Passive optical splitter detection method, device, equipment and medium

Abstract

The embodiments of the present disclosure provide a passive spectrometer detection method, device, equipment and medium, which relate to the field of image processing technology. The method includes: obtaining the first spectrometer feature of the original image and the second spectrometer feature of the image to be detected based on the spectrometer recognition network model, the first spectrometer feature and the second spectrometer feature both including the number of spectrometers, the size of the spectrometer and the spectrometer coordinates; comparing the first spectrometer feature of the original image with the second spectrometer feature of the image to be detected, and determining whether to issue an alarm based on the comparison result. According to the technical solution of the embodiments of the present disclosure, it is possible to timely and accurately determine that the spectrometer in the cabinet has changed.

Description

Background Art

[0002] Optical splitters, also known as optical splitters, are commonly used network devices in various optical network rooms. Optical splitters are optical fiber junction devices with multiple input ports and multiple output ports, commonly used for coupling, branching and distribution of optical signals. Most of the optical splitters in use are passive devices, namely passive optical splitters. Passive optical splitters do not require external energy and can work as long as there is input light.

[0003] At present, in the daily management of optical splitters in the computer room, there may be unauthorized changes to the optical splitters without review. Since most optical splitters are passive components, the device itself cannot detect whether the optical splitter has been changed by installing software or other means.

[0004] Therefore, how to timely and accurately determine whether the splitter has changed has become a technical problem that needs to be solved urgently.

[0005] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0006] The purpose of the embodiments of the present disclosure is to provide a passive optical splitter detection method, device, electronic device and computer-readable medium, thereby achieving timely and accurate determination of whether the optical splitter has changed, at least to a certain extent.

[0007] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present disclosure.

[0008] According to a first aspect of an embodiment of the present disclosure, a passive spectrometer detection method is provided, comprising: acquiring a first spectrometer feature of an original image and a second spectrometer feature of an image to be detected based on a spectrometer recognition network model, wherein the first spectrometer feature and the second spectrometer feature both include the number of spectrometers, the size of the spectrometers, and the spectrometer coordinates; comparing the first spectrometer feature of the original image with the second spectrometer feature of the image to be detected, and determining whether to issue an alarm based on the comparison result.

[0009] Based on the first aspect, in some example embodiments, comparing the first spectrometer feature of the original image with the second spectrometer feature of the image to be detected, and determining whether to issue an alarm based on the comparison result, includes: comparing the number of spectrometers of the original image with the number of spectrometers of the image to be detected, if the numbers are inconsistent, determining to issue an alarm; if the numbers are consistent, comparing the spectrometer coordinates and spectrometer sizes of the spectrometer of the original image and the corresponding spectrometer of the image to be detected in order of position; if the comparison results of the spectrometer coordinates and the spectrometer size are inconsistent, determining to issue an alarm.

[0010] Based on the first aspect, in some example embodiments, the method further includes: if the comparison results of the spectrometer coordinates and the spectrometer size are consistent, then based on the spectrometer coordinates and the spectrometer size, respectively, intercepting corresponding spectrometer images from the original image and the image to be detected; performing a similarity comparison between the spectrometer image of the original image and the spectrometer image of the image to be detected at the same coordinate position; and determining whether there is a privately connected line based on the comparison result.

[0011] Based on the first aspect, in some example embodiments, the similarity comparison between the spectrometer image of the original image at the same coordinate position and the spectrometer image of the image to be detected includes: obtaining a histogram of the spectrometer image of the original image at the same coordinate position and the corresponding spectrometer image of the image to be detected; and performing a similarity comparison between the histogram of the spectrometer image of the original image and the histogram of the corresponding spectrometer image of the image to be detected.

[0012] Based on the first aspect, in some example embodiments, the splitter identification network model is a neural network model, and the method further includes: acquiring a plurality of sample data, the sample data including a splitter cabinet image and labels of the number, size, and coordinates of the corresponding splitters in the splitter cabinet; training the neural network model based on the sample data to obtain the splitter identification network model.

[0013] Based on the first aspect, in some example embodiments, the neural network model is a yolo neural network model.

[0014] Based on the first aspect, in some example embodiments, the method further includes: acquiring an original image of the spectrometer in the target cabinet through an image acquisition terminal; and regularly acquiring an image to be detected of the spectrometer in the target cabinet through the image acquisition terminal.

[0015] According to a second aspect of an embodiment of the present disclosure, a passive spectrometer detection device is provided, comprising: a feature extraction module, used to obtain a first spectrometer feature of an original image and a second spectrometer feature of an image to be detected based on a spectrometer recognition network model, wherein the first spectrometer feature and the second spectrometer feature both include the number of spectrometers, the size of the spectrometer and the spectrometer coordinates; a comparison module, used to compare the first spectrometer feature of the original image with the second spectrometer feature of the image to be detected, and determine whether to issue an alarm based on the comparison result.

[0016] According to the second aspect, in some example embodiments, the comparison module is further used to: compare the number of spectrometers of the original image with the number of spectrometers of the image to be detected, and if the numbers are inconsistent, determine to issue an alarm; if the numbers are consistent, compare the spectrometer coordinates and spectrometer sizes of the spectrometer of the original image and the corresponding spectrometer of the image to be detected in order of position; if the comparison results of the spectrometer coordinates and the spectrometer size are inconsistent, determine to issue an alarm.

[0017] According to the second aspect, in some example embodiments, the device further includes: an image capture module, for capturing corresponding spectrometer images from the original image and the image to be detected based on the spectrometer coordinates and the spectrometer size if the comparison results of the spectrometer coordinates and the spectrometer size are consistent; an image comparison module, for performing a similarity comparison between the spectrometer image of the original image and the spectrometer image of the image to be detected at the same coordinate position; and a private connection judgment module, for determining whether there is a private connection line based on the comparison result.

[0018] According to the second aspect, in some example embodiments, the image comparison module is further used to: obtain a histogram of the spectrometer image of the original image and the corresponding spectrometer image of the image to be detected at the same coordinate position; and perform a similarity comparison between the histogram of the spectrometer image of the original image and the histogram of the corresponding spectrometer image of the image to be detected.

[0019] According to the second aspect, in some example embodiments, the splitter identification network model is a neural network model, and the device further includes: a sample acquisition module, used to acquire multiple sample data, the sample data including a splitter cabinet image and labels of the number, size and coordinates of the corresponding splitters in the splitter cabinet; a model training module, used to train the neural network model based on the sample data to obtain the splitter identification network model.

[0020] According to the second aspect, in some example embodiments, the neural network model is a yolo neural network model.

[0021] According to the second aspect, in some example embodiments, the device further includes: an image acquisition module, configured to acquire original images of the spectrometer in the target cabinet through an image acquisition terminal; and to periodically acquire images to be detected of the spectrometer in the target cabinet through the image acquisition terminal.

[0022] According to a third aspect of an embodiment of the present disclosure, a computer-readable medium is provided, on which a computer program is stored. When the program is executed by a processor, the passive optical splitter detection method as described in the first aspect of the above embodiment is implemented.

[0023] According to a fourth aspect of an embodiment of the present disclosure, an electronic device is provided, comprising: one or more processors; 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 one or more processors implement the passive spectrometer detection method as described in the first aspect of the above embodiment.

[0024] The technical solution provided by the embodiments of the present disclosure may have the following beneficial effects:

[0025] In some embodiments of the present disclosure, on the one hand, the accuracy of spectrometer recognition can be improved by learning and acquiring the number, size, and coordinates of the spectrometers in the original image and the image to be detected through a neural network model; on the other hand, the original image is compared with the image to be detected based on the number, size, and coordinate parameters of the spectrometers, so that changes in the spectrometer in the cabinet, such as being moved, can be determined in a timely and accurate manner.

[0026] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present disclosure, and together with the specification, are used to explain the principles of the present disclosure. Obviously, the drawings described below are only some embodiments of the present disclosure, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0028] Figure 1 A schematic diagram showing a flow chart of a passive optical splitter detection method according to some example embodiments of the present disclosure;

[0029] Figure 2 A schematic diagram showing a flow chart of a passive optical splitter detection method according to some other exemplary embodiments of the present disclosure;

[0030] Figure 3 A schematic flow chart of a passive optical splitter detection method according to some further example embodiments of the present disclosure is shown;

[0031] Figure 4 A schematic diagram showing detection results of a passive optical splitter detection method according to some further example embodiments of the present disclosure;

[0032] Figure 5 A schematic structural diagram of a passive optical splitter detection device according to an embodiment of the present disclosure is shown;

[0033] Figure 6 A schematic structural diagram of an electronic device in an exemplary embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0034] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be more comprehensive and complete and will fully convey the concept of the example embodiments to those skilled in the art.

[0035] In addition, the described features, structures or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known methods, devices, implementations or operations are not shown or described in detail to avoid blurring the various aspects of the present disclosure.

[0036] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0037] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0038] At present, in the daily management of optical splitters in the computer room, there may be unauthorized access to the optical splitter (hereinafter referred to as "private access") to steal data without review. Since most optical splitters are passive components, the device itself cannot detect how many optical fibers are connected by installing software, etc., and it is impossible to determine whether there is private access.

[0039] In one technical solution, in order to identify the situation where the occupied optical network port in an optical communication device such as a splitter is inconsistent with the preset port, a convolutional neural network is used to identify the occupied optical port, and then a resource comparison is performed with the pre-allocated optical port in the system. However, in this technical solution, due to the centralized deployment of splitters in the computer room, a large number of optical fibers are bundled together, resulting in a large number of optical fibers and optical ports being blocked. The convolutional neural network cannot analyze the occupancy of the optical ports in the blocked area, so this method cannot be used to determine the private connection of the splitter in the computer room.

[0040] Based on the above content, the embodiment of the present disclosure provides a passive splitter detection method. On the one hand, the number, size, and coordinates of the splitters in the image are learned and obtained through a neural network model, and the original image is compared with the image to be detected according to the above three parameters for preliminary screening; on the other hand, the original image and the image to be detected are compared for similarity of the identified splitter device through a histogram, and the private connection is judged based on the similarity probability. According to the technical solution of the embodiment of the present disclosure, on the one hand, it is possible to timely and accurately determine whether the splitter in the cabinet has changed, such as being moved; on the other hand, it is possible to accurately determine whether there is a privately connected optical fiber in the splitter.

[0041] The technical solutions in the exemplary embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0042] Figure 1 A schematic flow chart of a passive optical splitter detection method according to some example embodiments of the present disclosure is shown. The execution subject of the passive optical splitter detection method provided in the embodiment of the present disclosure may be a computing device with computing capabilities, such as a desktop computer. The passive optical splitter detection method includes steps S110 to S120. The passive optical splitter detection method in the example embodiment is described in detail below in conjunction with the accompanying drawings.

[0043] refer to Figure 1 As shown, in step S110, a first spectrometer feature of the original image and a second spectrometer feature of the image to be detected are obtained based on the spectrometer recognition network model, and both the first spectrometer feature and the second spectrometer feature include the number of spectrometers, the size of the spectrometers, and the spectrometer coordinates.

[0044] In an example embodiment, the original image and the image to be detected are images of the same spectrometer cabinet, and the spectrometer cabinet includes a plurality of spectrometers. For example, an original image of the spectrometer in the target cabinet is captured by an image acquisition terminal such as a camera; and the image to be detected of the spectrometer in the target cabinet is periodically captured by the image acquisition terminal.

[0045] Further, in an example embodiment, a first spectrometer feature of the original image and a second spectrometer feature in the image to be detected are obtained based on the spectrometer recognition network model. The first spectrometer feature and the second spectrometer feature both include the number of spectrometers, the size of the spectrometers, and the coordinates of the spectrometers. The number of spectrometers indicates the number of spectrometers included in the spectrometer device, such as a cabinet. The size of the spectrometer indicates the size of the rectangular frame area on the side of the optical port of the spectrometer. The spectrometer coordinates indicate the coordinate position of the spectrometer in the image.

[0046] The spectrometer recognition network model is a neural network model, and the neural network model can be a yolo neural network model such as a yolov5 neural network model.

[0047] It should be noted that, although the neural network model is taken as the yolo neural network model as an example, those skilled in the art should understand that the spectrometer recognition network model can also be other appropriate neural network models such as a paddle neural network model, which is also within the scope of protection of the present disclosure.

[0048] In step S120, the first spectrometer feature of the original image is compared with the second spectrometer feature of the image to be detected, and whether to issue an alarm is determined based on the comparison result.

[0049] In an example embodiment, the number of spectrometers in the original image is compared with the number of spectrometers in the image to be detected. If the numbers are inconsistent, it is determined to be an alarm; if the numbers are consistent, the spectrometer coordinates and spectrometer sizes of the spectrometers in the original image and the corresponding spectrometers in the image to be detected are compared in position order; if the comparison results of the spectrometer coordinates and the spectrometer size are inconsistent, it is determined to be an alarm.

[0050] according to Figure 1 According to the technical solution in the example embodiment, on the one hand, the accuracy of spectrometer recognition can be improved by learning and acquiring the number, size, and coordinates of the spectrometers in the original image and the image to be detected through a neural network model; on the other hand, the original image is compared with the image to be detected according to the number, size, and coordinate parameters of the spectrometers, so as to timely and accurately determine whether the spectrometer in the cabinet has changed, such as being moved.

[0051] In an example embodiment, if the comparison results of the spectrometer coordinates and the spectrometer size are consistent, the corresponding spectrometer image is intercepted from the original image and the image to be detected based on the spectrometer coordinates and the spectrometer size; the spectrometer image of the original image and the spectrometer image of the image to be detected at the same coordinate position are compared for similarity; and based on the comparison result, it is determined whether there is a private line.

[0052] Furthermore, a similarity comparison is performed between the spectrometer image of the original image at the same coordinate position and the spectrometer image of the image to be detected, including: obtaining a histogram of the spectrometer image of the original image at the same coordinate position and the corresponding spectrometer image of the image to be detected; and performing a similarity comparison between the histogram of the spectrometer image of the original image and the histogram of the corresponding spectrometer image of the image to be detected.

[0053] According to the technical solution in the above-mentioned embodiment, on the one hand, the position and size of the spectrometer in the image can be identified first, the spectrometer device can be accurately located, the comparison area can be reduced, and the interference of irrelevant image changes on the recognition effect can be minimized. For example, if the bundled network cable is slightly moved but the spectrometer is not newly connected to the optical fiber, etc., if the whole image histogram is directly compared, the above scenarios will result in serious misjudgment. On the other hand, after the spectrometer panel is detected, the original image and the image to be detected where the private connection device may exist are partially compared. By analyzing the similarity value of the image histogram before and after the private connection, whether the device has the possibility of private connection, this detection method can greatly reduce the comparison error, so that it can be better used to determine whether the spectrometer is privately connected to the optical fiber.

[0054] It should be noted that although the histogram is used as an example for explanation, those skilled in the art should understand that other methods may also be used to compare the similarity between the original image and the spectrometer image of the image to be detected, such as LBP (Local Binary Pattern), etc., which is also within the scope of protection of the present disclosure.

[0055] Figure 2 A schematic flow chart of a passive optical splitter detection method according to some other example embodiments of the present disclosure is shown.

[0056] Reference Figure 2 As shown, in step S205, a live image of the spectrometer device is acquired, and the spectrometer in the image is marked.

[0057] In an example embodiment, an image of a beam splitter device such as a cabinet captured by a camera is obtained, and the beam splitters in the image are annotated, for example, by annotating the number, size, and coordinates. The collected images can be images taken at various angles of the beam splitter device. The size of the beam splitter refers to the size of a rectangular frame of the beam splitter, and the rectangular frame should cover the entire panel area of ​​the beam splitter lithography side.

[0058] In step S210, a spectrometer recognition network model is constructed based on the annotated image.

[0059] In the example embodiment, a yolo neural network or a Paddle neural network is used to classify the labeled sample data into training data and verification data, and the learning parameters of the model are adjusted according to the machine performance, and the sample data is sent to the neural network for image learning to obtain a spectrometer recognition network model. The spectrometer recognition network model can identify the spectrometer device in the image and the coordinates and size of the spectrometer in the image.

[0060] Taking the yolo neural network as an example, there are multiple versions of the yolo neural network, such as the Yolov5 neural network model. Its network model is divided into four parts: input, Backbone, Neck, and Prediction, which are specifically divided into:

[0061] (1) Input: including Mosaic data enhancement, adaptive anchor frame calculation, and adaptive image scaling. Mosaic data enhancement uses 4 images, which are randomly scaled, randomly cropped, and randomly arranged for splicing. Yolov5 embeds the anchor frame function into the code. During each training, the optimal anchor frame value in different training sets is adaptively calculated, so that the coordinates and size of the spectrometer can be determined more accurately. Yolov5 adaptively adds the least black border to the original image, and the black borders at both ends of the image height are reduced. During inference, the amount of calculation will also be reduced, that is, the target detection speed will be improved.

[0062] (2) Backbone: includes Focus structure and CSP structure. The Focus structure of Yolov5s uses 32 convolution kernels. Two CSP structures are designed in Yolov5. Taking the Yolov5s network as an example, the CSP1_X structure is applied to the Backbone network, and the other CSP2_X structure is applied to the Neck.

[0063] (3) Neck: including FPN+PAN structure. In the Neck structure of Yolov5, the CSP2 structure designed by CSPnet is adopted to enhance the ability of network feature fusion.

[0064] (4) Prediction: GIOU_Loss. Yolov5 uses GIOU_Loss as the loss function of the Bounding box.

[0065] Yolov5 has 4 learning models, namely yolov5s, yolov5m, yolov5l, and yolov5x. The learning time and model effects after learning are different for different learning models. Taking Yolov5s as an example, its network is the smallest and takes the least time, which is suitable for detecting larger targets.

[0066] In step S215, an original image without private connection is stored for each cabinet.

[0067] In an example embodiment, an image acquisition terminal (such as a camera, etc.) is installed in front of the spectrometer cabinet. The acquisition screen of the image acquisition terminal needs to be fixed (not moved later). The original image of the spectrometer in the cabinet is acquired through the image acquisition terminal, and the unconnected image is saved as the original image.

[0068] In step S220, the image to be detected of the spectrometer cabinet is collected regularly, and the first spectrometer feature of the original image and the second spectrometer feature in the image to be detected are obtained through the spectrometer recognition model.

[0069] In the example embodiment, the first spectrometer feature and the second spectrometer feature both include the number of spectrometers, the size of the spectrometers, and the coordinates of the spectrometers. The spectrometer cabinet image is regularly collected by the image acquisition terminal as the image to be detected and compared with the original image. The original image and the image to be detected are identified by the above-mentioned spectrometer recognition model to obtain the coordinate position, image size, and number of detections of all spectrometers in the image; the image to be detected and the original image must be compared using the same type of image acquisition device to ensure that the range and resolution of the collected image are consistent.

[0070] Furthermore, the first spectrometer feature of the original image is compared with the second spectrometer feature of the image to be detected, and an alarm is issued for the cabinets with inconsistent comparisons. Specifically, the image to be detected is identified through the spectrometer recognition model, and the coordinate positions, image sizes, and detection numbers of all spectrometers in the image are obtained, and compared with the coordinate positions, image sizes, and detection numbers of the original image. If the comparison numbers are inconsistent, an alarm message is fed back, indicating that it is not the same cabinet, or the equipment in the cabinet has been modified; if the detection numbers are consistent, the coordinates and sizes of the same spectrometer, that is, the detection target in the original image and the image to be detected are continuously compared one by one in sequence. As long as the coordinate and size comparison results of the detection target of one spectrometer are greatly different, it means that the position of the equipment has been artificially modified, and an alarm message is fed back.

[0071] In step S225, if the coordinate position and image size of the spectrometers identified in the image to be detected are similar to those in the original image, and the number of detections is the same, then image capture is performed in the original image and the image to be detected respectively according to the coordinates and image size of the spectrometers in the original image to obtain multiple spectrometer images;

[0072] In step S230, the original image and the spectrometer image cut out from the image to be detected are compared using an image histogram similarity comparison method based on the coordinate and size approximation principle, and whether there is a private connection is determined based on the comparison result.

[0073] In the exemplary embodiment, the histograms of the same spectrometer in the original image and the image to be detected are compared, and the similarity of the target detected by each spectrometer is fed back respectively. The commonly used histogram similarity comparison methods are as follows:

[0074] (1) Correlation comparison. The larger the value, the higher the correlation. The maximum value is 1 and the minimum value is 0. In a non-strict case, when the value is 1, the two graphs can be considered to be the same.

[0075] (2) Chi-Square comparison. The smaller the value of the chi-square comparison, the higher the correlation. The maximum value has no upper bound and the minimum value is 0. The closer it is to 0, the higher the similarity. The closer it is to 1, the lowest similarity. When it is equal to 0, the two images are the same.

[0076] (3) Intersection. The larger the value, the higher the correlation. The maximum value is 9.455319 and the minimum value is 0.

[0077] (4) Bhattacharyya distance. The smaller the value of Bhattacharyya distance, the higher the correlation. The maximum value is 1 and the minimum value is 0.

[0078] In the example embodiment, taking chi-square comparison as an example, the higher the value (generally the similarity is higher than 0.01), the greater the possibility that the device has been abnormally modified (privately connected). If the similarity is lower than 0.01, the possibility that the device has been abnormally modified is very low. The following formula (1) is the formula for the chi-square similarity comparison method:

[0079]

[0080] Among them, H1 and H2 represent the histogram data of two images respectively.

[0081] Chi-square comparison comes from the chi-square test. The chi-square test is the degree of deviation between the actual observed value and the theoretical inference value of the statistical sample. The degree of deviation between the actual observed value and the theoretical inference value determines the size of the chi-square value. The larger the chi-square value, the greater the deviation, and the less consistent the actual observed value is with the theoretical inference value; the smaller the chi-square value, the smaller the deviation, and the closer they are to the theoretical inference value. If the two values ​​are completely equal, the chi-square value is 0, indicating that the theoretical value is completely consistent. The formula for the chi-square test is as follows (2):

[0082]

[0083] Where fi is the observed frequency, npi is the expected frequency, and X 2 is the chi-square value.

[0084] according to Figure 2The technical solution in the example embodiment, on the one hand, can first identify the position and size of the splitter in the image, accurately locate the splitter device, reduce the comparison area, and minimize the interference of irrelevant image changes on the recognition effect. For example, if the bundled network cables are slightly moved but the splitter is not newly connected to the optical fiber, etc., if the whole image histogram is directly compared, the above scenarios will result in serious misjudgment. On the other hand, after the splitter panel is detected, the original image and the image to be detected where the private connection device may exist are partially compared. By analyzing the similarity value of the image histogram before and after the private connection, it is analyzed whether the device has the possibility of private connection. This detection method can greatly reduce the comparison error, so that it can be better used to determine whether the splitter has a private connection to the optical fiber.

[0085] Figure 3 A schematic flow chart of a passive optical splitter detection method according to some further example embodiments of the present disclosure is shown.

[0086] Reference Figure 3 As shown, in step S310, a first spectrometer feature of the original image and a second spectrometer feature of the image to be detected are obtained based on the spectrometer recognition network model.

[0087] In an exemplary embodiment, the first beam splitter characteristic and the second beam splitter characteristic each include a beam splitter quantity, a beam splitter size, and a beam splitter coordinate.

[0088] In step S320, the first spectrometer feature of the original image is compared with the second spectrometer feature of the image to be detected.

[0089] In step S330, it is determined whether the comparison results are consistent.

[0090] In step S340, if the comparison results are inconsistent, an alarm is issued.

[0091] In step S350, corresponding spectrometer images are intercepted from the original image and the image to be detected based on the spectrometer coordinates and the spectrometer size.

[0092] In step S360, a similarity comparison is performed between the histograms of the spectrometer image of the original image and the spectrometer image of the image to be detected at the same coordinate position.

[0093] In step S370, it is determined whether a private line exists based on the comparison result.

[0094] In the example embodiment, a chi-square comparison method is used to determine whether there is a private connection line. For example, if the probability of the comparison result similarity is higher than 0.01, it can be said that the possibility of the device being abnormally modified is greater, that is, the probability of the private connection is higher; if the similarity is lower than 0.01, the possibility of the device being abnormally modified is very low, that is, the probability of the private connection is low.

[0095] according to Figure 3 The technical solution in the example embodiment, on the one hand, can first identify the position and size of the splitter in the image, accurately locate the splitter device, reduce the comparison area, and minimize the interference of irrelevant image changes on the recognition effect. For example, if the bundled network cables are slightly moved but the splitter is not newly connected to the optical fiber, etc., if the whole image histogram is directly compared, the above scenarios will result in serious misjudgment. On the other hand, after the splitter panel is detected, the original image and the image to be detected where the private connection device may exist are partially compared. By analyzing the similarity value of the image histogram before and after the private connection, it is analyzed whether the device has the possibility of private connection. This detection method can greatly reduce the comparison error, so that it can be better used to determine whether the splitter has a private connection to the optical fiber.

[0096] In addition, in some other exemplary embodiments of the present disclosure, a passive optical splitter detection method is provided, the method comprising the following steps:

[0097] Step 1: First, install the image acquisition terminal (such as a camera) in front of the splitter cabinet and fix it. The image acquisition area needs to be fixed and cover all the splitter devices to be detected;

[0098] Step 2: The image acquisition terminal acquires the image of the spectrometer in a normal state (not privately connected) and uploads it to the server for backup and storage (hereinafter referred to as the original image) for comparison with the image to be detected;

[0099] Step 3: The image acquisition terminal regularly acquires the image of the optical splitter cabinet (hereinafter referred to as the image to be detected) and uploads it. The server compares the image to be detected with the original image using the method of the present invention, thereby determining the probability that the optical splitter is privately connected, and feeding back the value of the similarity. The larger the value, the higher the possibility of private connection.

[0100] Step 4: If the splitter needs to perform normal fiber deployment, wiring arrangement, and splicing operations, which may cause a large gap between the detected image and the original image, it is necessary to re-collect an original image and save it as a backup after the normal operation is completed, as a standard image that has not been privately connected, and compare it with the subsequent image to be detected.

[0101] Figure 4 A schematic diagram showing detection results in some example embodiments according to the present disclosure.

[0102] Reference Figure 4 As shown, the dotted box 420 is the identified spectrometer. According to the size and coordinates of the spectrometer in the original image, screenshots are taken from the original image and the image to be detected to generate corresponding spectrometer images. The spectrometer image of the original image and the corresponding spectrometer image of the image to be detected are compared for similarity. It can be seen that there is a privately connected optical fiber 410 in the image to be detected on the right.

[0103] It should be noted that the above figures are only schematic illustrations of the processes included in the method according to the exemplary embodiment of the present disclosure, and are not intended to be limiting. It is easy to understand that the processes shown in the above figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0104] The following introduces an embodiment of a device of the present disclosure, which can be used to execute the above-mentioned passive optical splitter detection method of the present disclosure.

[0105] Figure 5 A schematic structural diagram of a passive optical splitter detection device according to an embodiment of the present disclosure is shown.

[0106] Reference Figure 5 As shown, the passive spectrometer detection device 500 includes: a feature extraction module 510, which is used to obtain a first spectrometer feature of the original image and a second spectrometer feature of the image to be detected based on a spectrometer recognition network model, wherein the first spectrometer feature and the second spectrometer feature both include the number of spectrometers, the size of the spectrometer and the spectrometer coordinates; a comparison module 520, which is used to compare the first spectrometer feature of the original image with the second spectrometer feature of the image to be detected, and determine whether to issue an alarm based on the comparison result.

[0107] In some example embodiments, the comparison module 520 is further used to: compare the number of spectrometers of the original image with the number of spectrometers of the image to be detected, and if the numbers are inconsistent, determine to issue an alarm; if the numbers are consistent, compare the spectrometer coordinates and spectrometer sizes of the spectrometer of the original image and the corresponding spectrometer of the image to be detected in order of position; if the comparison results of the spectrometer coordinates and the spectrometer size are inconsistent, determine to issue an alarm.

[0108] In some example embodiments, the device 500 also includes: an image capture module, which is used to capture corresponding spectrometer images from the original image and the image to be detected based on the spectrometer coordinates and the spectrometer size if the comparison results of the spectrometer coordinates and the spectrometer size are consistent; an image comparison module, which is used to compare the similarity of the spectrometer image of the original image and the spectrometer image of the image to be detected at the same coordinate position; and a private connection judgment module, which is used to determine whether there is a private connection line based on the comparison result.

[0109] In some example embodiments, the image comparison module is further used to: obtain a histogram of the spectrometer image of the original image and the corresponding spectrometer image of the image to be detected at the same coordinate position; and perform a similarity comparison between the histogram of the spectrometer image of the original image and the histogram of the corresponding spectrometer image of the image to be detected.

[0110] In some example embodiments, the splitter identification network model is a neural network model, and the device 500 further includes: a sample acquisition module, used to acquire multiple sample data, the sample data including a splitter cabinet image and labels of the number, size and coordinates of the corresponding splitters in the splitter cabinet; and a model training module, used to train the neural network model based on the sample data to obtain the splitter identification network model.

[0111] In some example embodiments, the neural network model is a yolo neural network model.

[0112] In some example embodiments, the apparatus 500 further includes: an image acquisition module, configured to acquire original images of the spectrometer in the target cabinet through an image acquisition terminal; and to periodically acquire images to be detected of the spectrometer in the target cabinet through the image acquisition terminal.

[0113] Since the functional modules of the passive optical splitter detection device of the exemplary embodiment of the present disclosure correspond to the steps of the exemplary embodiment of the passive optical splitter detection method described above, for details not disclosed in the network device embodiment of the present disclosure, please refer to the exemplary embodiment of the passive optical splitter detection method described above.

[0114] It should be noted that, although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. On the contrary, the features and functions of one module or unit described above can be further divided into multiple modules or units to be embodied.

[0115] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0116] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0117] In the exemplary embodiments of the present disclosure, a computer storage medium capable of implementing the above method is also provided. A program product capable of implementing the above method of the present specification is stored thereon. In some possible embodiments, various aspects of the present disclosure may also be implemented in the form of a program product, which includes a program code. When the above program product is run on a terminal device, the above program code is used to enable the above terminal device to execute the steps according to various exemplary embodiments of the present disclosure described in the above “Exemplary Method” section of the present specification.

[0118] The program product may be in a portable compact disk read-only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present disclosure is not limited thereto, and in this document, a readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0119] The above program product can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0120] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0121] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0122] Program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0123] In addition, in an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

[0124] Those skilled in the art will appreciate that various aspects of the present disclosure may be implemented as systems, methods or program products. Therefore, various aspects of the present disclosure may be specifically implemented in the following forms, namely: complete hardware implementation, complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to herein as "circuits", "modules" or "systems".

[0125] Refer to the following Figure 6 The electronic device 600 according to this embodiment of the present disclosure is described. Figure 6 The electronic device 600 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0126] like Figure 6As shown, the electronic device 600 is in the form of a general computing device. The components of the electronic device 600 may include but are not limited to: at least one processing unit 610, at least one storage unit 620, and a bus 630 connecting different system components (including the storage unit 620 and the processing unit 610).

[0127] The storage unit stores program codes, which can be executed by the processing unit 610, so that the processing unit 610 executes the steps described in the "Exemplary Method" section of the present specification according to various exemplary embodiments of the present disclosure. For example, the processing unit 610 can execute the following steps: Figure 1 As shown in: Step S110, based on the spectrometer recognition network model, the first spectrometer feature of the original image and the second spectrometer feature of the image to be detected are obtained, and the first spectrometer feature and the second spectrometer feature both include the number of spectrometers, the size of the spectrometers, and the spectrometer coordinates; Step S120, the first spectrometer feature of the original image is compared with the second spectrometer feature of the image to be detected, and whether to issue an alarm is determined based on the comparison result.

[0128] Exemplarily, the processing unit 610 may also execute the passive optical splitter detection method in the above-mentioned embodiment.

[0129] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 6201 and / or a cache memory unit 6202 , and may further include a read-only memory unit (ROM) 6203 .

[0130] The storage unit 620 may also include a program / utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0131] Bus 630 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0132] The electronic device 600 may also communicate with one or more external devices 690 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 600, and / or communicate with any device that enables the electronic device 600 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 650. Furthermore, the electronic device 600 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 660. As shown, the network adapter 660 communicates with other modules of the electronic device 600 via a bus 630. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0133] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the implementation of the present disclosure.

[0134] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present disclosure, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0135] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and examples are to be considered as exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.

Claims

1. A passive optical splitter detection method, characterized in that: include: Acquire a first spectrometer feature of the original image and a second spectrometer feature of the image to be detected based on the spectrometer recognition network model, wherein the first spectrometer feature and the second spectrometer feature both include the number of spectrometers, the size of the spectrometers, and the spectrometer coordinates; Comparing the first spectrometer feature of the original image with the second spectrometer feature of the image to be detected, and determining whether to issue an alarm based on the comparison result; The step of comparing the first spectrometer feature of the original image with the second spectrometer feature of the image to be detected, and determining whether to issue an alarm based on the comparison result, includes: If the number of spectrometers in the original image is consistent with the number of spectrometers in the image to be detected, and the comparison results of the spectrometer coordinates and the spectrometer sizes are consistent, intercepting corresponding spectrometer images from the original image and the image to be detected respectively based on the spectrometer coordinates and the spectrometer sizes; Comparing the similarity between the spectrometer image of the original image and the spectrometer image of the image to be detected at the same coordinate position; Determining whether there is a private line based on the comparison result; The similarity comparison between the spectrometer image of the original image and the spectrometer image of the image to be detected at the same coordinate position includes: Acquire a histogram of the spectrometer image of the original image and the corresponding spectrometer image of the image to be detected at the same coordinate position; Performing a similarity comparison between a histogram of the spectrometer image of the original image and a histogram of the corresponding spectrometer image of the image to be detected; The similarity comparison between the histogram of the spectrometer image of the original image and the histogram of the corresponding spectrometer image of the image to be detected is determined based on the following formula: ； Wherein, H1 and H2 respectively represent the histogram data of the spectrometer image of the original image and the corresponding spectrometer image of the image to be detected.

2. The method according to claim 1, characterized in that The comparing the first spectrometer feature of the original image with the second spectrometer feature of the image to be detected, and determining whether to issue an alarm based on the comparison result, comprises: Comparing the number of spectrometers of the original image with the number of spectrometers of the image to be detected, and if the numbers are inconsistent, determining to issue an alarm; If the comparison results of the spectrometer coordinates and the spectrometer size are inconsistent, an alarm is issued.

3. The method according to claim 1 or 2, characterized in that: The spectrometer recognition network model is a neural network model, and the method further includes: Acquire a plurality of sample data, the sample data including an image of a beam splitter cabinet and labels of the number, size, and coordinates of corresponding beam splitters in the beam splitter cabinet; The neural network model is trained based on sample data to obtain the spectrometer recognition network model.

4. The method according to claim 3, characterized in that The neural network model is a yolo neural network model.

5. The method according to claim 1 or 2, characterized in that: The method further comprises: Capture the original image of the optical splitter in the target cabinet through the image acquisition terminal; The image to be detected of the spectrometer in the target cabinet is regularly collected by the image collection terminal.

6. A passive optical splitter detection device, characterized in that: include: A feature extraction module, used for acquiring a first spectrometer feature of an original image and a second spectrometer feature of an image to be detected based on a spectrometer recognition network model, wherein the first spectrometer feature and the second spectrometer feature both include the number of spectrometers, the size of the spectrometers, and the spectrometer coordinates; A comparison module, used for comparing the first spectrometer feature of the original image with the second spectrometer feature of the image to be detected, and determining whether to issue an alarm based on the comparison result; Wherein, the comparison module is used for: If the number of spectrometers in the original image is consistent with the number of spectrometers in the image to be detected, and the comparison results of the spectrometer coordinates and the spectrometer sizes are consistent, intercepting corresponding spectrometer images from the original image and the image to be detected respectively based on the spectrometer coordinates and the spectrometer sizes; Comparing the similarity between the spectrometer image of the original image and the spectrometer image of the image to be detected at the same coordinate position; Determining whether there is a private line based on the comparison result; The similarity comparison between the spectrometer image of the original image and the spectrometer image of the image to be detected at the same coordinate position includes: Acquire a histogram of the spectrometer image of the original image and the corresponding spectrometer image of the image to be detected at the same coordinate position; Performing a similarity comparison between a histogram of the spectrometer image of the original image and a histogram of the corresponding spectrometer image of the image to be detected; The similarity comparison between the histogram of the spectrometer image of the original image and the histogram of the corresponding spectrometer image of the image to be detected is determined based on the following formula: ； Wherein, H1 and H2 respectively represent the histogram data of the spectrometer image of the original image and the corresponding spectrometer image of the image to be detected.

7. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the passive optical splitter detection method according to any one of claims 1 to 5 is implemented.

8. An electronic device, characterized in that: include: one or more processors; A storage device, used for storing one or more programs, when the one or more programs are executed by the one or more processors, enables the one or more processors to implement the passive optical splitter detection method according to any one of claims 1 to 5.

Images