Cable connector jack identification method, device and equipment and storage medium

Abstract

The invention relates to a cable connector jack identification method and device, equipment and a storage medium, and the method comprises the steps: obtaining a video stream of a scene collected by video perspective equipment worn by a user, and carrying out the interception of the video stream, and obtaining a frame image; utilizing a trained connector jack identification model to identify and mark a connector in the frame image and a jack on the surface of the connector to obtain a processed image; and transmitting the processed image back to the video perspective equipment, so that the user can carry out cable connection according to the marking conditions of the connector and the jack on the surface of the connector. The technical problems of complex industrial field environment and low recognition degree can be solved, the problems of wrong insertion and missing insertion easily caused by manual visual inspection in the connector assembly link in the operation process are solved, the recognition precision of the jack is improved, and the cable connection assembly efficiency is improved.

Description

Technical Field

[0001] This application relates to the field of image recognition technology, and in particular, to a method, device, equipment and storage medium for identifying cable connector jacks. Background Art

[0002] Connectors are used as carriers for connecting cables in the industrial field. They are small in size and have a small surface area ratio. There are several to dozens of jacks on the surface of the connector, and the target cable needs to be inserted into its corresponding jack. The assembly process of aviation products involves the connection of a large number of cables. How to ensure that these cables can be correctly inserted into the corresponding jacks is crucial. At present, cable connection mainly relies on manual visual inspection and manual insertion to complete the work, and problems such as incorrect insertion and missed insertion are likely to occur during the process. These errors will not only affect the manual assembly efficiency and loss of product performance, but also bring serious safety hazards, making the quality of cable connection face serious challenges. At present, the method of using a fixed terminal to display drawings can be used to assist in guiding the assembly task. However, due to the narrow actual operation site environment, the operator has to frequently switch perspectives, with a high degree of fatigue, the jacks are not easy to identify, and assembly is prone to errors. Summary of the Invention

[0003] This application provides a method, device, equipment and storage medium for identifying cable connector jacks to solve the problems in the above background art.

[0004] In a first aspect, this application provides a method for identifying cable connector jacks, including:

[0005] Obtain the video stream of the scene collected by the video see-through device worn by the user, and intercept the video stream to obtain frame images;

[0006] Use the trained connector jack recognition model to identify the connector and the jacks on the surface of the connector in the frame image and perform annotation to obtain a processed image;

[0007] Transmit the processed image back to the video see-through device so that the user can perform cable connection according to the annotation of the connector and the jacks on the surface of the connector.

[0008] Further, the connector jack recognition model is a model constructed based on a single-stage object detection neural network of the YOLO algorithm.

[0009] Further, before using the trained connector jack recognition model to annotate the connector and the jacks on the surface of the connector in the frame image to obtain a processed image, it further includes:

[0010] Use the pre-obtained training set and test set to train the connector jack recognition model to obtain a trained connector jack recognition model.

[0011] Further, before training the connector jack recognition model using the pre-acquired training set and test set to obtain a trained connector jack recognition model, it further includes:

[0012] Collect the jack images on the surface of the connector and the connector and perform annotation to obtain a data set, and divide the data set into a training set and a test set.

[0013] Further, training the connector jack recognition model using the pre-acquired training set and test set to obtain a trained connector jack recognition model includes:

[0014] Train the connector jack recognition model using the training set to obtain a trained connector jack recognition model;

[0015] Test the trained connector jack recognition model using the test set to obtain a test result;

[0016] Analyze the test result using the GIoU Loss curve, and adjust the connector jack recognition model to obtain a trained connector jack recognition model.

[0017] Further, before transmitting the processed image back to the video see-through device, it further includes:

[0018] If the time stamp of the frame image has a difference greater than a set threshold from the time stamp of the frame intercepted from the current video stream of the video see-through device, discard the frame image.

[0019] Further, after transmitting the processed image back to the video see-through device, it further includes:

[0020] If the scene collected by the video see-through device moves, perform positioning and tracking on the connector.

[0021] In a second aspect, the present application provides a cable connector jack recognition device, including:

[0022] An image acquisition module, configured to acquire a video stream of the scene collected by a video see-through device worn by a user, and intercept the video stream to obtain a frame image;

[0023] A jack recognition module, configured to use a trained connector jack recognition model to recognize the connector and the jacks on the surface of the connector in the frame image and perform annotation to obtain a processed image;

[0024] An image transmission module, configured to transmit the processed image back to the video see-through device, so that the user can perform cable connection according to the annotation of the connector and the jacks on the surface of the connector.

[0025] In a third aspect, the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above-described method for identifying the jack of a cable connector is implemented.

[0026] In a fourth aspect, the present application provides a computer-readable storage medium storing a computer program, which when executed by a processor implements the above-described method for identifying the jack of a cable connector.

[0027] The above technical solutions of the present application have the following advantages:

[0028] The method for identifying the jack of a cable connector provided in the first aspect of the present application obtains a video stream of a scene collected by a video see-through device worn by a user, intercepts the video stream to obtain a frame image, uses a trained connector jack recognition model to identify the connector and the jack on the surface of the connector in the frame image and performs annotation to obtain a processed image, and transmits the processed image back to the video see-through device so that the user can perform cable connection according to the annotation of the connector and the jack on the surface of the connector. The user can see the jack prompt in the field of view through the video see-through device, which can be used in the actual on-site environment of cable assembly, solves the technical problems of complex industrial on-site environment and low recognition rate, solves the problems of easy misinsertion and missed insertion in the manual visual inspection during the connector assembly process, improves the recognition accuracy of the jack, and improves the cable connection and assembly efficiency.

[0029] It can be understood that the beneficial effects of the above second aspect, third aspect, and fourth aspect can refer to the relevant descriptions in the above first aspect and will not be elaborated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the specific embodiments of the present application or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the following drawings are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0031] Figure 1 It is a schematic flowchart of the method for identifying the jack of a cable connector provided by the present application;

[0032] Figure 2 It is a schematic diagram of the principle of the scene displayed by the video see-through device provided by the present application;

[0033] Figure 3 It is a schematic diagram of the combined form of the glasses end and the computing unit of the video see-through device provided by the present application;

[0034] Figure 4 Schematic diagram of the cable connector assembly task and schematic diagram of the connector jack numbering method provided for this application;

[0035] Figure 5 Schematic diagram of the cable connector jack recognition provided for this application;

[0036] Figure 6 GIoU Loss curve analysis diagram of the model training process provided for this application;

[0037] Figure 7 Schematic diagram of the structure of the cable connector jack recognition device provided for this application;

[0038] Figure 8 Schematic diagram of the structure of the electronic device provided for this application. Detailed implementation manners

[0039] In the following description, specific details such as specific system architectures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of this application. However, those skilled in the art should clearly understand that this application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of this application.

[0040] It should be understood that when used in the specification of this application and the appended claims, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0041] In addition, in the description of the specification of this application and the appended claims, the terms "first", "second", "third", etc. are only used for differentiating descriptions and cannot be understood as indicating or implying relative importance.

[0042] The reference to "one embodiment" or "some embodiments" etc. in the specification of this application means that a specific feature, structure, or characteristic described in connection with the embodiment is included in one or more embodiments of this application. Thus, the statements "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification are not necessarily all referring to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "comprising", "including", "having", and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways. "Multiple" means "two or more".

[0043] The present application provides a cable connector jack identification method, device, equipment and storage medium to solve the problem that the actual operation site environment is relatively complex, the jacks are difficult to identify during the operation, and wrong insertion and missed insertion are prone to occur.

[0044] The specific implementation methods of the present application are further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present application but are not intended to limit the scope of the present application.

[0045] like Figure 1 As shown, an embodiment of the present application provides a cable connector jack identification method, which specifically includes the following steps: obtaining a video stream of a scene captured by a video perspective device worn by a user, and intercepting the video stream to obtain a frame image; using a trained connector jack identification model to identify the connector and the jack on the surface of the connector in the frame image and mark them to obtain a processed image; transmitting the processed image back to the video perspective device so that the user can make a cable connection based on the marking of the connector and the jack on the surface of the connector.

[0046] Video-see-through (VST) is a head-mounted device that integrates display and computing functions. Figure 2 As shown in the figure, virtual content is directly superimposed on the image captured by the camera, and the wearer sees the "virtual content" superimposed on the real and virtual on the screen. The video perspective device consists of a glasses end and a computing unit, and its structure is as follows Figure 3 shown.

[0047] The user wears the video perspective device on the head. The device is equipped with a display that can display the current user's work scene in real time in front of the user. The scene is consistent with the real scene in front of the user. The user faces the connector and uses the video stream input function of the video perspective camera to collect the video data of the connector in real time. A frame of the video data is captured and transmitted to the computing unit, which can detect whether there is a connector in the current screenshot frame.

[0048] The connector jack recognition model will filter out the jacks on the connector surface based on training features, connector models, etc. Cable connector assembly scenarios such as Figure 4 As shown in the figure, the user needs to identify the target jack into which the cable needs to be inserted and then complete the assembly. After identifying the connector and the several jacks on its surface, as shown in the figure, the user needs to identify the target jack into which the cable needs to be inserted and then complete the assembly. Figure 5 As shown in the image, guide marks of the connector and the socket are marked to remind the user of the location of the socket, which is helpful to improve the assembly precision and accuracy of the operator.

[0049] In some embodiments, the connector jack recognition model is a model constructed by a single-stage target detection neural network based on the YOLO algorithm.

[0050] In some embodiments, before using the trained connector jack recognition model to label the connectors and jacks on the surface of the connectors in the frame image to obtain a processed image, it further includes: using a pre-acquired training set and test set to train the connector jack recognition model to obtain a trained connector jack recognition model.

[0051] In some embodiments, before using the pre-acquired training set and test set to train the connector jack recognition model to obtain a trained connector jack recognition model, it further includes: collecting images of the connectors and jacks on the surface of the connectors and performing labeling to obtain a data set, and dividing the data set into a training set and a test set.

[0052] In some embodiments, using the pre-acquired training set and test set to train the connector jack recognition model to obtain a trained connector jack recognition model includes: using the training set to train the connector jack recognition model to obtain a trained connector jack recognition model; using the test set to test the trained connector jack recognition model to obtain a test result; using the GIoU Loss curve to analyze the test result and adjust the connector jack recognition model to obtain a trained connector jack recognition model.

[0053] The connector jack recognition model based on the single-stage object detection neural network needs to be pre-trained, and its training process includes: collecting connector image data to form an image data set; performing labeling on the image data set to form a label data set; dividing the image data set and the label data set to form an image training set, an image test set, a label training set, and a label test set; using the image training set and the label training set to train the connector jack recognition model to obtain a trained connector jack recognition model; using the image test set and the label test set to verify the effect of the trained connector jack recognition model; using the GIoU Loss curve to analyze the training results of the connector jack recognition model.

[0054] In some embodiments, before transmitting the processed image back to the video see-through device, it further includes: if the time stamp of the frame image has a difference greater than a set threshold from the time stamp of the frame intercepted from the current video stream of the video see-through device, then discard the frame image.

[0055] In some embodiments, after transmitting the processed image back to the video see-through device, it further includes: if the scene captured by the video see-through device moves, then perform positioning and tracking on the connectors.

[0056] Capture a frame of the video stream from the glasses end of the video see-through device and transmit it back to the computing unit: The video stream obtained by the video see-through device is a real-time display of the working area of the current user. Capture a frame from this video stream and transmit it to a computing unit within the local or local area network. To ensure that the frame image does not affect the user's viewing when transmitted back to the glasses end of the video see-through device, it is necessary to leave a timestamp on the frame image to ensure correct transmission of data and real-time matching.

[0057] The computing unit calls the connector jack recognition model to process the frame image: The model is built based on a single-stage object detection neural network and has performance characteristics such as fast inference speed and accurate detection results. Input the pre-processed training set (including the annotated image set and label set) into the model to train a model adapted to this scenario. Use this trained model to process the frame image input to the computing unit, detect whether there is a connector in the image, and if so, detect the connector and the jacks on the surface of the connector and annotate them.

[0058] Transmit the processed image back to the glasses end of the video see-through device: The processed image should highlight the connector and jacks with different colored annotations. When transmitting the above image back to the glasses end of the video see-through device, if there is a delay, the image frame can be discarded. The delay can be set when the time difference between the timestamp of the image frame and the timestamp of the currently captured frame of the video stream at the glasses end of the video see-through device is greater than a certain threshold, then it is considered that a delay has occurred. During the actual assembly of the cable and connector, the scenario may move, and it is necessary to locate and track the connector.

[0059] The connector jack recognition model is built by a single-stage object detection neural network based on the YOLO algorithm and needs to be pre-trained before recognizing the jacks. The detailed steps of the training process are as follows: Collect connector and jack image data as the data set. The connectors collected can be of different models. The collected connector images need to be clear and complete, and various issues such as lighting, angle, pixel, size, and environment need to be considered. The images can be collected by a camera or through a video see-through device.

[0060] Annotate the data set and generate an image data set and a label data set. The annotation of the image will be stored separately as a label data set in the form of characters, numbers, etc. The label data set needs to conform to the input format of YOLO, and the labels in the label data set need to correspond one by one to the images in the image data set. The Labelimg software can be used as a tool for collecting the label data set, and this tool can obtain character-form annotation information after image annotation.

[0061] Divide the dataset into a test set and a training set. The dataset can be divided into a test set and a training set according to a ratio of 9:1. The training set contains: most of the images in the image dataset and their corresponding labels in the label dataset. The test set contains: the part of the images in the image dataset excluding the training set and their corresponding labels in the label dataset. The dataset can be divided into a test set and a training set manually or randomly.

[0062] Process the training set using a single-stage object detection neural network to obtain a trained connector jack recognition model. Use the test set to test and evaluate the connector jack recognition model and obtain the test results. Analyze the test results with the GIoU Loss curve, and the training data and the model can be adjusted according to the GIoU Loss analysis results.

[0063] The method for identifying the connector jack provided by the embodiment of this application includes: locating the spatial position of the connector in the current image. The scene image is intercepted from a frame of the video stream of the video perspective device, and the timestamp needs to be retained when intercepting the image frame; identifying the connector and the jack in the current scene; marking the jack guide mark matching the jack and the connector guide mark matching the connector; intercepting a frame of the video stream at the glasses end of the video perspective device and transmitting it to the computing unit, and transmitting the processed picture to the glasses end of the video perspective device; discarding the target detection image frames of the delayed jacks and cables; training the connector jack recognition model adapted to the current connector.

[0064] The connector jack recognition model is constructed based on a single-stage object detection deep network, and its principle is basically similar to the YOLO algorithm. The model training method includes: collecting the image data of the connector and the jack and organizing it to obtain an image dataset; performing dataset annotation on this dataset to obtain the annotated image dataset and the label dataset, and the label includes the classification data of the jack; using the single-stage object detection neural network model to train the above-mentioned annotated image dataset and label dataset to obtain the connector jack recognition model.

[0065] Divide the image dataset and the label dataset to obtain a training set and a test set, and the number of images in the training set is much larger than that in the test set; use the test set to test and evaluate the object detection recognition model to obtain the test results; use the test results and the trained object detection recognition model to determine whether the intercepted picture of the video stream at the glasses end of the video perspective device can recognize the jack; analyze the training process and training results of the object detection model with the GIoU Loss curve.

[0066] As Figure 6As shown, it is an example of the GIoU Loss curve analysis model, and this curve consists of two parts: Classification Loss and Bounding Box Regression Loss. train / box_loss is the mean of the model loss function, train / obj_loss is the mean of the recognition loss function of the model, and train / cls_loss is the mean of the classification loss function of the model; precision is the validation accuracy of the model; recall is the recall rate of the model; val / box_loss is the mean of the test set loss function of the model; val / obj_loss is the mean of the object recognition loss function of the test set of the model; val / cls_loss is the mean of the classification loss function of the test set of the model; mAP_0.5 is the average mAP of the model; mAP_0.5:0.95 is the average mAP of the model at different IoU thresholds.

[0067] In this application example, considering that the current cable connection mainly relies on manual visual inspection and manual insertion to complete the work, and quality problems such as incorrect insertion and missed insertion are likely to occur during the process. Therefore, a method for identifying the jacks of a cable connector is proposed to solve the technical problems of easy error in manual visual inspection in the connector assembly link during the operation process and potential hidden dangers in product quality, and improve the assembly efficiency. Information on the cable connector and its jacks is obtained based on the glasses end of the video perspective device, and the guiding marks of the jacks can be simulated. The jack detection and recognition model can be used to locate and track the connector and the jacks, solving the technical problem of low recognition of the jacks during the installation process of connecting the cables, and improving the installation accuracy and assembly efficiency. The user can see the highlighted jack prompts in the field of view through this video perspective device, which can be used in the actual on-site environment of cable assembly, solving the technical problems of complex industrial on-site environment and low recognition. The target detection of the connector jacks is realized through the jack recognition network of the computing unit, realizing the real-time tracking and positioning of the connector, improving the recognition accuracy of the jacks, and improving the cable connection and assembly efficiency.

[0068] Corresponding to the method for identifying the jacks of a cable connector described in the above embodiment, as Figure 7 shown, the embodiment of this application also provides a device for identifying the jacks of a cable connector, and this device for identifying the jacks of a cable connector includes:

[0069] An image acquisition module, configured to acquire the video stream of the scene collected by the video perspective device worn by the user, and intercept the video stream to obtain frame images;

[0070] A jack recognition module, configured to use the trained connector jack recognition model to identify the connector and the jacks on the surface of the connector in the frame image and perform annotation to obtain a processed image;

[0071] An image transmission module, configured to transmit the processed image back to the video see-through device, so that the user can connect the cable according to the markings of the connector and the jacks on the surface of the connector.

[0072] It should be noted that, for the information interaction, execution process, etc. between the above-mentioned modules / units, since they are based on the same concept as the method embodiments of this application, their specific functions and the technical effects brought about can be specifically referred to the method embodiment part, and will not be elaborated here.

[0073] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the above-mentioned division of each functional unit and module is used as an example. In actual applications, the above-mentioned functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working processes of the units and modules in the above-mentioned system can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated here.

[0074] The embodiments of this application also provide an electronic device, such as Figure 8 shown, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the cable connector jack recognition method provided in the first aspect.

[0075] In applications, the electronic device may include, but is not limited to, a processor and a memory. Figure 8 This is only an example of an electronic device and does not limit the electronic device. It may include more or fewer components than shown, or combine some components, or different components. For example, input / output devices, network access devices, etc. The input / output devices may include a camera, an audio collection / playback device, a display screen, etc. The network access device may include a network module for performing wireless network with external devices.

[0076] In an application, the processor can be a Central Processing Unit (CPU), and the processor can also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc.

[0077] In an application, in some embodiments, the memory can be an internal storage unit of an electronic device, such as the hard disk or memory of the electronic device. In other embodiments, the memory can also be an external storage device of the electronic device, for example, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the electronic device. The memory can also include both the internal storage unit and the external storage device of the electronic device. The memory is used to store an operating system, application programs, a BootLoader, data, and other programs, such as the program code of a computer program. The memory can also be used to temporarily store data that has been output or will be output.

[0078] The embodiments of the present application also provide a computer-readable storage medium. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the steps in the above method embodiments can be implemented.

[0079] To implement all or part of the processes in the above method embodiments of the present application, it can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps in the above method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable files, or some intermediate forms, etc. The computer-readable medium can at least include: any entity or device that can carry the computer program code to an electronic device, a recording medium, a computer memory, a Read-Only Memory (ROM), a Random Access Memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk, or an optical disc, etc.

[0080] Those of ordinary skill in the art will appreciate that the device and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled professionals can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of this application.

[0081] In the embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. Additionally, the couplings or direct couplings or communication connections shown or discussed among each other can be through some interfaces. The devices are indirectly coupled or communication-connected, and can be in electrical, mechanical, or other forms.

[0082] The above-described embodiments are only used to illustrate the technical solutions of this application, rather than to limit them; although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of each embodiment of this application, and should all be included within the protection scope of this application.

Claims

1. A cable connector jack identification method, characterized in that: include: Obtaining a video stream of a scene captured by a video perspective device worn by a user, and intercepting the video stream to obtain a frame image; Using the trained connector jack recognition model to recognize the connector and the jack on the surface of the connector in the frame image and mark them to obtain a processed image; The processed image is transmitted back to the video perspective device so that the user can make cable connections according to the markings of the connector and the jack on the surface of the connector.

2. The cable connector jack identification method according to claim 1, characterized in that: The connector jack recognition model is a model constructed by a single-stage target detection neural network based on the YOLO algorithm.

3. The cable connector jack identification method according to claim 1, characterized in that: Before labeling the connector and the sockets on the connector surface in the frame image using the trained connector socket recognition model to obtain the processed image, the method further includes: The connector jack recognition model is trained using the pre-acquired training set and test set to obtain a trained connector jack recognition model.

4. The cable connector jack identification method according to claim 3, characterized in that: Before the connector jack recognition model is trained using the pre-acquired training set and test set to obtain the trained connector jack recognition model, the method further includes: The images of the connector and the jack on the connector surface are collected and annotated to obtain a data set, and the data set is divided into a training set and a test set.

5. The cable connector jack identification method according to claim 3, characterized in that: The method of training the connector jack recognition model using the pre-acquired training set and test set to obtain the trained connector jack recognition model includes: Using the training set to train the connector jack recognition model to obtain a trained connector jack recognition model; Using the test set to test the trained connector jack recognition model, and obtaining the test results; The test results are analyzed using the GIoU Loss curve, and the connector jack recognition model is adjusted to obtain a trained connector jack recognition model.

6. The cable connector jack identification method according to claim 1, characterized in that: Before transmitting the processed image back to the video perspective device, the method further includes: If the difference between the timestamp of the frame image and the timestamp of the frame captured by the current video stream of the video perspective device is greater than a set threshold, the frame image is discarded.

7. The cable connector jack identification method according to claim 1, characterized in that: After transmitting the processed image back to the video perspective device, the method further includes: If the scene captured by the video perspective device moves, the connector is located and tracked.

8. A cable connector jack identification device, characterized in that: include: An image acquisition module is used to acquire a video stream of a scene captured by a video perspective device worn by a user, and intercept the video stream to obtain a frame image; A socket recognition module, used to recognize and annotate the connector and the socket on the surface of the connector in the frame image using a trained connector socket recognition model to obtain a processed image; The image transmission module is used to transmit the processed image back to the video perspective device so that the user can make cable connections according to the markings of the connector and the jack on the surface of the connector.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the cable connector jack identification method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the cable connector jack identification method according to any one of claims 1 to 7 is implemented.

Images