Sewing efficiency detection method and system based on sewing machine worker action analysis, medium and terminal

Abstract

The invention provides a sewing efficiency detection method and system based on sewing machine worker action analysis, a medium and a terminal. The method comprises the following steps of obtaining a motor starting time point and a motor stopping time point of sewing equipment; obtaining a turner sewing image of a time period between the adjacent motor stop time point and the motor start time point; based on the sewing image of the turner, acquiring the action duration of each sewing action executed by the turner, wherein the sewing actions comprise cutting piece taking, cutting piece sewing, cutting piece arranging and cutting piece placing; and obtaining the sewing efficiency of the lathe worker based on the sewing action and the action duration. According to the sewing efficiency detection method and system based on sewing turner action analysis, the medium and the terminal, the turner sewing efficiency is detected based on action recognition of the sewing turner and action data of the sewing machine, and the method and the system are rapid and efficient.

Description

Technical Field

[0001] This application belongs to the technical field of data processing, and relates to a sewing efficiency detection method, system, medium, and terminal based on the action analysis of sewing workers. Background Art

[0002] Currently, garment factories generally face the problem of identifying and improving the sewing efficiency of sewing workers. To improve sewing efficiency, it is necessary to accurately identify which actions of employees are slower during the sewing process and which links have room for optimization.

[0003] In the prior art, Internet of Things sewing equipment has basically replaced ordinary sewing machines. With the development of the Internet of Things system, Internet of Things sewing equipment can provide real-time sewing information of sewing workers. Therefore, how to achieve the efficiency detection of sewing workers based on the sewing information of sewing workers has become an important problem to be solved in the current garment production field. Summary of the Invention

[0004] The purpose of this application is to provide a sewing efficiency detection method, system, medium, and terminal based on the action analysis of sewing workers, which can quickly and efficiently count the sewing efficiency of sewing workers based on the action recognition of sewing workers and the action data of sewing machines.

[0005] In a first aspect, this application provides a sewing efficiency detection method based on the action analysis of sewing workers. The method includes the following steps: obtaining the motor start time point and the motor stop time point of the sewing equipment; obtaining the sewing image of the sewing worker during the time period between adjacent motor stop time points and motor start time points; obtaining the action duration of the sewing worker performing each sewing action based on the sewing image of the sewing worker, where the sewing actions include picking up the cut piece, sewing the cut piece, trimming the cut piece, and placing the cut piece; obtaining the sewing efficiency of the sewing worker based on the sewing actions and the action duration.

[0006] In one implementation manner of the first aspect, obtaining the motor start time point and the motor stop time point of the sewing equipment includes the following steps: obtaining the event data of the sewing equipment; the event data includes the event generation time and the event type; taking the event generation times corresponding to the motor start and motor stop as the motor start time point and the motor stop time point.

[0007] In one implementation manner of the first aspect, obtaining the action duration of the sewing worker performing each sewing action based on the sewing image of the sewing worker includes the following steps: obtaining the hand distance of the sewing worker in the sewing image of the sewing worker; When the hand distance at the motor stop time point is less than or equal to the preset threshold, it is determined that the sewing action at the motor stop time point is for a whole cut piece, and the sewing action at the next motor start time point corresponding to the motor stop time point is for a sewn cut piece; When the hand distance at the motor stop time point is greater than the preset threshold, it is determined that the sewing action at the motor stop time point is for a released cut piece, and the sewing action at the next motor start time point corresponding to the motor stop time point is for a sewn cut piece; the sewing action at the time point with the maximum hand distance between the motor stop time point and the next motor start time point is for picking up a cut piece; The duration between the motor stop time point corresponding to the whole cut piece and the next motor start time point is used as the whole cut piece duration; the duration between the motor start time point corresponding to the sewn cut piece and the next motor stop time point is used as the sewn cut piece duration; the duration between the motor stop time point corresponding to the released cut piece and the time point of the picked-up cut piece is used as the released cut piece duration; the duration corresponding to the time point of the picked-up cut piece and the next motor start time point is used as the picked-up cut piece duration.

[0008] In one implementation manner of the first aspect, obtaining the hand distance of the sewing worker in the sewing worker image includes the following steps: Obtain the hand position of the sewing worker in the sewing worker image based on the target detection model; Obtain the depth image of the sewing worker image based on the depth estimation model, and use the image depth corresponding to the hand position in the depth image as the hand distance.

[0009] In one implementation manner of the first aspect, the target detection model uses the YOLO model; the depth estimation model uses the depth anything model.

[0010] In one implementation manner of the first aspect, obtaining the sewing efficiency of the sewing worker based on the sewing action and the action duration includes the following steps: Obtain the benchmark action duration corresponding to each sewing action; Calculate the sewing efficiency of the sewing worker based on the action duration and the benchmark action duration, and the sewing efficiency of the sewing worker includes the cut piece sewing efficiency and the sewing action efficiency.

[0011] In a second aspect, the present application provides a sewing efficiency detection system based on sewing worker action analysis, and the system includes a time point acquisition module, an image acquisition module, a judgment module, and a detection module; The time point acquisition module is used to acquire the motor start time point and the motor stop time point of the sewing device; The image acquisition module is used to acquire the sewing image of the worker during the time period between adjacent motor stop time points and motor start time points; The judgment module is configured to obtain the action duration of each sewing action performed by the lathe worker based on the lathe worker sewing image, and the sewing actions include picking up the cut piece, sewing the cut piece, trimming the cut piece, and placing the cut piece; The detection module is configured to obtain the sewing efficiency of the lathe worker based on the sewing action and the action duration.

[0012] In a third aspect, the present application provides a terminal, which includes: a processor and a memory; The memory is used to store a computer program; The processor is configured to execute the computer program stored in the memory, so that the terminal executes the above-mentioned sewing efficiency detection method based on the analysis of the sewing lathe worker's actions.

[0013] In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a terminal, it implements the above-mentioned sewing efficiency detection method based on the analysis of the sewing lathe worker's actions.

[0014] In a fifth aspect, the present application provides a sewing efficiency detection system based on the analysis of the sewing lathe worker's actions, including a sewing device and the above-mentioned terminal; The sewing device includes an information collection module and an image collection module; The information collection module is configured to collect the motor start time point and the motor stop time point of the sewing device, and provide them to the terminal; The image collection module is configured to collect the lathe worker sewing image during the time period between adjacent motor stop time points and motor start time points, and provide it to the terminal.

[0015] As described above, the sewing efficiency detection method, system, medium, and terminal based on the analysis of the sewing lathe worker's actions according to the present application have the following beneficial effects.

[0016] (1) Detecting the sewing efficiency of the lathe worker based on the action recognition of the sewing lathe worker and the action data of the sewing machine is fast and efficient.

[0017] (2) Using a depth detection algorithm and an object detection algorithm for action recognition of the sewing lathe worker provides information support for subsequent sewing efficiency detection.

[0018] (3) Avoiding the misdetection of sewing efficiency caused by simply relying on the action data of the sewing device effectively improves the accuracy of sewing efficiency detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It shows a flowchart of the sewing efficiency detection method based on the analysis of the sewing lathe worker's actions according to the present application in an embodiment.

[0020] Figure 2Schematic diagram showing the event data of the present application in an embodiment.

[0021] Figure 3 Schematic diagram showing the motor start time point and the motor stop time point in the present application in an embodiment.

[0022] Figure 4 Schematic diagram showing the hand position in the present application in an embodiment.

[0023] Figure 5 Schematic diagram showing the sewing image of a sewing worker and the corresponding depth image in the present application in an embodiment.

[0024] Figure 6 Schematic structural diagram showing the sewing efficiency detection system based on sewing worker motion analysis in the present application in an embodiment.

[0025] Figure 7 Schematic structural diagram showing the terminal of the present application in an embodiment.

[0026] Figure 8 Schematic structural diagram showing the sewing efficiency detection system based on sewing worker motion analysis in the present application in another embodiment. Detailed implementation manners

[0027] The following uses specific specific examples to illustrate the implementation manners of the present application. Those skilled in the art can easily understand 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 implementation manners. Various 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, without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0028] It should be noted that the diagrams provided in the following embodiments only illustrate the basic concept of the present application in a schematic manner. Therefore, only the components related to the present application are shown in the diagrams, rather than being drawn according to the number, shape, and size of the components in actual implementation. The type, quantity, and ratio of each component in its actual implementation can be arbitrarily changed, and the component layout type may also be more complex.

[0029] In addition, in this application, descriptions such as "first" and "second" are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include at least one such feature. In addition, the technical solutions between various embodiments can be combined with each other, but it must be based on the ability of those of ordinary skill in the art to implement. When the combination of technical solutions results in contradictions or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0030] As Figure 1 shown, in one embodiment, the sewing efficiency detection method based on sewing worker motion analysis of this application includes steps S1 - S4.

[0031] Step S1: Obtain the motor start time point and the motor stop time point of the sewing equipment.

[0032] Specifically, an information collection module is provided in the sewing equipment of this application. The information collection module is used to collect the event data of the sewing equipment. As Figure 2 shown, the event data includes the event occurrence time, event type, and event parameters. In one embodiment, the event type can be represented by digital numbers such as 0, 1, 2, etc. For example, 2 represents motor start, 3 represents motor stop, and 6 and 7 respectively represent the thread cutting and post - thread cutting actions of the sewing equipment. The event parameters represent the parameter information involved in the corresponding event type. For example, for an event with the event type of motor stop, its event parameter is the number of stitches sewn this time. Therefore, obtain the event data of the sewing equipment, and use the event generation times corresponding to the event types of motor start and motor stop as the motor start time point and the motor stop time point. As Figure 3 shown, the time point marked in red is the motor stop time point; the time point marked in blue is the motor start time point.

[0033] Step S2: Obtain the sewing worker's sewing image during the time period between adjacent motor stop time points and motor start time points.

[0034] Specifically, in this application, the sewing worker's sewing operation is divided into four actions: picking up the cut piece, sewing the cut piece, trimming the cut piece, and placing the cut piece. Among them, picking up the cut piece is the starting process of the sewing operation, indicating going to pick up the cut piece to be sewn. Sewing the cut piece is the intermediate process of the sewing operation, indicating sewing the cut piece. Trimming the cut piece is the intermediate process of the sewing operation, indicating trimming the cut piece. Placing the cut piece is the ending process of the sewing operation, indicating placing the sewn cut piece. Therefore, for one cut piece, its sewing operation is successively picking up the cut piece, sewing the cut piece, trimming the cut piece, sewing the cut piece... (the number of times of trimming the cut piece and sewing the cut piece depends on different sewing requirements), and placing the cut piece.

[0035] An image acquisition module, such as a camera, is provided on the sewing device. The image acquisition module is used to acquire images of the sewing operator during sewing operations, that is, the operator sewing images. When the motor starts, the operator performs sewing operations; when the motor stops, the operator trims or places the cut pieces. That is to say, at the motor stop time point, the operator trims or places the cut pieces; at the next motor start time point, the operator sews the cut pieces. And for picking up the cut pieces, it occurs between the motor stop time point and the next motor start time point. Therefore, in order to identify the sewing actions of the operator, it is necessary to acquire the operator sewing images during the time period between adjacent motor stop time points and motor start time points to identify the operator's actions through the operator sewing images.

[0036] Step S3: Obtain the action duration of the operator performing each sewing action based on the operator sewing images, where the sewing actions include picking up the cut pieces, sewing the cut pieces, trimming the cut pieces, and placing the cut pieces.

[0037] Specifically, obtaining the action duration of the operator performing each sewing action based on the operator sewing images includes the following steps.

[0038] 31) Obtain the hand distance of the operator in the operator sewing images.

[0039] Among them, obtaining the hand distance of the operator in the operator sewing images includes the following steps.

[0040] a) Based on the object detection model, obtain the hand position of the operator in the operator sewing images.

[0041] Among them, object detection is a computer vision technology that uses neural networks to classify and locate objects (such as people, buildings, or cars) in images or videos. The object detection model takes an image as input and then outputs the bounding box coordinates of the detected objects and the labels for identifying these objects. Therefore, in this application, an object detection model is used to identify the hand position of the operator in the operator sewing images. YOLO (You Only Look Once) is a set of real-time object detection machine learning algorithms. Preferably, in this application, the YOLO model is used to identify the hand position of the operator in the operator sewing images. As Figure 4 shown, based on the YOLO model, the hand position can be accurately located. Among them, the YOLO model outputs the predicted box coordinates of the hand, and the center point of the predicted box coordinates is the hand coordinate.

[0042] b) Based on the depth estimation model, obtain the depth image of the operator sewing images, and use the image depth corresponding to the hand position in the depth image as the hand distance.

[0043] Among them, the image depth information refers to the distance information of each pixel point in the image to the camera, which is used to describe the three-dimensional structure of the scene in computer vision. There are various methods to obtain the image depth information, including using lidar, structured light, binocular cameras, deep learning models, etc. In this application, a depth estimation model is used to obtain the depth image of the lathe worker sewing image. The depth estimation model can identify the depth at each position in the image. Preferably, this application uses the depthanything model to obtain the depth image of the lathe worker sewing image. The depth anything model adopts a monocular depth estimation algorithm, and by using large-scale unlabeled data and data augmentation techniques, it improves the generalization ability and zero-shot performance of the model.

[0044] As Figure 5 shown, the greater the depth, the farther the object is from the camera; the smaller the depth, the closer the object is to the camera. Therefore, in this application, the image depth corresponding to the hand position in the depth image is used as the hand distance.

[0045] 32) When the hand distance at the motor stop time point is less than or equal to the preset threshold, it is determined that the sewing action at the motor stop time point is a whole cut piece, and the sewing action at the next motor start time point corresponding to the motor stop time point is a sewn cut piece.

[0046] Among them, a preset threshold is set to judge the distance between the lathe worker's hand and the camera according to the preset threshold. Among them, the preset threshold is obtained and updated through multiple learning processes.

[0047] 33) When the hand distance at the motor stop time point is greater than the preset threshold, it is determined that the sewing action at the motor stop time point is a release cut piece, and the sewing action at the next motor start time point corresponding to the motor stop time point is a sewn cut piece; the sewing action at the time point with the maximum hand distance from the motor stop time point to the next motor start time point is a pick-up cut piece.

[0048] Among them, according to the sewing operation sequence of the cut pieces, that is, pick up the cut piece, sew the cut piece, trim the cut piece, sew the cut piece... put down the cut piece. When the hand distance at the motor stop time point is less than or equal to the preset threshold, it indicates that the hand of the sewing worker is close to the camera, then it is determined that the sewing action at the motor stop time point is trimming the cut piece, and the sewing action at the next motor start time point corresponding to the motor stop time point is sewing the cut piece. When the hand distance at the motor stop time point is greater than the preset threshold, it indicates that the hand of the sewing worker is far from the camera, then it is determined that the sewing action at the motor stop time point is putting down the cut piece, and the sewing action at the next motor start time point corresponding to the motor stop time point is sewing the cut piece; at the same time, the sewing action at the time point with the maximum hand distance from the motor stop time point to the next motor start time point is picking up the cut piece. For example, assuming that the depth data change of the sewing worker's hand is [10, 20, 10], and the difference between the latter term and the former term is [10, -10], then the time point when the image depth is 20 at this time is the time point of picking up the cut piece, that is, the moment when the hand is farthest from the camera during the action of moving away from and then approaching the camera.

[0049] 34) Take the duration between the motor stop time point corresponding to the trimmed cut piece and the next motor start time point as the trimmed cut piece duration; take the duration between the motor start time point corresponding to the sewn cut piece and the next motor stop time point as the sewn cut piece duration; take the duration between the motor stop time point corresponding to the put-down cut piece and the time point of picking up the cut piece as the put-down cut piece duration; take the duration corresponding to the time point of picking up the cut piece and the next motor start time point as the picking-up cut piece duration.

[0050] Step S4, obtain the sewing efficiency of the sewing worker based on the sewing action and the action duration.

[0051] Specifically, for each cut piece, the benchmark action durations of its corresponding various sewing actions are preset. Based on the benchmark action duration and the action duration, the sewing efficiency of the sewing worker can be calculated. Among them, calculate the sum of the benchmark action durations of each sewing action corresponding to a cut piece to obtain the total benchmark action duration; sum up the action durations of each sewing action of the sewing worker for this cut piece to obtain the total action duration; calculate the ratio of the total action duration to the total benchmark action duration as the cut piece sewing efficiency. Calculate the ratio of the action duration of a sewing action of a cut piece to the benchmark action duration as the sewing action efficiency. By calculating the sewing efficiency of the sewing worker, the efficiency parameters of the sewing worker during the sewing process can be accurately obtained, providing data support for improving the sewing efficiency in the future.

[0052] In summary, through depth estimation and object detection, the present application realizes the accurate recognition of the sewing actions of the sewing worker, and then accurately detects the sewing efficiency, avoiding the misdetection of the sewing efficiency caused by simply relying on the action data of the sewing equipment, and effectively improving the accuracy of the sewing efficiency detection.

[0053] The protection scope of the sewing efficiency detection method based on the sewing worker's motion analysis described in the embodiments of the present application is not limited to the execution order of the steps listed in this embodiment. Any solution achieved by adding or subtracting steps of the prior art and replacing steps according to the principle of the present application is included in the protection scope of the present application.

[0054] The embodiments of the present application further provide a sewing efficiency detection system based on the sewing worker's motion analysis. The sewing efficiency detection system based on the sewing worker's motion analysis can implement the sewing efficiency detection method described in the present application. However, the implementation devices of the sewing efficiency detection system based on the sewing worker's motion analysis described in the present application include, but are not limited to, the structures of the sewing efficiency detection system listed in this embodiment. Any structural deformation and replacement of the prior art made according to the principle of the present application are included in the protection scope of the present application.

[0055] As Figure 6 shown, in one embodiment, the present application provides a sewing efficiency detection system based on the sewing worker's motion analysis, including a time point acquisition module 61, an image acquisition module 62, a judgment module 63, and a detection module 64.

[0056] The time point acquisition module 61 is used to acquire the motor start time point and the motor stop time point of the sewing device.

[0057] The image acquisition module 62 is connected to the time point acquisition module 61 and is used to acquire the sewing worker's sewing images during the time period between adjacent motor stop time points and motor start time points.

[0058] The judgment module 63 is connected to the hand information acquisition module 62 and is used to obtain the action duration of the sewing worker performing each sewing action based on the sewing worker's sewing images. The sewing actions include picking up the cut piece, sewing the cut piece, trimming the cut piece, and placing the cut piece. The detection module 64 is connected to the judgment module 63 and is used to obtain the sewing efficiency of the sewing worker based on the sewing actions and the action duration.

[0059] Among them, the structures and principles of the time point acquisition module 61, the image acquisition module 62, the judgment module 63, and the detection module 64 correspond one by one to the steps in the above-mentioned sewing efficiency detection method based on the sewing worker's motion analysis, so they will not be elaborated here.

[0060] In several embodiments provided by the present application, it should be understood that the disclosed system, device or method can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of modules / units is only a logical function division. In actual implementation, there may be other division methods. 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 displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces. The indirect coupling or communication connection of devices or modules or units can be in electrical, mechanical or other forms.

[0061] The modules / units described as separate components may or may not be physically separated. The components shown as modules / units may or may not be physical modules, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules / units can be selected according to actual needs to achieve the purpose of the embodiments of the present application. For example, in each embodiment of the present application, the functional modules / units can be integrated in a processing module, or each module / unit can exist physically alone, or two or more modules / units can be integrated in one module / unit.

[0062] Those of ordinary skill in the art should further realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0063] The embodiments of the present application also provide a computer-readable storage medium. Those of ordinary skill in the art can understand that all or part of the steps in the methods of the above embodiments can be completed by instructing a processor through a program. The program can be stored in a computer-readable storage medium, and the storage medium is a non-transitory medium, such as random access memory, read-only memory, flash memory, hard disk, solid-state drive, magnetic tape, floppy disk, 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 integrating one or more available media. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, or a magnetic tape), an optical medium (such as a digital video disc (DVD)), or a semiconductor medium (such as a solid-state disk (SSD)).

[0064] The embodiments of the present application also provide a terminal. The terminal includes a processor and a memory.

[0065] The memory is used to store a computer program.

[0066] The memory includes various media that can store program codes, such as ROM, RAM, magnetic disks, USB flash drives, memory cards, or optical discs.

[0067] The processor is connected to the memory and is used to execute the computer program stored in the memory, so that the terminal executes the above sewing efficiency detection method based on the action analysis of sewing workers.

[0068] Preferably, the processor can be a general-purpose processor, including a central processing unit (CPU for short), a network processor (NP for short), etc.; it can also be a digital signal processor (DSP for short), an application specific integrated circuit (ASIC for short), a field programmable gate array (FPGA for short), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0069] Such as Figure 7As shown, the terminal of the present application is presented 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 71, a memory 72, and a bus 73 that connects different system components (including the memory 72 and the processing unit 71).

[0070] The bus 73 represents one or more of several types of bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. By way of example, these architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.

[0071] 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.

[0072] The memory 72 may include computer system-readable media in the form of volatile memory, such as random access memory (RAM) 721 and / or cache memory 722. The terminal may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, a storage system 723 may be used for reading and writing on non-removable, non-volatile magnetic media ( Figure 7 not shown, commonly referred to as a "hard disk drive"). Although Figure 7 not shown in the figure, a disk drive for reading and writing on a removable non-volatile disk (such as a "floppy disk"), and an optical disk drive for reading and writing on a removable non-volatile optical disk (such as a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 73 through one or more data media interfaces. The memory 72 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 embodiments of the present application.

[0073] A program / utility 724 having a set (at least one) of program modules 7241 may be stored, for example, in the memory 72. Such program modules 7241 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include the implementation of a network environment. The program modules 7241 generally perform the functions and / or methods in the embodiments described in the present application.

[0074] The terminal can also communicate with one or more external devices (such as a keyboard, a pointing device, a display, etc.), and can also communicate with one or more devices that enable a user to interact with the terminal, and / or communicate with any device that enables the terminal to communicate with one or more other computing devices (such as a network card, a modem, etc.). Such communication can be carried out through the input / output (I / O) interface 74. Moreover, the terminal can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through the network adapter 75. As Figure 7 shown, the network adapter 75 communicates with other modules of the terminal through the bus 73. It should be understood that, although not shown in the figure, other hardware and / or software modules can be used in combination 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, etc.

[0075] As Figure 8 shown, in one embodiment, the sewing efficiency detection system based on the sewing worker motion analysis of the present application includes a sewing device 81 and the above-mentioned terminal 82.

[0076] The sewing device 81 includes an information collection module 811 and an image collection module 812.

[0077] The information collection module 811 is used to collect the motor start time point and the motor stop time point of the sewing device and provide them to the terminal 82. Among them, the information collection module 811 conducts data communication with the terminal 82 in a wired or wireless manner.

[0078] The image collection module 812 is used to collect the sewing worker sewing image during the time period between adjacent motor stop time points and motor start time points and provide it to the terminal 82. Among them, the image collection module 812 conducts image communication with the terminal 82 in a wired or wireless manner. Preferably, the image collection module 812 adopts devices such as a camera and a camera, and the collected sewing worker sewing image is a two-dimensional image.

[0079] It should be noted that the terminal 82 can be set on the sewing device 81 for local processing; or it can be set in the cloud for cloud processing. When the terminal 82 is set in the cloud, one terminal can simultaneously detect the sewing efficiency of multiple sewing devices.

[0080] The above embodiments are only illustrative of the principles and effects of the present application and are not intended to limit the present application. Any person familiar with this technology can modify or change the above embodiments without departing from the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by those with ordinary knowledge in the technical field without departing from the spirit and technical ideas disclosed in the present application should still be covered by the claims of the present application.

Claims

1. A sewing efficiency detection method based on the analysis of the actions of sewing workers, characterized in that, The method includes the following steps: Obtain the motor start time point and the motor stop time point of the sewing device; Obtain the sewing image of the turner during the time period between adjacent motor stop time points and motor start time points; Based on the sewing image of the turner, obtain the action duration of each sewing action performed by the turner. The sewing actions include picking up the cut piece, sewing the cut piece, trimming the cut piece, and placing the cut piece; Obtain the sewing efficiency of the turner based on the sewing action and the action duration.

2. The sewing efficiency detection method based on the sewing worker's motion analysis according to claim 1, wherein Obtaining the motor start time point and the motor stop time point of the sewing device includes the following steps: Obtain the event data of the sewing device; the event data includes the event generation time and the event type; Use the event generation times corresponding to the motor start and motor stop as the motor start time point and the motor stop time point.

3. The sewing efficiency detection method based on the sewing worker's motion analysis according to claim 1, wherein Based on the sewing image of the turner, obtaining the action duration of each sewing action performed by the turner includes the following steps: Obtain the hand distance of the turner in the sewing image of the turner; When the hand distance at the motor stop time point is less than or equal to the preset threshold, determine that the sewing action at the motor stop time point is trimming the cut piece, and the sewing action at the next motor start time point corresponding to the motor stop time point is sewing the cut piece; When the hand distance at the motor stop time point is greater than the preset threshold, determine that the sewing action at the motor stop time point is placing the cut piece, and the sewing action at the next motor start time point corresponding to the motor stop time point is sewing the cut piece; the sewing action at the time point with the maximum hand distance from the motor stop time point to the next motor start time point is picking up the cut piece; Use the duration between the motor stop time point corresponding to trimming the cut piece and the next motor start time point as the trimming duration; use the duration between the motor start time point corresponding to sewing the cut piece and the next motor stop time point as the sewing duration; use the duration between the motor stop time point corresponding to placing the cut piece and the time point of picking up the cut piece as the placing duration; use the duration corresponding to the time point of picking up the cut piece and the next motor start time point as the picking up duration.

4. The sewing efficiency detection method based on the action analysis of sewing workers according to claim 3, characterized in that Obtaining the hand distance of the turner in the sewing image of the turner includes the following steps: Based on the target detection model, obtain the hand position of the turner in the sewing image of the turner; Based on the depth estimation model, obtain the depth image of the sewing image of the turner, and use the image depth corresponding to the hand position in the depth image as the hand distance.

5. The sewing efficiency detection method based on the action analysis of sewing workers according to claim 4, characterized in that, The target detection model uses the YOLO model; the depth estimation model uses the depth anything model.

6. The sewing efficiency detection method based on the action analysis of sewing workers according to claim 1, characterized in that, Based on the sewing action and the action duration, obtaining the sewing efficiency of the turner includes the following steps: Obtain the reference action duration corresponding to each sewing action; Calculate the sewing efficiency of the turner based on the action duration and the reference action duration. The sewing efficiency of the turner includes the cut piece sewing efficiency and the sewing action efficiency.

7. A sewing efficiency detection system based on the analysis of sewing worker's actions, characterized in that, The system includes a time point acquisition module, an image acquisition module, a judgment module, and a detection module; The time point acquisition module is used to obtain the motor start time point and the motor stop time point of the sewing device; The image acquisition module is used to acquire the sewing images of the lathe worker during the time period between adjacent motor stop time points and motor start time points; The judgment module is used to obtain the action duration of the lathe worker performing each sewing action based on the sewing images of the lathe worker, and the sewing actions include picking up the cut piece, sewing the cut piece, trimming the cut piece, and placing the cut piece; The detection module is used to obtain the sewing efficiency of the lathe worker based on the sewing actions and the action duration.

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 used to execute the computer programs stored in the memory, so that the terminal executes the sewing efficiency detection method based on the analysis of the sewing actions of the lathe worker 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 the terminal, it implements the sewing efficiency detection method based on the analysis of the sewing actions of the lathe worker according to any one of claims 1 to 6.

10. A sewing efficiency detection system based on the action analysis of sewing workers, characterized in that, It includes a sewing device and the terminal according to claim 8; The sewing device includes an information acquisition module and an image acquisition module; The information acquisition module is used to acquire the motor start time point and the motor stop time point of the sewing device and provide them to the terminal; The image acquisition module is used to acquire the sewing images of the lathe worker during the time period between adjacent motor stop time points and motor start time points and provide them to the terminal.

Images