Monitoring method and device for target ports in optical cable junction boxes

Abstract

This application discloses a method and apparatus for monitoring target ports in an optical cable junction box. The method includes: acquiring an image of the optical cable junction box; extracting target text information from the image to obtain the box's code, and determining a first position of the target port in the port monitoring interface corresponding to the code; acquiring a port image inside the junction box and determining a second position of the target port in that image; identifying the target port whose first and second positions differ, and obtaining a monitoring result. This application solves the technical problem of low monitoring efficiency for target ports due to manual monitoring.

Description

Technical Field

[0001] This application relates to the field of artificial intelligence, and more specifically, to a method and apparatus for monitoring target ports in an optical cable junction box. Background Technology

[0002] Wired access networks are the most important link between operators and broadband users, and the stability and security of the network directly affect user experience. Within wired access networks, the most crucial passive facility is the fiber optic junction box. Undoubtedly, the accuracy of port occupancy in these junction boxes directly impacts the efficiency of broadband service activation for users. However, the accuracy of port occupancy in fiber optic junction boxes has traditionally relied entirely on manual visual inspection. In fact, due to the sheer number of fiber optic junction boxes, relying solely on daily manual inspections to verify port occupancy accuracy requires a significant amount of manpower and resources.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This application provides a method and apparatus for monitoring target ports in optical cable junction boxes, so as to at least solve the technical problem of low monitoring efficiency of target ports due to manual monitoring.

[0005] According to one aspect of the embodiments of this application, a method for monitoring a target port in an optical cable junction box is provided, comprising: acquiring an image of the optical cable junction box; extracting target text information from the image of the optical cable junction box to obtain the code of the optical cable junction box, and determining a first position of the target port in the port monitoring interface corresponding to the code; acquiring a port image inside the optical cable junction box, and determining a second position of the target port in the port image; determining a target port whose first position and second position are different, and obtaining a monitoring result.

[0006] Optionally, after acquiring the image of the optical cable junction box, the method further includes: determining the location of the optical cable junction box in the image; extracting features from the image of the location of the optical cable junction box; and determining that the acquired image of the optical cable junction box is qualified if the extracted features are the same as the pre-stored features.

[0007] Optionally, determining the location of the optical cable junction box in the image includes: determining a target detection box, wherein the size of the target detection box is greater than a set size threshold; and determining the location of the optical cable junction box in the image using the target detection box.

[0008] Optionally, the target text information in the optical cable junction box image is extracted to obtain the code of the optical cable junction box, including: performing text detection on the optical cable junction box image and filtering out regions containing text; segmenting all regions containing text to obtain a set of text images; recognizing the text of a set type in the set of text images to obtain multiple candidate text information; determining the candidate text information that is the same as the preset text information from the multiple candidate text information to obtain the target text information, and determining the code of the optical cable junction box from the target text information.

[0009] Optionally, determining the second location of the target port in the port image includes: inputting the port image into a pre-determined recognition model for processing to obtain a feature density map of the port image; and determining the second location of the target port in the port image from the feature density map.

[0010] Optionally, the port image is input into a pre-determined recognition model for processing to obtain a feature density map of the port image, including: extracting multi-branch features from the port image; performing convolution and pooling operations on each branch feature and then connecting the branch features to obtain a connection feature map; and performing convolution operations on the connection feature map to obtain a feature density map.

[0011] Optionally, the predetermined recognition model is determined by the following methods: obtaining an initial crowd detection model; adjusting the propagation parameters of the initial crowd detection model based on the size of the terminals in the port image to obtain a target detection model; and training the target detection model using a predetermined training dataset to obtain the predetermined recognition model.

[0012] Optionally, determining the target port whose second position is different from the first position includes: determining the first number corresponding to the first position of the target port; determining the number of rows and columns corresponding to the second position of the target port; determining the second number corresponding to the second position of the target port based on the number of rows and columns; comparing the first number and the second number, and determining that the first position and the second position of the target port are different if the second number is different from the first number.

[0013] According to another aspect of the embodiments of this application, a monitoring device for a target port in an optical cable junction box is also provided, comprising: an acquisition module for acquiring an image of the optical cable junction box; an extraction module for extracting target text information from the image of the optical cable junction box to obtain the code of the optical cable junction box, and determining a first position of the target port in the port monitoring interface corresponding to the code; a first determination module for acquiring a port image inside the optical cable junction box and determining a second position of the target port in the port image; and a second determination module for determining a target port whose first position and second position are different, thereby obtaining a monitoring result.

[0014] According to another aspect of the embodiments of this application, a non-volatile storage medium is also provided, the non-volatile storage medium including a stored program, wherein, when the program is running, it controls the device where the storage medium is located to execute a monitoring method for a target port in an optical cable junction box.

[0015] According to another aspect of the embodiments of this application, an electronic device is also provided, including a processor and a memory, wherein the processor is used to run a program, wherein the program executes a method for monitoring a target port in an optical cable junction box.

[0016] In this embodiment, the method involves acquiring an image of the optical cable junction box; extracting target text information from the image to obtain the code of the optical cable junction box, and determining the first position of the target port in the port monitoring interface corresponding to the code; acquiring a port image inside the optical cable junction box and determining the second position of the target port in the port image; and determining the target port where the first position and the second position are different to obtain the monitoring result. By recognizing the acquired image of the optical cable junction box and comparing the first position of the target port obtained from the recognition result with the second position of the target port in the corresponding monitoring interface, the method determines the target port where the first position and the second position are different, thereby achieving the purpose of intelligent monitoring of the target port and thus realizing the technical effect of improving monitoring efficiency. This solves the technical problem of low monitoring efficiency of target ports caused by manual monitoring. Attached Figure Description

[0017] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0018] Figure 1 This is a hardware structure block diagram of a computer terminal (or mobile device) for a method of monitoring a target port in an optical cable junction box according to an embodiment of this application.

[0019] Figure 2 This is a flowchart illustrating a method for monitoring a target port in an optical cable junction box according to this application;

[0020] Figure 3 This is a schematic diagram of a port image according to an embodiment of this application;

[0021] Figure 4 This is a schematic diagram of a monitoring interface according to an embodiment of this application;

[0022] Figure 5 This is a flowchart illustrating another method for monitoring a target port in an optical cable junction box according to an embodiment of this application;

[0023] Figure 6This is a schematic diagram of a monitoring device for a target port in an optical cable junction box according to an embodiment of this application. Detailed Implementation

[0024] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0025] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0026] The methods and embodiments provided in this application can be executed on mobile terminals, computer terminals, cloud servers, or similar computing devices. Figure 1 A hardware block diagram of a computer terminal (or mobile device) for implementing a monitoring method for target ports in an optical cable junction box is shown. Figure 1 As shown, the computer terminal 10 (or mobile device 10) may include one or more processors 102 (shown as 102a, 102b, ..., 102n in the figure) 102 (processor 102 may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data, and a transmission module 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0027] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10 (or mobile device). As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0028] The memory 104 can be used to store software programs and modules for application software, such as the program instructions / data storage device corresponding to the monitoring method of the target port in the optical cable junction box in this embodiment of the application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the above-mentioned monitoring method of the target port in the optical cable junction box. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the computer terminal 10 via a network. Examples of the above-mentioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0029] The transmission module 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission module 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission module 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0030] The display can be, for example, a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10 (or mobile device).

[0031] According to an embodiment of this application, a method for monitoring a target port in an optical cable junction box is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0032] Figure 2 This is a monitoring method for the target port in an optical cable junction box according to an embodiment of this application, such as... Figure 2 As shown, the method includes the following steps:

[0033] Step S202: Obtain an image of the optical cable junction box;

[0034] Step S204: Extract the target text information from the image of the optical cable junction box, obtain the code of the optical cable junction box, and determine the first position of the target port in the port monitoring interface corresponding to the code;

[0035] Step S206: Obtain the port image inside the optical cable junction box and determine the second position of the target port in the port image;

[0036] Step S208: Determine the target port where the first position and the second position are different, and obtain the monitoring results.

[0037] The above steps enable the identification of the optical cable junction box image, and then the comparison between the first position of the target port obtained from the identification result and the second position of the target port in the corresponding monitoring interface to determine the target port with different first and second positions. This achieves the purpose of intelligent monitoring of the target port, thereby improving the technical effect of monitoring efficiency and solving the technical problem of low monitoring efficiency of target ports caused by manual monitoring.

[0038] In practical applications, the target port refers to the occupied port (the port with the terminal inserted). It should be noted that the first position indicates the occupied port location on the monitoring interface corresponding to the fiber optic junction box, while the second position indicates the actual occupied port location within the fiber optic junction box. The accuracy of the port occupancy status obtained by the monitoring system is determined by comparing the first and second positions.

[0039] It should be noted that the monitoring interface is displayed on the remote terminal interface. The remote terminal determines whether a terminal is inserted into a port by collecting port data inside the fiber optic junction box. For example, if a terminal is inserted into a port, the port transmits a signal to the remote terminal. This signal indicates that the port is occupied, and the monitoring interface displays the port occupancy status based on the signal. One fiber optic junction box corresponds to one display interface.

[0040] Currently, the accuracy of optical cable junction box occupancy is entirely determined by manual visual verification, which is time-consuming, labor-intensive, and inefficient. This application improves monitoring efficiency by identifying the actual images of the optical cable junction boxes, automatically verifying the accuracy of port occupancy, and statistically analyzing the results to generate report data.

[0041] Figure 3 A schematic diagram of a port image is shown, which clearly shows which ports inside the fiber optic junction box are occupied.

[0042] Figure 4 A schematic diagram of a monitoring interface is shown, reflecting the situation where the internal ports of the corresponding optical cable junction box are occupied.

[0043] If the first and second positions of the target port are different, it reflects two different situations: one is that there are terminals occupying the port inside the optical cable junction box, but the monitoring interface shows that the port is not occupied; the other is that there are no terminals occupying the port inside the optical cable junction box, but the monitoring interface shows that the port is occupied.

[0044] This application also provides another method for monitoring the target port, such as... Figure 5 As shown, it includes:

[0045] S501, use the APP to obtain images of the optical cable junction box;

[0046] S502, Determine whether the acquired image fully displays the optical cable junction box;

[0047] S503, Extract the fiber optic junction box code from the fiber optic junction box image;

[0048] S504, retrieve the monitoring interface corresponding to the optical cable junction box code, and determine the first position occupied by the fiber core in the monitoring interface;

[0049] S505, use the APP to obtain images of the internal port panels of the optical cable junction box;

[0050] S506 identifies the second position occupied by the fiber core in the port panel image;

[0051] S507, confirm the monitoring results.

[0052] By identifying the images acquired on-site, the actual location of the occupied port is determined, and the location of the occupied port displayed on the monitoring interface is compared. The two locations are then compared to quickly determine whether the occupied location displayed on the monitoring interface is accurate.

[0053] In some embodiments of this application, after obtaining the image of the optical cable junction box, it is also necessary to determine the location of the optical cable junction box in the image; feature extraction is performed on the image of the location of the optical cable junction box, and if the extracted features are the same as the pre-stored features, the obtained image of the optical cable junction box is determined to be qualified.

[0054] First, the image of the fiber optic junction box is preprocessed, including color filtering and size adjustment. The preprocessed image is then input into a target detection model to detect the specific location of the junction box. This model can be a YOLO network (a convolutional neural network). After detecting the junction box's location, the image of its exterior is extracted using image matting and fed into a feature extraction network. Finally, a classification head determines whether the junction box is qualified. The feature extraction network uses a ResNet50 (a neural network model) pre-trained model, and its parameters are trained through transfer learning.

[0055] To improve the detection rate, the target detection box is first determined, and the size of the target detection box is larger than a set size threshold. The location of the optical cable junction box in the image is then determined by the target detection box.

[0056] It should be noted that the size of the target detection box refers to the area of ​​the target detection box.

[0057] Since the front of the fiber optic junction box has a large area, a larger detection box can be used to detect the image of the fiber optic junction box. In order to better capture the detection effect of the fiber optic junction box image under different lighting and tilt backgrounds, a 53-layer Darknet CNN convolutional network can be used as the backbone of the detection model algorithm to train and recognize targets for fiber optic junction boxes with different resolutions and display percentages.

[0058] Meanwhile, in order to improve detection accuracy, the activation function of the detection layer of the target detection model can be set to the Mish function.

[0059] In some embodiments of this application, target text information is extracted from the image of the optical cable junction box to obtain the code of the optical cable junction box. This is achieved by: performing text detection on the image of the optical cable junction box and filtering out regions containing text; segmenting all regions containing text to obtain a set of text images; recognizing a set type of text in the set of text images to obtain multiple candidate text information; determining candidate text information that is the same as preset text information from the multiple candidate text information to obtain target text information, and determining the code of the optical cable junction box from the target text information.

[0060] Specifically, the input image of the optical cable junction box is first subjected to text detection using a backbone network based on MobileNetV3 (a network model). Then, text orientation correction is performed, and training reinforcement is carried out for text in different orientations. Text recognition is then performed on the segmented text image set. The text features extracted from the previous two steps are combined with the weights of the pre-trained model trained on a large scale. Finally, the text output includes the position of the rectangle containing the text in the image, the text itself, and the relevant confidence score.

[0061] To improve the detection rate, during the detection of text images, fonts with a size larger than a set threshold are ignored, and only the offset angle within a set angle range of the text image is detected, such as offsets within 90 degrees and offsets within 270 degrees.

[0062] To improve the accuracy of character recognition, considering that the encoding on the surface of the optical cable junction box is printed font, printed font data was added to the training dataset of the character recognition model.

[0063] In some embodiments of this application, the second position of the target port in the port image can be determined by: inputting the port image into a predetermined recognition model for processing to obtain a feature density map of the port image; and determining the second position of the target port in the port image from the feature density map.

[0064] In one alternative approach, multi-branch feature extraction can be performed on the port image; after performing convolution and pooling operations on each branch feature, the branch features are connected to obtain a connection feature map; and a convolution operation is performed on the connection feature map to obtain a feature density map.

[0065] Obtain an initial crowd detection model; adjust the propagation parameters of the initial crowd detection model based on the size of the terminals in the port image to obtain a target detection model; train the target detection model using a pre-determined training dataset to obtain a pre-determined recognition model.

[0066] To quickly identify the difference between the first and second positions, the following method can be used: determine the first number corresponding to the first position of the target port; determine the row and column number corresponding to the second position of the target port; determine the second number corresponding to the second position of the target port based on the row and column number; compare the first number and the second number, and if the second number is different from the first number, determine that the first and second positions of the target port are different.

[0067] It should be noted that the first number refers to the location number displayed on the monitoring interface, and the second number refers to the location number identified from the acquired image of the fiber optic junction box.

[0068] For example, if the row number of the second position is X and the column number is Y, the number of the second position can be 12(X-1)+Y.

[0069] In some embodiments of this application, a monitoring device for the target port in an optical cable junction box is also provided, such as... Figure 6 As shown, the device includes:

[0070] The acquisition module 60 is used to acquire an image of the optical cable junction box; the extraction module 62 is used to extract target text information from the image of the optical cable junction box, obtain the code of the optical cable junction box, and determine the first position of the target port in the port monitoring interface corresponding to the code; the first determination module 64 is used to acquire a port image inside the optical cable junction box and determine the second position of the target port in the port image; the second determination module 66 is used to determine the target port where the first position and the second position are different, and obtain the monitoring result. It should be noted that... Figure 6 The device shown is Figure 2 The methods shown are in a one-to-one correspondence. Specifically, the acquisition module 60 corresponds to step S202, the extraction module 62 corresponds to step S204, the first determination module 64 corresponds to step S206, and the second determination module 66 corresponds to step S208. Therefore, the above explanations of steps S202-S208 also apply to... Figure 6 The device will not be described in detail here.

[0071] The acquisition module 60 includes: a verification submodule; the verification submodule is used to determine the location of the optical cable junction box in the image after acquiring the image of the optical cable junction box; to extract features from the image of the location of the optical cable junction box; and to determine that the acquired image of the optical cable junction box is qualified if the extracted features are the same as the pre-stored features.

[0072] The extraction module 62 includes: a first determining submodule and an extraction submodule; the first determining submodule is used to determine a target detection box, the size of which is greater than a set size threshold; the target detection box is used to determine the location of the optical cable junction box in the image; the extraction submodule is used to perform text detection on the image of the optical cable junction box and filter out regions containing text; all regions containing text are segmented to obtain a set of text images; a set type of text is identified in the set of text images to obtain multiple candidate text information; candidate text information that is the same as the preset text information is determined from the multiple candidate text information to obtain target text information, and the code of the optical cable junction box is determined from the target text information.

[0073] The first determining module 64 includes: a second determining submodule; the second determining submodule is used to input the port image into a pre-determined recognition model for processing to obtain a feature density map of the port image; and to determine the second position of the target port in the port image from the feature density map.

[0074] The second determination submodule includes: an acquisition unit and a training unit; the acquisition unit is used to extract multi-branch features from the port image; after performing convolution and pooling operations on each branch feature, the branch features are connected to obtain a connection feature map; the connection feature map is convolved to obtain a feature density map; the training unit is used to acquire an initial crowd detection model; the propagation parameters of the initial crowd detection model are adjusted based on the size of the terminals in the port image to obtain a target detection model; and the target detection model is trained using a pre-determined training dataset to obtain a pre-determined recognition model.

[0075] The second determining module 66 includes: a third determining submodule, which is used to determine the first number corresponding to the first position of the target port; determine the number of rows and columns corresponding to the second position of the target port; determine the second number corresponding to the second position of the target port based on the number of rows and columns; compare the first number with the second number, and determine that the first position and the second position of the target port are different if the second number is different from the first number.

[0076] This application also provides a non-volatile storage medium, which includes a stored program, wherein, when the program is running, it controls the device where the storage medium is located to execute a monitoring method for the target port in the optical cable junction box.

[0077] This application also provides an electronic device, including a processor and a memory, wherein the processor is used to run a program, wherein the program executes a method for monitoring a target port in an optical cable junction box.

[0078] The aforementioned electronic device's method for monitoring target ports in optical cable junction boxes involves identifying the acquired image of the optical cable junction box, then comparing the first position of the target port obtained from the identification result with the second position of the target port in the corresponding monitoring interface to determine the target ports with different first and second positions. This achieves the goal of intelligently monitoring target ports, thereby improving monitoring efficiency and solving the technical problem of low monitoring efficiency of target ports caused by manual monitoring.

[0079] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0080] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0081] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0082] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0083] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0084] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0085] The above are merely preferred embodiments of this application. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for monitoring a target port in an optical cable junction box, characterized in that, The method comprises the following steps: obtaining an optical cable cross-connect box image of an optical cable cross-connect box; extracting target text information in the optical cable cross-connect box image to obtain a code of the optical cable cross-connect box, and determining a first position of a target port in a port monitoring interface corresponding to the code; obtaining a port image inside the optical cable cross-connect box, and determining a second position of a target port in the port image; determining the target port whose first position is different from the second position to obtain a monitoring result, wherein a first number corresponding to the first position of the target port is determined; a row number and a column number corresponding to the second position of the target port are determined; a second number corresponding to the second position of the target port is determined based on the row number and the column number; the first number and the second number are compared, and in the case that the first number is different from the second number, it is determined that the first position of the target port is different from the second position.

2. The method of claim 1, wherein, After obtaining the optical cable cross-connect box image of the optical cable cross-connect box, the method further comprises: determining the position of the optical cable cross-connect box in the optical cable cross-connect box image; performing feature extraction on the image of the optical cable cross-connect box position, and in the case that the extracted feature is the same as a pre-stored feature, determining that the obtained optical cable cross-connect box image is qualified.

3. The method of claim 2, wherein, Determining the position of the optical cable cross-connect box in the optical cable cross-connect box image comprises: determining a target detection box, wherein the size of the target detection box is greater than a set size threshold; determining the position of the optical cable cross-connect box in the optical cable cross-connect box image through the target detection box.

4. The method of claim 1, wherein, Extracting target text information in the optical cable cross-connect box image to obtain a code of the optical cable cross-connect box comprises: performing text detection on the optical cable cross-connect box image to screen out regions containing text; cutting all regions containing text to obtain a text picture set; recognizing a set type of text in the text picture set to obtain a plurality of candidate text information; determining candidate text information that is the same as pre-set text information from the plurality of candidate text information to obtain target text information, and determining the code of the optical cable cross-connect box from the target text information.

5. The method of claim 1, wherein, Determining the second position of the target port in the port image comprises: inputting the port image into a pre-determined recognition model for processing to obtain a feature density map of the port image; determining the second position of the target port in the port image from the feature density map.

6. The method of claim 5, wherein, Inputting the port image into a pre-determined recognition model for processing to obtain a feature density map of the port image comprises: performing multi-branch feature extraction on the port image; connecting the branch features after convolution and pooling operations on each branch feature to obtain a connection feature map; performing convolution operation on the connection feature map to obtain a feature density map.

7. The method of claim 5, wherein, The pre-determined recognition model is determined by the following method, comprising: obtaining an initial crowd detection model; adjusting the propagation parameters of the initial crowd detection model based on the size of the terminal in the port image to obtain a target detection model, and training the target detection model using a pre-determined training data set to obtain the pre-determined recognition model.

8. A monitoring device for a target port in an optical cable junction box, characterized in that, The method comprises the following steps: An acquisition module is configured to acquire an optical cable terminal box image of an optical cable terminal box; An extraction module is configured to extract target text information in the optical cable terminal box image, to obtain a code of the optical cable terminal box, and to determine a first position of a target port in a port monitoring interface corresponding to the code; A first determination module is configured to acquire a port image inside the optical cable terminal box, and to determine a second position of a target port in the port image; A second determination module is configured to determine the target port with different first and second positions, to obtain a monitoring result, wherein a first number corresponding to the first position of the target port is determined; a row number and a column number corresponding to the second position of the target port are determined; a second number corresponding to the second position of the target port is determined based on the row number and the column number; and the first number and the second number are compared, and in a case where the first number and the second number are different, it is determined that the first position and the second position of the target port are different.

9. A non-volatile storage medium, comprising: The non-volatile storage medium includes a stored program, wherein when the program is running, the device in which the storage medium is located is controlled to perform the method for monitoring the target port in the optical cable terminal box according to any one of claims 1 to 7.

10. An electronic device, comprising: The device includes a processor and a memory, and the processor is configured to run a program, wherein when the program is running, the method for monitoring the target port in the optical cable terminal box according to any one of claims 1 to 7 is performed.

Images