Sewing system and sewing method

Abstract

A sewing system (100) includes: a plurality of imaging devices (37) that acquire an image of a sewing object (S); one or more sewing machines (1) that perform sewing on the basis of a recognition result obtained by the image recognition processing of the object (S) to be sewn; and a data processing unit (50) that acquires template data (70) of the sewing object (S) created on the basis of an image captured by a first imaging device (37) among the plurality of imaging devices (37), and transmits the template data (70) to another second imaging device (37). The sewing machine (1) has unique data (60B) including imaging conditions of the imaging device (37). A sewing machine (1) having a second imaging device (37) performs image recognition processing using template data (72) corrected on the basis of unique data (60B) of the second imaging device (37), or corrects a recognition result obtained using template data (70) on the basis of the unique data (60B) of the second imaging device (37).

Description

TECHNICAL FIELD

[0001] The present application relates to a sewing system and a sewing method. BACKGROUND

[0002] Sometimes, a stitch is formed in a sewing object in order to improve the design property of the sewing object. In Patent Literature 1, a technique of forming a stitch in a skin material used for a vehicle seat is disclosed.

[0003] Patent Literature 1: Japanese Patent Application Publication No. 2013-162957 SUMMARY

[0004] The skin material used for a vehicle seat has a thickness and has elasticity. If a stitch is formed in a sewing object having a thickness and having elasticity, it is possible that the sewing object shrinks and the surface of the sewing object is displaced. For example, in a case where a second stitch is formed after a first stitch is formed, it is preferable that the second stitch is formed in a target position of the sewing object in correspondence with the displacement of the surface of the sewing object due to the formation of the first stitch. As a countermeasure to form a stitch in a target position of a sewing object, it is proposed that the surface of the sewing object is imaged before a sewing process, and the displacement of the surface of the sewing object is detected. In the displacement detection, an image recognition process such as template matching is used.

[0005] In a case where a plurality of sewing machines are used to manufacture the same product in a sewing factory or the like, the plurality of sewing machines form the same shape of a stitch in the same shape of a sewing object, and therefore template data used in the image recognition process is also common. However, in practice, the imaging conditions of an imaging device provided in each sewing machine are different due to individual differences of the imaging devices, assembly errors, or the like, and therefore the template data is prepared separately in each sewing machine. Therefore, the working hours and the management hours of data in the plurality of sewing machines as a whole increase.

[0006] An object of an aspect of the present application is to reduce the working hours and the management hours of data related to image recognition in a sewing system having a plurality of sewing machines.

[0007] According to a first aspect of the present application, there is provided a sewing system including: a plurality of imaging devices that acquire images of a sewing target; one or more sewing machines that sew based on recognition results obtained through image recognition processing of the sewing target; and a data processing section that acquires template data of the sewing target created based on images captured by a first imaging device among the plurality of imaging devices, and transmits the template data to a second imaging device. The sewing machine has intrinsic data including a capturing condition of the imaging device, and the sewing machine having the second imaging device performs image recognition processing using the template data corrected based on the intrinsic data of the second imaging device, or corrects recognition results obtained using the template data based on the intrinsic data of the second imaging device.

[0008] According to a second aspect of the present application, there is provided a sewing method using a plurality of sewing machines having imaging devices that acquire images of a sewing target, and sew based on recognition results obtained through image recognition processing of the sewing target, or using a sewing machine having a plurality of the imaging devices. In the sewing method, there are included steps of acquiring template data of the sewing target created based on images captured by a first imaging device among the plurality of sewing machines or the plurality of imaging devices, and transmitting the template data to a second imaging device, and in the sewing machine having the second imaging device, performing image recognition processing using the template data corrected based on intrinsic data including a capturing condition of the second imaging device, or correcting recognition results obtained using the template data based on the intrinsic data.

[0009] Effects of the Invention

[0010] According to the aspect of the present application, it is possible to reduce work hours and management hours of data related to image recognition in a sewing system having a plurality of sewing machines. BRIEF DESCRIPTION OF DRAWINGS

[0011] Figure 1 FIG. 1 is a diagram schematically showing a sewing system according to the present embodiment.

[0012] Figure 2 FIG. 3 is a functional block diagram showing a sewing machine and a data processing section according to the present embodiment.

[0013] Figure 3 FIG. 4 is an explanatory diagram of intrinsic data possessed by a plurality of sewing machines.

[0014] Figure 4 FIG. 5 is a cross-sectional view showing a part of a sewing target.

[0015] Figure 5is a plan view showing a sewing object.

[0016] Figure 6 is a sectional view showing one example of a sewing object.

[0017] Figure 7 is a diagram for explaining template data of a recognition target.

[0018] Figure 8 is a diagram for explaining correction of template data performed by a sewing system according to the present embodiment.

[0019] Figure 9 is a diagram for explaining transmission of inherent template data.

[0020] Figure 10 is a diagram for explaining a sewing method according to the present embodiment.

[0021] Figure 11 is an oblique view showing a sewing machine according to the present embodiment.

[0022] Figure 12 is an oblique view showing a part of a sewing machine according to the present embodiment.

[0023] Figure 13 is a plan view for explaining a configuration example of a photographing device according to the present embodiment.

[0024] Figure 14 is a flowchart for explaining a sewing operation of a sewing machine according to the present embodiment.

[0025] Figure 15 is a diagram for explaining an image joining process.

[0026] Figure 16 is a diagram for explaining a recognition target detection process. DETAILED DESCRIPTION

[0027] Hereinafter, embodiments according to the present application will be described with reference to the accompanying drawings, but the present application is not limited thereto. Structural elements of the embodiments described below can be appropriately combined. In addition, a part of the structural elements can not be used.

[0028] In the present embodiment, a local coordinate system is defined with respect to the sewing machine 1. In the following description, the local coordinate system defined with respect to the sewing machine 1 is appropriately referred to as a sewing machine coordinate system. The sewing machine coordinate system is defined by an XYZ orthogonal coordinate system. In the present embodiment, the positional relationship of each part is described based on the sewing machine coordinate system. The direction parallel to the X axis in the defined plane is set as the X axis direction. The direction parallel to the Y axis in the defined plane orthogonal to the X axis is set as the Y axis direction. The direction parallel to the Z axis orthogonal to the defined plane is set as the Z axis direction. In addition, the direction of rotation or inclination centered on the X axis is set as the θX direction. The direction of rotation or inclination centered on the Y axis is set as the θY direction. The direction of rotation or inclination centered on the Z axis is set as the θZ direction. In addition, in the present embodiment, the plane including the X axis and the Y axis is appropriately referred to as an XY plane. The plane including the X axis and the Z axis is appropriately referred to as an XZ plane. The plane including the Y axis and the Z axis is appropriately referred to as a YZ plane. The XY plane is parallel to the defined plane. The XY plane, the XZ plane, and the YZ plane are orthogonal to each other. In addition, in the present embodiment, the XY plane and the horizontal plane are parallel. The Z axis direction is the up-down direction in the defined plane. The +Z direction is the upward direction. The -Z direction is the downward direction. Furthermore, the XY plane can also be inclined with respect to the horizontal plane.

[0029] [Outline of sewing system]

[0030] Figure 1 is a diagram schematically showing a sewing system 100 to which the present embodiment is applied. As shown in Figure 1 , the sewing system 100 has a plurality of sewing machines 1, a plurality of gateways 101 corresponding to the respective sewing machines 1, a communication network 102, and a data processing section 50. The sewing system 100 is, for example, equipped in a running facility, i.e., a sewing factory, in which a plurality of sewing machines 1 operate. In the sewing factory, a sewing object S is sewn by a sewing thread by the sewing machine 1, thereby manufacturing a sewn product. Furthermore, in the sewing factory, the sewing object S is sewn by a plurality of sewing machines 1, thereby manufacturing a sewn product. Figure 1 Although three sewing machines 1 are shown in the present embodiment, the number of sewing machines 1 possessed by the sewing system 100 is not particularly limited. The number of sewing machines 1 possessed by the sewing system 100 can be one, two, or four or more.

[0031] In addition, data can be exchanged between the sewing machine 1 and the data processing section 50 without passing through the communication network 102. Data can be exchanged between the sewing machine 1 and the data processing section 50 via an external storage medium such as a USB memory.

[0032] In addition, even if the number of sewing machines 1 is one, in the case where the shooting conditions are changed due to replacement or the like due to a failure of a camera or the like, the template data can be corrected based on the same principle as the following description. With this correction of the template data, the working hours of the sewing system 100 can be reduced.

[0033] The sewing machine 1 is an industrial sewing machine operated by the operator Ma. The sewing machine 1 of the present embodiment is a circular sewing machine that automatically performs pattern sewing based on a prescribed sewing pattern set. The sewing machine 1 starts a process of sewing the prescribed sewing pattern set by the operator Ma performing a prescribed operation in a state where the sewing object S and the sewing thread are set to prescribed positions.

[0034] In the present embodiment, a plurality of sewing machines 1 are used in the manufacture of the same product. That is, the plurality of sewing machines 1 sew the same pattern to the same shape of the sewing object S. For example, a plurality of production lines that manufacture the same product are provided in a sewing factory. Each of the sewing machines 1 is provided in the plurality of production lines that manufacture the same product.

[0035] The sewing machine 1 is connected to the communication network 102 via the corresponding gateway 101. The gateway 101 is provided in a communication line that connects the sewing machine 1 and the communication network 102. The gateway 101 relays the transmission and reception of various data in communication between the sewing machine 1 and the communication network 102, and forwards the received data by converting the protocol of the data.

[0036] The data processing section 50 is an information terminal operated by the manager Mb in order to manage the data of the plurality of sewing machines 1 of the sewing system 100. As a typical example of the data processing section 50, a file server or a NAS (Network Attached Storage) or the like that performs file management is assumed. The data processing section 50 can also be realized by effectively using the file management-sharing function of a desktop PC (Personal Computer) or a notebook PC, a smartphone, a tablet terminal, or the like. One of the plurality of sewing machines 1 can also be used as a host computer, serving as the data processing section 50.

[0037] The data processing section 50 can be connected to the communication network 102, and communicates with the plurality of sewing machines 1 via each gateway 101. The data processing section 50 transmits and receives data required for sewing between each sewing machine 1 via the communication network 102.

[0038] [SEWING MACHINE AND MANAGEMENT DEVICE]

[0039] Figure 2 is a functional block diagram that shows the sewing machine 1 and the data processing section 50 according to the present embodiment. In Figure 2Only the outline structure of the sewing machine 1 is shown.

[0040] As shown in Figure 2 the sewing machine 1 has a sewing machine main body 10, a control device 30, a storage device 35, an image processing section 36, a photographing device 37, an illuminating device 38, and a communication device 39.

[0041] The sewing machine main body 10 is a mechanism portion that sews a sewing object S. The sewing machine main body 10 has an actuator 10A and a driving amount sensor 10B.

[0042] The actuator 10A includes various driving mechanisms and driving sources that cause each portion of the sewing machine main body 10 to operate. The actuator 10A performs various actions for sewing a prescribed sewing pattern set by the sewing machine 1.

[0043] The driving amount sensor 10B detects a driving amount of the actuator 10A. The driving amount sensor 10B includes, for example, an encoder that detects a rotation amount of a motor, a position sensor that detects a position of a holding member of a sewing needle, and the like. Based on a detection result of the driving amount sensor 10B, the actuator 10A of the sewing machine main body 10 is controlled by the control device 30.

[0044] The control device 30 includes a computer system. The control device 30 performs various controls in each portion of the sewing machine 1. The control device 30 includes a processor such as a CPU (Central Processing Unit) or an MPU (Micro Processing Unit). The processor performs various arithmetic processing that realizes a function of the control device 30 based on a program stored in the storage device 35. The control device 30 controls the actuator 10A of the sewing machine main body 10 in accordance with sewing data set in the storage device 35.

[0045] The storage device 35 includes a primary storage device that is a volatile memory that temporarily stores data and a secondary storage device that stores various programs and various data used by the processor in arithmetic processing. The primary storage device is, for example, a RAM (Random Access Memory) or the like. The secondary storage device is, for example, a ROM (Read Only Memory), an HDD (Hard Disk Drive), an SSD (Solid State Drive), or a storage or the like. As described later, in the storage device 35, in addition to the program of the control device 30, there is also stored inherent data 60 related to the photographing device 37 possessed by the sewing machine 1 and the sewing machine main body 10. In the storage device 35, there is stored sewing data for performing sewing processing.

[0046] Sewing data is known data that can be derived from design data of the sewing object S, like CAD (Computer Aided Design) data. The sewing data is referred to by the control device 30 in a sewing process. The sewing process refers to a process of forming stitches CH (refer to FIG. 1) on the sewing object S. In addition, in the storage device 35, template data used for image recognition processing on an image of the sewing object S captured by the imaging device 37 is stored. Figure 6

[0047] The image processing section 36 includes a computer system. The image processing section 36 has a processor, a storage device including a non-volatile memory and a volatile memory, and an input-output section including an input-output interface. The processor is, for example, a CPU (Central Processing Unit). The non-volatile memory is, for example, a ROM (Read Only Memory) or a storage. The volatile memory is, for example, a RAM (Random Access Memory). The image processing section 36 performs the following image recognition processing, that is, detection of a recognition object UP (refer to FIG. 1) from an image, by capturing the sewing object S by the imaging device 37 in accordance with a computer program stored in the storage device. Figure 5

[0048] The imaging device 37 captures the sewing object S. The imaging device 37 has an optical system and an image sensor that receives light that has entered via the optical system. The image sensor includes a CCD (Couple Charged Device) image sensor or a CMOS (Complementary Metal Oxide Semiconductor) image sensor.

[0049] The illuminating device 38 irradiates the field of view of the imaging device 37 with light. The illuminating device 38 has a light source such as an LED light emitting element.

[0050] The communication device 39 communicates with the data processing section 50 via the gateway 101 and the communication network 102. The communication device 39 includes a communication interface in accordance with a wired or wireless communication standard.

[0051] The data processing section 50 includes a computer system. The data processing section 50 has a processor 51, a storage device 52, and an input-output section 53.

[0052] ​​The data processing unit 50 can be connected to an input device and a display device (not shown). The input device may be, for example, a keyboard, mouse, operation keys, or a microphone for receiving sound input. The display device displays various information. The display device may include, for example, a flat panel display. The flat panel display may be, for example, a liquid crystal display (LCD) or an organic EL display.

[0053] Alternatively, the data processing unit 50 can be a simple shared memory. In the case of a simple shared memory, no input device or display device is needed. In the case of a simple shared memory, operation information is sent to the input / output unit 53 via communication.

[0054] The processor 51 consists of a CPU, MPU, etc. The processor 51 operates based on programs stored in the storage device 52, performing various processes. The processor 51 includes a main data management unit 51A and a data adjustment unit 51B. By executing programs, the main data management unit 51A and the data adjustment unit 51B perform various functions. The main data management unit 51A and the data adjustment unit 51B can be configured separately by dedicated processors.

[0055] Master Data Management Department 51A, for example, creating Figure 8 The generalized template data shown is 71. Figure 8 The generalized template data 71 is obtained by generalizing the template data 70 of the first sewing machine SM1. The generalized template data 71 is template data used in image recognition processing of images of the sewing object S, and it excludes individual differences of each sewing machine 1 and the image shooting conditions for each machine. Excluding the image shooting conditions means generalization, which means correcting it to an ideal shape obtained using design values. For example... Figure 2 As shown in the structure, data transformation and processing can be implemented centrally, but the sewing machine side can also have this function, allowing the system to be built in a decentralized manner. Generally speaking, decentralized systems are efficient, can be simple in structure, and are therefore easy to install.

[0056] The data adjustment unit 51B acquires the inherent data 60 of multiple shooting devices 37, and based on the generalized template data 71 and the inherent data 60, creates inherent template data 72 for each shooting device (see reference). Figure 8the second sewing machine SM2). The individual template data 72 is template data obtained by reflecting individual differences of the respective photographing devices 37, photographing conditions on the generalized template data 71. This function can be similarly provided on the sewing machine side because the installation is performed by the same operation as the generalization of the template data. If the data conversion processing is installed on the distributed type on the sewing machine side, the data processing section 50 can manage only the generalized template data. Thus, it is not necessary to centrally manage the data of all the plurality of sewing machines 1, and the structure becomes simpler.

[0057] The storage 52 includes a primary storage that is a volatile memory that temporarily stores data, and a secondary storage that stores various programs and various data used for the operation of the processor 51. The volatile memory is, for example, a RAM or the like. The nonvolatile memory is, for example, a ROM, an HDD, an SSD, or a storage or the like. In the storage 52, a program for realizing the function of the data processing section 50 is stored. In the storage 52, the individual data 60 of the respective photographing devices 37 is stored. The generalized template data 71 is stored as master data in the storage 52. By centrally managing the individual data 60 of the respective photographing devices 37, the security of the data is ensured, but because the management is also performed on each of the sewing machines 1, in the data processing section 50, the function can be reduced to reduce the burden.

[0058] The input / output section 53 communicates with each of the sewing machines 1 via the communication network 102. The input / output section 53 includes a communication interface in accordance with a wired or wireless communication standard. The input / output section 53 receives, for example, the individual data 60A or the template data 70 transmitted from the first sewing machine SM1. Figure 8 The input / output section 53 transmits the individual template data 72 obtained by reflecting the individual data 60B of the photographing device 37 possessed by the second sewing machine SM2 on the generalized template data 71 to the second sewing machine SM2.

[0059] In the case where the data conversion processing function as the master data management section 51A and the data adjustment section 51B is provided in each of the sewing machines 1, the input / output section 53 transmits and receives the generalized template data 71 in each of the sewing machines 1.

[0060] [Individual data]

[0061] Figure 3is a diagram of the inherent data 60 possessed by the plurality of sewing machines 1. The inherent data 60 is data inherent to each of the plurality of sewing machines 1. Differences in the inherent data 60 indicate individual differences in the photographing devices 37 of the respective sewing machines 1. In the present embodiment, the inherent data 60 contains information related to photographing of the sewing object S. The information related to photographing of the sewing object S is the photographing conditions of the photographing device 37. Specifically, the inherent data 60 contains information of photographing conditions inherent to each of the sewing machines 1. The information of photographing conditions inherent to each of the sewing machines 1 is information due to fluctuation factors such as individual differences or assembly errors of the photographing device 37 and the illuminating device 38 of each of the sewing machines 1. Further, the inherent data 60 can contain data other than that shown in the drawing. Figure 3

[0062] The inherent data 60 is managed for each photographing device 37 of the respective sewing machines 1. In addition, the inherent data 60 is embedded in the template data file each time the template is photographed. By embedding the inherent data 60 in the template data file each time the photographing is performed, the data can be reliably managed as one pair even after being output from the sewing machine to the communication line, without being separated. Of course, the sharing of data is effective not only between different sewing machines 1 but also between different photographing devices 37 of the same sewing machine 1.

[0063] In the inherent data 60, the pixel rate 61 of the photographing device 37, the photographing offset 62, and the illumination information 63 are contained as photographing conditions.

[0064] The pixel rate 61 of the photographing device 37 is information indicating the actual distance corresponding to each pixel of the photographed image. The pixel rate 61 varies in correspondence with the distance between the photographing device 37 and the subject (sewing object S). By performing so-called calibration of measuring the number of pixels between two points in the image by photographing a measuring tool of which the distance between the two points is known, the pixel rate 61 can be obtained. By performing calibration at a plurality of distances, a regression line is calculated from the pixel rates of the plurality of distances, whereby the pixel rate 61 for an arbitrary distance can be obtained.

[0065] ​The photographing offset 62 is information indicating a deviation of a camera coordinate system of the photographing device 37 from a design value in the sewing machine coordinate system. The photographing offset 62 is information for correcting a deviation caused by an assembly error of the photographing device 37, individual differences of an optical system of the photographing device 37, and the like. The individual differences of the optical system of the photographing device 37 are, for example, optical axis deviation, lens aberration. The photographing offset 62 includes information of XYZ position coordinates of the photographing device 37, inclination of a camera optical axis (θX direction and θY direction), a rotation angle around the camera optical axis (θZ direction), a lens distortion coefficient, and the like. By performing photographing with a measurement tool of a known shape positioned at a prescribed position, so-called calibration of calculating the XY position deviation, the distortion of the image, and the angle deviation from the position and shape of the measurement tool photographed in the image is performed, and thus the photographing offset 62 can be acquired.

[0066] The illumination information 63 is information indicating a light amount of illumination light emitted from the illuminating device 38. By performing photographing of an image while changing a light amount setting value of the illuminating device 38 for a prescribed subject, so-called calibration of finding a light amount setting value at which the contrast of the image converges in a desired range is performed, and thus the illumination information can be acquired. The prescribed subject is, for example, the sewing object S. In a case where brightness adjustment is performed by image processing on a photographed image, the illumination information 63 can further include information of a brightness adjustment parameter, a lookup table, and the like.

[0067] In the sewing system 100 according to the present embodiment, with respect to each photographing device 37 possessed by the plurality of sewing machines 1, calibration work is performed in advance, and thus the inherent data 60 including the pixel rate 61, the photographing offset 62, and the illumination information 63 is acquired for each sewing machine 1. Each of the plurality of sewing machines 1 stores the inherent data 60 including the photographing conditions of the photographing device 37 in the storage device 35.

[0068] [SEWING OBJECT]

[0069] Figure 4 is a cross-sectional view indicating a part of the sewing object S according to the present embodiment. Figure 5 is a plan view indicating the sewing object S according to the present embodiment. Figure 4 and Figure 5 The sewing object S before the sewing process is shown. In the present embodiment, the sewing object S is a skin material used for a seat for a vehicle.

[0070] As shown in Figure 4 , the sewing object S has a surface material 4, a cushion material 5, and a back material 6. The hole 7 is provided in the surface material 4.

[0071] The surface material 4 is the seating surface that comes into contact with the occupant when seated in the vehicle seat. Surface material 4 comprises at least one of woven fabric, nonwoven fabric, and leather. Padding material 5 is elastic. Padding material 5 may include, for example, polyurethane resin. Backing material 6 comprises at least one of woven fabric, nonwoven fabric, and leather.

[0072] like Figure 5 As shown, a plurality of holes 7 are provided in the surface material 4. The holes 7 are formed to be scattered throughout the sewn object S. The holes 7 are arranged in a regular pattern. That is, the sewn object S contains a plurality of reference patterns DPh. The reference patterns DPh are constituted by the regular arrangement of the plurality of holes 7. Figure 5 In the example, the reference pattern DPh consists of 17 holes 7.

[0073] like Figure 5 As shown, reference patterns DPh are arranged at intervals on surface material 4. The reference patterns DPh are arranged at equal intervals in both the X-axis and Y-axis directions. Reference patterns DPh at different positions in the Y-axis direction are arranged between adjacent reference patterns DPh in the X-axis direction. No holes 7 are formed between adjacent reference patterns DPh.

[0074] In the area between the reference patterns DPh, the target patterns RP (RP1, RP2, RP3, RP4, RP5, RP6, RP7, RP8, RP9, RP10) of the stitch CH to be formed on the sewn object S are specified. Figure 5 In the object S to be sewn before sewing, the target pattern RP of the stitch CH is virtually shown. The sewing machine 1 forms the stitch CH along each target pattern RP according to the pre-set sewing pattern.

[0075] In the case of performing multiple sewing processes to form multiple stitches CH, a first sewing process is performed to form the first stitch CH on the sewing object S based on the first target pattern RP1. After the first sewing process, a second sewing process is performed to form the second stitch CH on the sewing object S based on the second target pattern RP2. Then, corresponding to the number N of stitches CH that should be formed, a third to an Nth sewing process are performed sequentially. Figure 5 An example with N=10 is shown, specifying the first target pattern RP1 to the tenth target pattern RP10.

[0076] Furthermore, multiple identification objects UP (UP1, UP2, UP3, UP4, UP5, UP6, UP7) are arranged on the sewn object S. In this embodiment, the identification objects UP are arranged in a predetermined pattern among multiple holes 7 in the sewn object S. Specifically, the identification objects UP are part of a reference pattern DPh. Figure 6In the example, the identified objects UP (UP1, UP2, UP3, UP4, UP5, UP6, UP7) are patterns (the arrangement of holes 7) that include the corner of one acute angle of the reference pattern DPh with a rhomboid shape. The identified objects UP are patterns that can be determined by template matching, which is an image processing method.

[0077] use Figure 6 The displacement that occurs on the surface of a sewn object S when a stitch CH is formed on the object S with thickness and elasticity is explained. Figure 6 This is a cross-sectional view showing an example of the sewing object S involved in this embodiment. Figure 6 The image shows a sewn object S after the sewing process has been performed. The sewn object S has thickness and elasticity. By forming a stitch CH on the thick, elastic sewn object S, as shown... Figure 2 As shown, the sewn object S is highly likely to shrink. If the sewn object S shrinks, its surface may shift. If the surface of the sewn object S shifts, the target position of the stitch CH defined on the surface of the sewn object S is highly likely to shift in the XY plane. If the target position of the stitch CH shifts in the XY plane, it will be difficult to form the stitch CH at the target position if the sewn object S is moved to the position coordinates of the designed target pattern RP.

[0078] Therefore, in this embodiment, the image processing unit 36 ​​(refer to...) Figure 7 The image processing unit 36 ​​obtains the displacement amount of the surface of the object to be sewn, S (a correction amount for correcting the displacement amount). Using the obtained displacement amount of the surface of the object to be sewn, S is moved accordingly, so that even if the surface of the object to be sewn shrinks due to the formation of the stitch CH and the surface of the object to be sewn is displaced, the next stitch CH will be formed at the target position. The image processing unit 36 ​​detects the object to be identified, UP, based on the image of the object to be sewn captured by the imaging device 37, and obtains the displacement amount based on the displacement of the object to be identified, UP.

[0079] [Template Data]

[0080] Figure 8is a diagram for explaining the template data 70 of the recognition target UP. The template data 70 is created using the first photographing device 37 as an arbitrary one among the plurality of photographing devices 37. Hereinafter, the sewing machine 1 having the first photographing device 37 used for the creation of the template data 70 will be referred to as "first sewing machine SM1". In addition, the other sewing machine 1 than the first sewing machine SM1 among the plurality of sewing machines 1 will be referred to as "second sewing machine SM2". The second sewing machine SM2 is the sewing machine 1 having the other second photographing device 37 than the first photographing device 37.

[0081] The template data 70 is data used in the image recognition processing of the recognition target UP. Specifically, the template data 70 is an image photographed by photographing the recognition target UP, and is a reference image referred to in the template matching. The template data 70 is acquired by photographing the recognition target UP formed on the sewing object S by the first photographing device 37 possessed by the first sewing machine SM1.

[0082] Therefore, the template data 70 becomes an image dependent on the intrinsic data 60 of the first photographing device 37. That is, the size, distortion, inclination, average brightness, contrast, and the like of the recognition target UP included in the image of the template data 70 reflect the photographing conditions (pixel rate 61, photographing offset 62, illumination information 63) of the first photographing device 37 of the first sewing machine SM1.

[0083] In the actual sewing work, the image photographed by the first sewing machine SM1 (first photographing device 37) is photographed by the same photographing conditions as the template data 70. Therefore, in the first sewing machine SM1, the image of the sewing object S involved in the sewing work and the template data 70 are consistent in the parameters of the image, and detection can be performed with high accuracy.

[0084] On the other hand, the image photographed by the second photographing device 37 possessed by the second sewing machine SM2 reflects the photographing conditions of the second photographing device 37, and becomes an image parameter different from that in the first photographing device 37. Therefore, in the sewing work, if the template data 70 created by the first sewing machine SM1 (first photographing device 37) is directly used in the second sewing machine SM2 (second photographing device 37), the image parameters of the template data 70 and the image of the sewing object S photographed by the second photographing device 37 are not consistent, and the detection accuracy of the recognition target UP can be reduced.

[0085] Therefore, in the sewing system 100 involved in the present embodiment, the photographing conditions of the template data 70 and the inconsistency of the photographing conditions of the sewing object S in each photographing device 37 are corrected using the intrinsic data 60 of the photographing device 37 possessed by each sewing machine 1.

[0086] [Correction of template data]

[0087] Figure 8 is a view for explaining correction of the template data 70 performed by the sewing system 100 according to the present embodiment.

[0088] In Figure 2 , a process of applying the template data 70 created by the 1st sewing machine SM1 (1st photographing device 37) to another 2nd sewing machine SM2 (2nd photographing device 37) is shown. Here, the intrinsic data 60 of the 1st sewing machine SM1 is referred to as intrinsic data 60A, and the intrinsic data 60 of the 2nd sewing machine SM2 is referred to as intrinsic data 60B. In the present embodiment, the data processing section 50 creates template data (intrinsic template data 72) reflecting the intrinsic data 60B of the 2nd sewing machine SM2, based on the template data 70 created by the 1st sewing machine SM1. The template data 70 created by the 1st sewing machine SM1 is also intrinsic template data 72 of the 1st sewing machine SM1, since it reflects the intrinsic data 60A of the 1st sewing machine SM1.

[0089] The data processing section 50 acquires the template data 70 created by the 1st sewing machine SM1 and the intrinsic data 60A of the 1st sewing machine SM1 from the 1st sewing machine SM1.

[0090] The data processing section 50 creates, by the master data management section 51A, generalization template data 71 generalizing (normalizing) the template data 70, based on the template data 70 and the intrinsic data 60A of the 1st sewing machine SM1.

[0091] That is, the template data 70 is intrinsic template data reflecting the intrinsic data 60A of the 1st sewing machine SM1, but the intrinsic data 60A is known by calibration. In order to simply explain the concept of normalization, various parameters are focused on. The master data management section 51A normalizes the image scale based on the pixel rate 61 of the intrinsic data 60A. The generalization template data 71 becomes normalized data capable of being converted into a scale of a photographed image in a desired photographing condition, by being given information of the pixel rate 61. Thus, in the generalization template data 71, by applying the pixel rate 61 of the intrinsic data 60B of the 2nd sewing machine SM2 to be used as data, it becomes possible to coincide with the pixel rate 61 of an image photographed by the 2nd sewing machine SM2.

[0092] The main data management section 51A normalizes the luminance information of the image based on the illumination information 63 of the unique data 60A. The generalized template data 71 becomes normalized data capable of reproducing the luminance distribution of the captured image in the desired capturing condition by being given the illumination information 63. Thus, the generalized template data 71 is capable of matching the luminance distribution (average luminance and contrast) of the image captured by the second sewing machine SM2 by applying the illumination information 63 of the unique data 60B of the second sewing machine SM2 to be used as the data.

[0093] The main data management section 51A normalizes the geometric information of the image based on the capturing offset 62 of the unique data 60A. That is, the image position deviation, distortion, and rotation angle deviation of the template data 70 are removed from the information of the capturing offset 62. That is, it is transformed into data in a case where the capturing device 37 is accurately installed at the designed position. The generalized template data 71 becomes normalized data capable of being transformed into the geometric condition of the captured image in the desired capturing condition where the relative positional relationship is known by being deformed to a certain reference position (here, the designed value) based on the information of the capturing offset 62. Thus, the generalized template data 71 is capable of matching the geometric information of the image captured by the second sewing machine SM2 by applying the capturing offset 62 of the unique data 60B of the second sewing machine SM2 to be used as the data. In addition, if the capturing offset of the unique data 60A and the capturing offset of the unique data 60B are matched, the transformation of the geometric information from the first sewing machine SM1 to the second sewing machine SM2 can be calculated directly without passing through the generalized template.

[0094] The main data management section 51A records the created generalized template data 71 as the main data common to each sewing machine 1 in the storage device 52 (refer to FIG. 1). Figure 9 ).

[0095] The data processing section 50 acquires the unique data 60B of the second sewing machine SM2. The data processing section 50 creates the unique template data 72 for each sewing machine based on the generalized template data 71 and the unique data 60B through the data adjustment section 51B.

[0096] That is, the data adjustment section 51B acquires the unique data 60B of the second sewing machine SM2 to be the application target of the generalized template data 71, applies the unique data 60B to the generalized template data 71, thereby creating the template data (unique template data 72) reflecting the unique data 60B of the application target second sewing machine SM2. One generalized template data 71 is created for all the sewing machines 1 (sewing system 100). The unique template data 72 is separately created for each sewing machine 1 (capturing device 37).

[0097] Figure 9 is a diagram illustrating transmission of the unique template data 72. In Figure 10 Three second sewing machines SM2P, SM2Q, and SM2R are exemplified in The second sewing machines SM2P, SM2Q, and SM2R transmit the unique data 60B to the data processing section 50, respectively. Here, the unique data 60B of the second sewing machines SM2P, SM2Q, and SM2R are set as unique data 60P, 60Q, and 60R, respectively.

[0098] The data adjustment section 51B creates the unique template data 72P of the second sewing machine SM2P by applying the unique data 60P to the generalized template data 71, and transmits it to the second sewing machine SM2P. The data adjustment section 51B creates the unique template data 72Q of the second sewing machine SM2Q by applying the unique data 60Q to the generalized template data 71, and transmits it to the second sewing machine SM2Q. The data adjustment section 51B creates the unique template data 72R of the second sewing machine SM2R by applying the unique data 60R to the generalized template data 71, and transmits it to the second sewing machine SM2R.

[0099] The second sewing machines SM2P, SM2Q, and SM2R execute the image recognition processing using the unique template data 72P, 72Q, and 72R of the own machine acquired from the data processing section 50, respectively. Further, in the first sewing machine SM1, since the template data 70 created by the own machine is the unique template data 72 of the first sewing machine SM1, the first sewing machine SM1 directly uses the template data 70 to execute the image recognition processing.

[0100] As described above, in the present embodiment, the data processing section 50 acquires the template data of the sewing object S created based on the image captured by the first sewing machine SM1 (first photographing device 37) among the plurality of sewing machines 1 (photographing devices 37), and transmits it to the other second sewing machines SM2 (second photographing devices 37). Further, the second sewing machines SM2 execute the image recognition processing using the unique template data 72 obtained by correcting the generalized template data 71 based on the unique data 60 of the own machine.

[0101] Further, here, an example in which the data processing section 50 creates the unique template data 72 of each of the second sewing machines SM2 based on the generalized template data 71 is shown. However, the creation of the unique template data 72 is not limited to the above-described example. It is also possible to transmit the generalized template data 71 from the data processing section 50 to the second sewing machines SM2, and each of the second sewing machines SM2 (image processing section 36) creates the unique template data 72 using the unique data 60 of the own machine.

[0102] In addition, the second sewing machine SM2 can perform the image recognition processing using the generalized template data 71 instead of using the unique template data 72, and correct the recognition result obtained using the generalized template data 71 based on the unique data 60 of the machine. For example, in a case where the result of the calibration is that the error from the design value of the photographing condition of the machine becomes sufficiently small, the detection of the recognition target UP can be appropriately performed using the generalized template data 71 (or the template data 70 of the first sewing machine SM1). Thus, after the image recognition processing at the time of the sewing work, the XY position coordinates, the rotation angle, and the like of the detected recognition target UP are corrected using only the unique data 60 of the machine, and thus appropriate image recognition of the sewing target object S can be achieved.

[0103] [SEWING METHOD]

[0104] Figure 10 is a diagram for explaining a sewing method according to the present embodiment. Referring to Figure 7 The flow of transmission of the template data 70 in the sewing system 100 will be explained.

[0105] First, in each of the plurality of sewing machines 1 (the plurality of photographing devices 37), the acquisition work of the unique data 60 is performed (S (step) 1). That is, by the calibration work, the unique data 60 including the pixel rate 61 of the photographing device 37, the photographing offset 62, and the illumination information 63 is acquired for each photographing device 37. The acquisition of the unique data 60 is performed in either of the first sewing machine SM1 and the second sewing machine SM2 described above.

[0106] Next, the first sewing machine SM1 having the first photographing device 37 as an arbitrary one of the plurality of photographing devices 37 performs the creation of the template data 70 (S2). The control device 30 of the first sewing machine SM1 actually photographs the sewing target object S by the first photographing device 37 possessed by the first sewing machine SM1, and acquires the image of the recognition target UP. The image processing section 36 of the first sewing machine SM1 creates the template data 70 from the acquired image of the recognition target UP (see Figure 11 ).

[0107] Next, the data processing section 50 creates the generalized template data 71 (S3). The data processing section 50 acquires the template data 70 created by S2 and the unique data 60A of the first photographing device 37 from the first sewing machine SM1 through the input and output section 53. The main data management section 51A normalizes the template data 70 by the unique data 60A, and thereby creates the generalized template data 71, which is recorded in the storage device 52.

[0108] Next, the data processing section 50 creates the unique template data 72 (S4). The data processing section 50 acquires the unique data 60B of the second photographing device 37 from the second sewing machine SM2 other than the first sewing machine SM1 through the input / output section 53. The data adjustment section 51B creates the unique template data 72 of the second photographing device 37 possessed by the second sewing machine SM2 by applying the unique data 60B to the generalized template data 71 recorded in the storage device 52. In the case where a plurality of second sewing machines SM2 are present, the data adjustment section 51B creates the unique template data 72 for each individual using the unique data 60B acquired from each of the second sewing machines SM2.

[0109] Next, the data processing section 50 transmits the unique template data 72 to the second sewing machine SM2 (S5). The data processing section 50 transmits the corresponding unique template data 72 to each of the second sewing machines SM2 through the input / output section 53.

[0110] Then, the plurality of sewing machines 1 respectively perform the sewing process. That is, the plurality of sewing machines 1 acquire the image of the sewing object S through the photographing device 37, perform the image recognition process of the sewing object S through the image processing section 36, and perform sewing based on the recognition result obtained through the image recognition process. At this time, each of the second sewing machines SM2 performs the image recognition process using the unique template data 72 corrected through the unique data 60B of the own machine. In addition, the first sewing machine SM1 performs the image recognition process using the template data 70 created at S2 as the unique template data of the own machine.

[0111] Further, as described above, in the sewing method according to the present embodiment, the second sewing machine SM2 can correct the recognition result obtained using the template data (generalized template data 71) based on the unique data 60 instead of using the corrected template data (unique template data 72).

[0112] [SEWING MACHINE]

[0113] Next, a specific example of the sewing machine 1 possessed by the sewing system 100 will be described below. Figure 12 is a perspective view showing the sewing machine 1 according to the present embodiment. Figure 11 is a perspective view showing a part of the sewing machine 1 according to the present embodiment. Figure 12 The sewing machine 1 shown in the drawing includes a sewing machine main body 10, an operation device 20 operated by an operator Ma, a control device 30 that performs control of the sewing machine main body 10, an image processing section 36, and a plurality of photographing devices 37.

[0114] The sewing machine main body 10 is mounted on the upper surface of the workbench 2. As shown in Figure 11As shown, the sewing machine main body 10 has a sewing machine frame 11, a needle bar 12, a needle plate 13, a holding member 15, an actuator 16, an actuator 17, and an actuator 18. The needle bar 12 and the needle plate 13 are respectively supported to the sewing machine frame 11. The holding member 15 is supported to the sewing machine frame 11 via a support member 14. The actuator 16 (refer to Figure 11 ) generates a motive force that moves the needle bar 12. The actuator 17 (refer to Figure 11 ) generates a motive force that moves the holding member 15. The actuator 18 (refer to Figure 2 ) generates a motive force that moves at least a part of the holding member 15. The actuator 16, the actuator 17, and the actuator 18 are one example of the actuator 10A shown in Figure 11

[0115] The sewing machine frame 11 has a horizontal arm 11A, a base 11B, a vertical arm 11C, and a head 11D. The horizontal arm 11A extends in the Y-axis direction. The base 11B (refer to Figure 11 ) is arranged below compared to the horizontal arm 11A. The vertical arm 11C (refer to Figure 11 ) is arranged to connect an end of the +Y side of the horizontal arm 11A and the base 11B. The head 11D is arranged at the -Y side of the horizontal arm 11A.

[0116] The needle bar 12 holds the sewing machine needle 3. The needle bar 12 holds the sewing machine needle 3 in a manner that the sewing machine needle 3 becomes parallel to the Z-axis. The needle bar 12 is movably supported to the head 11D in the Z-axis direction.

[0117] The needle plate 13 supports the sewing object S. The needle plate 13 supports the holding member 15. The needle plate 13 is supported to the base 11B (refer to Figure 6 ). The needle plate 13 is arranged below compared to the holding member 15.

[0118] The holding member 15 holds the sewing object S. The holding member 15 holds the sewing object S in the XY plane including the sewing position Ps directly below the sewing machine needle 3, and is movable. The holding member 15 is able to hold the sewing object S in the XY plane including a position directly below the imaging device 37. The holding member 15 moves in the XY plane based on the sewing data in a state where the sewing object S is held. As a result, a stitch CH (refer to Figure 11 ) is formed in the sewing object S that has passed the sewing position Ps. The holding member 15 is supported to the horizontal arm 11A via the support member 14.

[0119] ​The holding member 15 has a presser foot member 15A and a lower plate 15B opposite to the presser foot member 15A. The presser foot member 15A is a frame-shaped member. The presser foot member 15A is movable in the Z-axis direction. The lower plate 15B is disposed below the presser foot member 15A. The holding member 15 holds the sewing object S by clamping it with the presser foot member 15A and the lower plate 15B.

[0120] If the presser foot component 15A moves in the +Z direction, the presser foot component 15A and the lower plate 15B separate. This allows the operator Ma to place the sewing object S between the presser foot component 15A and the lower plate 15B. If the presser foot component 15A moves in the -Z direction with the sewing object S placed between the presser foot component 15A and the lower plate 15B, the sewing object S is clamped by the presser foot component 15A and the lower plate 15B. Thus, the sewing object S is held by the holding member 15. Furthermore, if the presser foot component 15A moves in the +Z direction, the holding of the sewing object S by the holding member 15 is released. This allows the operator Ma to remove the sewing object S from between the presser foot component 15A and the lower plate 15B.

[0121] like Figure 12 As shown, actuator 16 generates power to move needle bar 12 in the Z-axis direction. Actuator 16 includes a pulse motor. Actuator 16 is disposed on horizontal arm 11A.

[0122] A horizontal arm shaft extending in the Y-axis direction is configured inside the horizontal arm 11A. An actuator 16 is connected to the +Y side end of the horizontal arm shaft. The -Y side end of the horizontal arm shaft is connected to the needle bar 12 via a power transmission mechanism configured inside the head 11D. The horizontal arm shaft rotates due to the operation of the actuator 16. The power generated by the actuator 16 is transmitted to the needle bar 12 via the horizontal arm shaft and the power transmission mechanism. Consequently, the sewing machine needle 3 held by the needle bar 12 reciprocates in the Z-axis direction.

[0123] A timing belt extending in the Z-axis direction is arranged inside the vertical arm 11C. Additionally, a base shaft extending in the Y-axis direction is arranged inside the base 11B. Pulleys are respectively arranged on the horizontal arm shaft and the base shaft. The timing belt is mounted on the pulleys on both the horizontal arm shaft and the base shaft. The horizontal arm shaft and the base shaft are connected via a power transmission mechanism including the timing belt.

[0124] A vessel is disposed inside the base 11B. The vessel houses the spool that has been placed into the spool housing. The horizontal arm shaft and the base shaft rotate independently due to the operation of the actuator 16. The power generated by the actuator 16 is transmitted to the vessel via the horizontal arm shaft, the timing belt, and the base shaft. Thus, the vessel and the needle bar 12 rotate synchronously in the Z-axis reciprocating motion.

[0125] Actuator 17 generates power to move holding member 15 in the XY plane. Actuator 17 includes a pulse motor. Actuator 17 includes: an X-axis motor 17X, which generates power to move holding member 15 in the X-axis direction; and a Y-axis motor 17Y, which generates power to move holding member 15 in the Y-axis direction. Actuator 17 is disposed inside base 11B.

[0126] The power generated by the actuator 17 is transmitted to the holding member 15 via the support member 14. Thus, the holding member 15 can move between the sewing machine needle 3 and the needle plate 13 in the X-axis and Y-axis directions, respectively. Through the operation of the actuator 17, the holding member 15 can hold and move the sewing object S within the XY plane, including the sewing position Ps directly below the sewing machine needle 3.

[0127] Actuator 18 generates power to move presser foot member 15A of holding member 15 in the Z-axis direction. Actuator 18 includes a pulse motor. Presser foot member 15A moves in the +Z direction, thereby separating presser foot member 15A from lower plate 15B. Presser foot member 15A moves in the -Z direction, thereby clamping the sewing object S by presser foot member 15A and lower plate 15B.

[0128] like Figure 11 As shown, the sewing machine body 10 has a presser foot member 19 arranged around the sewing machine needle 3. The presser foot member 19 presses down on the workpiece S to be sewn around the sewing machine needle 3. The presser foot member 19 is movably supported on the head 11D in the Z-axis direction. A presser foot motor is arranged inside the head 11D to generate the power to move the presser foot member 19 in the Z-axis direction. Through the operation of the presser foot motor, the presser foot member 19 moves synchronously with the needle bar 12 in the Z-axis direction. The presser foot member 19 suppresses the lifting of the workpiece S caused by the movement of the sewing machine needle 3.

[0129] like Figure 2 As shown, the sewing machine 1 includes: a drive quantity sensor 31, which detects the drive quantity of the actuator 16; and a drive quantity sensor 32, which detects the drive quantity of the actuator 17. The drive quantity sensor 31 and the drive quantity sensor 32 are... Figure 11 An example of a drive quantity sensor 10B.

[0130] The control device 30 controls the actuator 16 based on the detection data from the drive quantity sensor 31. The control device 30 determines, for example, the operating timing of the actuator 16 based on the detection data from the drive quantity sensor 31.

[0131] The drive amount sensor 32 includes an X-axis sensor 32X that detects the drive amount of the X-axis motor 17X of the actuator 17, and a Y-axis sensor 32Y that detects the drive amount of the Y-axis motor 17Y of the actuator 17. The X-axis sensor 32X includes an encoder that detects the rotation amount of the X-axis motor 17X. The Y-axis sensor 32Y includes an encoder that detects the rotation amount of the Y-axis motor 17Y. The detection data of the drive amount sensor 32 is output to the control device 30. The control device 30 controls the actuator 17 based on the detection data of the drive amount sensor 32. The control device 30 performs feedback control of the actuator 17 based on the detection data of the drive amount sensor 32 so that the holding member 15 moves to the target position.

[0132] The drive amount sensor 32 functions as a position sensor that detects the position of the holding member 15 in the XY plane. The drive amount of the actuator 17 and the movement amount of the holding member 15 are in a one-to-one correspondence.

[0133] The X-axis sensor 32X is able to detect the movement amount of the holding member 15 in the X-axis direction from the origin in the sewing machine coordinate system by detecting the rotation amount of the X-axis motor 17X. The Y-axis sensor 32Y is able to detect the movement amount of the holding member 15 in the Y-axis direction from the origin in the sewing machine coordinate system by detecting the rotation amount of the Y-axis motor 17Y.

[0134] The operation device 20 accepts an operation input by the operator Ma. The sewing machine 1 operates by operating the operation device 20. The operation device 20 includes an operation panel 21 and an operation pedal 22. The operation panel 21 is mounted on the upper surface of the table 2. The operation pedal 22 is disposed below the table 2. The operator Ma operates the operation pedal 22 by the foot. The sewing machine 1 operates by the operator Ma operating at least one of the operation panel 21 and the operation pedal 22.

[0135] The plurality of photographing devices 37 photograph the sewing object S held by the holding member 15. The plurality of photographing devices 37 are disposed above the needle plate 13 and the holding member 15. The plurality of photographing devices 37 respectively photograph at least a part of the sewing object S held by the holding member 15 from above. The number of photographing devices 37 is not particularly limited. In Figure 13 An example in which four photographing devices 37 are provided is shown in FIG. 8.

[0136] [Photographing Device]

[0137] Figure 13 is a plan view that explains an example of the arrangement of the photographing device 37 according to the present embodiment. The plurality of photographing devices 37 are arranged, for example, as shown in Figure 13 FIG. 8.

[0138] The plurality of photographing devices 37 are arranged in a manner so as to be spaced apart in a horizontal plane with respect to the sewing machine body 10. The plurality of photographing devices 37 are arranged in the sewing area SA. The sewing area SA is a range in the XY plane in which the sewing object S is able to be sewn by the head 11D by moving the sewing object S by the holding member 15. The head 11D (i.e., the sewing position Ps) is arranged in the center of the sewing area SA. The plurality of photographing devices 37 are arranged in a manner so as to be along the head 11D of the sewing machine body 10.

[0139] In the example of Figure 13 , the sewing machine 1 has photographing units 40A, 40B in a manner so as to be adjacent to each other by one in the X-axis direction on both sides (+X side, -X side) with respect to the head 11D. In the photographing units 40A, 40B, the plurality of photographing devices 37 are able to be installed. The photographing units 40A, 40B are arranged above the sewing area SA. The photographing units 40A, 40B are fixed to the sewing machine 1.

[0140] In the example of Figure 13 , in the mounting portion 41A of the photographing unit 40A, two photographing devices 37 are installed, and in the mounting portion 41B, two photographing devices 37 are also installed. The two photographing devices 37 of the photographing unit 40A are arranged in the length direction (X-axis direction) of the sewing area SA. In the mounting portion 41C of the photographing unit 40B, two photographing devices 37 are installed, and in the mounting portion 41D, two photographing devices 37 are also installed. The two photographing devices 37 of the photographing unit 40B are arranged in the width direction (Y-axis direction) of the sewing area SA.

[0141] The photographing device 37 acquires an image of at least a portion of the sewing object S arranged in the photographing field of view. The plurality of photographing devices 37 are each arranged so as to have a photographing field of view that partially overlaps with the photographing field of view of an adjacent other photographing device 37 in an overlapping region JA. Specifically, the photographing device 37 of the mounting portion 41A has a photographing field of view 42A. The photographing device 37 of the mounting portion 41B has a photographing field of view 42B. The photographing field of view 42A and the photographing field of view 42B have an overlapping region JA that has a rectangular shape and extends in the Y-axis direction. An enlarged photographing region 43A is formed by the photographing field of view 42A and the photographing field of view 42B. The enlarged photographing region 43A is a region in which the photographing fields of view of the plurality of photographing devices 37 that share the overlapping region JA are combined. By the photographing field of view 42A and the photographing field of view 42B being arranged in the X-axis direction, a wide enlarged photographing region 43A that extends in the X-axis direction is formed.

[0142] The imaging device 37 of the mounting part 41C has an imaging field of view 42C. The imaging device 37 of the mounting part 41D has an imaging field of view 42D. The imaging fields of view 42C and the imaging fields of view 42D have an overlapping area JA, which has a rectangular shape and extends in the X-axis direction. An enlarged imaging area 43B is formed by the imaging fields of view 42C and the imaging fields of view 42D. A wide enlarged imaging area 43B extending in the Y-axis direction is formed by the imaging fields of view 42C and the imaging fields of view 42D arranged in the Y-axis direction.

[0143] exist Figure 5 In the structure, the field of view of the shooting device 37, the size of the overlapping area JA (the spacing of the mounting parts), and the number of shooting devices 37 are related to the target pattern RP of the sewing object S (refer to...). Figure 2 The dimensions of the imaging units are set accordingly. That is, the enlarged imaging areas 43A and 43B formed by the multiple imaging devices 37 are designed to include the entire target pattern RP of the sewn object S. The sewn object S with stitches CH extending along the X-axis can be positioned in the enlarged imaging area 43A of the imaging unit 40A and photographed, and the sewn object S with stitches CH extending along the Y-axis can also be positioned in the enlarged imaging area 43A of the imaging unit 40A and photographed. Therefore, regardless of which direction the stitches CH extend in, the entire target pattern RP can be photographed without changing the mounting position of the imaging devices 37.

[0144] Furthermore, the positions of each imaging device 37 are fixed at six arbitrary installation locations. The relative positions of the imaging device 37 and the sewing machine frame 11 are fixed. The relative positions of the optical axis of the imaging device 37 and the sewing machine needle 3 (sewing position Ps) in the XY plane are fixed. The relative position data representing the relative positions of the centers of the enlarged imaging areas 43A and 43B in the XY plane and the sewing machine needle 3 are known data that can be derived from the design data of the sewing machine 1.

[0145] The position of the image acquired by the imaging device 37 is defined in the camera coordinate system. Through a defined transformation formula or transformation matrix, the position of the image defined in the camera coordinate system is transformed into the position of the image defined in the sewing machine coordinate system.

[0146] Additionally, the shooting units 40A and 40B hold multiple lighting devices 38A and 38B in place. The shooting units 40A and 40B hold the lighting devices 38A and 38B in a fixed position above the sewing area SA. The lighting devices 38A and 38B are... Figure 11 An example of a lighting device 38.

[0147] In the shooting unit 40A, one (total of three) lighting device 38A is arranged on both outer sides of the arrangement of mounting portions 41A and 41B along the X-axis and between the arrangement of mounting portions 41A and 41B. Each lighting device 38A extends linearly along the Y-axis. Each lighting device 38A illuminates the shooting field of view set below the mounting portions 41A and 41B in a direct illumination manner. In the shooting unit 40B, one (total of three) lighting device 38B is arranged on both outer sides of the arrangement of mounting portions 41C and 41D along the Y-axis and between the arrangement of mounting portions 41C and 41D. Each lighting device 38B extends linearly along the X-axis. Each lighting device 38B illuminates the shooting field of view set below the mounting portions 41C and 41D in a direct illumination manner.

[0148] [Image Processing]

[0149] Next, the image processing using multiple imaging devices 37 will be explained. Image processing unit 36 ​​(see reference) Figure 13 The image processing unit 36 ​​acquires images of the sewn object S from multiple imaging devices 37. If the sewn object S is positioned at a predetermined shooting position by the control device 30, the image processing unit 36 ​​controls the operation of the imaging devices 37 and the lighting device 38 corresponding to the shooting position to acquire images of the sewn object S.

[0150] exist Figure 3 In the imaging unit 40A, a shooting position Pf is set at the center of the enlarged shooting areas 43A and 43B. Shooting is performed with the holding member 15 (the object being sewn S) positioned at the center of any shooting position Pf within the enlarged shooting areas 43A and 43B. For example, in the imaging unit 40A, if the object being sewn S is positioned at shooting position Pf in the enlarged shooting area 43A, the image processing unit 36 ​​illuminates the lighting device 38A, and the shooting devices 37 of the mounting unit 41A and 41B substantially simultaneously perform shooting. As a result, an image corresponding to the shooting field of view 42A and an image corresponding to the shooting field of view 42B are obtained. In the imaging unit 40B, if the object being sewn S is positioned at shooting position Pf in the enlarged shooting area 43B, the image processing unit 36 ​​illuminates the lighting device 38B, and the shooting devices 37 of the mounting unit 41C and 41D substantially simultaneously perform shooting. Shooting can also be performed sequentially.

[0151] When the identified object UP is located at the boundary of the images from multiple imaging devices 37, the image processing unit 36 ​​performs image compositing processing, combining the images from the multiple imaging devices 37. In this case, it is necessary to align the coordinate systems of the two imaging devices 37. The imaging conditions of the other imaging device 37 are made consistent relative to either imaging device 37. That is, the process is performed not between the sewing machines 1, but between the imaging devices 37 of the same sewing machine 1. Figure 15 The inherent data 60 undergoes data transformation processing. The image processing unit 36 ​​combines multiple images constituting the expanded shooting area (43A or 43B) based on the image portions of their overlapping regions JA to generate a composite image 46 (see reference). Figure 5 Therefore, the composite image 46 becomes an image capturing a range equivalent to that of the expanded shooting area 43A or 43B. The expanded shooting areas 43A and 43B have multiple recognizable objects UP of the sewn object S (see reference). Figure 2 The size includes the image. Therefore, the composite image 46 is an image capturing multiple identified objects UP. Preferably, the composite image 46 includes all identified objects UP (UP1 to UP7) detected when forming one line trace CH.

[0152] The image processing unit 36 ​​performs image recognition processing to detect multiple recognition objects UP based on the synthesized image 46. The image processing unit 36 ​​obtains the position coordinates of the recognition objects UP in the synthesized image 46 by matching with the inherent template data 72. The image processing unit 36 ​​detects the multiple recognition objects UP contained in the synthesized image 46 sequentially and obtains the position coordinates of each of the multiple recognition objects UP.

[0153] Based on the detection results obtained by the image processing unit 36, the image processing unit 36 ​​calculates correction data for correcting the displacement of the surface of the sewing object S.

[0154] Here, in storage device 35 (refer to) Figure 14 The sewing data stored in the ) includes the target pattern RP of the stitch CH formed on the sewing object S, the position coordinates of the identification object UP, and the movement conditions of the holding component 15.

[0155] The target pattern RP defines the target shape of the stitch CH formed on the sewing object S and the target position of the stitch CH in the sewing machine coordinate system.

[0156] The movement conditions of the holding component 15 include the movement trajectory of the holding component 15 as defined in the sewing machine coordinate system. The movement trajectory of the holding component 15 includes the movement trajectory of the holding component 15 in the XY plane. The movement conditions of the holding component 15 are determined based on the target pattern RP.

[0157] The target pattern RP of the sewing data is generated under the premise that the sewing object S has not shrunk, and is stored in the control device 30. When displacement occurs on the surface of the sewing object S, the image processing unit 36 ​​calculates the displacement of the detected identification object UP and generates correction data for correcting the sewing data.

[0158] The image processing unit 36 ​​sends the correction data calculated by the image processing unit 36 ​​to the control device 30. The control device 30 performs the sewing process based on the correction data.

[0159] [Sewing action]

[0160] Figure 13 This is a flowchart for explaining the sewing operation of the sewing machine 1 according to this embodiment. The sewing operation of the sewing machine 1 includes image capture processing S11, image stitching processing S12, object detection processing S13, correction data calculation processing S14, sewing processing S15, and end determination processing S16.

[0161] (Photo processing)

[0162] The imaging process S11 involves photographing the sewn object S using multiple imaging devices 37. The operator Ma, or the control device 30, pre-sets whether to acquire an image of an enlarged imaging area 43A extending in the X-axis direction using imaging unit 40A, or an image of an enlarged imaging area 43B extending in the Y-axis direction using imaging unit 40B. The control device 30 moves the holding member 15 that holds the sewn object S, positioning it at a pre-set imaging position. If the holding member 15 is positioned at the corresponding imaging position Pf, the image processing unit 36 ​​performs imaging using the pre-set multiple imaging devices 37.

[0163] Below, as an example, we will discuss the process of... Figure 15 The following describes the case where each of the imaging devices 37 of the imaging unit 40A acquires an image of the expanded imaging area 43A. In this case, the image processing unit 36 ​​acquires an image corresponding to the imaging field of view 42A and an image corresponding to the imaging field of view 42B via the imaging devices 37 of the mounting unit 41A and the mounting unit 41B.

[0164] (Image stitching processing)

[0165] Image stitching processing S12 is a process of stitching together images of the sewn object S captured by multiple shooting devices 37. Figure 15 This is a schematic diagram illustrating the image joining process S12.

[0166] like Figure 5As shown, the image obtained by the imaging device 37 via the mounting portion 41A is set as a first image 44. The image obtained by the imaging device 37 via the mounting portion 41B is set as a second image 45. In this case, the second image 45 contains a region on the +X direction side with respect to the first image 44. The first image 44 corresponds to the imaging field 42A, and the second image 45 corresponds to the imaging field 42B. The first image 44 and the second image 45 share the overlapping region JA.

[0167] In the overlapping region JA of the first image 44 and the second image 45, there is an image element GE common to at least a part of the recognition target UP. That is, as shown, in the case where the recognition target UP is an arrangement of a plurality of holes 7 existing in the sewing target object S in a prescribed pattern, the image element GE is an image of each hole 7. The hole 7 is a structural element constituting the recognition target UP or the reference pattern DPh. In the case where the recognition target UP is a pattern of a plurality of holes 7, the image element GE is an image of each hole 7. Figure 15 Figure 15 In the case where the recognition target UP is an arrangement of a plurality of holes 7 existing in the sewing target object S in a prescribed pattern, the image element GE is an image of each hole 7. The hole 7 is a structural element constituting the recognition target UP or the reference pattern DPh. In the case where the recognition target UP is a pattern of a plurality of holes 7, the image element GE is an image of each hole 7.

[0168] As shown, the image processing portion 36 detects the image element GE contained in the overlapping region JA of the first image 44 and the image element GE contained in the overlapping region JA of the second image 45, respectively. The position coordinates of the imaging centers of the imaging devices 37 mounted to the mounting portions 41A, 41B and the sizes of the imaging fields 42A, 42B are known, and thus the range of the overlapping region JA in each image is known. The image processing portion 36 selects three or more image elements GE contained in the overlapping region JA, and deforms the second image 45 so that the selected image elements GE coincide with each other with respect to the first image 44. The deformation of the second image 45 is performed, for example, based on an affine transformation. By the deformation, the overlapping region JA of the first image 44 and the deformed second image 45 (hereinafter referred to as the second image 45A) coincide with each other in the image. Figure 14

[0169] The image processing portion 36 generates a composite image 46 in which the first image 44 and the second image 45A are joined. With respect to the pixels constituting the overlapping region JA, one of the first image 44 and the second image 45A can be adopted, or the pixel information of both can be averaged, etc. In this way, in the image joining process S12, the composite image 46 of a size corresponding to the enlarged imaging region 43A is generated.

[0170] (Recognition target detection process)

[0171] Next,​​Figure 16 The recognition object detection processing S13 is processing of detecting the recognition object UP from the composite image 46 generated by the image joining processing S12, and acquiring the position coordinates of the detected recognition object UP. Figure 16 is a schematic view for explaining the recognition object detection processing S13.

[0172] As shown in Figure 16 , the image processing section 36 extracts an image of a recognition area AR in which the detection processing of the recognition object UP is performed, from the composite image 46. The recognition area AR is set to a range in which an assumed positional deviation amount of the recognition object UP accompanying the formation of a stitch with respect to the design position coordinates of the recognition object UP set in the sewing data is taken into account. Figure 5 The setting of the recognition area AR with respect to the arbitrary-shaped target pattern RP is schematically shown. The image processing section 36 sets the recognition area AR for each of a plurality of recognition objects UP that should be detected in one stitch formation, and acquires an extraction image obtained by clipping the image of the set recognition area AR. For example, in the example of Figure 14 , the recognition area AR is set for each of the seven recognition objects UP from the recognition object UP1 to the recognition object UP7.

[0173] The image processing section 36 sequentially performs image recognition processing by the template matching method with respect to each of the acquired extraction images. The image processing section 36 reads out the intrinsic template data 72 from the storage 35, and acquires the position coordinates of the recognition object UP in the extraction image (recognition area AR) by matching with the intrinsic template data 72.

[0174] Through the recognition object detection processing S13, the image processing section 36 acquires the position coordinates in the sewing machine coordinate system of each of the recognition objects UP (UP1 to UP7) that should be detected in one stitch formation.

[0175] (Correction data calculation processing)

[0176] The correction data calculation processing S14 is processing of calculating correction data for correcting the displacement of the surface of the sewing object S, based on the detection result obtained by the recognition object detection processing S13. The image processing section 36 calculates the displacement amount of the recognition object UP from the initial position to the current position, based on the initial position and the current position of the recognition object UP involved in the present sewing processing. The initial position of the recognition object UP is the design position coordinates of the recognition object UP set in the sewing data. The current position of the recognition object UP is the position coordinates of the recognition object UP detected by the recognition object detection processing S13. The image processing section 36 calculates the correction data for each of the correction points CP on the target pattern RP (refer to Figures 11 to 16The correction position coordinates are calculated, and the correction data of the target pattern RP passing through the correction point CP is calculated so that the stitch CH is formed at the target position in the sewing machine coordinate system. Furthermore, in the initial sewing process (first sewing process), no displacement of the surface of the sewing object S associated with stitch formation occurs, and therefore no displacement of the identification object UP occurs. Therefore, in the initial sewing process (first sewing process), the target pattern RP in the initial state specified by the sewing data is used directly, and thus correction data is not calculated.

[0177] (Sewing process)

[0178] Sewing process S15 is a process of forming stitch CH based on target pattern RP. Sewing process S15 is implemented by controlling each part of sewing machine 1 via control device 30. The sewing process includes a first sewing process to an Nth sewing process. The first sewing process is implemented based on the target pattern RP in an initial state specified by sewing data. In the first sewing process, control device 30 outputs control commands to actuator 17 to form stitch CH according to the target pattern RP in the initial state specified by sewing data. The second to Nth sewing processes are implemented based on correction data (corrected target pattern RP) calculated by correction data calculation process S14. In the second sewing process and thereafter, control device 30 obtains correction data from image processing unit 36 ​​and outputs control commands to actuator 17 to form stitch CH according to the obtained correction data target pattern RP.

[0179] The end-of-process determination S16 is a process that determines whether the sewing process of the object S has ended. The control device 30 determines whether the sewing process of the object S has ended based on the sewing data. If the sewing process has ended from the first to the (N-1)th sewing process, the control device 30 determines in the end-of-process determination S16 that the sewing process has not ended. If the sewing process has ended at the Nth time, the control device 30 determines in the end-of-process determination S16 that the sewing process has ended.

[0180] Therefore, the following series of processes are repeated in the first to the Nth sewing processes: at the end of each sewing process, the following processes are performed: image capture process S11, image joining process S12, object detection process S13, and correction data calculation process S14. The correction data for the next sewing process is calculated, and the next sewing process is performed based on the calculated correction data.

[0181] As mentioned above, in Figure 12In the example shown, the plurality of sewing machines 1 possessed by the sewing system 100 each have a plurality of imaging devices 37 having overlapping regions JA in which the imaging fields of view (42A and 42B, 42C and 42D) partially overlap. Moreover, the image recognition processing based on the template data (inherent template data 72) is performed with respect to a composite image 46 that is created by joining a plurality of images obtained from the plurality of imaging devices 37.

[0182] Thus, the plurality of recognition targets UP detected in the sewing processing of one stitch CH can be detected from the composite image 46 obtained by the plurality of imaging devices 37 in one imaging. As a result, the processing time required for the imaging processing S11, the recognition target detection processing S13, and the correction data calculation processing S14 performed at each sewing processing is shortened compared to the case in which the recognition targets UP are imaged and detected one by one by one imaging device 37.

[0183] On the other hand, in the case in which a large-scale composite image 46 is created by joining the images obtained from the plurality of imaging devices 37, the imaging field of view of each imaging device 37 also becomes large, and the influence of fluctuations in the imaging conditions of each imaging device 37 also becomes large. Thus, compared to the case in which the recognition targets UP are simply imaged and detected one by one by one imaging device 37, the influence of the difference between the imaging conditions at the time of creating the template data 70 of the first sewing machine SM1 and the imaging conditions of the second sewing machine SM2 on the image recognition processing is also large. Thus, the structure of the present embodiment in which the difference between the imaging conditions of the template data 70 and the imaging conditions of the second sewing machine SM2 can be corrected by the inherent data 60 is effective for improving the recognition accuracy in the image recognition processing using the composite image 46.

[0184] [Effects]

[0185] As described above, according to the present embodiment, the second sewing machine SM2 (the sewing machine 1 having the second imaging device 37) performs the image recognition processing using the template data (the intrinsic template data 72) corrected based on the intrinsic data 60B of the second imaging device 37. Thereby, in the second sewing machine SM2, it is possible to correct the template data 70 created by the first sewing machine SM1 (the sewing machine 1 having the first imaging device 37) and reflecting the imaging conditions unique to the first sewing machine SM1, and perform the image recognition processing in a manner matching the imaging conditions unique to the second sewing machine SM2. Therefore, it is possible to create the template data 70 without performing the creation individually for each of the plurality of sewing machines 1 included in the sewing system 100. In addition, the manager Mb can manage only one template data 70 (the generalized template data 71) created by the first sewing machine SM1 in the data processing section 50, and does not need to manage each template data (the intrinsic template data 72) for each of the sewing machines 1. As a result, it is possible to reduce the working hours and the management hours of data related to the image recognition in the sewing system 100 having the plurality of sewing machines 1. Further, the second sewing machine SM2 can also perform the image recognition processing using the template data 70 created by the first sewing machine SM1, and correct the recognition result of the image recognition processing based on the intrinsic data 60B of the second sewing machine SM2, and in this case as well, it is possible to reduce the working hours and the management hours of data related to the image recognition.

[0186] Also, as shown in Figure 13 , ​ , for the structure in which one sewing machine 1 has a plurality of imaging devices 37 (i.e., the first imaging device 37 and the second imaging device 37), it is also possible to correct the template data 70 created by the first imaging device 37 based on the intrinsic data 60 of the second imaging device 37, or correct the image recognition result using the template data 70 based on the intrinsic data 60 of the second imaging device 37, thereby obtaining the same effect.

[0187] Further, according to the present embodiment, the data processing section 50 has the master data management section 51A that creates the generalized template data 71, and thus can exclude elements that are generated due to the unique data 60A of the first sewing machine SM1 from the template data 70 created by the first sewing machine SM1 (the sewing machine 1 having the first photographing device 37). As a result, when creating the unique template data 72 of the second sewing machine SM2 (the sewing machine 1 having the second photographing device 37), it is not necessary to use the unique data 60A of the first sewing machine SM1 as the creation source of the template data 70 each time, and thus it is possible to reduce the data management man-hours. Further, the data processing section 50 has the data adjustment section 51B that creates the unique template data 72 for each photographing device based on the generalized template data 71 and the unique data 60, and thus it is possible to obtain the unique template data 72 that is suitable for the second sewing machine SM2 even without correcting the image recognition result of the second sewing machine SM2 each time.

[0188] [Other Embodiments]

[0189] In the above embodiment, an example is shown in which the unique template data 72 for the second sewing machine SM2 is created from the template data 70 of the first sewing machine SM1 and transmitted to the second sewing machine SM2, but the correction of the template data according to the present application is not limited to the above example. The data processing section 50 can directly transmit the template data 70 and the unique data 60A of the first sewing machine SM1 to the second sewing machine SM2, and the second sewing machine SM2 can correct the template data 70 based on the difference between the unique data 60A of the first sewing machine SM1 and the unique data 60B of the second sewing machine SM2 (create the unique template data 72). Further, in the case where the difference in photographing conditions is small, the image recognition processing can be performed using the template data 70 of the first sewing machine SM1 directly in the second sewing machine SM2, and the recognition result obtained using the template data 70 can be corrected based on the difference between the unique data 60A of the first sewing machine SM1 and the unique data 60B of the second sewing machine SM2.

[0190] In the above embodiment, the master data management section 51A that creates the generalized template data 71 is provided to the data processing section 50, but the generalized template data 71 can not be created. As described above, the unique template data 72 of the second sewing machine SM2 can be created using the template data 70 and the unique data 60A of the first sewing machine SM1 and the unique data 60B of the second sewing machine SM2. In this case, the template data 70 and the unique data 60A of the first sewing machine SM1 can be managed as master data without using the generalized template data 71.

[0191] In the above embodiment, the data adjustment section 51B that creates the unique template data 72 for each sewing machine is provided in the data processing section 50, but the data processing section 50 can not have the data adjustment section 51B. The data processing section 50 can transmit the generalized template data 71 to each of the second sewing machines SM2, and each of the second sewing machines SM2 can create the unique template data 72 using the unique data 60B thereof.

[0192] In the above embodiment, the example in which the plurality of imaging devices 37 are provided in the sewing machine 1 and the image recognition processing is performed using the composite image 46 in which the plurality of images are joined is shown, but the sewing machine 1 can have one imaging device 37. The sewing machine 1 can perform the image recognition processing for each of a plurality of images obtained by imaging the sewing object S a plurality of times.

[0193] The present application includes the following modes. (1)

[0195] A sewing system has: a plurality of imaging devices that acquire images of a sewing object; one or more sewing machines that sew based on a recognition result obtained by image recognition processing of the sewing object; and a data processing section that acquires template data of the sewing object created based on an image captured by a first imaging device of the plurality of imaging devices, and transmits the template data to a second imaging device, the sewing machine has unique data including a capturing condition of the imaging device, the sewing machine has the second imaging device, the image recognition processing is performed using the template data corrected based on the unique data of the second imaging device, or a recognition result obtained using the template data is corrected based on the unique data of the second imaging device. (2)

[0197] In the sewing system described in (1), the unique data includes a pixel rate, a capturing offset, and illumination information of the imaging device. (3)

[0199] In the sewing system described in (1) or (2), the data processing section has a master data management section that creates generalized template data in which template data is generalized based on the template data and the unique data of the first imaging device, the sewing machine has the second imaging device, perform image recognition processing using the intrinsic template data corrected using the intrinsic data based on the local machine, or correct the recognition result obtained using the generalized template data based on the intrinsic data based on the local machine. (4)

[0201] In the sewing system described in (3), The data processing section has a data adjustment section that acquires the intrinsic data of the plurality of photographing devices, creates the intrinsic template data for each of the photographing devices based on the intrinsic template data including the generalized template data or the intrinsic data of the photographing device used at the time of template creation, and the intrinsic data, The sewing machine having the second photographing device performs image recognition processing using the intrinsic template data of the local machine acquired from the data processing section. (5)

[0203] In any one of the sewing systems described in (1) to (4), The sewing machine has a plurality of photographing devices having an overlapping region in which photographing fields partially overlap, and performs image recognition processing based on the template data with respect to a composite image obtained by joining a plurality of images obtained from the plurality of photographing devices. (6)

[0205] A sewing method using a plurality of sewing machines having photographing devices that acquire images of a sewing object, or a sewing method using a sewing machine having a plurality of photographing devices, In the sewing method, the following steps are included: acquiring template data of the sewing object created based on images photographed by a first photographing device among the plurality of sewing machines or the plurality of photographing devices, and transmitting the template data to another second photographing device; and In the sewing machine having the second photographing device, performing image recognition processing using the template data corrected based on intrinsic data including photographing conditions of the second photographing device, or correcting the recognition result obtained using the template data based on the intrinsic data.

[0206] This application is based on Japanese Patent Application No. 2023-108670 filed on June 30, 2023, the content of which is incorporated herein by reference.

Claims

1. A sewing system comprising: Multiple imaging devices acquire images of the object being sewn; One or more sewing machines that sew based on recognition results obtained through image recognition processing of the object being sewn; and The data processing unit acquires template data of the sewn object based on images captured by the first of the plurality of shooting devices, and sends it to the other second shooting devices. The sewing machine has inherent data including the shooting conditions of the shooting device. The sewing machine equipped with the second shooting device, Image recognition processing is performed using the template data corrected based on the inherent data of the second imaging device, or... The recognition results obtained using the template data are corrected based on the inherent data of the second imaging device.

2. The sewing system according to claim 1, wherein, The inherent data includes the pixel rate of the shooting device, the shooting offset, and the lighting information.

3. The sewing system according to claim 1 or 2, wherein, The data processing unit includes a master data management unit, which creates generalized template data based on the template data and inherent data of the first shooting device. The sewing machine equipped with the second shooting device, Image recognition processing is performed using native template data that has been corrected from the generalized template data based on the native data, or... The recognition results obtained using the generalized template data are corrected based on the inherent data of the local machine.

4. The sewing system according to claim 3, wherein, The data processing unit includes a data adjustment unit that acquires the inherent data of the plurality of shooting devices, and based on the inherent template data including the generalized template data or the inherent data of the shooting devices used when the template is created, creates inherent template data for each of the shooting devices. The sewing machine equipped with the second imaging device performs image recognition processing using the machine's inherent template data obtained from the data processing unit.

5. The sewing system according to claim 1 or 2, wherein, The sewing machine has multiple shooting devices with overlapping areas where the shooting fields of view partially overlap. The sewing machine performs image recognition processing based on the template data for a composite image formed by combining multiple images obtained from the multiple shooting devices.

6. A sewing method using multiple sewing machines, each sewing machine having an imaging device for acquiring an image of an object to be sewn, and sewing based on a recognition result obtained through image recognition processing of the object to be sewn; or, the sewing method using sewing machines having multiple said imaging devices. This sewing method includes the following steps: Obtain template data of the sewn object created based on images captured by the first camera among the plurality of sewing machines or camera devices, and send it to the other second camera devices; and In the sewing machine equipped with the second shooting device Image recognition processing is performed using the template data, which has been corrected based on inherent data including the shooting conditions of the second shooting device, or... The recognition results obtained using the template data are corrected based on the inherent data.

Images