CN116152179A - Method, device, equipment and storage medium for detecting optical cable cross connecting cabinet - Google Patents
Method, device, equipment and storage medium for detecting optical cable cross connecting cabinet Download PDFInfo
- Publication number
- CN116152179A CN116152179A CN202211733552.4A CN202211733552A CN116152179A CN 116152179 A CN116152179 A CN 116152179A CN 202211733552 A CN202211733552 A CN 202211733552A CN 116152179 A CN116152179 A CN 116152179A
- Authority
- CN
- China
- Prior art keywords
- detection
- feature
- inputting
- information
- network
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/50—Photovoltaic [PV] energy
Abstract
The invention discloses a method, a device, equipment and a storage medium for detecting an optical cable cross connecting cabinet. According to the invention, a plurality of detection images of all detection parts of the optical cable cross connecting cabinet are firstly obtained, the detection parts contained in all detection images are different, and the detection parts comprise dust caps, holes and tail fibers. And then inputting the detection image containing the dust cap into a first detection model to perform first feature detection, and determining distribution feature information of the dust cap. And then inputting the detection image containing the holes into a second detection model to perform second feature detection, and determining the plugging feature information of the holes. And inputting the detection image containing the tail fiber into a third detection model for third feature detection, and determining the wiring feature information of the tail fiber. And finally, generating a detection result of the optical cable cross connecting cabinet according to the characteristic information. Therefore, the inspection record of the optical cable distributing box is generated according to the automatic detection of the multiple models, and the detection efficiency is improved.
Description
Technical Field
The present invention relates to the field of communications technologies, and in particular, to a method, an apparatus, a device, and a storage medium for detecting an optical cable cross-connecting box.
Background
The passive optical network is the most main bearing mode of the current broadband access network, and the optical cable cross-connecting box is used as a core passive facility in the passive optical network and bears important functions such as user optical signal distribution, routing jumper connection, transfer and the like. Therefore, the maintenance and detection of the optical cable cross-connecting cabinet are particularly important.
However, in the prior art, detection of the cable splice box is often performed by a maintenance person in the field, and a corresponding paper record is formed. This approach is not only time consuming and laborious, but also reduces the detection efficiency.
Disclosure of Invention
The present invention has been made in view of the above problems, and provides a method, apparatus, device and storage medium for detecting a cable cross-connect cabinet, which overcomes or at least partially solves the above problems.
Based on a first aspect of the present invention, there is provided a method for detecting an optical cable cross-connect box, the method comprising:
acquiring a plurality of detection images of all detection parts comprising the optical cable cross connecting box, wherein the detection parts contained in all detection images are different, and the detection parts comprise dust caps, holes and tail fibers;
inputting a detection image containing the dust cap into a first detection model to perform first feature detection, and determining distribution feature information of the dust cap;
inputting the detection image containing the holes into a second detection model to perform second feature detection, and determining plugging feature information of the holes;
inputting the detection image containing the tail fiber into a third detection model for third feature detection, and determining the wiring feature information of the tail fiber;
and generating a detection result of the optical cable cross connecting cabinet according to the distribution characteristic information, the plugging characteristic information and the wiring characteristic information.
Based on the second aspect of the present invention, there is also provided a detection device for an optical cable cross-connecting box, the device comprising:
the image acquisition module is used for acquiring a plurality of detection images of all detection parts of the optical cable cross connecting cabinet, wherein the detection parts contained in all the detection images are different, and the detection parts comprise dust caps, holes and tail fibers;
the first feature determining module is used for inputting the detection image containing the dust cap into a first detection model to perform first feature detection and determining distribution feature information of the dust cap;
the second feature determining module is used for inputting the detection image containing the holes into a second detection model to perform second feature detection and determining plugging feature information of the holes;
the third characteristic determining module is used for inputting the detection image containing the tail fiber into a third detection model to perform third characteristic detection and determining the wiring characteristic information of the tail fiber;
and the result generation module is used for generating a detection result of the optical cable cross connecting cabinet according to the distribution characteristic information, the plugging characteristic information and the wiring characteristic information.
Based on a third aspect of the present invention, there is also provided an electronic device, comprising:
one or more processors;
a memory;
one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to perform the method of any of the above.
Based on a fourth aspect of the present invention, there is also provided a computer readable storage medium storing a computer program for use in connection with an electronic device, the computer program being executable by a processor to perform any one of the methods described above.
Compared with the prior art, the method and the device have the advantages that a plurality of detection images of all detection positions of the optical cable cross connecting cabinet are firstly obtained, the detection positions contained in all detection images are different, and the detection positions comprise dust caps, holes and tail fibers. And then inputting the detection image containing the dust cap into a first detection model to perform first feature detection, and determining the distribution feature information of the dust cap. And then inputting the detection image containing the holes into a second detection model to perform second feature detection, and determining the plugging feature information of the holes. And inputting the detection image containing the tail fiber into a third detection model to perform third feature detection, and determining the wiring feature information of the tail fiber. And finally, generating a detection result of the optical cable cross connecting cabinet according to the distribution characteristic information, the plugging characteristic information and the wiring characteristic information. Therefore, after inspection photographing of maintenance personnel, the inspection record of the optical cable cross connecting cabinet is generated according to automatic detection of a plurality of models, so that the detection efficiency is improved, and time and labor are saved.
The foregoing description is only an overview of the present invention, and is intended to be implemented in accordance with the teachings of the present invention in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present invention more readily apparent.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to designate like parts throughout the figures.
In the drawings:
fig. 1 is a schematic step flow diagram of a method for detecting an optical cable cross-connecting box according to an embodiment of the present invention;
FIG. 2 is a schematic step flow diagram of another method for detecting an optical cable cross-connecting box according to an embodiment of the present invention;
FIG. 3 is a schematic view of a dust cap of an optical cable cross-connecting box according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a hole of an optical cable cross-connecting box according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of a fiber optic cable splice provided by an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a detection device for an optical cable cross-connecting box according to an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
Referring to fig. 1, a method for detecting an optical cable cross-connecting box provided by an embodiment of the present invention is shown, where the method may include:
s101, acquiring a plurality of detection images of all detection positions of the optical cable cross connecting cabinet, wherein the detection positions contained in all detection images are different, and each detection position comprises a dust cap, a hole and a tail fiber.
In the embodiment of the invention, each detection part of the optical cable cross connecting box can be shot through the imaging device, so that a plurality of detection images containing different detection parts can be obtained. The camera device is moved in a handheld manner by maintenance personnel during inspection. For example, when different detection sites are photographed, different image identifications are used to mark the detection images of the different detection sites.
Referring to fig. 3, the dust cap is used for sealing the connection terminal on the terminal panel in the optical cable cross connecting box, so that the influence on the performance of the optical cable due to the fact that impurities such as dust enter the connection terminal under the condition that no service plug wire exists on the connection terminal is avoided. Therefore, no terminal of service plug wire needs to be sleeved with a dust prevention cap. If the detection device is not sleeved, the detection device is determined to be out of compliance in detection of the dust cap.
Referring to fig. 4, the hole is located at the lower part of the optical cable cross-connecting box, and is used for providing a penetrating path of service plugs such as optical cables. However, in order to realize the functions of water resistance, moisture resistance, theft prevention and the like, the holes are required to be plugged by plugging pugs after the line is laid. Therefore, when all the holes in the optical cable distributing box are in a blocking state, the hole detection compliance is described; when one of the plurality of holes is not in a plugged state (also referred to as a unblocked state), the hole detection is not compliant.
Referring to fig. 5, the tail fiber is detected, mainly to detect whether the routing of the tail fiber is compliant. For example, each bundle of tail fibers is strictly regular, the wiring is orderly, and the tail fiber detection compliance is determined. If the wiring is disordered and shielding winding and the like exist, the tail fiber detection is not legal.
S102, inputting the detection image containing the dust cap into a first detection model to perform first feature detection, and determining distribution feature information of the dust cap.
S103, inputting the detection image containing the holes into a second detection model to perform second feature detection, and determining the plugging feature information of the holes.
S104, inputting the detection image containing the tail fiber into a third detection model for third feature detection, and determining the wiring feature information of the tail fiber.
In the embodiment of the invention, the detection image containing the dustproof cap can be input into the first detection model to carry out first feature detection, the detection image containing the hole is input into the second detection model to carry out second feature detection, and the detection image containing the tail fiber is input into the third detection model to carry out third feature detection. The first detection model, the second detection model and the third detection model are all obtained through deep learning training, and can be used for rapidly identifying the detection images after obtaining the corresponding detection images, so that the detection efficiency and the detection accuracy of the optical cable cross connecting box are improved.
In an embodiment, the distribution characteristic information may include a terminal position and number of the terminal panel where the dust cap is not sleeved on the terminal; the plugging feature information may include a current state of the hole; the routing characteristic information may include a current routing state of the pigtail.
S105, generating a detection result of the optical cable cross connecting cabinet according to the distribution characteristic information, the plugging characteristic information and the wiring characteristic information.
In the embodiment of the invention, the characteristic information, the plugging characteristic information and the wiring characteristic information can be comprehensively distributed to generate the detection result of the optical cable cross connecting cabinet. Therefore, after the maintenance personnel finish inspection, the inspection record is automatically generated, and the detection efficiency is improved.
Referring to fig. 2, another method for detecting an optical cable cross-connecting box according to an embodiment of the present invention is shown, where the method may include:
s201, acquiring a plurality of detection images of all detection parts comprising the optical cable cross connecting cabinet, wherein the detection parts contained in all detection images are different, and the detection parts comprise dust caps, holes and tail fibers.
In the embodiment of the present invention, the description of step S201 refers to the description of step S101.
In one embodiment, the first detection model may include a first feature network and a target detection network, where the first feature network is used to extract image features of a detection image including the dust cap, and the target detection network is used to predict positions and numbers of terminals on the terminal panel, where the dust cap is not sleeved, according to the image features.
S202, inputting the detection image containing the dust cap into the first feature network to perform first feature extraction, and obtaining first feature information corresponding to the detection image.
In the embodiment of the present invention, the first feature network may further include a first feature extraction module and a first feature fusion module.
And inputting the detection image containing the dust cap into the first feature extraction module to extract first features, and obtaining a plurality of pieces of first extraction information corresponding to the detection image.
And respectively inputting the plurality of first extraction information into the first feature fusion module to carry out first feature fusion to obtain first feature information corresponding to the detection image.
In an example, the first feature extraction module may include a plurality of cascaded convolution layers, so as to obtain a plurality of first extraction information corresponding to the detection image including the dust cap. The first extraction information may be a convolution layer output convolution feature image of a corresponding hierarchy. After feature extraction is performed on the convolution layers of each layer, the obtained convolution feature image is sent to the convolution layer of the next layer to continue feature extraction, and on the one hand, the convolution feature image can be used as first extraction information and output to the outside of the first feature network, so that feature fusion is conveniently performed on a plurality of first extraction information in the later stage. The image resolutions corresponding to the plurality of first extraction information are different.
And respectively inputting the plurality of first extraction information into the first feature fusion module to carry out first feature fusion to obtain first feature information corresponding to the detection image. The first feature fusion module is used for carrying out multi-scale fusion on feature images of different levels, and sending first feature information obtained through the first feature fusion module into a target detection network. In an embodiment, the first feature fusion network may include a plurality of feature fusion modules. For example, each feature fusion module is used for fusing feature images of two adjacent levels. Fusion can be understood as performing image stitching on two levels of feature images. For feature images of two levels, upsampling may be performed on first extraction information of a lower level (which may be understood as lower image resolution) to make its image resolution coincide with first extraction information of a higher level (which may be understood as higher image resolution). The length and the width of the detection images are consistent, and then splicing operation is carried out, so that semantic expressions of the detection images on different levels can be obtained. And further improving the recognition accuracy of the subsequent target detection network to the dust cap. Correspondingly, the dimensions of the different first characteristic information are different (also understood as different image resolution).
S203, inputting the first characteristic information into the target detection network for first characteristic identification, and determining the distribution characteristic information of the dust cap.
In the embodiment of the invention, the target detection network comprises a plurality of detection head modules and a second feature fusion module. The detection heads are used for identifying first characteristic information of different scales respectively. And respectively inputting the plurality of first characteristic information into a detection head module with a corresponding scale to conduct first characteristic prediction to obtain a plurality of prediction characteristic information corresponding to the detection image, wherein the prediction characteristic information comprises prediction frame information of the dust cap.
In an embodiment, the detection head module includes a feature image of the dust cap obtained by training. The characteristic image of the dust cap is mainly characterized in that: small size and high resolution, thereby facilitating feature recognition of small-sized dust caps. In the first feature prediction process, the detection head module calculates feature similarity between the first feature information and the feature image at the same position, and if the similarity is greater than or equal to a preset threshold value, it is determined that the dust cap exists in the prediction frame at the corresponding position. And if the similarity is smaller than a preset threshold value, determining that the dust cap is not in the prediction frame of the corresponding position. And by analogy, obtaining the prediction characteristic information corresponding to the detected image.
In consideration of possible differences of the prediction feature information obtained on different scales, a plurality of prediction feature information can be input into the second feature fusion module to carry out second feature fusion, so that the distribution feature information of the dust cap is determined. The second feature fusion module is configured to synthesize a plurality of prediction feature information, output final prediction feature information, for example, in the process of second feature fusion, according to each feature weight value determined by an attention mechanism, multiply a feature vector corresponding to each prediction feature information with each feature weight value, and then accumulate to obtain final prediction feature information of the detected image.
In an alternative embodiment of the invention, the second detection model may include an image-cutting network, a second feature network, and a classification network.
S204, inputting the detection image containing the holes into the image cutting network for image cutting to obtain a plurality of second images.
S205, inputting a plurality of second images into the second feature network in sequence to perform feature extraction, and obtaining corresponding second feature information.
S206, inputting the second characteristic information into the classification network for classification prediction, and determining the plugging characteristic information of the holes.
In the embodiment of the present invention, the image cutting network is used for image cutting, and when the detected image including the hole is input into the image cutting network, a plurality of second images with identical resolutions may be obtained, for example, N second images with 16 x 16 may be obtained, and correspondingly, the resolution corresponding to the detected image including the hole is preset and is in a multiple relationship with the resolution of the second image, for example, the resolution of the detected image including the hole may be 224 x 224.
The second feature network may further include a second mapping module, a second encoding module, and other structures, and the plurality of second images are input into the second feature network according to the cutting sequence of the images to perform feature extraction. And firstly, performing convolution operation on each second image, and sequentially and respectively inputting the characteristic information obtained after the convolution operation of each second image into the second mapping module to perform linear mapping to obtain the linear characteristic information after the combination of each second image. And inputting the linear characteristic information into the second coding module for compiling and converting to obtain corresponding second characteristic information. And obtaining second characteristic information of the detection image containing the holes, wherein the second characteristic information is a one-dimensional vector.
The classification network is used for determining whether the hole is in a blocking state or a dredging state according to the second characteristic information. The training images of the classification network can be hole images with different shooting angles under different illumination. Wherein, the holes in the training images comprise two states of blocking and dredging. And inputting the training image into the classification network to perform classification prediction to obtain the prediction category of the training image. And determining a loss function value (the loss function can adopt a cross entropy loss function) of the classification model based on the predicted category and the real category of the training image, and adjusting network parameters of the classification network according to the loss function value to determine the classification network after training.
S207, inputting the detection image containing the tail fibers into the third feature network for third feature extraction to obtain a plurality of third feature images containing the wiring textures of the tail fibers.
S208, inputting a plurality of third characteristic images into the characteristic aggregation network to perform characteristic identification, and determining the wiring characteristic information of the tail fiber.
In an embodiment of the present invention, the third detection model may include a third feature network and a feature aggregation network. And inputting the detection image containing the tail fiber into the third characteristic network to perform third characteristic extraction. In the process of extracting the third features, features with different resolutions of the images can be generated through different convolution modules in the third feature network, so that a plurality of third feature images containing the routing textures of the tail fibers can be obtained, wherein the image resolutions of the plurality of third feature images are different.
The feature aggregation network is used for aggregating features with different resolutions, namely, third feature images with different image resolutions are converted into the same image resolution in an up-sampling or down-sampling mode, then feature images with the same image resolution are spliced to obtain an aggregate feature image, and through identification of the aggregate feature image, wiring feature information of the tail fiber is determined, wherein the wiring feature information can comprise two categories of orderly wiring and disordered wiring.
The training image of the third detection model can adopt images comprising two types of tail fibers, the training image is input into the third detection model for recognition to obtain a prediction type, a loss function value of the third detection model is determined according to the prediction type and the real type of the training image, model parameters are adjusted according to the loss function value, and a trained third detection model is determined, wherein parameter adjustment is stopped when the loss function value is reduced by a small extent or is unchanged.
209. And generating a detection result of the optical cable cross connecting cabinet according to the distribution characteristic information, the plugging characteristic information and the wiring characteristic information.
In the embodiment of the invention, the characteristic information, the plugging characteristic information and the wiring characteristic information can be comprehensively distributed to generate the detection result of the optical cable cross connecting cabinet. For example, according to the distribution characteristic information, it can be determined that all the wiring terminals which are not wired on the terminal panel are sleeved with dust caps; the current state of the hole can be determined to be a blocking state according to the blocking characteristic information; and determining that the current wiring state of the tail fiber is tidy according to the wiring characteristic information. The corresponding detection result may be as follows: the dust cap detects compliance, and the hole detects compliance, and the pigtail detects compliance. Therefore, after maintenance personnel finish inspection, the inspection record of the optical cable cross connecting cabinet is automatically generated, and the detection efficiency is improved.
In summary, an embodiment of the present invention discloses a method for detecting an optical cable cross-connecting box, where the method may include first acquiring a plurality of detection images including detection positions of the optical cable cross-connecting box, where the detection positions included in the detection images are different, and the detection positions include a dust cap, a hole, and a tail fiber. And then inputting the detection image containing the dust cap into a first detection model to perform first feature detection, and determining the distribution feature information of the dust cap. And then inputting the detection image containing the holes into a second detection model to perform second feature detection, and determining the plugging feature information of the holes. And inputting the detection image containing the tail fiber into a third detection model to perform third feature detection, and determining the wiring feature information of the tail fiber. And finally, generating a detection result of the optical cable cross connecting cabinet according to the distribution characteristic information, the plugging characteristic information and the wiring characteristic information. Therefore, after inspection photographing of maintenance personnel, the inspection record of the optical cable cross connecting cabinet is generated according to automatic detection of a plurality of models, so that the detection efficiency is improved, and time and labor are saved.
It should be noted that, for simplicity of description, the method embodiments are shown as a series of acts, but it should be understood by those skilled in the art that the embodiments are not limited by the order of acts described, as some steps may occur in other orders or concurrently in accordance with the embodiments. Further, those skilled in the art will appreciate that the embodiments described in the specification are all preferred embodiments and that the acts referred to are not necessarily required by the embodiments of the present application.
Referring to fig. 6, a detection apparatus for an optical cable cross-connecting box provided by an embodiment of the present invention is shown, where the apparatus may include:
the image acquisition module 601 is configured to acquire a plurality of detection images including detection positions of the optical cable cross-connecting box, where the detection positions included in the detection images are different, and the detection positions include a dust cap, a hole, and a tail fiber;
the first feature determining module 602 is configured to input a detection image including the dust cap into a first detection model to perform first feature detection, and determine distribution feature information of the dust cap;
the second feature determining module 603 is configured to input a detection image including the hole into a second detection model to perform second feature detection, and determine plugging feature information of the hole;
the third feature determining module 604 is configured to input a detection image including the tail fiber into a third detection model to perform third feature detection, and determine routing feature information of the tail fiber;
and the result generating module 605 is configured to generate a detection result of the optical cable cross connecting cabinet according to the distribution characteristic information, the plugging characteristic information and the routing characteristic information.
In an alternative embodiment of the invention, the first detection model includes a first feature network and an object detection network, and the first feature determining module 602 may include:
and the first feature extraction sub-module is used for inputting the detection image containing the dust cap into the first feature network to perform first feature extraction so as to obtain first feature information corresponding to the detection image.
And the first characteristic identification sub-module is used for inputting the first characteristic information into the target detection network to carry out first characteristic identification and determining the distribution characteristic information of the dust cap.
In an optional embodiment of the invention, the first feature network includes a first feature extraction module and a first feature fusion module, and the first feature extraction sub-module may further include:
and the first feature extraction unit is used for inputting the detection image containing the dust cap into the first feature extraction module for first feature extraction to obtain a plurality of first extraction information corresponding to the detection image.
And the first feature fusion unit is used for inputting the plurality of first extraction information into the first feature fusion module respectively to carry out first feature fusion so as to obtain first feature information corresponding to the detection image.
In an alternative embodiment of the invention, the target detection network includes a plurality of detection head modules and a second feature fusion module, and the first feature identification sub-module may include:
the first feature prediction unit is used for inputting a plurality of first feature information into the plurality of detection head modules respectively to perform first feature prediction to obtain a plurality of prediction feature information corresponding to the detection image, wherein the prediction feature information comprises a prediction frame of the dust cap.
And the second feature fusion unit is used for inputting the plurality of predicted feature information into the second feature fusion module to perform second feature fusion, so as to obtain the distribution feature information of the dust cap.
In an alternative embodiment of the invention, the second detection model includes an image cutting network, a second feature network, and a classification network, and the second feature determining module 603 may include:
and the image cutting sub-module is used for inputting the detection image containing the holes into the image cutting network to perform image cutting so as to obtain a plurality of second images.
And the feature extraction sub-module is used for inputting a plurality of second images into the second feature network in sequence to perform feature extraction so as to obtain corresponding second feature information.
And the classification prediction sub-module is used for inputting the second characteristic information into the classification network to perform classification prediction and determining the plugging characteristic information of the holes.
An alternative inventive embodiment, the second feature network comprises a second mapping module and a second encoding module, the feature extraction submodule further being adapted to:
and sequentially inputting a plurality of second images into the second mapping module respectively for linear mapping to obtain the linear characteristic information of each second image after combination.
And inputting the linear characteristic information into the second coding module for compiling and converting to obtain corresponding second characteristic information.
In an alternative embodiment of the invention, the third feature determining module 604 may include:
and the third feature extraction sub-module is used for inputting the detection image containing the tail fiber into the third feature network to perform third feature extraction to obtain a plurality of third feature images containing the wiring textures of the tail fiber, wherein the image resolutions of the plurality of third feature images are different.
And the characteristic identification sub-module is used for inputting a plurality of third characteristic images into the characteristic aggregation network to carry out characteristic identification and determining the routing characteristic information of the tail fiber.
In summary, the embodiment of the invention discloses a detection device for an optical cable cross-connecting box, which can comprise the steps of firstly acquiring a plurality of detection images containing detection parts of the optical cable cross-connecting box, wherein the detection parts contained in the detection images are different, and the detection parts comprise dust caps, holes and tail fibers. And then inputting the detection image containing the dust cap into a first detection model to perform first feature detection, and determining the distribution feature information of the dust cap. And then inputting the detection image containing the holes into a second detection model to perform second feature detection, and determining the plugging feature information of the holes. And inputting the detection image containing the tail fiber into a third detection model to perform third feature detection, and determining the wiring feature information of the tail fiber. And finally, generating a detection result of the optical cable cross connecting cabinet according to the distribution characteristic information, the plugging characteristic information and the wiring characteristic information. Therefore, after inspection photographing of maintenance personnel, the inspection record of the optical cable cross connecting cabinet is generated according to automatic detection of a plurality of models, so that the detection efficiency is improved, and time and labor are saved.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described by differences from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other.
As will be readily appreciated by those skilled in the art: any combination of the above embodiments is possible, and thus is an embodiment of the present invention, but the present specification is not limited by the text.
In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the above description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be construed as reflecting the intention that: i.e., the claimed invention requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules in the apparatus of the embodiments may be adaptively changed and disposed in one or more apparatuses different from the embodiments. The modules or units or components of the embodiments may be combined into one module or unit or component and, furthermore, they may be divided into a plurality of sub-modules or sub-units or sub-components. Any combination of all features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or units of any method or apparatus so disclosed, may be used in combination, except insofar as at least some of such features and/or processes or units are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings), may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
An electronic device, comprising:
one or more processors;
a memory;
one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to perform the methods described in the above embodiments.
A computer readable storage medium storing a computer program for use in connection with an electronic device, the computer program being executable by a processor to perform the method of the above embodiments.
It will be apparent to those skilled in the art that embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the invention may take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiment and all such alterations and modifications as fall within the scope of the embodiments of the invention.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or terminal device comprising the element.
The above description of the method for detecting the optical cable cross-connecting box and the device for detecting the optical cable cross-connecting box provided by the invention applies specific examples to illustrate the principle and the implementation of the invention, and the description of the above examples is only used for helping to understand the method and the core idea of the invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.
Claims (10)
1. A method for detecting an optical cable cross-connect cabinet, the method comprising:
acquiring a plurality of detection images of all detection parts comprising the optical cable cross connecting box, wherein the detection parts contained in all detection images are different, and the detection parts comprise dust caps, holes and tail fibers;
inputting a detection image containing the dust cap into a first detection model to perform first feature detection, and determining distribution feature information of the dust cap;
inputting the detection image containing the holes into a second detection model to perform second feature detection, and determining plugging feature information of the holes;
inputting the detection image containing the tail fiber into a third detection model for third feature detection, and determining the wiring feature information of the tail fiber;
and generating a detection result of the optical cable cross connecting cabinet according to the distribution characteristic information, the plugging characteristic information and the wiring characteristic information.
2. The method for detecting an optical cable cross-connecting cabinet according to claim 1, wherein the first detection model includes a first feature network and a target detection network, the detecting image including the dust cap is input into the first detection model to perform first feature detection, and determining distribution feature information of the dust cap includes:
inputting a detection image containing the dust cap into the first feature network to perform first feature extraction to obtain first feature information corresponding to the detection image;
and inputting the first characteristic information into the target detection network for first characteristic identification, and determining the distribution characteristic information of the dust cap.
3. The method for detecting an optical cable cross-connecting cabinet according to claim 2, wherein the first feature network includes a first feature extraction module and a first feature fusion module, the inputting the detection image including the dust cap into the first feature network to perform first feature extraction, and obtaining first feature information corresponding to the detection image includes:
inputting the detection image containing the dust cap into the first feature extraction module to perform first feature extraction to obtain a plurality of pieces of first extraction information corresponding to the detection image;
and respectively inputting the plurality of first extraction information into the first feature fusion module to carry out first feature fusion to obtain first feature information corresponding to the detection image.
4. The method for detecting an optical cable cross-connect cabinet according to claim 3, wherein the target detection network includes a plurality of detection head modules and a second feature fusion module, the inputting the first feature information into the target detection network for first feature recognition, determining the distribution feature information of the dust cap includes:
inputting a plurality of first characteristic information into a plurality of detection head modules respectively for first characteristic prediction to obtain a plurality of prediction characteristic information corresponding to the detection image, wherein the prediction characteristic information comprises a prediction frame of the dust cap;
and inputting the plurality of prediction characteristic information into the second characteristic fusion module to carry out second characteristic fusion, so as to obtain the distribution characteristic information of the dust cap.
5. The method for detecting an optical cable cross-connecting cabinet according to claim 1, wherein the second detection model includes an image cutting network, a second feature network and a classification network, the detecting image including the hole is input into the second detection model for second feature detection, and determining the plugging feature information of the hole includes:
inputting the detection image containing the holes into the image cutting network for image cutting to obtain a plurality of second images;
sequentially inputting a plurality of second images into the second feature network to perform feature extraction to obtain corresponding second feature information;
and inputting the second characteristic information into the classification network for classification prediction, and determining the plugging characteristic information of the holes.
6. The method for detecting an optical cable cross-connect cabinet according to claim 5, wherein the second feature network includes a second mapping module and a second encoding module, the sequentially inputting a plurality of second images into the second feature network for feature extraction, and obtaining corresponding second feature information, including:
sequentially inputting a plurality of second images into the second mapping module respectively for linear mapping to obtain linear characteristic information of each second image after combination;
and inputting the linear characteristic information into the second coding module for compiling and converting to obtain corresponding second characteristic information.
7. The method for detecting an optical cable cross-connecting cabinet according to claim 1, wherein the third detection model includes a third feature network and a feature aggregation network, the detecting image including the tail fiber is input into the third detection model to perform third feature detection, and determining routing feature information of the tail fiber includes:
inputting the detection image containing the tail fiber into the third feature network for third feature extraction to obtain a plurality of third feature images containing the wiring textures of the tail fiber, wherein the image resolutions of the plurality of third feature images are different;
and inputting a plurality of third characteristic images into the characteristic aggregation network to perform characteristic identification, and determining the routing characteristic information of the tail fiber.
8. A device for detecting an optical cable cross-connect cabinet, the device comprising:
the image acquisition module is used for acquiring a plurality of detection images of all detection parts of the optical cable cross connecting cabinet, wherein the detection parts contained in all the detection images are different, and the detection parts comprise dust caps, holes and tail fibers;
the first feature determining module is used for inputting the detection image containing the dust cap into a first detection model to perform first feature detection and determining distribution feature information of the dust cap;
the second feature determining module is used for inputting the detection image containing the holes into a second detection model to perform second feature detection and determining plugging feature information of the holes;
the third characteristic determining module is used for inputting the detection image containing the tail fiber into a third detection model to perform third characteristic detection and determining the wiring characteristic information of the tail fiber;
and the result generation module is used for generating a detection result of the optical cable cross connecting cabinet according to the distribution characteristic information, the plugging characteristic information and the wiring characteristic information.
9. An electronic device, comprising:
one or more processors;
a memory;
one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs configured to perform the method of any of claims 1-7.
10. A computer readable storage medium storing a computer program for use in connection with an electronic device, the computer program being executable by a processor to perform the method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211733552.4A CN116152179A (en) | 2022-12-30 | 2022-12-30 | Method, device, equipment and storage medium for detecting optical cable cross connecting cabinet |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211733552.4A CN116152179A (en) | 2022-12-30 | 2022-12-30 | Method, device, equipment and storage medium for detecting optical cable cross connecting cabinet |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116152179A true CN116152179A (en) | 2023-05-23 |
Family
ID=86340113
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211733552.4A Pending CN116152179A (en) | 2022-12-30 | 2022-12-30 | Method, device, equipment and storage medium for detecting optical cable cross connecting cabinet |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116152179A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117232577A (en) * | 2023-09-18 | 2023-12-15 | 杭州奥克光电设备有限公司 | Optical cable distributing box bearing interior monitoring method and system and optical cable distributing box |
-
2022
- 2022-12-30 CN CN202211733552.4A patent/CN116152179A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117232577A (en) * | 2023-09-18 | 2023-12-15 | 杭州奥克光电设备有限公司 | Optical cable distributing box bearing interior monitoring method and system and optical cable distributing box |
| CN117232577B (en) * | 2023-09-18 | 2024-04-05 | 杭州奥克光电设备有限公司 | Optical cable distributing box bearing interior monitoring method and system and optical cable distributing box |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108416028B (en) | Method, device and server for searching content resources | |
| CN110853033B (en) | Video detection method and device based on inter-frame similarity | |
| US11481862B2 (en) | System and method for real-time, simultaneous object detection and semantic segmentation | |
| US20160335493A1 (en) | Method, apparatus, and non-transitory computer-readable storage medium for matching text to images | |
| CN109508404B (en) | Maintenance teaching video management method and device, terminal equipment and storage medium | |
| CN116152179A (en) | Method, device, equipment and storage medium for detecting optical cable cross connecting cabinet | |
| CN112465049A (en) | Method and device for generating anomaly detection model and method and device for detecting anomaly event | |
| CN108881947A (en) | A kind of infringement detection method and device of live stream | |
| CN107133951B (en) | Image tampering detection method and device | |
| CN114863221A (en) | Training method, device, system, equipment and storage medium for detection model | |
| CN111044149A (en) | Method and device for detecting temperature abnormal point of voltage transformer and readable storage medium | |
| CN203083532U (en) | A system used for detecting the safe operation of a power transmission line | |
| CN113076961B (en) | Image feature library updating method, image detection method and device | |
| CN112163480A (en) | Behavior identification method and device | |
| CN114743217A (en) | Pedestrian identification method based on local feature perception image-text cross-modal model and model training method | |
| CN117033981A (en) | Submarine cable fault detection method, submarine cable fault detection device, submarine cable fault detection equipment and submarine cable fault detection medium | |
| CN113378118B (en) | Method, apparatus, electronic device and computer storage medium for processing image data | |
| CN110716857B (en) | Test case management method, device, computer equipment and storage medium | |
| CN106874829A (en) | The method for improving the reliability of monitoring system | |
| CN115909408A (en) | Pedestrian re-identification method and device based on Transformer network | |
| CN109783713A (en) | A kind of dynamic website classification method, system, equipment and medium | |
| CN114638304A (en) | Training method of image recognition model, image recognition method and device | |
| Zheng et al. | Exif as language: Learning cross-modal associations between images and camera metadata | |
| US11200583B2 (en) | Using surface textures as unique identifiers for tracking material with a distributed ledger | |
| CN110909798A (en) | Multi-algorithm intelligent studying and judging method, system and server |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |