit 1 by winding a long object 3 around a drum 5.
- the unit manufacturing apparatus 10 has a supply source (not shown) for supplying the long object 3 to the drum 5, and a winding device 12 for winding the long object 3 around the drum 5.
- the supply source (not shown) is, for example, a long product manufacturing apparatus for manufacturing a long product 3.
- the winding device 12 is, for example, a motor that rotates the drum 5.
- the unit manufacturing device 10 of the present embodiment has a registration data creating device 14.
- the registration data creating device 14 continuously photographs the unit 1 while the long object 3 is wound around the drum 5 at the time of manufacturing the unit 1, and captures the winding amount of the long object 3 and the photographing result at the time of photographing. It is a device that creates the associated data (registered data). The amount of winding of a long object wound around the drum at the time of shooting the shooting result is associated with the shooting result of the registered data.
- Registration data will be created when the unit 1 is manufactured (S101: see FIG. 3).
- the registration data creating device 14 includes a length measuring device 16, a photographing device 17, and a control device 15.
- the length measuring device 16 is a device that measures the length of the long object 3 wound around the drum 5.
- the length measuring device 16 measures the length (winding amount) of the long object 3 wound around the drum 5 by, for example, measuring the amount (delivery amount) of the long object 3 being sent out to the drum 5.
- the length measuring device 16 may measure the winding amount by another method.
- the length measuring device 16 may be configured by a rotary encoder that measures the rotation amount of the drum 5, and may measure the winding amount based on the rotation amount of the drum 5.
- the length measuring device 16 outputs the measurement result (information about the winding amount) to the control device 15.
- the photographing device 17 is a device that photographs the unit 1 while the long object 3 is wound around the drum 5.
- the photographing device 17 is composed of, for example, a camera such as a digital still camera for photographing a still image or a digital video camera for photographing a moving image.
- the photographing device 17 may be composed of one camera or a plurality of cameras. When the photographing device 17 has a plurality of cameras, it is preferable that the plurality of cameras are arranged along the outer circumference of the drum 5 (the outer circumference of the cable wound around the drum 5). Further, the photographing device 17 may include a light emitting device such as a strobe device. The photographing device 17 outputs image data to the control device 15 as a photographing result.
- the shooting device 17 When shooting a still image, the shooting device 17 continuously shoots while the long object 3 is wound around the drum 5, and outputs image data of a large number of continuous still images to the control device 15. .. Further, when shooting a moving image, the shooting device 17 acquires a plurality of still images (frames) by shooting the moving image while winding the long object 3 around the drum 5, and the shooting device 17 obtains a plurality of still images (frames). The image data of the moving image including the frame) is output to the control device 15. When the photographing device 17 shoots a moving image, the long object 3 may be continuously photographed from the beginning to the end of winding, or may be intermittently photographed.
- the control device 15 is a control unit (controller) that controls the registration data creation device 14.
- the control device 15 is composed of, for example, a personal computer.
- the control device 15 may control the unit manufacturing device 10 (for example, a winding device).
- the control device 15 acquires a measurement result (information on the length of the long object 3 wound around the drum 5) from the length measuring device 16. Further, the control device 15 acquires image data as a shooting result from the shooting device 17.
- the control device 15 creates registration data in which the winding amount of the long object 3 at the time of shooting and the shooting result are associated with each other based on the measurement result of the length measuring device 16 and the shooting result of the shooting device 17. ..
- the control device 15 creates registration data in which the winding amount of the long object 3 at the time of shooting and the image data (shooting result) of the still image are associated with each other.
- the shooting result included in the registered data is not limited to the image data of the still image.
- the control device 15 by providing the control device 15 with a part of the functions of the management device 20 (the function of the image processing unit 32) described later, the feature amount information (described later) acquired from the image data is used as the shooting result, and is long at the time of shooting.
- Registration data may be created in which the winding amount of the object 3 and the feature amount information are associated with each other.
- FIG. 4A is an explanatory diagram of an example of registered data.
- the registered data 41 in the figure is data in which the winding amount of the long object 3 at the time of shooting and the image data which is the shooting result are associated with each other.
- the registered data 41 is associated with one image data (for example, jpg data) for every 10 m of winding amount.
- the control device 15 detects that the length measuring device 16 has sent the long object 3 to the drum 5 by 10 m, the control device 15 causes the photographing device 17 to photograph one still image, thereby performing such registration data. Can be created. It is desirable that the registration data 41 is also given a unit ID for identifying the unit 1.
- FIG. 4B is an explanatory diagram of another example of the registered data.
- this registration data 41 three image data are associated with each winding amount.
- a plurality of image data associated with the winding amount may be used.
- a plurality of cameras are arranged along the outer circumference of the drum 5, and each time the control device 15 detects that the length measuring device 16 has sent a long object 3 to the drum 5 by 10 m, a plurality of photographing devices 17 are arranged.
- Such registration data 41 can be created by taking pictures one by one with a single camera.
- the control device 15 divides the length measuring device 16 into a plurality of times while the drum 5 makes one rotation each time it detects that the long object 3 has been sent out to the drum 5 by 10 m.
- Such registration data can be created by causing the camera to take a picture (by making the camera take a picture every time the drum 5 rotates 120 degrees). Thereby, for a certain winding amount, an image of the entire circumference (or a wide range) of the long object 3 wound around the drum 5 can be registered.
- FIG. 5 is an explanatory diagram of an example of unit basic data.
- the unit basic data is data in which the unit ID is associated with the information at the time of manufacturing the unit 1 (unit basic information).
- the unit basic information includes, for example, a drum ID for identifying the type of the drum 5, an ID for identifying the type of the long object 3 (cable ID in this case), and a length wound around the unit 1. Information such as the total length of the scale 3 and the date of manufacture of the unit 1 is included. However, the manufacturing information associated with the unit ID is not limited to these.
- the registration data creation device 14 of the unit manufacturing device 10 transmits the created registration data 41 (and unit basic data) to the management device 20 (S002: see FIG. 3). As a result, the registration data 41 is registered in the management device 20 (the pattern of the unit 1 at the time of manufacture is registered). Every time the unit manufacturing apparatus 10 manufactures the unit 1, the registration data creating apparatus 14 creates the registration data 41 corresponding to the unit 1 and transmits the registration data 41 to the management apparatus 20.
- the management device 20 is a device that manages the unit 1 (see FIG. 2). In the present embodiment, the management device 20 manages the remaining amount of the long object 3 of the unit 1.
- the management device 20 is composed of a computer such as a personal computer or a server.
- FIG. 6 is an explanatory diagram showing the hardware configuration of the management device 20.
- the management device 20 has an arithmetic processing unit, a storage device, and a communication device. Each element in the figure is connected via a bus (not shown).
- the arithmetic processing unit is a device that controls the management device 20.
- the arithmetic processing unit is composed of, for example, a CPU, a GPU, an AI chip, or the like.
- the storage device is composed of, for example, a main storage device such as RAM and an auxiliary storage device such as a hard disk drive or SSD.
- the storage device includes a non-transitory storage medium (non-transitory storage medium) for recording a program for causing the management device 20 to execute various processes described later.
- the communication device is a device for connecting to the communication network 90, and is composed of, for example, a communication module or the like.
- the management device 20 may include a display device (for example, a display) and an input device (for example, a keyboard, a mouse, etc.).
- the management device 20 may be composed of one computer or a plurality of computers. When the management device 20 is configured by a plurality of computers, a plurality of functions (for example, image processing and collation processing) described later may be realized by dividing them into different computers for each function, or the same function may be realized by a plurality of computers. It may be distributed by a computer.
- FIG. 7 is a block diagram showing the functions of the management device 20.
- the control unit 30 performs various processes to be performed by the management device 20.
- the control unit 30 is realized by the arithmetic processing unit executing a control program stored in the storage device to perform various controls.
- the control unit 30 includes a data acquisition unit 31, an image processing unit 32, a collation data generation unit 33, a collation processing unit 34, and a management processing unit 35.
- the management device 20 has an image processing unit 32, a collation data generation unit 33, and the like. It doesn't have to be. Each function of the control unit 30 will be described later.
- the data storage unit 40 is a storage unit for storing predetermined data.
- the data storage unit 40 is mainly realized by a part of the storage area of the storage device.
- the data storage unit 40 has the collation data 42 and the management data 44.
- the registration data 41 and the collation data 42 store data in a device different from the management device 20. It may be stored in the department.
- Various data stored in the data storage unit 40 will be described later.
- the communication unit 50 communicates data.
- the communication unit 50 is realized by controlling the communication device (see FIG. 6) by the arithmetic processing unit.
- the communication unit 50 includes a reception unit 50A and a transmission unit 50B.
- the receiving unit 50A receives data from, for example, the unit manufacturing device 10 (registered data creating device 14), the user terminal 70, or the like.
- the transmission unit 50B transmits data to, for example, a user terminal 70 or the like.
- the management device 20 receives the registration data 41 from the unit manufacturing device 10 (registration data creation device 14) (S201: see FIG. 3). As a result, the management device 20 includes data including the winding amount of the long object 3 and the photographing result corresponding to the winding amount when the unit 1 is continuously photographed while the long object 3 is wound around the drum 5. To get multiple.
- the data acquisition unit 31 of the management device 20 stores the received registration data in the data storage unit 40.
- the data acquisition unit 31 also stores the unit basic data (see FIG. 5) received from the unit manufacturing apparatus 10 in the data storage unit 40.
- the collation data generation unit 33 of the management device 20 generates collation data 42 based on the registration data 41 (S202: see FIG. 3).
- the image processing unit 32 of the management device 20 performs image processing on the image data of the registration data 41, and then the collation data generation unit 33 generates the collation data 42.
- the collation data 42 is data for performing a collation process (described later: S206) for collating the shooting result at the time of unit manufacturing with the shooting result of the user, and is sometimes called a collation database or a collation model.
- the collation data 42 is data in which the winding amount of the long object 3 when the unit 1 is continuously photographed while the long object 3 is wound around the drum 5 at the time of manufacturing the unit 1 and the photographing result are associated with each other. Is.
- the collation data is data in which the shooting result of the unit 1 is input and the winding amount of the long object 3 is output.
- the image processing unit 32 performs image processing on the image data.
- the image processing unit 32 has a preprocessing unit 32A and a feature amount extraction unit 32B, and the feature amount extraction processing is performed after preprocessing the image data.
- the pre-processing unit 32A performs pre-processing on the image data.
- the pre-processing performed by the pre-processing unit 32A on the image data includes, for example, distortion correction processing, area extraction processing, coordinate conversion processing, combination processing, edge extraction processing, and the like.
- the preprocessing unit 32A performs, for example, a process (distortion correction process) for correcting the distortion of the image indicated by the image data.
- a process disortion correction process
- the preprocessing unit 32A may apply a lens correction filter to the image data, or may perform a projection conversion processing on the image data.
- the preprocessing unit 32A performs a process (area extraction process) of extracting an area of the image of the unit 1 from the image indicated by the image data, for example.
- a process area extraction process
- the preprocessing unit 32A performs a process (area extraction process) of extracting an area of the image of the unit 1 from the image indicated by the image data, for example.
- FIG. 8 is an explanatory diagram of the coordinate conversion process of the present embodiment.
- the image before the coordinate conversion process is shown on the left side of the figure.
- the long object 3 is photographed in a state of being wound in a cylindrical shape, the long object 3 is photographed at an angle in the upper and lower edge regions in the dotted line frame in the figure as compared with the central region. Has been done.
- On the right side of the figure an image obtained by performing coordinate conversion processing on the image in the dotted line frame is shown.
- the long object 3 wound in a cylindrical shape is converted into an image taken along the circumferential direction in a pseudo manner. can.
- the arrangement of feature points (described later) can be corrected, and highly accurate collation can be performed.
- the preprocessing unit 32A performs, for example, a process (combination process) of combining images of a plurality of image data.
- a process for example, a process (combination process) of combining images of a plurality of image data.
- FIG. 4B when a plurality of image data are associated with each winding amount, a combination process (mozai kinging) in which a plurality of images are combined into one image by using the overlapping portion of each image is used. ) Is possible. This makes it possible to create image data showing an image of the entire circumference (or a wide range) of the long object 3 wound around the drum 5.
- the preprocessing unit 32A performs a process (edge extraction process) for extracting an edge (contour) of an image of image data, for example.
- edge extraction process for extracting an edge (contour) of an image of image data.
- the pretreatment performed by the pretreatment unit 32A is not limited to the above.
- other processing such as color correction processing and luminance correction processing may be performed.
- the feature amount extraction unit 32B performs a process of extracting a feature amount from image data (feature amount extraction process).
- the feature amount extraction unit 32B extracts the feature amount by using, for example, SIFT (Scale-Invariance Feature Transform).
- SIFT Scale-Invariance Feature Transform
- a plurality of points such as the intersection of the contour lines of the long object 3 shown in the image data and the bending point of the contour line of the long object 3 are extracted as feature points, and 128 at each feature point.
- Dimensional features (vectors) are extracted.
- the feature amount is not limited to the SIFT feature amount.
- FIG. 9 is an explanatory diagram of an example of collation data 42.
- the collation data 42 in the figure is data in which the winding amount and the feature amount information are associated with each other.
- the feature amount vi for a certain winding amount is acquired by the image processing unit 32 (feature amount extraction unit 32B) based on the image data (shooting result) corresponding to the winding amount of the registered data 41. It was done.
- the winding amount and the feature amount information are associated with each unit (for each unit ID).
- the feature amount information is not limited to this, and may not include, for example, arrangement information.
- the unit 1 is shipped from the unit manufacturing factory (S103) and is delivered to the user (S701).
- the control device 15 of the unit manufacturing apparatus 10 causes the management device 20 to receive shipping data (purchase data) in which the ID (customer ID) of the purchased user and the unit ID of the shipped unit 1 are associated with each other at the time of shipment of the unit 1. Transmit (S104).
- FIG. 10 is an explanatory diagram of an example of management data 44.
- the management data 44 is data in which the management device 20 (specifically, the management processing unit 35) manages the information of the customer and the unit 1.
- the management data 44 has, for example, customer data, purchase data, unit basic data, and the like.
- Customer data is data that manages customer information.
- the customer data is data in which the customer ID and the customer information (for example, a company name or an address) are associated with each other.
- Purchase data is data that manages the unit 1 purchased by the customer.
- the purchase data is data in which the customer ID is associated with the unit ID of the unit 1 purchased by the customer.
- the management processing unit 35 of the management device 20 receives the shipping data (S203)
- the management processing unit 35 updates the purchase data based on the shipping data (data in which the customer ID and the unit ID are associated with each other) (S204).
- the customer ID of the purchase data is associated with the customer ID of the customer data.
- the unit ID of the purchase data is associated with the unit ID of the unit basic data (and the remaining amount data).
- the unit basic data is the data that manages the information at the time of manufacturing the unit 1 (unit basic information).
- the unit basic data is data in which the unit ID and the unit basic information are associated with each other (see FIG. 5).
- the unit manufacturing apparatus 10 transmits the unit basic data (see FIG. 5) created at the time of manufacturing the unit 1 to the management apparatus 20, and the management apparatus 20 (management processing unit 35) is based on the received data.
- the drum ID and cable ID included in the unit basic information are linked to the drum ID of the drum data that manages the information of the drum 5 and the cable ID of the cable data that manages the information of the cable (an example of the long object 3). It is attached.
- the management data 44 has the remaining amount data.
- the remaining amount data is data for managing the remaining amount of the long object 3 (cable in this case) wound around the unit 1.
- the remaining amount data is data in which the unit ID and the remaining amount information are associated with each other.
- the unit ID of the remaining amount data is associated with the unit ID of the purchase data, the unit ID of the unit basic data, and the like.
- the remaining amount data will be managed by the management device 20 by the processing (described later) of S205 to S208 of FIG.
- the user who purchased the unit 1 pulls out the long object 3 from the drum 5 and consumes the long object 3 (S702: see FIG. 3).
- the user photographs the long object 3 wound around the unit 1 using the user terminal 70 (S703) and manages the photographing result. It is transmitted to the device 20 (S704).
- the image data of the still image is transmitted from the user terminal 70 to the management device 20 as a shooting result.
- the shooting result transmitted from the user terminal 70 is not limited to the image data of the still image.
- the user terminal 70 may transmit image data of a moving image as a shooting result, or may transmit feature amount information acquired from the image data by performing the above-mentioned image processing.
- the management device 20 receives a shooting result (here, still image image data) from the user terminal 70 (S205: see FIG. 3).
- the management device 20 (data acquisition unit 31) stores the shooting result received from the user terminal 70 via the reception unit 50A in the data storage unit 40.
- the management device 20 performs a collation process based on the shooting result received from the user terminal 70 (S206).
- the image processing unit 32 of the management device 20 performs image processing on the image data, and then the collation unit of the management device 20 performs the collation processing.
- the image processing unit 32 performs image processing (pre-processing, feature amount extraction processing) on the image data received from the user terminal 70. Since the image processing performed on the image data received from the user terminal 70 is the same as the image processing on the image data included in the registration data 41, the description thereof is omitted here.
- image processing the feature amount vi'(vi'is a 128-dimensional vector) of a plurality of feature points and the arrangement information of the feature points are obtained.
- the collation processing unit 34 collates the feature amount information which is the shooting result of the user terminal 70 with the feature amount information stored in the collation data 42 (S206).
- the management device 20 (collation processing unit 34) has an access unit 34A for accessing the collation data 42 (see FIG. 7).
- the access unit 34A is realized by an input / output device that inputs / outputs data.
- the input / output device constituting the access unit 34A also includes a communication device (see FIG. 7).
- the collation processing unit 34 has the minimum difference between the feature amount vi'corresponding to each winding amount of the collation data 42 and the feature amount vi'of the shooting result of the user terminal 70 (two vectors).
- the collation processing unit 34 specifies a winding amount from the collation data 42 at which the collation score S becomes a high value, and outputs the winding amount as a collation result. Further, when the collation processing unit 34 outputs the winding amount as the collation result, the unit ID corresponding to the winding amount is also output as the collation result.
- the collation processing unit 34 limits the collation target to the unit ID corresponding to the customer ID based on the purchase data (see FIG. 10).
- the collation process may be performed. For example, when the collation processing unit 34 adds the information "customer ID: No. A" to the shooting result received from the user terminal 70, the collation processing unit 34 has "customer ID: customer ID” based on the purchase data (see FIG. 10). : No. A ”, the collation target is limited to the unit IDs (here, No. 001, No. 002), and the collation process is performed based on the collation data 42. As a result, the time required for the collation process can be shortened.
- the collation processing unit 34 may perform the collation process after limiting the collation target to the specified unit ID. For example, when the information of "unit ID: No. 001" is added to the shooting result received from the user terminal 70, the collation processing unit 34 limits the collation target to the unit ID and collates data. The collation process is performed based on 42. As a result, the time required for the collation process can be shortened. In this case, the collation processing unit 34 does not have to output the unit ID as the collation result.
- FIG. 11A is an explanatory diagram of image data used for acquiring feature quantity information.
- the left side of the figure shows the image data taken at the time of manufacturing the unit 1, and the right side shows the image data taken by the user terminal 70.
- the winding amount of the long object 3 is assumed to be the same.
- the image of the unit 1 taken by the user terminal 70 is different from the image of the unit 1 taken at the time of manufacture.
- the unit 1 may be photographed obliquely by the user terminal 70.
- the end portion (hatched portion) of the long object 3 cut by the user hangs down, and the unit 1 is photographed in a state different from that at the time of manufacture. There is.
- the position of the end portion of the long object 3 wound around the drum 5 may be different from the position at the time of manufacture.
- FIG. 11B is a conceptual explanatory diagram of the collation process. Also in FIG. 11B, the image data taken at the time of manufacturing the unit 1 is shown on the left side of the figure, and the image data taken by the user terminal 70 is shown on the right side, and the arrangement is consistent. The feature points of the pair are connected by a line.
- the collation process using the feature amount has a feature (robust) that it is not easily affected by the rotation of the image and the change of the scale. Therefore, as shown on the right side of FIG. 11A, even when the unit 1 is photographed obliquely by the user terminal 70, the collation process can be stably performed in the present embodiment.
- the portion other than the end portion (the portion other than the hatching in FIG. 11A) is at the time of manufacture.
- the position of the long object 3 is maintained. That is, even if the position of the end portion of the long object 3 wound around the drum 5 is different from the position at the time of manufacture, the other portion (the portion other than the hatching in FIG. 11A) depends on the winding amount.
- the pattern of the unit 1 is retained. Therefore, as shown in FIG. 11B, in the portion where the pattern is retained, a pair having a matching arrangement is formed, and the collation process can be performed.
- the collation processing unit 34 determines the remaining amount of the long object 3 based on the collation result (S207).
- the management device 20 (collation processing unit 34) has a determination unit 34B that determines the remaining amount of the long object 3 based on the collation result (see FIG. 7).
- the determination unit 34B is realized, for example, by the arithmetic processing unit executing a program stored in the storage device (see FIG. 6).
- the collation processing unit 34 determines the winding amount at which the collation score S has the highest value as the remaining amount of the long object 3.
- the method for determining the remaining amount is not limited to this.
- the collation processing unit 34 specifies two winding amounts having a high collation score S, and performs weighting according to the collation score S to interpolate the value between the two winding amounts.
- the calculated value may be used as the remaining amount of the long object 3.
- the management processing unit 35 of the management device 20 After determining the remaining amount (S207), the management processing unit 35 of the management device 20 updates the remaining amount information corresponding to the predetermined unit ID of the management data 44 (see FIG. 10) (S208). For example, the management processing unit 35 stores "remaining amount: 510 m" in association with "unit ID: No. 001" in the remaining amount data of the management data 44 (see FIG. 10).
- the remaining amount of the long object 3 is determined based on the collation result of collating the collation data (see FIG. 9) associated with the above and the shooting result of the unit acquired from the user terminal 70. This simplifies the remaining amount management of the long object 3.
- the management device 20 of the first embodiment corresponds to the winding amount and the winding amount of the long object 3 when the unit 1 is continuously photographed while the long object 3 is wound around the drum 5.
- a plurality of data including the shooting result are acquired, and the plurality of data (registered data) are used to generate collation data in which the shooting result of the unit 1 is input and the winding amount of the long object 3 is output. .. This makes it possible to generate collation data that can easily manage the remaining amount of long objects.
- the collation processing unit 34 can specify the remaining amount of the unit ID to be collated, it is desirable to exclude the winding amount larger than the remaining amount from the collation target and perform the collation processing.
- the collation processing unit 34 has a unit ID of No. 1.
- the winding amount is larger than the remaining amount (here, 510 m) corresponding to the "unit ID: No. 001" stored in the remaining amount data. Exclude from the collation target and perform collation processing. As a result, the time required for the collation process can be shortened.
- the management processing unit 35 of the management device 20 may transmit the remaining amount information to the user terminal 70 that has transmitted the shooting result.
- the management device 20 (management processing unit 35) transmits the remaining amount information to the user terminal 70 via the transmission unit 50B (see FIG. 7).
- the user terminal 70 can grasp the remaining amount of the long object 3 only by transmitting the shooting result of the unit 1, so that the burden of management on the user side can be reduced.
- the management processing unit 35 when the management device 20 (detailedly, the management processing unit 35) outputs the winding amount and the unit ID corresponding to the winding amount as the collation result in the collation process (S206: see FIG. 3) described above, the unit ID is output.
- the unit ID and information associated with the unit ID may be transmitted to the user terminal 70.
- the management device 20 sends the user terminal 70 that has transmitted the shooting result to the unit basic cable (see FIGS. 5 and 10; for example, the cable ID and the date of manufacture) and cable information (such as the cable ID and the date of manufacture) associated with the unit ID. (See FIG. 10; for example, cable type) may be transmitted via the transmission unit 50B.
- the user terminal 70 can grasp the information of the unit 1 only by transmitting the shooting result of the unit 1, so that the burden of management on the user side can be reduced.
- FIG. 12 is an explanatory diagram of the management data 44 of the modified example.
- the management data 44 of the modified example has usage history data.
- the usage history data is data for managing the usage history of the unit 1.
- the usage history data is data in which the unit ID and the usage information of the unit 1 are associated with each other. By accumulating the usage information of the unit 1, it is possible to manage the usage history of the unit 1.
- the unit usage information includes the date and time of use, the amount of use, and the position of use.
- the management processing unit 35 additionally registers the unit usage information in the usage history data after the collation processing (S206) and the remaining amount determination processing (S207) described above. For example, the management processing unit 35 registers the date and time when the shooting result is received from the user terminal 70 as the usage date and time of the unit 1. Further, the management processing unit 35 registers the difference in the remaining amount information before and after updating in S208 as the usage amount of the unit 1. Further, if the position information based on GPS is transmitted when the user terminal 70 transmits the shooting result, the management processing unit 35 can register the position information received from the user terminal 70 as the used position of the unit 1. It is possible.
- FIG. 13A is an explanatory diagram of the unit manufacturing apparatus 10 of the modified example.
- FIG. 13B is an explanatory diagram of the unit 1 of the modified example.
- the unit manufacturing device 10 of the modified example has a mark forming device 18.
- the mark forming device 18 is a device for forming a mark 4 on a long object 3.
- the mark forming apparatus 18 is composed of a printing apparatus.
- the mark forming apparatus 18 is not limited to the printing apparatus.
- the mark 4 is a mark or pattern formed on the outer circumference of the long object 3.
- the mark 4 may be formed flatly on the surface of the long object 3 or may be formed three-dimensionally by unevenness or the like.
- the winding amount (remaining amount) and the unit ID are specified not only by the uneven pattern formed by the surface of the long object but also by the pattern appearing on the surface of the unit including the mark 4.
- the mark 4 is a ring mark printed on the entire circumference of the long object 3. Further, the mark 4 is not limited to what is printed, and may be, for example, an engraved pattern or an uneven pattern.
- the mark 4 may be composed of a pattern, a symbol, a character, a sign, a logo, or the like, or may be a combination thereof (for example, a combination of a character indicating a unit ID and a scale symbol indicating a predetermined length).
- the marks 4 are formed at predetermined intervals along the longitudinal direction of the long object 3.
- the interval between the marks 4 does not have to be constant, and may be a random interval. It suffices if the mark 4 is formed on the long object 3 so that the longitudinal direction of the long object 3 does not become uniform.
- the unit manufacturing apparatus 10 of the modified example manufactures the unit 1 by winding the long object 3 on which the mark 4 is formed around the drum 5.
- the registration data creation device 14 of the modified example continuously photographs the long object 3 (the long object with a mark 3) wound around the drum 5 at the time of manufacturing the unit 1, and winds the long object 3 at the time of photographing. Data (registered data) that associates the amount with the shooting result will be created.
- the long object 3 wound around the drum 5 forms a pattern on the surface of the unit 1.
- the pattern of the unit 1 becomes complicated.
- the pattern of the unit 1 has a large individual difference depending on the winding amount, and can be easily distinguished from other patterns.
- the pattern of the unit 1 becomes complicated due to the formation of the mark 4 on the long object 3, the number of feature points can be increased, and the accuracy of the collation process (S206: see FIG. 3) is improved. do.
- the mark 4 is composed of a ring mark and is formed on the entire circumference of the long object 3, but the mark 4 may be formed on a part of the circumferential direction of the long object 3. ..
- the mark 4 is formed in a part of the circumferential direction of the long object 3, when the long object 3 is wound around the drum 5 while randomly rotating (randomly twisting) in the circumferential direction, the pattern of the unit 1 is formed. Since it becomes more complicated and it becomes more advantageous to distinguish it from other patterns, the accuracy of the collation process (S206: see FIG. 3) is further improved.
- the feature amount information stored in the collation data 42 (an example of the collation data 42) shown in FIG. 9 is collated with the feature amount information which is the shooting result of the user terminal 70.
- the collation process was being performed.
- the collation process is not limited to this.
- the collation process may be performed based on the collation model (another example of the collation data 42) generated by machine learning.
- FIG. 14A and 14B are explanatory views of the second embodiment.
- FIG. 14A is a conceptual explanatory diagram for generating a matching model.
- FIG. 14B is a conceptual explanatory diagram of the collation process using the collation model.
- the process shown in FIG. 14A corresponds to the so-called learning phase of machine learning.
- the process shown in FIG. 14B corresponds to the prediction phase based on the trained model.
- the management device 20 receives the registration data from the unit manufacturing device 10 (S201: see FIG. 3).
- the registered data includes a plurality of data in which the winding amount of the long object 3 at the time of shooting and the shooting result corresponding to the winding amount are associated with each other, and this registered data is used as learning data (teacher data).
- the photographing result included in the registered data may be image data as shown in FIGS. 4A and 4B, or may be feature quantity information as shown in FIG.
- the collation data generation unit 33 of the second embodiment uses the registered data as teacher data and the shooting result included in the registered data (teacher data) as input data, and is associated with the shooting result.
- a learning model with the winding amount as output data is generated by machine learning.
- a collation model is generated as a trained model (S202: see FIG. 3).
- S202 see FIG. 3
- this collation model the winding amount of the long object 3 when the unit 1 is continuously photographed while the long object 3 is wound around the drum 5 at the time of manufacturing the unit 1 and the imaging result are associated with each other. It becomes the data for.
- this collation model is collation data in which the shooting result of the unit 1 is input and the winding amount of the long object 3 is output.
- the collation processing unit 34 inputs the shooting result (image data or feature amount information) acquired from the user terminal 70 into the collation model and collates.
- the predicted value of the take-up amount is output from the model as a collation result.
- the predicted value of the winding amount output from the collation model is determined as the remaining amount of the unit 1 (S207).
- the management device 20 also captures the winding amount of the long object 3 when the unit 1 is continuously photographed while the long object 3 is wound around the drum 5 at the time of manufacturing the unit 1.
- the remaining amount of the long object 3 is determined based on the collation result of collating the collation data (collation model of FIG. 14A) associated with the result and the shooting result of the unit acquired from the user terminal 70 (FIG. See 14B). This simplifies the remaining amount management of the long object 3 also in the second embodiment.
- the management device 20 determines the winding amount and winding amount of the long object 3 when the unit 1 is continuously photographed while the long object 3 is wound around the drum 5.
- a collation model that acquires a plurality of data including the corresponding shooting results, uses the plurality of data (registered data), inputs the shooting results of the unit 1, and outputs the winding amount of the long object 3. Data) is generated. This makes it possible to generate collation data that can easily manage the remaining amount of long objects.
- the collation process is not limited to the first embodiment and the second embodiment. If the shooting results taken continuously during the manufacturing of the unit 1 and the shooting results acquired from the user terminal 70 can be collated, and the shooting results close to the shooting results of the user terminal 70 can be specified from the shooting results at the time of manufacturing. , Other collation processing may be performed.
- the management device 20 creates collation data (S202; see FIG. 3), receives shooting data (S205), and performs collation processing (S206).
- a device different from the device 20 may create collation data (S202), and the management device 20 may perform shooting data reception (S205) and collation processing (S206).
- the management device 20 includes a data storage unit that stores collation data (see FIG. 7), but the collation data is different from the management device 20. It may be stored in the data storage unit of another device.
- the registration data creation device 14 of the unit manufacturing device 10 Sends the registration data 41 to the collation data creation device.
- the collation data creation device receives the registration data 41 from the unit manufacturing device 10 and stores the registration data 41 in the data storage unit of its own device (a device different from the management device 20 is the above-mentioned S201. Will be processed). Further, the collation data creation device generates collation data 42 based on the registration data 41 (a device other than the management device 20 will perform the processing of S202).
- the generated collation data 42 may be stored in the data storage unit 40 of the management device 20, may be stored in the data storage unit of the collation data creation device, or may be stored in the data storage unit of the management device or the collation data. It may be stored in a device different from the creating device. In the following description, the device that stores the collation data 42 may be referred to as a “collation data management device”.
- the management device 20 stores the collation data (of the collation data) in the process of S206 described above. By accessing the management device), collation processing is performed based on the shooting result received from the user terminal 70. Then, after the collation process of S206, the management device 20 determines the remaining amount of the long object 3 based on the collation result, as in the first embodiment and the second embodiment described above.
- the management device receives the photographing result of photographing the unit from the user terminal (S205), and the photographing acquired from the user terminal.
- Data for collation with the result data that associates the shooting result when the unit is continuously shot while the long object is wound around the drum and the winding amount of the long object wound around the drum at the time of shooting. ;
- the remaining amount of the long object is determined based on the collation result collated with the collation data 42) in FIG. 9 (S206, S207).
- the management device collates with the receiving unit 50A (see FIG.
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
- Length Measuring Devices By Optical Means (AREA)
- General Factory Administration (AREA)
- Controlling Rewinding, Feeding, Winding, Or Abnormalities Of Webs (AREA)
- Communication Control (AREA)
Abstract
Description
以下の説明において、「長尺物」とは、長尺な部材を意味する。長尺物には、例えば、ケーブル(電線ケーブルや光ケーブルなど)、糸、ワイヤのような線状の部材や、テープやフィルムのような帯状の部材が含まれる。
図2は、本実施形態の管理システム100の一例の説明図である。図3は、本実施形態の処理フローの一例の説明図である。
図5は、ユニット基本データの一例の説明図である。ユニット基本データは、ユニットIDに対して、ユニット1の製造時の情報(ユニット基本情報)を対応付けたデータである。ユニット基本情報には、例えば、ドラム5の種類を識別するためのドラムIDや、長尺物3の種類を識別するためのID(ここではケーブルID)や、そのユニット1に巻き付けられている長尺物3の全長や、ユニット1の製造年月日などの情報が含まれる。但し、ユニットIDに対応付けられる製造時の情報は、これらに限られるものではない。
図12は、変形例の管理用データ44の説明図である。
図13Aは、変形例のユニット製造装置10の説明図である。図13Bは、変形例のユニット1の説明図である。
前述の実施形態では、図9に示す照合用データ42(照合用データ42の一例)に記憶されている特徴量情報と、ユーザー端末70の撮影結果である特徴量情報とを照合することによって、照合処理が行われていた。但し、照合処理は、これに限られるものではない。例えば、次に説明するように、機械学習によって生成した照合モデル(照合用データ42の他の一例)に基づいて、照合処理を行っても良い。
前述の第1実施形態及び第2実施形態では、管理装置20が照合用データの作成(S202;図3参照)、撮影データの受信(S205)及び照合処理(S206)を行っているが、管理装置20とは別の装置(照合用データの作成装置)が照合用データの作成(S202)を行い、管理装置20が撮影データの受信(S205)及び照合処理(S206)を行っても良い。また、前述の第1実施形態及び第2実施形態では、管理装置20は、照合用データを記憶したデータ記憶部を備えているが(図7参照)、照合用データは、管理装置20とは別の装置のデータ記憶部に記憶されても良い。
上述の実施形態は、本発明の理解を容易にするためのものであり、本発明を限定して解釈するためのものではない。本発明は、その趣旨を逸脱することなく、変更・改良され得ると共に、本発明には、その等価物が含まれることは言うまでもない。
4 マーク、5 ドラム、
10 ユニット製造装置、12 巻付装置、
14 登録データ作成装置、15 制御装置、16 測長装置、
17 撮影装置、18 マーク形成装置、
20 管理装置、30 制御部、
31 データ取得部、32 画像処理部、
32A 前処理部、32B 特徴量抽出部、
33 照合用データ生成部、34 照合処理部、
34A アクセス部、34B 決定部、35 管理処理部、
40 データ記憶部、41 登録データ、
42 照合用データ、44 管理用データ、
50 通信部、50A 受信部、50B 送信部、
70 ユーザー端末、90 通信ネットワーク、
100 管理システム
Claims (10)
- 長尺物をドラムに巻き付けたユニットを管理する管理装置であって、
前記長尺物を前記ドラムに巻き付けている間に前記ユニットを連続撮影したときの撮影結果と、撮影時の前記ドラムに巻き付けられている前記長尺物の巻付量とを対応付けた照合用データと、ユーザー端末から取得した前記ユニットの撮影結果とを照合した照合結果に基づいて、前記長尺物の残量を決定することを特徴とする管理装置。 - 請求項1に記載の管理装置であって、
前記照合用データには、ユニットを識別するユニットIDと、前記長尺物の巻付量と、撮影結果と、が対応付けられており、
前記照合用データと、前記ユーザー端末から取得した前記撮影結果とを照合した照合結果に基づいて、前記ユニットIDを決定することを特徴とする管理装置。 - 請求項2に記載の管理装置であって、
前記ユニットIDには、前記ユニットに関する情報が対応付けられており、
前記照合用データと、前記ユーザー端末から取得した前記撮影結果とを照合することによって前記ユニットIDを決定した後、前記ユニットIDに対応付けられた前記ユニットに関する情報を前記ユーザー端末に送信することを特徴とする管理装置。 - 請求項1~3のいずれかに記載の管理装置であって、
前記長尺物には、マークが形成されていることを特徴とする管理装置。 - 請求項1~4のいずれかに記載の管理装置であって、
前記照合用データには、前記長尺物の巻付量と、前記ユニットを撮影した画像データから抽出した特徴量とが対応付けられていることを特徴とする管理装置。 - 請求項5に記載の管理装置であって、
前記照合結果に基づいて決定した前記長尺物の前記残量を記憶することを特徴とする管理装置。 - 請求項6に記載の管理装置であって、
前記ユーザー端末から再び前記ユニットの撮影結果を取得したとき、前記残量よりも多い前記巻付量を照合対象から除外して、前記ユーザー端末から取得した前記撮影結果と前記照合用データとを照合することを特徴とする管理装置。 - 請求項1~4のいずれかに記載の管理装置であって、
前記照合用データは、前記撮影結果を入力データとし、前記巻付量を出力データとする機械学習により生成された学習済みモデルであることを特徴とする管理装置。 - 長尺物をドラムに巻き付けたユニットを管理する管理方法であって、
ユーザー端末から前記ユニットの撮影結果を取得すること、及び、
前記長尺物を前記ドラムに巻き付けている間に前記ユニットを連続撮影したときの撮影結果と、撮影時の前記ドラムに巻き付けられている前記長尺物の巻付量とを対応付けた照合用データと、前記ユーザー端末から取得した前記撮影結果とを照合した照合結果に基づいて、前記長尺物の残量を決定すること
を行う管理方法。 - 長尺物をドラムに巻き付けている間にユニットを連続撮影することによって、撮影結果と、撮影時に前記ドラムに巻き付けられている前記長尺物の巻付量とを含む登録データを複数取得すること、及び
複数の前記登録データを用いて、前記ユニットの撮影結果を入力とし、前記巻付量を出力とする照合用データを生成すること
を行う照合用データ生成方法。
Priority Applications (7)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
AU2021340327A AU2021340327A1 (en) | 2020-09-08 | 2021-07-07 | Management device, management method, and method for generating data for collation |
CN202180057639.1A CN116133970A (zh) | 2020-09-08 | 2021-07-07 | 管理装置、管理方法以及比对用数据生成方法 |
CA3190076A CA3190076A1 (en) | 2020-09-08 | 2021-07-07 | Management device, management method, and matching data generating method |
US18/020,355 US20230289946A1 (en) | 2020-09-08 | 2021-07-07 | Management device, management method, and correspondence data generating method |
JP2022547413A JP7329697B2 (ja) | 2020-09-08 | 2021-07-07 | 管理装置、管理方法及び照合用データ生成方法 |
EP21866345.8A EP4212469A1 (en) | 2020-09-08 | 2021-07-07 | Management device, management method, and method for generating data for collation |
KR1020227035502A KR20220154747A (ko) | 2020-09-08 | 2021-07-07 | 관리 장치, 관리 방법 및 대조용 데이터 생성 방법 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2020150260 | 2020-09-08 | ||
JP2020-150260 | 2020-09-08 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2022054385A1 true WO2022054385A1 (ja) | 2022-03-17 |
Family
ID=80632207
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2021/025676 WO2022054385A1 (ja) | 2020-09-08 | 2021-07-07 | 管理装置、管理方法及び照合用データ生成方法 |
Country Status (8)
Country | Link |
---|---|
US (1) | US20230289946A1 (ja) |
EP (1) | EP4212469A1 (ja) |
JP (1) | JP7329697B2 (ja) |
KR (1) | KR20220154747A (ja) |
CN (1) | CN116133970A (ja) |
AU (1) | AU2021340327A1 (ja) |
CA (1) | CA3190076A1 (ja) |
WO (1) | WO2022054385A1 (ja) |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH01318990A (ja) * | 1988-06-21 | 1989-12-25 | Toshiba Corp | トラッキングセンサ |
JPH02196913A (ja) * | 1989-01-26 | 1990-08-03 | Matsushita Electric Works Ltd | 巻き材料の巻き径測定装置 |
JPH0437167U (ja) * | 1990-07-26 | 1992-03-27 | ||
JP2000053326A (ja) * | 1998-08-10 | 2000-02-22 | W Schlafhorst Ag & Co | 紡績コップ巻管における残糸を検知する方法と装置 |
JP2003118939A (ja) * | 2001-10-16 | 2003-04-23 | Konica Corp | 画像記録媒体及び画像記録装置 |
JP2015024888A (ja) * | 2013-07-25 | 2015-02-05 | 株式会社ジェイテクト | フィラメントワインディング方法及びフィラメントワインディング装置 |
JP2017074975A (ja) * | 2015-10-15 | 2017-04-20 | 株式会社デュプロ | 包装装置 |
JP2017226485A (ja) * | 2016-06-20 | 2017-12-28 | 住友電工産業電線株式会社 | ボビン残量検出装置および方法 |
US20170369262A1 (en) * | 2015-02-25 | 2017-12-28 | Kimberly-Clark Worldwide, Inc. | Method and System for Determining Usage of a Rolled or Stacked Product |
JP2019218201A (ja) | 2018-06-22 | 2019-12-26 | 株式会社フジクラ | 長尺物用ドラム、管理用コンピューター、及び、長尺物管理システム |
-
2021
- 2021-07-07 WO PCT/JP2021/025676 patent/WO2022054385A1/ja unknown
- 2021-07-07 US US18/020,355 patent/US20230289946A1/en active Pending
- 2021-07-07 EP EP21866345.8A patent/EP4212469A1/en active Pending
- 2021-07-07 KR KR1020227035502A patent/KR20220154747A/ko not_active Application Discontinuation
- 2021-07-07 JP JP2022547413A patent/JP7329697B2/ja active Active
- 2021-07-07 CN CN202180057639.1A patent/CN116133970A/zh active Pending
- 2021-07-07 CA CA3190076A patent/CA3190076A1/en active Pending
- 2021-07-07 AU AU2021340327A patent/AU2021340327A1/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH01318990A (ja) * | 1988-06-21 | 1989-12-25 | Toshiba Corp | トラッキングセンサ |
JPH02196913A (ja) * | 1989-01-26 | 1990-08-03 | Matsushita Electric Works Ltd | 巻き材料の巻き径測定装置 |
JPH0437167U (ja) * | 1990-07-26 | 1992-03-27 | ||
JP2000053326A (ja) * | 1998-08-10 | 2000-02-22 | W Schlafhorst Ag & Co | 紡績コップ巻管における残糸を検知する方法と装置 |
JP2003118939A (ja) * | 2001-10-16 | 2003-04-23 | Konica Corp | 画像記録媒体及び画像記録装置 |
JP2015024888A (ja) * | 2013-07-25 | 2015-02-05 | 株式会社ジェイテクト | フィラメントワインディング方法及びフィラメントワインディング装置 |
US20170369262A1 (en) * | 2015-02-25 | 2017-12-28 | Kimberly-Clark Worldwide, Inc. | Method and System for Determining Usage of a Rolled or Stacked Product |
JP2017074975A (ja) * | 2015-10-15 | 2017-04-20 | 株式会社デュプロ | 包装装置 |
JP2017226485A (ja) * | 2016-06-20 | 2017-12-28 | 住友電工産業電線株式会社 | ボビン残量検出装置および方法 |
JP2019218201A (ja) | 2018-06-22 | 2019-12-26 | 株式会社フジクラ | 長尺物用ドラム、管理用コンピューター、及び、長尺物管理システム |
Also Published As
Publication number | Publication date |
---|---|
US20230289946A1 (en) | 2023-09-14 |
JPWO2022054385A1 (ja) | 2022-03-17 |
AU2021340327A1 (en) | 2023-03-09 |
CN116133970A (zh) | 2023-05-16 |
CA3190076A1 (en) | 2022-03-17 |
JP7329697B2 (ja) | 2023-08-18 |
EP4212469A1 (en) | 2023-07-19 |
KR20220154747A (ko) | 2022-11-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US10970821B2 (en) | Image blurring methods and apparatuses, storage media, and electronic devices | |
US10360313B2 (en) | Apparatus and method for generating 3D printing model using multiple textures | |
JP2020523703A (ja) | ダブル視野角画像較正および画像処理方法、装置、記憶媒体ならびに電子機器 | |
CN106559601B (zh) | 校准系统、校准方法以及图像形成装置 | |
US9734594B2 (en) | Producing three-dimensional representation based on images of an object | |
CN109945841B (zh) | 一种无编码点的工业摄影测量方法 | |
US10692262B2 (en) | Apparatus and method for processing information of multiple cameras | |
CN107871201B (zh) | 调整作业支援系统 | |
CN107705356A (zh) | 图像处理方法和装置 | |
JPWO2020263471A5 (ja) | ||
CN108665541A (zh) | 一种基于激光传感器的地图生成方法及装置和机器人 | |
JP2014127902A (ja) | 画像補正データ生成装置および画像補正データ生成プログラム | |
CN107506748A (zh) | 电子购物方法和装置 | |
WO2022054385A1 (ja) | 管理装置、管理方法及び照合用データ生成方法 | |
CN110264452A (zh) | 一种工件检测方法、装置、设备及存储介质 | |
CN111126493B (zh) | 深度学习模型的训练方法、装置、电子设备及存储介质 | |
CN107703792A (zh) | 智能家电的控制方法和装置 | |
WO2020039897A1 (ja) | 駅監視システム及び駅監視方法 | |
JP7321772B2 (ja) | 画像処理装置、画像処理方法、およびプログラム | |
CN107547798A (zh) | 拍摄对焦控制方法、装置和终端设备 | |
CN107609511A (zh) | 信息交互方法和装置 | |
CN114168695A (zh) | 目标位置确定方法、装置、终端以及存储介质 | |
CN112183563A (zh) | 一种图像识别模型的生成方法、存储介质及应用服务器 | |
CN109425309B (zh) | 图像处理装置、图像处理系统以及存储介质 | |
JP6939071B2 (ja) | 考査処理装置及び印画物作製システム |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 21866345 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2022547413 Country of ref document: JP Kind code of ref document: A |
|
ENP | Entry into the national phase |
Ref document number: 20227035502 Country of ref document: KR Kind code of ref document: A |
|
ENP | Entry into the national phase |
Ref document number: 3190076 Country of ref document: CA |
|
ENP | Entry into the national phase |
Ref document number: 2021340327 Country of ref document: AU Date of ref document: 20210707 Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2021866345 Country of ref document: EP Effective date: 20230411 |