A method, apparatus, device, and storage medium for identifying the broken state of a packaging wire.

Abstract

This invention provides a method, apparatus, device, and storage medium for identifying the broken state of a packing line. The method involves acquiring a target environment image of a target packing station; identifying the features of the packing station markers and packing lines in the target environment image; labeling the packing station markers and packing lines; determining the number of packing station markers and packing lines; and comparing the number of packing station markers and packing lines to determine the broken state of the packing line at the target packing station. The image acquisition, image processing, and final conclusion of this invention are all completed by machine equipment, thus greatly improving the accuracy of the judgment and effectively reducing labor costs.

Description

Technical Field

[0001] This invention relates to the field of wire rods, and more particularly to a method, apparatus, device, and storage medium for identifying the broken state of packaged wire. Background Technology

[0002] In steel product manufacturing, the packaging process is a crucial step in wire rod production. The packaging station employs multiple packaging machines, each requiring specific wire for packaging. A break in the packaging wire can lead to serious quality issues in the finished product, making wire breakage identification paramount in the production process. Currently, the most common method for identifying wire breakage relies on experienced workers. However, due to the long operating hours of multiple production lines, a significant amount of manpower is required to identify wire breakage. Furthermore, manual identification is limited by human subjectivity and experience, resulting in uncertainties and unpredictable accuracy.

[0003] Therefore, intelligent monitoring methods are needed throughout the packaging process to detect whether the packaging line is broken in real time, thereby saving more labor costs and improving the accuracy of judgments. Summary of the Invention

[0004] In view of the shortcomings of the prior art, the present invention provides a method, apparatus, device and storage medium for identifying the broken state of a packaging wire, so as to solve the above-mentioned technical problems.

[0005] This invention provides a method, apparatus, device, and storage medium for identifying the broken state of a packing line, comprising: acquiring a target environment image of a target packing station; identifying the packing station marker features and packing line features in the target environment image, marking the packing station markers and packing line identifiers, and determining the number of packing station markers and the number of packing line identifiers; comparing the number of packing station markers and the number of packing line identifiers to determine the broken state of the packing line at the target packing station.

[0006] In one embodiment of the present invention, labeling the packaging station marker and the packaging line marker includes: acquiring multiple sample environmental images of the target station and labeling them to obtain a training sample dataset; training an initial labeling model using the training sample dataset; inputting the target environmental image into the trained labeling model, identifying the packaging station marker features and packaging line features in the target environmental image to obtain a packaging line annotation box and a packaging station marker annotation box, determining the packaging line annotation box as the packaging line marker, and determining the packaging station marker annotation box as the packaging station marker.

[0007] In one embodiment of the present invention, inputting the target environment image into the trained labeling model to identify the packing station marker features and packing line features in the target environment image to obtain the packing line annotation box and the packing station marker annotation box includes: performing rotation box annotation on the plurality of target environment images using rectangular boxes, the rectangular boxes including non-standard rectangular boxes; correcting the non-standard rectangular boxes to standard rectangular boxes and obtaining the angle prediction result of the labeling model; and detecting packing lines and packing station markers with rotation attributes within a preset angle range based on the angle prediction result to obtain the packing line annotation box and the packing station marker annotation box.

[0008] In one embodiment of the present invention, comparing the number of the packaging station marker bits and the number of the packaging line marker bits to determine the packaging line breakage status of the target packaging station includes at least one of the following: when the number of packaging line marker bits and the number of packaging station marker bits of the target packaging station are equal, the packaging line breakage status of the target packaging station is determined to be a no-breakage status; when the number of packaging line marker bits and the number of packaging station marker bits of the target packaging station are not equal, the packaging line breakage status of the target packaging station is determined to be a broken status.

[0009] In one embodiment of the present invention, after comparing the number of markers at the packaging station and the number of markers on the packaging line to determine the broken state of the packaging line at the target packaging station, the method further includes: if there is no broken line, acquiring the next moment image and marking the packaging line annotation box of the next moment image; determining the current moment image as the image to be tracked and marking the packaging line annotation box of the image to be tracked; comparing the number of annotation boxes of the image to be tracked and the number of packaging line annotation boxes of the next moment image, if the number of packaging line annotation boxes of the next moment image is less than the number of packaging line annotation boxes of the image to be tracked, then determining that the broken state of the packaging line at the target packaging station is a broken state.

[0010] In one embodiment of the present invention, after determining the broken state of the packing line at the target packing station, the method further includes: acquiring multiple frames of environmental images of the target station and detecting the broken state of the packing line at the target station in the multiple frames; when at least one frame of the target station is detected to be in a broken state, an alarm message is issued.

[0011] In one embodiment of the present invention, before issuing an alarm message, the method further includes: obtaining the number of frames in which the packaging line of the target workstation is in a disconnected state; if the number of frames in the multi-frame method is greater than or equal to a preset safe frame number threshold, then issuing an alarm message.

[0012] This invention provides a device for identifying the broken state of a packing line, comprising: an image acquisition module for acquiring a target environment image of a target packing station; an identification and annotation module for identifying the packing station marker features and packing line features in the target environment image, annotating the packing station markers and packing line markers, and determining the number of packing station markers and the number of packing line markers; and a state determination module for comparing the number of packing station markers and the number of packing line markers to determine the broken state of the packing line at the target packing station.

[0013] The present invention provides an electronic device, characterized in that the electronic device includes: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the electronic device enables the packaging wire breakage status identification method as described above.

[0014] The present invention provides a computer-readable storage medium, characterized in that it stores a computer program thereon, which, when executed by a computer processor, causes the computer to perform the packaged wire breakage status identification method as described above.

[0015] Beneficial effects: This invention provides a method, apparatus, device, and storage medium for identifying the broken state of a packing line. It acquires a target environment image of a target packing station; identifies the packing station marker features and packing line features in the target environment image; labels the packing station markers and packing line identifiers; and determines the number of packing station markers and packing line identifiers. By comparing the number of packing station markers and the number of packing line identifiers, the broken state of the packing line at the target packing station is determined. The image acquisition, image processing, and final conclusion are all completed by machine equipment, thus greatly improving the accuracy of the judgment and effectively reducing labor costs. Attached Figure Description

[0016] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application. It is obvious that the drawings described below are merely some embodiments of this application, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort. In the drawings:

[0017] Figure 1 This is a schematic diagram of a system architecture for identifying the broken state of packaged wires in a wire yard, as illustrated in an exemplary embodiment of this application.

[0018] Figure 2 This is a flowchart illustrating the steps for identifying the broken state of a packaging wire, as shown in an exemplary embodiment of this application.

[0019] Figure 3 This is an exemplary embodiment of the rotating annotation frame shown in this application;

[0020] Figure 4 This is a schematic diagram of a packaging station shown in an exemplary embodiment of this application;

[0021] Figure 5 This is a block diagram illustrating a wire breakage status identification device according to an exemplary embodiment of this application;

[0022] Figure 6 A schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present application is shown. Detailed Implementation

[0023] The embodiments of the present invention will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and 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 invention. It should be understood that the preferred embodiments are only for illustrating the present invention and not for limiting the scope of protection of the present invention.

[0024] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Therefore, the drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0025] In the following description, numerous details are explored to provide a more thorough explanation of embodiments of the invention. However, it will be apparent to those skilled in the art that embodiments of the invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring embodiments of the invention.

[0026] First, it should be noted that the broken wire status recognition method provided by this invention acquires high-resolution images of the packing station using a camera device, preprocesses the images, and annotates the packing lines and markers. The annotated packing station images are then input into a deep learning network for training to obtain a rotation detection model with a high recognition rate. The detection model is then used to detect the packing lines and markers in the real-time screenshot to obtain their feature information, such as number information. Based on the associated feature information, a logical judgment is made on the packing station scene to determine whether there is a broken packing line, which improves detection efficiency and timeliness, and avoids human error and safety hazards caused by manual judgment.

[0027] Figure 1 This is a schematic diagram of a system architecture for identifying the broken state of packaged wires in a wire yard, as shown in an exemplary embodiment of this application.

[0028] Reference Figure 1 As shown, the system architecture may include an image acquisition device 101 and a computer device 102. The computer device 102 may be at least one of a desktop graphics processing unit (GPU) computer, a GPU computing cluster, or a neural network computer. The image acquisition device acquires environmental images of the packaging station, and then relevant technicians can use the computer device 102 to process these images to determine whether there are any broken lines on the packaging line at the packaging station.

[0029] Indicatively, the image acquisition device 101 first acquires an environmental image of the target packaging station and transmits the environmental image to the computer device 102. After receiving the environmental image of the target packaging station, the computer device 102 first marks the packaging line identifier and the packaging station marker in the environmental image by rotating the annotation model. Then, by comparing the number of packaging line identifiers and the number of packaging station markers, it determines the packaging line breakage status of the packaging station.

[0030] Figure 2 This is a flowchart illustrating the steps for identifying the broken state of a packaging wire, as shown in an exemplary embodiment of this application.

[0031] like Figure 2 As shown, in an exemplary embodiment, the method for identifying the broken state of the packaging wire includes at least steps S210 to S230, which are described in detail below:

[0032] Step S210: Obtain the target environment image of the target packaging station.

[0033] It should be understood that fixed cameras are installed at each packaging station to capture the working status of each station. These fixed cameras capture environmental images of the target packaging station. One or more cameras are positioned around the target station, and the angle of the captured environmental images can be adjusted by changing the camera angles to obtain multiple environmental images that include information about the target packaging station. Ideally, multiple images should capture 360 ​​degrees of the target packaging station.

[0034] In one embodiment of the present invention, multiple high-definition cameras with 2,073,600 pixels are set at different angles of the target packaging station, and the cameras are matched with the work stations so that the relevant cameras can capture images of the working conditions at each work station in the scene. Based on the cameras set at the packaging station, high-resolution environmental images of 1920x1080 are acquired to ensure that the labeling and annotation model can extract accurate image information for training, thereby improving the accuracy of the labeling and annotation model.

[0035] Step S220: Identify the features of the packing station markers and packing lines in the target environment image, mark the packing station markers and packing lines, and determine the number of packing station markers and packing lines.

[0036] The labeling of packaging station markers and packaging line markers includes: acquiring multiple sample environmental images of the target station and labeling them to obtain a training sample dataset; training the initial labeling model using the training sample dataset; inputting the target environmental image into the trained labeling model to identify the packaging station marker features and packaging line features in the target environmental image, obtaining the packaging line annotation box and the packaging station marker annotation box; determining the packaging line annotation box as the packaging line marker and the packaging station marker annotation box as the packaging station marker.

[0037] It should be understood that the annotation of multiple sample environment images is carried out, and the annotation method includes, but is not limited to, manual annotation. No restrictions are placed on the annotation method here. After multiple sample data are annotated, a training sample dataset is generated, which includes multiple sample environment images.

[0038] The target environment image is input into the trained labeling model to identify the features of the packing station marker and packing line in the target environment image, and obtain the packing line annotation box and the packing station marker annotation box. Rotation boxes are generated for multiple target environment images using rectangular boxes, including non-standard rectangular boxes. The minimum bounding rectangle of OpenCV (an open-source computer vision library) is used to correct the non-standard rectangular boxes to standard rectangular boxes, and the angle prediction result of the labeling model is obtained. Based on the angle prediction result, packing lines and packing station markers with rotation attributes are detected within a preset angle range to obtain the packing line annotation box and the packing station marker annotation box.

[0039] It should be understood that due to the near-large-to-small visual effect and rotational properties, multiple packing lines within the camera's field of view may overlap significantly, potentially leading to numerous missed detections by traditional non-rotational detection algorithms. To avoid such missed detections, we innovatively developed a high-precision rotating target detection model by adding angle prediction results to the model output.

[0040] In one embodiment of the present invention, the angular periodicity problem is solved by employing a circular smooth label (CSL) method to increase the error tolerance between adjacent angles. The formula for the circular smooth label method is as follows:

[0041]

[0042] Where g(x) is the window function, r is the radius of the window function, and θ is the angle of the current bounding box.

[0043] It should be understood that the initial environmental images acquired contain diverse environmental information, including complex lighting conditions and task objectives. Therefore, it is necessary to create a dataset with sufficient training significance based on rotation annotation for deep learning model training, in order to obtain the packing line identification information and packing station marker information for the target packing station. The standard rectangular box involved is a parallelogram with one right angle, while the non-standard rectangle is any other quadrilateral that is not a rectangle.

[0044] Figure 3 This is an exemplary embodiment of the rotating annotation frame shown in this application.

[0045] like Figure 3As shown, starting from the top left corner, any packing line or packing station marker in the target environment image is labeled in a clockwise direction to form a quadrilateral label box. The packing lines and packing station markers in the target environment image are labeled using a rotation labeling model (i.e., a marker labeling model). This rotation labeling model detects packing lines and packing station markers based on shape information and determines whether the number of detected packing lines and the number of packing station markers are consistent. If not, it is determined that there is a broken packing line in the scene.

[0046] In one embodiment of the present invention, images of packing stations captured in a specific industrial setting are annotated, learned, and detected, and their bounding boxes (i.e., packing line annotation boxes and packing station marker annotation boxes) are obtained. The positional information of the packing lines and packing station markers in the image is detected through the bounding boxes, and this information is recorded and compiled into a packing station rotation dataset, which is divided into three parts: a training set, a test set, and a validation set. The training set data is used to train a target detection model for packing lines and packing station markers (i.e., an annotation model). During the training of the detection model, the effective information available for training in the annotated training set includes basic image attributes and annotation information. Basic image attributes include: filename, width, height, and depth. Annotation information includes: Xmin, Ymin, Xmax, and Ymax, representing the x-coordinate of the top-left corner, y-coordinate of the top-left corner, the x-coordinate of the bottom-right corner, and the y-coordinate of the bottom-right corner of each bounding box in the image, respectively; and class, i.e., the category of the target object. This paper uses a deep learning network to extract the packaging line markers and packaging station markers within the target bounding boxes of each packaging station's target environment image from the training set images. This results in a rotation detection model (i.e., a marker annotation model) for the packaging lines and markers. This embodiment uses the YOLOv5 neural network, but other models can also be used, such as transformers, RNNs (LSTM), Faster-RCNN, and R3det. During the training of the classification model, the effective information available for training in the labeled training set includes basic image attributes and annotation information. Basic image attributes include: filename, width, height, and depth. Annotation information includes: Xmin, Ymin, Xmax, and Ymax, representing the x-coordinate of the top-left corner, y-coordinate of the top-left corner, the x-coordinate of the bottom-right corner, and the y-coordinate of the bottom-right corner of each target bounding box in the image; and class, which represents the category of the target object, divided into packaging lines and markers, both of which have rotation attributes. By learning the target features and their categories within the target bounding boxes of each packaging station's training set images, a packaging station target classification model is finally obtained.

[0047] It should be understood that, through the above-mentioned rotation annotation model (i.e., the labeling annotation model), the packing lines and packing station markers in the target environment image are respectively labeled with packing line labels and packing station marker labels. The number of packing line labels is the number of packing lines. Similarly, the number of packing station marker labels is the number of packing station markers. Therefore, obtaining the number of packing line labels and the number of packing station marker labels is equivalent to obtaining the number of packing lines and the number of packing station markers. By comparing the number of packing line labels and the number of packing station marker labels, the state of the packing line breakage at the packing station can be determined.

[0048] Step S230: Compare the number of markers at the packaging station with the number of markers on the packaging line to determine the broken state of the packaging line at the target packaging station.

[0049] By comparing the number of markings on the packaging station markers and the number of markings on the packaging line, the broken state of the packaging line at the target packaging station is determined to include at least one of the following: when the number of markings on the packaging line at the target packaging station is equal to the number of markings on the packaging station markers, the broken state of the packaging line at the target packaging station is determined to be a no-broken state; when the number of markings on the packaging line at the target packaging station is not equal to the number of markings on the packaging station markers, the broken state of the packaging line at the target packaging station is determined to be a broken state.

[0050] In one embodiment of the present invention, after annotating the target environment image, the packing line annotation box of the target packing station is obtained as K1, and the packing station mark annotation box is obtained as K2, where K1 is less than K2, then the packing line of the target packing station is determined to be in a broken state.

[0051] In one embodiment of the present invention, after annotating the target environment image, the packing line annotation box of the target packing station is obtained as K3 and the packing station mark annotation box is obtained as K4, where K3 equals K4. Then, it is determined that the packing line of the target packing station is in a state of no breakage.

[0052] After comparing the number of markers at the packaging station and the number of packaging line markers to determine the broken packaging line status of the target packaging station, the method further includes: if there is no broken line, acquiring the image of the next moment and marking the packaging line annotation box of the next moment image; determining the image at the current moment as the image to be tracked and marking the packaging line annotation box of the image to be tracked; comparing the number of annotation boxes of the image to be tracked and the number of packaging line annotation boxes of the next moment image, if the number of packaging line annotation boxes of the next moment image is less than the number of packaging line annotation boxes of the image to be tracked, then determining that the broken packaging line status of the target packaging station is a broken line status.

[0053] In one embodiment of the present invention, two consecutive environmental images of the packing station are acquired, and the packing lines in the two environmental images are labeled respectively. The number of packing line labels in the preceding environmental image is determined by a label count model as S1, and the number of packing line labels in the following environmental image is determined as S2. Comparing S1 and S2, if S1 is greater than S2, then the packing line at the packing station is determined to be broken. By tracking the target within the labeled packing lines, the robustness of the detection results is effectively enhanced, thereby improving the overall accuracy of the detection.

[0054] After determining the broken state of the packing line at the target packing station, the process also includes: acquiring multiple frames of environmental images of the target station and detecting the broken state of the packing line at the target station in multiple frames; when at least one frame of the target station is detected to be in a broken state, an alarm message is issued.

[0055] Before issuing an alarm message, the process also includes: obtaining the number of frames in which the packaging line of the target workstation is in a disconnected state; if the number of frames is greater than or equal to the preset safe frame number threshold, then an alarm message is issued.

[0056] In one embodiment of the present invention, when the packing line at a certain packing station is in a broken state, a preset safety frame threshold for issuing an alarm is set to M. Once it is determined that the packing line at the target packing station is in a broken state, N frames of images are acquired based on that moment, and these N frames are annotated. If it is confirmed that the environmental information of the packing station in these N frames all indicate that the packing line at the packing station is in a broken state, and N is greater than M, then the controller of the packing station is controlled to issue an alarm.

[0057] It should be understood that the packing line markers and packing station markers in the target environment image are obtained based on the rotation annotation model (i.e., the marker annotation model). Then, the number of packing line markers and packing station markers in the target environment image is determined through the marker quantity determination model. The breakage status of the packing line at the target packing station is then determined by comparing the number of packing line markers and the number of packing station markers. When it is determined that the packing line at the target packing station is in a broken state, an alarm can be triggered by detecting the breakage status across multiple frames of images.

[0058] Figure 4 This is a schematic diagram of a packaging station shown in an exemplary embodiment of this application.

[0059] like Figure 4As shown, a certain packaging station includes multiple packaging station markers and multiple packaging lines. Each packaging station marker corresponds to one packaging line. Positions A, B, and C are packaging station markers, while positions a, b, and c are packaging lines. Packing lines a and b are intact, while packaging line c is broken. During image recognition and annotation, a and b will be correctly identified and annotated, while c will not be successfully annotated. Therefore, in the target environment image, when the packaging line at the packaging station is in an unbroken state, the number of packaging station markers and the number of packaging line markers are equal; when the packaging line at the packaging station is in a broken state, the number of packaging station markers is greater than the number of packaging line markers.

[0060] In one embodiment of the present invention, the packing line identifier and packing station marker identifier in the target environment image are obtained by rotating the annotation model (i.e., the identifier annotation model). Then, the number of packing line identifiers and the number of packing station marker identifiers in the target environment image are obtained by using the identifier quantity determination model. The number of packing line identifiers is A1 and the number of packing station marker identifiers is B1. The number of packing line identifiers and the number of packing station marker identifiers are compared. It is found that A1 equals B1, that is, the number of packing line identifiers equals the number of packing station marker identifiers. Therefore, it is determined that the packing line of the target packing station is in the state of no breakage.

[0061] In another embodiment of the present invention, the packing line markers and packing station markers in the target environment image are obtained by rotating the annotation model (i.e., the marker annotation model). Then, the number of packing line markers and the number of packing station markers in the target environment image are obtained by using the marker quantity determination model. The number of packing line markers is A2, and the number of packing station markers is B2. Comparing the number of packing line markers and the number of packing station markers, A2 is less than B2, that is, the number of packing line markers is less than the number of packing station markers. Therefore, the packing line at the target packing station is determined to be in a broken state. Furthermore, multiple frames of environmental images of the packing station are collected for annotation and identification. It is found that the packing line at the target packing station is in a broken state for K consecutive frames, and K is greater than the preset waiting value (safe frame number threshold) K0. Therefore, the alarm device of the target packing station is activated to realize the function of alarming relevant personnel or relevant processing units.

[0062] Figure 5 This is a block diagram illustrating a wire breakage status identification device according to an exemplary embodiment of this application. The device can be applied to... Figure 1 The implementation environment shown is specifically configured in the smart terminal 102. This device can also be applied to other exemplary implementation environments and specifically configured in other devices. This embodiment does not limit the implementation environment to which the device is applicable.

[0063] like Figure 5 As shown, the exemplary cable breakage status recognition device includes: an image acquisition module 510, an identification and labeling module 520, and a status determination module 530.

[0064] The image acquisition module 510 is used to acquire the target environment image of the target packaging station; the labeling module 520 is used to identify the packaging station marker features and packaging line features in the target environment image, label the packaging station markers and packaging line identifiers, and determine the number of packaging station markers and packaging line identifiers; the status determination module 530 is used to compare the number of packaging station markers and packaging line identifiers to determine the broken packaging line status of the target packaging station.

[0065] The status determination module 530 also includes a disconnection status identification module, a disconnection duration determination module, and an alarm module.

[0066] The module includes a disconnection status identification module for identifying the disconnection status of the packaging line at the target packaging station; a disconnection duration determination module for determining the number of frames in which the packaging line at the target station is in a disconnection status; and an alarm module for issuing an alarm when the number of frames in which the packaging line at the target station is in a disconnection status exceeds a preset safety frame threshold.

[0067] It should be noted that the cable breakage status identification device and the cable breakage status identification method provided in the above embodiments belong to the same concept. The specific operation methods of each module and unit have been described in detail in the method embodiments and will not be repeated here. In practical applications, the cable breakage status identification device provided in the above embodiments can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. This is not a limitation here.

[0068] Embodiments of this application also provide an electronic device, including: one or more processors; and a storage device for storing one or more programs, which, when executed by one or more processors, cause the electronic device to implement the cable breakage status identification method provided in the above embodiments.

[0069] Figure 6 A schematic diagram of a computer system suitable for implementing the embodiments of this application is shown. It should be noted that... Figure 6 The computer system 600 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0070] like Figure 6As shown, the computer system 600 includes a Central Processing Unit (CPU) 601, which can perform various appropriate actions and processes, such as executing the methods described in the above embodiments, based on a program stored in Read-Only Memory (ROM) 602 or a program loaded from Storage Section 608 into Random Access Memory (RAM) 603. The RAM 603 also stores various programs and data required for system operation. The CPU 601, ROM 602, and RAM 603 are interconnected via a bus 604. An Input / Output (I / O) interface 605 is also connected to the bus 604.

[0071] The following components are connected to I / O interface 605: an input section 606 including a keyboard, mouse, etc.; an output section 607 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to I / O interface 605 as needed. A removable medium 611, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 610 as needed so that computer programs read from it can be installed into storage section 608 as needed.

[0072] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 609, and / or installed from removable medium 611. When the computer program is executed by central processing unit (CPU) 601, it performs various functions defined in the system of this application.

[0073] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program. Such propagated data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0074] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. Each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, or they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0075] The units described in the embodiments of this application can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0076] Another aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a computer's processor, causes the computer to perform the aforementioned method for identifying the broken state of a packaged wire. This computer-readable storage medium may be included in the electronic device described in the above embodiments, or it may exist independently and not assembled into the electronic device.

[0077] Another aspect of this application provides a computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the cable breakage status identification method provided in the various embodiments described above.

[0078] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. A method for identifying the broken state of a packaging wire, characterized in that, include: Acquire multiple target environment images of the target packaging station; Identify the features of the packing station marker and the packing line in the target environment image, mark the packing station marker and the packing line, and determine the number of packing station markers and the number of packing lines, wherein each packing station marker corresponds to one packing line; By comparing the number of the markings at the packaging station with the number of the packaging line markings, the broken state of the packaging line at the target packaging station can be determined. Specifically, comparing the number of markers at the packaging station and the number of markers on the packaging line determines the broken packaging line status at the target packaging station, which includes at least one of the following: When the number of packaging line markers and the number of packaging station flag markers are equal, the packaging line breakage status of the target packaging station is determined to be a no-breakage status. If the number of packaging line markers and the number of packaging station flag markers are not equal, the packaging line at the target packaging station is determined to be in a broken state.

2. The method for identifying the broken state of a packing wire according to claim 1, characterized in that, The markings for the packing workstation and the packing line include: Acquire multiple sample environmental images of the target workstation and annotate them to obtain a training sample dataset; The initial labeling model is trained using the training sample dataset. The target environment image is input into the trained labeling model to identify the features of the packing station marker and the packing line in the target environment image, thereby obtaining the packing line annotation box and the packing station marker annotation box. The packing line annotation box is determined as the packing line identifier, and the packing station marker annotation box is determined as the packing station marker identifier.

3. The method for identifying the broken state of a packing wire according to claim 2, characterized in that, The target environment image is input into the trained labeling model to identify the packing station marker features and packing line features in the target environment image, resulting in packing line bounding boxes and packing station marker bounding boxes, including: The multiple target environment images are labeled with rotating bounding boxes using rectangular boxes, including non-standard rectangular boxes. The non-standard rectangle is corrected to a standard rectangle, and the angle prediction result of the labeling model is obtained; Based on the angle prediction results, the packing line and packing station marker with rotational attributes are detected within a preset angle range to obtain the packing line annotation frame and the packing station marker annotation frame.

4. The method for identifying the broken state of a packing wire according to claim 1, characterized in that, After comparing the number of markers at the packaging station with the number of markers on the packaging line to determine the broken state of the packaging line at the target packaging station, the method further includes: If there is no broken line, obtain the image of the next moment and mark the packing line annotation box of the next moment image; The image at the current moment is identified as the image to be tracked, and the packing line annotation box of the image to be tracked is marked; Compare the number of bounding boxes in the image to be tracked with the number of bounding boxes in the packaging line of the image at the next moment. If the number of bounding boxes in the packaging line of the image at the next moment is less than the number of bounding boxes in the image to be tracked, then the packaging line at the target packaging station is determined to be in a broken state.

5. The method for identifying the broken state of a packing wire according to any one of claims 1-4, characterized in that, After determining the broken state of the packing line at the target packing station, the process also includes: Acquire multiple frames of environmental images of the target packaging station and detect the broken packaging line status of the target packaging station in the multiple frames; When at least one frame of the target packaging station is detected to have a broken packaging line, an alarm message is issued.

6. The method for identifying the broken state of a packaging wire according to claim 5, characterized in that, Before issuing an alarm message, the following should also be included: The number of frames in which the packing line of the target packing station is in a broken state is obtained. If the number of frames is greater than or equal to a preset safe frame count threshold, an alarm message will be issued.

7. A device for identifying the broken state of a packaging wire, characterized in that, include: The image acquisition module is used to acquire images of the target environment at the target packaging station; The labeling module is used to identify the features of the packing station marker and the packing line in the target environment image, label the packing station marker and the packing line, and determine the number of packing station markers and the number of packing lines, wherein each packing station marker corresponds to one packing line; The status determination module is used to compare the number of marker bits at the packaging station with the number of marker bits on the packaging line to determine the broken state of the packaging line at the target packaging station. Specifically, when the number of marker bits on the packaging line at the target packaging station is equal to the number of marker bits at the packaging station, the module determines that the broken state of the packaging line at the target packaging station is a no-broken state; when the number of marker bits on the packaging line at the target packaging station is not equal to the number of marker bits at the packaging station, the module determines that the broken state of the packaging line at the target packaging station is a broken state.

8. An electronic device, characterized in that, The electronic device includes: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the electronic device to implement the method for identifying the broken state of a packaged wire as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, It stores a computer program, which, when executed by the computer's processor, causes the computer to perform the packaging wire breakage status identification method according to any one of claims 1 to 6.

Images