Sewing process self-identification method and system, medium and terminal

Abstract

The invention provides a sewing process self-recognition method and system, a medium and a terminal, and the method comprises the following steps: constructing a sewing process template for a sewing action, the sewing process template being generated based on a sewing image and sewing parameters; acquiring a real-time sewing image of the employee; acquiring real-time sewing parameters of the sewing machine; and based on the sewing process template, obtaining a sewing process identification result corresponding to the real-time sewing image and the real-time sewing parameter. According to the sewing process self-recognition method and system, the medium and the terminal, the sewing process is accurately recognized based on the sewing image and the sewing parameters of the sewing machine, and rapidness and high efficiency are achieved.

Description

Technical Field

[0001] The present application belongs to the field of data processing technology and relates to a sewing process self-identification method, system, medium and terminal. Background Art

[0002] In the garment production process, improving production efficiency has always been the focus of the industry. However, the existing production management method mainly relies on manual records and simple timekeeping tools, which has the following shortcomings:

[0003] (1) It is difficult to accurately divide the time of each process, especially the working time statistics of key actions such as "taking the cloth, arranging, sewing, and placing the cloth" have large errors;

[0004] (2) Lack of real-time monitoring and analysis capabilities for each link in the production process, resulting in managers being unable to quickly locate specific links with low production efficiency;

[0005] (3) When dividing the process, once an error occurs, it may lead to errors in the division of all subsequent processes, affecting the accuracy of the overall data;

[0006] (4) Lack of in-depth analysis capabilities for production data and inability to provide effective optimization suggestions.

[0007] IoT-enabled sewing equipment has already largely replaced conventional sewing machines. With the development of IoT systems, these devices can provide real-time sewing information to operators. Therefore, identifying and improving sewing machine operator efficiency requires a critical challenge in garment production: identifying sewing steps using IoT-enabled sewing equipment.

[0008] Application Contents

[0009] The purpose of this application is to provide a sewing process self-identification method, system, medium and terminal, which can accurately identify the sewing process based on the sewing image and sewing parameters of the sewing machine, quickly and efficiently.

[0010] In a first aspect, the present application provides a method for self-identification of sewing processes, the method comprising the following steps: constructing a sewing process template for a sewing action, the sewing process template being generated based on a sewing image and sewing parameters; obtaining a real-time sewing image of an employee; obtaining real-time sewing parameters of a sewing machine; and based on the sewing process template, obtaining a sewing process identification result corresponding to the real-time sewing image and the real-time sewing parameters.

[0011] In an implementation of the first aspect, constructing a sewing process template includes the following steps:

[0012] Acquire sewing images and sewing parameters within a preset time period; the sewing parameters include sewing start, sewing stop, and sewing in progress;

[0013] Acquiring the distance between the employee's hands based on the sewing image and determining whether there is fabric in the sewing area;

[0014] Constructing a sewing state array based on sewing start and stop time points, wherein the sewing state array records the sewing state of the sewing machine based on a preset interval, wherein the sewing state includes sewing start, sewing in progress, and sewing stop;

[0015] Constructing a cloth presence array, wherein the cloth presence array records whether there is cloth in the sewing area based on the preset interval;

[0016] Constructing a two-hand distance array, wherein the two-hand distance array records the employee's two-hand distance information based on the preset interval;

[0017] Obtaining the period lengths of the sewing state array, the cloth presence array, and the hands distance array, and obtaining the sewing state sub-array, the cloth presence sub-array, and the hands distance sub-array of each period based on the period lengths;

[0018] Selecting a sewing state subarray template, a cloth presence subarray template, and a hands distance subarray template based on the sewing state subarray, the cloth presence subarray, and the hands distance subarray of each cycle;

[0019] The sewing process template is constructed based on the sewing state sub-array template, the cloth presence sub-array template and the two-hand distance sub-array template.

[0020] In an implementation of the first aspect, obtaining the period lengths of the sewing state array, the fabric presence array, and the two-hand distance array comprises the following steps:

[0021] Calculating autocorrelation values ​​of the sewing state array, the fabric presence array, and the two-hand distance array at different lag values;

[0022] When the autocorrelation values ​​of the sewing state array, the cloth presence array, and the two-hand distance array all reach peak values ​​and the difference between the peak values ​​is less than a first preset difference, the average of the peak values ​​is selected as the process peak value;

[0023] The duration between the peaks of adjacent processes is taken as the cycle length.

[0024] In an implementation of the first aspect, obtaining the period lengths of the sewing state array, the fabric presence array, and the two-hand distance array comprises the following steps:

[0025] Performing Fourier transform on the sewing state array, the cloth presence array, and the hands distance array respectively to obtain a sewing state frequency domain array, a cloth presence frequency domain array, and a hands distance frequency domain array;

[0026] Obtaining peak values ​​of the sewing state frequency domain array, the fabric presence frequency domain array, and the hands distance frequency domain array;

[0027] When the difference between the peak values ​​is less than a second preset difference, selecting the mean of the peak values ​​as the process peak value;

[0028] The duration between the peaks of adjacent processes is taken as the cycle length.

[0029] In an implementation of the first aspect, selecting a sewing state subarray template, a cloth presence subarray template, and a hands distance subarray template based on the sewing state subarray, the cloth presence subarray, and the hands distance subarray of each cycle includes the following steps:

[0030] Get the preset process duration;

[0031] Remove the sewing state sub-array, the fabric presence sub-array, and the hands distance sub-array whose cycle length is greater than the preset process time;

[0032] Among the remaining sewing state sub-arrays, fabric presence sub-arrays, and two-hand distance sub-arrays, the sewing state sub-arrays, fabric presence sub-arrays, and two-hand distance sub-arrays located in the middle are selected as the sewing state sub-array templates, the fabric presence sub-array templates, and the two-hand distance sub-array templates.

[0033] In an implementation of the first aspect, obtaining, based on the sewing process template, a sewing process recognition result corresponding to the real-time sewing image and the real-time sewing parameters includes the following steps:

[0034] Obtaining a real-time sewing state array, a real-time cloth presence array, and a real-time two-hand distance array corresponding to the real-time sewing image and the real-time sewing parameters;

[0035] Comparing the real-time sewing state array, the real-time cloth presence array, and the real-time hands distance array with the sewing state sub-array template, the cloth presence sub-array template, and the hands distance sub-array template, respectively;

[0036] When the sub-arrays of the real-time sewing state array, the real-time cloth presence array, and the real-time two-hand distance array under the same cycle length all match the sewing state sub-array template, the cloth presence sub-array template, and the two-hand distance sub-array template, it is identified as a sewing process of the sewing action.

[0037] In a second aspect, the present application provides a sewing process self-identification system, the system comprising a construction module, a first acquisition module, a second acquisition module and an identification module;

[0038] The construction module is used to construct a sewing process template for a sewing action, wherein the sewing process template is generated based on a sewing image and sewing parameters;

[0039] The first acquisition module is used to acquire the real-time sewing movements of employees;

[0040] The second acquisition module is used to obtain the real-time sewing parameters of the sewing machine;

[0041] The recognition module is used to obtain a sewing process recognition result corresponding to the real-time sewing image and the real-time sewing parameters based on the sewing process template.

[0042] In a third aspect, the present application provides a terminal, comprising: a processor and a memory;

[0043] The memory is used to store computer programs;

[0044] The processor is used to execute the computer program stored in the memory, so as to enable the terminal to execute the above-mentioned sewing process self-identification method.

[0045] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the above-mentioned sewing process self-identification method when executed by a terminal.

[0046] In a fifth aspect, the present application provides a sewing process self-identification system, comprising the above-mentioned terminal and a sewing machine;

[0047] The sewing machine includes an image acquisition module and an information acquisition module;

[0048] The image acquisition module is used to collect real-time sewing images of the sewing machine and provide them to the terminal;

[0049] The information acquisition module is used to collect real-time sewing parameters of the sewing machine and provide them to the terminal.

[0050] As described above, the sewing process self-identification method, system, medium, and terminal described in this application have the following beneficial effects:

[0051] (1) Accurately identify sewing processes based on sewing machine sewing images and sewing parameters, quickly and efficiently;

[0052] (2) Effectively avoid the problem of error accumulation during process identification;

[0053] (3) It can monitor each link of the sewing process in real time, quickly locate the specific reasons for low efficiency, and effectively improve the work efficiency and management level of clothing production. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 Shown is a flow chart of a sewing process self-identification method in one embodiment of the present application;

[0055] Figure 2 A schematic diagram showing the peak values ​​of the autocorrelation values ​​of the sewing state array, the fabric presence array, and the two-hand distance array in one embodiment of the present application;

[0056] Figure 3 A schematic diagram showing the period lengths of the sewing state frequency domain array, the fabric presence frequency domain array, and the hand distance frequency domain array in one embodiment of the present application;

[0057] Figure 4 Shown is a schematic structural diagram of a sewing process self-identification system according to an embodiment of the present application;

[0058] Figure 5 Shown is a schematic structural diagram of a terminal in one embodiment of the present application;

[0059] Figure 6 Shown is a structural schematic diagram of another embodiment of the sewing process self-identification system of the present application. DETAILED DESCRIPTION

[0060] The following describes the embodiments of the present application through specific examples. Those skilled in the art can easily understand the other advantages and effects of the present application from the content disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments. The details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other unless they conflict.

[0061] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application. Therefore, the illustrations only show components related to the present application and are not drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component can be changed at will, and the component layout type may also be more complicated.

[0062] In addition, the descriptions of "first", "second", etc. in this application are for descriptive purposes only and should not be understood as indicating or implying their relative importance or implicitly indicating the number of the technical features indicated. Therefore, the features defined as "first" or "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions between the various embodiments can be combined with each other, but this must be based on the fact that they can be implemented by ordinary technicians in this field. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0063] like Figure 1 As shown, in one embodiment, the sewing process self-identification method of the present application includes steps S1 to S4.

[0064] Step S1: constructing a sewing process template for a sewing action, wherein the sewing process template is generated based on a sewing image and sewing parameters.

[0065] Specifically, in the garment production process, employees' sewing actions are divided into four types: taking fabric, sewing fabric, arranging fabric, and placing fabric. Among them, taking fabric is the starting process of the sewing operation, which means taking the fabric to be sewn. Sewing fabric is the intermediate process of the sewing operation, which means sewing fabric. Arranging fabric is the intermediate process of the sewing operation, which means arranging fabric. Placing fabric is the ending process of the sewing operation, which means placing the sewn fabric. Usually, one employee is only responsible for one sewing action. Therefore, this application constructs a corresponding sewing process template for each sewing action to perform self-identification of the process of the corresponding sewing action.

[0066] In this application, the sewing process template is generated based on the sewing image and sewing parameters. In one embodiment, constructing the sewing process template includes the following steps:

[0067] 11) Acquire sewing images and sewing parameters within a preset time period; the sewing parameters include sewing start, sewing stop, and sewing in progress.

[0068] The employee can perform multiple sewing actions within the preset time period. For example, the preset time period is one hour. An image acquisition module, such as a camera, is used to capture images of the employee sewing. An information acquisition module, such as a sensor, is used to capture sewing machine parameters, such as when the sewing machine starts and stops, when sewing is in progress, and the number of stitches between starts and stops.

[0069] 12) Based on the sewing image, the distance information between the employee's hands is obtained and whether there is cloth in the sewing area is determined.

[0070] The sewing image is subjected to image recognition to obtain the distance information between the worker's hands and detect whether there is fabric placed in the sewing area of ​​the sewing machine. Preferably, the distance information between the worker's hands is represented by the difference in the coordinates of the center of gravity of the worker's hands.

[0071] 13) Constructing a sewing state array based on the sewing start and stop time points, wherein the sewing state array records the sewing state of the sewing machine based on a preset interval, and the sewing state includes sewing start, sewing in progress, and sewing stop.

[0072] Among them, a preset interval is set to collect the sewing parameters and the distance information of the employee's hands, as well as to detect whether there is fabric in the sewing area. For example, when collecting data every 30 milliseconds, 3600 data can be collected in one hour. According to the collected sewing parameters, a sewing status array can be constructed. Different numerical values ​​are used in the sewing status array to represent sewing start, sewing in progress and sewing stop. For example, the sewing status array = {2,2,2,2,2,2,2,3,3,3,3,3,6,6,}, where 2 represents sewing in progress, 3 represents sewing machine stop, and 6 represents sewing machine start. 100 consecutive 2s represent a sewing state for 3 consecutive seconds.

[0073] 14) Constructing a fabric presence array, wherein the fabric presence array records whether fabric exists in the sewing area based on the preset interval.

[0074] Based on the presence of fabric in the detected sewing area, information is collected at preset intervals to construct a fabric presence array, with different values ​​indicating the presence of fabric. For example, the fabric presence array = {0,0,0,0,0,0,0,0,1,1,1,0,0,0,1,1,1}, where 0 indicates the absence of fabric in the sewing area and 1 indicates the presence of fabric in the sewing area.

[0075] 15) Constructing a two-hand distance array, wherein the two-hand distance array records the employee's two-hand distance information based on the preset interval.

[0076] The data is collected at preset intervals based on the distance between the worker's hands, and a hand distance array is constructed. For example, the hand distance array = {110, 108, 122, 56, 55, 62, 75, 100, 400}. The data in the array is the number of pixels between the centers of gravity of the hands in the sewing image.

[0077] 16) Obtaining the period lengths of the sewing state array, the fabric presence array, and the hands distance array, and obtaining the sewing state sub-array, the fabric presence sub-array, and the hands distance sub-array of each period based on the period lengths.

[0078] Because the same employee performs the same sewing action, the sewing status array, the fabric presence array, and the hands distance array exhibit a certain periodic pattern. Specifically, one cycle length completes one sewing process. By analyzing each of these arrays separately, the cycle length of each array can be determined. Based on these cycle lengths and the time sequence from sewing start to sewing stop, the corresponding arrays are divided into sewing status sub-arrays, fabric presence sub-arrays, and hands distance sub-arrays.

[0079] In one embodiment, the cycle length is obtained by autocorrelation calculation. Specifically, obtaining the cycle length of the sewing state array, the fabric presence array, and the hands distance array includes the following steps:

[0080] a) calculating the autocorrelation values ​​of the sewing state array, the fabric presence array, and the two-hand distance array at different lag values.

[0081] For each array, the autocorrelation value of the array and the lag array is calculated separately. When the lag value is equal to the period length, the autocorrelation value reaches a local maximum. The autocorrelation value is expressed as Where a(i) represents the sewing status array, the fabric presence array, or the hand distance array, N represents the array length, and k represents the hysteresis value.

[0082] b) When the autocorrelation values ​​of the sewing state array, the fabric presence array, and the two-hand distance array all reach peak values ​​and the difference between the peak values ​​is less than a first preset difference, the average of the peak values ​​is selected as the process peak value.

[0083] like Figure 2 As shown, the peak values ​​of the autocorrelation values ​​of the sewing state array, the fabric presence array, and the two-hand distance array are obtained. When the peak values ​​of the three arrays converge, that is, the difference is less than a first preset difference, the average of the three peak values ​​is calculated as the process peak value. The first preset difference value is a custom value and can also be adjusted through learning.

[0084] c) The duration between the peaks of adjacent processes is taken as the cycle length.

[0085] The duration of the peak time of adjacent processes is the cycle length of a sewing process.

[0086] In another embodiment, the array is converted to the frequency domain, and the frequency of the periodic signal appears as a peak in the spectrum, thereby obtaining the period length. Specifically, obtaining the period length of the sewing state array, the fabric presence array, and the hand distance array includes the following steps:

[0087] a) performing Fourier transform on the sewing state array, the cloth presence array, and the two-hand distance array, respectively, to obtain a sewing state frequency domain array, a cloth presence frequency domain array, and a two-hand distance frequency domain array.

[0088] b) obtaining peak values ​​of the sewing state frequency domain array, the fabric presence frequency domain array, and the two-hand distance frequency domain array.

[0089] like Figure 3 As shown, the peak value of each frequency domain array can be obtained according to the spectrum.

[0090] c) When the difference between the peak values ​​is less than a second preset difference, selecting the mean of the peak values ​​as the process peak value.

[0091] When the peak values ​​of the three frequency domain arrays are clustered together, that is, the difference is less than a second preset difference, the average of the three peak values ​​is calculated as the process peak value. The second preset difference is a user-defined value that can also be adjusted through learning.

[0092] d) The duration between the peak values ​​of adjacent processes is taken as the cycle length.

[0093] The duration of the peak time of adjacent processes is the cycle length of a sewing process.

[0094] 17) Selecting a sewing state subarray template, a cloth presence subarray template, and a hands distance subarray template based on the sewing state subarray, the cloth presence subarray, and the hands distance subarray of each cycle.

[0095] First, a preset process duration is obtained, which can be a statistical value of the process duration. Then, to eliminate abnormal data in the array, the sewing status subarray, fabric presence subarray, and hands distance subarray whose cycle lengths are greater than the preset process duration are removed, thereby ensuring data accuracy and reliability. Finally, among the remaining sewing status subarrays, fabric presence subarrays, and hands distance subarrays, the sewing status subarray, fabric presence subarray, and hands distance subarray located in the middle are selected as the sewing status subarray template, the fabric presence subarray template, and the hands distance subarray template. It should be noted that when the number of remaining arrays is odd, the array at the most central position is selected. When the number of remaining arrays is even, either of the two arrays at the most central position is selected.

[0096] 18) Constructing the sewing process template based on the sewing state sub-array template, the cloth presence sub-array template and the hands distance sub-array template.

[0097] Step S2: Acquire the real-time sewing image of the employee.

[0098] Specifically, based on an image acquisition module such as a camera, real-time sewing images of employees are collected.

[0099] Step S3: Acquire the real-time sewing parameters of the sewing machine.

[0100] Specifically, based on an information collection module such as a sensor, real-time sewing images of the sewing machine are collected.

[0101] Step S4: Based on the sewing process template, obtaining a sewing process recognition result corresponding to the real-time sewing image and the real-time sewing parameters.

[0102] First, a real-time sewing state array, a real-time cloth presence array, and a real-time two-hand distance array corresponding to the real-time sewing image and the real-time sewing parameters are obtained.

[0103] Next, the real-time sewing status array, the real-time cloth presence array, and the real-time hands distance array are compared with the sewing status sub-array template, the cloth presence sub-array template, and the hands distance sub-array template, respectively. Specifically, the real-time sewing status array, the real-time cloth presence array, and the real-time hands distance array are checked to see if the sewing status sub-array template, the cloth presence sub-array template, and the hands distance sub-array template exist.

[0104] Finally, when the subarrays of the real-time sewing state array, the real-time cloth presence array, and the real-time hands distance array all match the sewing state subarray template, the cloth presence subarray template, and the hands distance subarray template within the same cycle length, the sewing process of the sewing action is identified. In other words, if the sewing state subarray template, the cloth presence subarray template, and the hands distance subarray template exist within the same cycle length of the real-time sewing state array, the real-time cloth presence array, and the real-time hands distance array, then that cycle length represents a process cycle of the sewing action, thereby achieving accurate sewing process identification.

[0105] The protection scope of the sewing process self-identification method described in the embodiment of the present application is not limited to the execution order of the steps listed in this embodiment. All solutions implemented by adding, reducing, or replacing steps in the existing technology based on the principles of the present application are included in the protection scope of the present application.

[0106] An embodiment of the present application also provides a sewing process self-identification system, which can implement the sewing process self-identification method described in the present application. However, the implementation device of the sewing process self-identification system described in the present application includes but is not limited to the structure of the sewing process self-identification system listed in this embodiment. All structural deformations and replacements of the existing technology made according to the principles of the present application are included in the protection scope of the present application.

[0107] like Figure 4 As shown, in one embodiment, the sewing process self-identification system of the present application includes a construction module 41 , a first acquisition module 42 , a second acquisition module 43 and an identification module 44 .

[0108] The construction module 41 is used to construct a sewing process template for a sewing action, and the sewing process template is generated based on a sewing image and sewing parameters.

[0109] The first acquisition module 42 is used to acquire the real-time sewing movements of employees.

[0110] The second acquisition module 43 is used to acquire the real-time sewing parameters of the sewing machine.

[0111] The recognition module 44 is connected to the construction module 41 , the first acquisition module 42 , and the second acquisition module 43 , and is configured to acquire the real-time sewing image and the sewing process recognition result corresponding to the real-time sewing parameters based on the sewing process template.

[0112] The structures and principles of the construction module 41 , the first acquisition module 42 , the second acquisition module 43 and the identification module 44 correspond one-to-one to the steps in the aforementioned sewing process self-identification method, and therefore will not be described in detail here.

[0113] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices or methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of modules / units is only a logical function division. There may be other division methods in actual implementation. For example, multiple modules or units can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules or units, which can be electrical, mechanical or other forms.

[0114] The modules / units described as separate components may or may not be physically separate, and the components displayed as modules / units may or may not be physical modules, that is, they may be located in one place or distributed across multiple network elements. Some or all of the modules / units may be selected according to actual needs to achieve the purpose of the embodiments of the present application. For example, the functional modules / units in the various embodiments of the present application may be integrated into a processing module, or each module / unit may exist physically separately, or two or more modules / units may be integrated into a single module / unit.

[0115] Those skilled in the art should further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the composition and steps of each example according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0116] The embodiment of the present application also provides a computer-readable storage medium. Those skilled in the art will understand that all or part of the steps in the method for implementing the above embodiment can be completed by instructing the processor through a program, and the program can be stored in a computer-readable storage medium, and the storage medium is a non-transitory medium, such as a random access memory, a read-only memory, a flash memory, a hard disk, a solid-state drive, a magnetic tape, a floppy disk, an optical disc, and any combination thereof. The above storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more available media. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a digital video disc (DVD)), or a semiconductor medium (for example, a solid-state drive (SSD)), etc.

[0117] An embodiment of the present application further provides a terminal comprising a processor and a memory.

[0118] The memory is used to store computer programs.

[0119] The memory includes various media that can store program codes, such as ROM, RAM, magnetic disk, USB flash drive, memory card or optical disk.

[0120] The processor is connected to the memory and is used to execute the computer program stored in the memory so as to enable the terminal to execute the above-mentioned sewing process self-identification method.

[0121] Preferably, the processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0122] like Figure 5 As shown, the terminal of the present application is in the form of a general-purpose computing device. The components of the terminal may include but are not limited to: one or more processors or processing units 51, a memory 52, and a bus 53 connecting different system components (including the memory 52 and the processing unit 51).

[0123] Bus 53 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. Examples of these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0124] The terminal typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the terminal, including volatile and non-volatile media, removable and non-removable media.

[0125] The memory 52 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 521 and / or cache memory 522. The terminal may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 523 may be used to read and write non-removable, non-volatile magnetic media ( Figure 5 Not shown, often called a "hard drive"). Although Figure 5Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 53 via one or more data medium interfaces. The memory 52 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present application.

[0126] A program / utility 524 having a set (at least one) of program modules 5241 may be stored, for example, in memory 52. ​​Such program modules 5241 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may include an implementation of a network environment. Program modules 5241 generally implement the functions and / or methods of the embodiments described herein.

[0127] The terminal may also communicate with one or more external devices (e.g., a keyboard, a pointing device, a display, etc.), one or more devices that enable a user to interact with the terminal, and / or any device that enables the terminal to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed via input / output (I / O) interface 54. Furthermore, the terminal may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network such as the Internet) via network adapter 55. Figure 5 As shown, the network adapter 55 communicates with other modules of the terminal via the bus 53. It should be understood that, although not shown in the figures, other hardware and / or software modules may be used in conjunction with the terminal, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0128] like Figure 6 As shown, in one embodiment, the sewing process self-identification system of the present application includes the above-mentioned terminal 61 and sewing machine 62.

[0129] The sewing machine 62 includes an image acquisition module 621 and an information acquisition module 622 .

[0130] The image acquisition module 621 is connected to the terminal 61 and is used to acquire real-time sewing images of the sewing machine and provide the images to the terminal 61 .

[0131] The information acquisition module 622 is connected to the terminal 61 and is used to collect real-time sewing parameters of the sewing machine and provide them to the terminal 61 .

[0132] It should be noted that the terminal 61 can be set on the sewing machine 62 for local processing or set on the cloud for cloud processing. When the terminal 61 is set on the cloud, one terminal can simultaneously perform sewing process self-identification on multiple sewing machines.

[0133] The above embodiments are merely illustrative of the principles and effects of this application and are not intended to limit this application. Anyone skilled in the art may modify or alter the above embodiments without departing from the spirit and scope of this application. Therefore, all equivalent modifications or alterations made by one of ordinary skill in the art without departing from the spirit and technical concepts disclosed in this application shall be covered by the claims of this application.

Claims

1. A sewing process self-identification method, characterized in that: The method comprises the following steps: Constructing a sewing process template for a sewing action, wherein the sewing process template is generated based on a sewing image and sewing parameters; Get real-time images of employees sewing; Get the real-time sewing parameters of the sewing machine; Based on the sewing process template, a sewing process recognition result corresponding to the real-time sewing image and the real-time sewing parameters is obtained.

2. The sewing process self-identification method according to claim 1, characterized in that: Building a sewing process template involves the following steps: Acquire sewing images and sewing parameters within a preset time period; the sewing parameters include sewing start, sewing stop, and sewing in progress; Acquiring the distance between the employee's hands based on the sewing image and determining whether there is fabric in the sewing area; Constructing a sewing state array based on sewing start and stop time points, wherein the sewing state array records the sewing state of the sewing machine based on a preset interval, wherein the sewing state includes sewing start, sewing in progress, and sewing stop; Constructing a cloth presence array, wherein the cloth presence array records whether there is cloth in the sewing area based on the preset interval; Constructing a two-hand distance array, wherein the two-hand distance array records the employee's two-hand distance information based on the preset interval; Obtaining the period lengths of the sewing state array, the cloth presence array, and the hands distance array, and obtaining the sewing state sub-array, the cloth presence sub-array, and the hands distance sub-array of each period based on the period lengths; Selecting a sewing state subarray template, a cloth presence subarray template, and a hands distance subarray template based on the sewing state subarray, the cloth presence subarray, and the hands distance subarray of each cycle; The sewing process template is constructed based on the sewing state sub-array template, the cloth presence sub-array template and the two-hand distance sub-array template.

3. The sewing process self-identification method according to claim 2, characterized in that: Obtaining the cycle lengths of the sewing state array, the fabric presence array, and the two-hand distance array comprises the following steps: Calculating autocorrelation values ​​of the sewing state array, the fabric presence array, and the two-hand distance array at different lag values; When the autocorrelation values ​​of the sewing state array, the cloth presence array, and the two-hand distance array all reach peak values ​​and the difference between the peak values ​​is less than a first preset difference, the average of the peak values ​​is selected as the process peak value; The duration between the peaks of adjacent processes is taken as the cycle length.

4. The sewing process self-identification method according to claim 2, characterized in that: Obtaining the cycle lengths of the sewing state array, the fabric presence array, and the two-hand distance array comprises the following steps: Performing Fourier transform on the sewing state array, the cloth presence array, and the two-hand distance array respectively to obtain a sewing state frequency domain array, a cloth presence frequency domain array, and a two-hand distance frequency domain array; Obtaining peak values ​​of the sewing state frequency domain array, the fabric presence frequency domain array, and the hands distance frequency domain array; When the difference between the peak values ​​is less than a second preset difference, selecting the mean of the peak values ​​as the process peak value; The duration between the peaks of adjacent processes is taken as the cycle length.

5. The sewing process self-identification method according to claim 2, characterized in that: Selecting a sewing state subarray template, a cloth presence subarray template, and a hands distance subarray template based on the sewing state subarray, the cloth presence subarray, and the hands distance subarray of each cycle includes the following steps: Get the preset process duration; Remove the sewing state sub-array, the fabric presence sub-array, and the hands distance sub-array whose cycle length is greater than the preset process time; Among the remaining sewing state sub-arrays, fabric presence sub-arrays, and two-hand distance sub-arrays, the sewing state sub-arrays, fabric presence sub-arrays, and two-hand distance sub-arrays located in the middle are selected as the sewing state sub-array templates, the fabric presence sub-array templates, and the two-hand distance sub-array templates.

6. The sewing process self-identification method according to claim 2, characterized in that: Based on the sewing process template, obtaining the real-time sewing image and the sewing process recognition result corresponding to the real-time sewing parameters includes the following steps: Obtaining a real-time sewing state array, a real-time cloth presence array, and a real-time two-hand distance array corresponding to the real-time sewing image and the real-time sewing parameters; Comparing the real-time sewing state array, the real-time cloth presence array, and the real-time hands distance array with the sewing state sub-array template, the cloth presence sub-array template, and the hands distance sub-array template, respectively; When the sub-arrays of the real-time sewing state array, the real-time cloth presence array, and the real-time two-hand distance array under the same cycle length all match the sewing state sub-array template, the cloth presence sub-array template, and the two-hand distance sub-array template, it is identified as a sewing process of the sewing action.

7. A sewing process self-identification system, characterized in that: The system includes a construction module, a first acquisition module, a second acquisition module and an identification module; The construction module is used to construct a sewing process template for a sewing action, wherein the sewing process template is generated based on a sewing image and sewing parameters; The first acquisition module is used to acquire the real-time sewing movements of employees; The second acquisition module is used to obtain the real-time sewing parameters of the sewing machine; The recognition module is used to obtain a sewing process recognition result corresponding to the real-time sewing image and the real-time sewing parameters based on the sewing process template.

8. A terminal, characterized in that: The terminal includes: a processor and a memory; The memory is used to store computer programs; The processor is configured to execute the computer program stored in the memory, so as to enable the terminal to execute the sewing process self-identification method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a terminal, the sewing process self-identification method according to any one of claims 1 to 6 is realized.

10. A sewing process self-identification system, characterized in that: comprising the terminal and sewing machine according to claim 8; The sewing machine includes an image acquisition module and an information acquisition module; The image acquisition module is used to acquire real-time sewing images of the sewing machine and provide them to the terminal; The information acquisition module is used to collect real-time sewing parameters of the sewing machine and provide them to the terminal.

Images