Intelligent visual perception and early warning method and device for steam pipe network and computer equipment

Abstract

The invention relates to an intelligent visual perception and early warning method and device for a steam pipe network and computer equipment. The method comprises the following steps: acquiring image information of a leakage pipeline; performing frame insertion processing on the image information to obtain steam cloud data; performing target feature extraction on the steam cloud data to generate a visual recognition model; and recognizing a current pipeline image according to the visual recognition model, and generating prompt information. By the adoption of the method, the steam pipe network can be monitored in real time, and the abnormal state of the steam conveying pipeline can be recognized and early warned. On the basis of the Internet of Things technology, real-time intelligent visual perception is carried out on key links of the whole steam pipe network, the heat supply state of the whole steam pipe network is comprehensively mastered, emergency situations are rapidly and accurately reflected, convenience is brought to managers to check, repair and maintain in time, scientific and accurate information is provided for comprehensive management of a heat supply station, and the management level is made to be higher.

Description

Technical Field

[0001] The present application relates to the technical field of steam pipe network monitoring, and in particular to a method, device and computer equipment for intelligent visual perception and early warning of steam pipe networks. Background Art

[0002] With the development of the supply and demand system of industrial parks, decentralized clusters exist between heating stations and users. The steam pipeline network is reasonably arranged on the basis of meeting the design specifications. However, there is no shortage of scenarios in which the steam pipeline is laid across the U-bends, corners, and under viaducts in the heating radiation area due to many reasons, which may easily cause physical collisions and steam leakage.

[0003] The steam power system consists of three parts: the heating station, the steam pipeline network, and the end users. The steam pipeline network, as an important part of the steam power system, is responsible for timely transporting and distributing the steam from the heating station to each end user, and serves as a bridge connecting the source end and the load end. There are many scenarios for steam transportation in general industrial parks, such as U-bends across highways, passing through viaducts and railways, and laying around residential activity areas. Due to the large heating range, long steam pipelines, and complex environmental conditions, manual inspections are difficult. When the steam pipeline leaks due to rust, large vehicles collide and leak due to over-limit, and foreign objects collide and displace and fall off the bracket, it is difficult for managers to discover abnormal phenomena in the first time. If they are not discovered and remedied in time, it will not only cause economic losses and pollute the environment, but also endanger personal safety and even cause disasters.

[0004] Traditional park steam pipeline transportation monitoring generally uses remote flow, pressure, temperature and other instruments installed at the steam start and end, and judges whether the steam pipeline has leaks by analyzing the long-term difference values ​​in the instrument data, or the management personnel regularly inspect the steam pipelines along the way. This method is not real-time, and cannot detect minor leaks or pipeline deformation in time when a collision occurs. Summary of the invention

[0005] Based on this, it is necessary to provide a steam pipeline network intelligent visual perception and early warning method, device, computer equipment, computer readable storage medium and computer program product that can timely detect steam pipeline leaks in response to the above technical problems.

[0006] In a first aspect, the present application provides a steam pipeline network intelligent visual perception and early warning method. The method comprises:

[0007] Obtain image information of leaking pipeline;

[0008] Performing frame interpolation processing on the image information to obtain steam cloud data;

[0009] Extract target features from the steam cloud data to generate a visual recognition model;

[0010] The current pipeline image is identified according to the visual recognition model, and prompt information is generated.

[0011] In one of the embodiments, the image information includes a plurality of continuous frame images;

[0012] Perform interpolation processing on adjacent frame images to obtain interpolation results;

[0013] Perform background interpolation operation according to the interpolation result to obtain a background interpolation result;

[0014] The steam cloud data is obtained by performing an OR operation based on the interpolation result and the background interpolation result.

[0015] In one of the embodiments, the steam cloud data is subjected to dimensionality reduction processing to obtain a dimensionality reduction space sequence;

[0016] The target features are extracted from the reduced-dimensional space sequence, and a supervised learning SVM network is built to generate a visual recognition model.

[0017] In one of the embodiments, the pipeline and the environmental background in the image information are segmented to obtain a pipeline edge model;

[0018] Prompt information is generated according to the degree of overlap between the pipeline edge model and the initial shape of the pipeline.

[0019] In one of the embodiments, detecting whether the overlap between the pipeline edge model and the initial shape of the pipeline exceeds a preset overlap threshold;

[0020] If the overlap between the pipeline edge model and the initial shape of the pipeline exceeds a preset overlap threshold, an abnormal prompt is generated;

[0021] If the overlap between the pipeline edge model and the initial shape of the pipeline does not exceed a preset overlap threshold, a normal prompt is generated.

[0022] In one of the embodiments, obtaining temperature information;

[0023] Prompt information is generated according to the visual recognition model, the temperature information and the overlap degree.

[0024] In a second aspect, the present application also provides a steam pipe network intelligent visual perception and early warning device. The device comprises:

[0025] An image acquisition module, used to acquire image information of the leaking pipeline;

[0026] A frame insertion processing module, used for performing frame insertion processing on the image information to obtain steam cloud data;

[0027] A model generation module, used for extracting target features from the steam cloud data and generating a visual recognition model;

[0028] The information prompt module is used to identify the current pipeline image according to the visual recognition model and generate prompt information.

[0029] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0030] Obtain image information of leaking pipeline;

[0031] Performing frame interpolation processing on the image information to obtain steam cloud data;

[0032] Extract target features from the steam cloud data to generate a visual recognition model;

[0033] The current pipeline image is identified according to the visual recognition model, and prompt information is generated.

[0034] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0035] Obtain image information of leaking pipeline;

[0036] Performing frame interpolation processing on the image information to obtain steam cloud data;

[0037] Extract target features from the steam cloud data to generate a visual recognition model;

[0038] The current pipeline image is identified according to the visual recognition model, and prompt information is generated.

[0039] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0040] Obtain image information of leaking pipeline;

[0041] Performing frame interpolation processing on the image information to obtain steam cloud data;

[0042] Extract target features from the steam cloud data to generate a visual recognition model;

[0043] The current pipeline image is identified according to the visual recognition model, and prompt information is generated.

[0044] The above-mentioned intelligent visual perception and early warning method, device and computer equipment of the steam pipe network obtain image information of the leaking pipe; perform interpolation processing on the image information to obtain steam cloud data; perform target feature extraction on the steam cloud data to generate a visual recognition model; recognize the current pipeline image according to the visual recognition model to generate prompt information. The present invention monitors the steam pipe network in real time and identifies and warns of abnormal conditions of the steam transport pipe. Based on the Internet of Things technology, real-time intelligent visual perception is performed on the key links of the entire steam pipe network, the heating status of the entire steam pipeline is fully grasped, and sudden situations are reflected quickly and accurately, which facilitates management personnel to check and maintain in time, and provides scientific and accurate information for the comprehensive management of the heating station, so that the management level is taken to a higher level. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 is an application environment diagram of a steam pipe network intelligent visual perception and early warning method in one embodiment;

[0046] Figure 2 A schematic diagram of a process of a steam pipe network intelligent visual perception and early warning method in one embodiment;

[0047] Figure 3 A schematic diagram of a flow chart of a steam pipe network intelligent visual perception and early warning method in another embodiment;

[0048] Figure 4 is a structural block diagram of an intelligent visual perception and early warning device for a steam pipe network in one embodiment;

[0049] Figure 5 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0051] The steam pipe network intelligent visual perception and early warning method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The server 104 obtains the image information of the leaking pipeline; interpolates the image information to obtain steam cloud data; extracts target features from the steam cloud data to generate a visual recognition model; identifies the current pipeline image according to the visual recognition model to generate prompt information. Among them, the terminal 102 can be but is not limited to various personal computers, laptops, smart phones, tablets, Internet of Things devices and portable wearable devices. The Internet of Things devices can be cameras, instruments, sensor devices, etc. Portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The server 104 can be implemented with an independent server or a server cluster consisting of multiple servers.

[0052] In one embodiment, Figure 2 As shown, a steam pipeline network intelligent visual perception and early warning method is provided, and the method is applied to Figure 1 Taking the server 104 in the example as an example, the following steps are included:

[0053] Step 202, obtaining image information of the leaking pipeline;

[0054] The image information includes a plurality of continuous frame images.

[0055] Step 204, interpolating the image information to obtain steam cloud data.

[0056] Specifically, adjacent frame images are interpolated to obtain an interpolation result; a background interpolation operation is performed based on the interpolation result to obtain a background interpolation result; and an OR operation is performed based on the interpolation result and the background interpolation result to obtain steam cloud data.

[0057] In one embodiment, a frame image of a frame in the image information is extracted, and two adjacent frame images before and after the frame image are interpolated. The specific formula is as follows:

[0058]

[0059] Among them, R m is the judgment result; T is the judgment threshold.

[0060] Perform an AND operation on the mth scout image and the judgment results of the two scout images before and after it to obtain the mth scout five-scan interpolation result F m The five-detection and insertion results of the infrared streaming media multi-detection obtained in a time period are accumulated to obtain F, which is the insertion frame result.

[0061]

[0062] The expected value of m in the interpolation result is taken as the background B, and then the frame image of the kth frame in the image information is extracted to perform background interpolation operation on it. The specific formula is as follows:

[0063]

[0064] Among them, the background model B is continuously updated with the duration of streaming media, σ is the first background learning rate, and β is the second background learning rate.

[0065] Finally, the interpolation result is ORed with the background interpolation result to obtain the steam cloud data of the image information.

[0066] Step 206: extract target features from the steam cloud data to generate a visual recognition model.

[0067] Specifically, the steam cloud data is subjected to dimensionality reduction processing to obtain a reduced-dimensional space sequence; target features are extracted from the reduced-dimensional space sequence, and a supervised learning SVM network is built to generate a visual recognition model.

[0068] In one embodiment, for the steam cloud data, the principal component analysis method (PCA) is used to reduce the dimension of the steam cloud data, retain the main features and remove the pseudo features. Suppose a large-dimensional numerical vector of the steam cloud is X = {X1, X2, ..., X n}. The specific formula is as follows:

[0069]

[0070] in, is the large-dimensional numerical vector of the steam cloud image, COV(X,Y) is the mean and covariance matrix of the data set.

[0071] Reduce the high-latitude data of the steam cloud data to low-latitude data and select the eigenvector ν i and eigenvalue λ i , set the eigenvalue fitness λ T , obtain a dimensionality reduction space sequence W = (w1, w2, ..., w T ), which covers the main features of the steam cloud data through the eigenvalue fitness and updates the steam cloud data.

[0072] In one embodiment, the eigenvalue fitness λ is greater than or equal to T The eigenvalues ​​are retained, which are less than the eigenvalue fitness λ T The eigenvalues ​​are discarded.

[0073] The original space vector is used to construct the optimal plane for classification and recognition. i,y i ) 1≤i≤l , where x i ∈R n ,y i ∈{-1,1},y i For x i The category. At the same time, the relaxation factor θ≥0 and the penalty parameter C are introduced. Under the constraint yi(w·x+b)≥1-θ i ,(i=1,…l) minimize the function Where δ = 0.5. At the same time, the classification rules are met in b * is the Lagrange multiplier.

[0074] In addition, in order to avoid falling into "dimensionality bloat" again, the kernel function is introduced φ is represented as a mapping relationship. By building a supervised learning SVM network, a visual recognition model M1 for steam clouds generated by steam leaks is formed.

[0075] Step 208: Identify the current pipeline image according to the visual recognition model and generate prompt information.

[0076] Among them, the prompt information includes abnormal prompts and normal prompts.

[0077] Specifically, the current pipeline image is input into the visual recognition model to detect whether the current pipeline image leaks and produces a steam cloud; if the current pipeline image leaks and produces a steam cloud, an abnormal prompt is generated; if the current pipeline image does not leak and produce a steam cloud, a normal prompt is generated.

[0078] After acquiring the image information of the leaking pipeline, the method includes: segmenting the pipeline and the environmental background in the image information to obtain a pipeline edge model; and generating prompt information according to the overlap between the pipeline edge model and the initial shape of the pipeline.

[0079] Specifically, the data of the intact shape of the key steam pipeline is collected, including the laying information of the steam pipeline in the monitoring area (overhead U-bend, bridge laying, etc.), pipeline length, and aluminum plate wrapping information. The monitored pipeline and the environmental background are segmented and extracted through image processing technology to obtain the pipeline edge model M2. According to the overlap between the pipeline edge model and the initial shape of the pipeline, prompt information is generated.

[0080] More specifically, it is detected whether the overlap between the pipeline edge model and the initial form of the pipeline exceeds a preset overlap threshold; if the overlap between the pipeline edge model and the initial form of the pipeline exceeds the preset overlap threshold, an abnormal prompt is generated; if the overlap between the pipeline edge model and the initial form of the pipeline does not exceed the preset overlap threshold, a normal prompt is generated.

[0081] In one embodiment, the overlap is set to 5, and the overlap of the extracted pipe edge is compared with the initial intact pipe edge. When the overlap deviation between the real-time monitored pipe and the initial shape is ≥5, an early warning of pipe displacement or deformation caused by foreign body collision is issued, and an abnormal prompt is generated.

[0082] The method comprises: acquiring temperature information; and generating prompt information according to the visual recognition model, the temperature information and the overlap degree.

[0083] Specifically, the infrared radiation signal of the steam pipe or the leaking steam cloud surface is captured by an infrared physical camera to obtain the temperature information of the area. According to the preset parameters and thresholds, the temperature value of the monitored steam pipe surface is converted into a digital signal and loaded into the ROI (Region of Interest) image of a fixed area.

[0084] In one embodiment, Figure 3 As shown, according to the visual recognition model, the pipeline edge model and the temperature information, the image information of the steam pipe network is simultaneously judged in terms of steam cloud, overlap and temperature to monitor whether the steam pipe network is leaking.

[0085] Obtain an infrared steam leakage video dataset, perform comprehensive detection and background interpolation on the dataset, and obtain target feature extraction by retaining important features. Use supervised learning SVM method to realize target recognition, and establish a visual recognition model M1 for steam leakage identification.

[0086] The intact shape data of the steam pipeline in the key link is obtained, and the infrared video stream pipeline and the environmental background under monitoring are segmented and extracted through image processing technology, and the pipeline edge model M2 for pipeline collision deformation or displacement identification is established.

[0087] The image information of infrared streaming media monitored in real time in the key link steam pipeline network is input into the visual recognition model M1 and the pipeline edge model M2 to perform steam cloud and overlap recognition and obtain the recognition result.

[0088] Obtain infrared temperature, make judgments based on the infrared temperature auxiliary recognition results, generate prompt information, and display early warnings at the application layer.

[0089] In the above-mentioned intelligent visual perception and early warning method for steam pipe network, image information of the leaking pipe is obtained; the image information is subjected to interpolation processing to obtain steam cloud data; the steam cloud data is subjected to target feature extraction to generate a visual recognition model; the current pipeline image is identified according to the visual recognition model to generate prompt information. The present invention monitors the steam pipe network in real time and identifies and warns of abnormal conditions of the steam transport pipe. Based on the Internet of Things technology, real-time intelligent visual perception is performed on the key links of the entire steam pipe network, the heating status of the entire steam pipeline is fully grasped, and emergencies are reflected quickly and accurately, which facilitates timely inspection and maintenance by management personnel, and provides scientific and accurate information for the comprehensive management of the heating station, so that the management level is taken to a higher level.

[0090] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0091] Based on the same inventive concept, the embodiment of the present application also provides a steam pipe network intelligent visual perception and early warning device for implementing the above-mentioned steam pipe network intelligent visual perception and early warning method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in one or more steam pipe network intelligent visual perception and early warning device embodiments provided below can refer to the above-mentioned limitations on the steam pipe network intelligent visual perception and early warning method, and will not be repeated here.

[0092] In one embodiment, Figure 4 As shown, a steam pipe network intelligent visual perception and early warning device is provided, including: an image acquisition module 410, an interpolation processing module 420, a model generation module 430 and an information prompt module 440, wherein:

[0093] The image acquisition module 410 is used to acquire image information of the leaking pipeline.

[0094] The interpolation processing module 420 is used to perform interpolation processing on the image information to obtain steam cloud data.

[0095] The model generation module 430 is used to extract target features from the steam cloud data and generate a visual recognition model.

[0096] The information prompt module 440 is used to identify the current pipeline image according to the visual recognition model and generate prompt information.

[0097] The interpolation processing module 420 is also used to perform interpolation processing on adjacent frame images to obtain interpolation results; perform background interpolation operations based on the interpolation results to obtain background interpolation results; and perform OR operations based on the interpolation results and the background interpolation results to obtain steam cloud data.

[0098] The model generation module 430 is also used to perform dimensionality reduction processing on the steam cloud data to obtain a reduced-dimensional space sequence; extract target features from the reduced-dimensional space sequence, and build a supervised learning SVM network to generate a visual recognition model.

[0099] The image acquisition module 410 is further used to segment the pipeline from the environmental background in the image information to obtain a pipeline edge model; and generate prompt information according to the overlap between the pipeline edge model and the initial shape of the pipeline.

[0100] The image acquisition module 410 is also used to detect whether the overlap between the pipeline edge model and the initial shape of the pipeline exceeds a preset overlap threshold; if the overlap between the pipeline edge model and the initial shape of the pipeline exceeds the preset overlap threshold, an abnormal prompt is generated; if the overlap between the pipeline edge model and the initial shape of the pipeline does not exceed the preset overlap threshold, a normal prompt is generated.

[0101] The information prompt module 440 is also used to obtain temperature information; and generate prompt information according to the visual recognition model, the temperature information and the overlap degree.

[0102] Each module in the above steam pipe network intelligent visual perception and early warning device can be implemented in whole or in part by software, hardware and their combination. Each module can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to each module above.

[0103] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 5As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a steam pipeline network intelligent visual perception and early warning method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse.

[0104] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0105] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, any one of the steam network intelligent visual perception and early warning methods in the above embodiments is implemented.

[0106] Obtain image information of leaking pipeline;

[0107] Performing frame interpolation processing on the image information to obtain steam cloud data;

[0108] Extract target features from the steam cloud data to generate a visual recognition model;

[0109] The current pipeline image is identified according to the visual recognition model, and prompt information is generated.

[0110] In one embodiment, when the processor executes the computer program, the following steps are further implemented: interpolating adjacent frame images to obtain interpolation results;

[0111] Perform background interpolation operation according to the interpolation result to obtain a background interpolation result;

[0112] The steam cloud data is obtained by performing an OR operation based on the interpolation result and the background interpolation result.

[0113] In one embodiment, when the processor executes the computer program, the following steps are further implemented: performing dimensionality reduction processing on the steam cloud data to obtain a dimensionality reduction space sequence;

[0114] The target features are extracted from the reduced-dimensional space sequence, and a supervised learning SVM network is built to generate a visual recognition model.

[0115] In one embodiment, when the processor executes the computer program, the following steps are further implemented: segmenting the pipeline from the environmental background in the image information to obtain a pipeline edge model;

[0116] Prompt information is generated according to the degree of overlap between the pipeline edge model and the initial shape of the pipeline.

[0117] In one embodiment, when the processor executes the computer program, the following steps are further implemented: detecting whether the overlap between the pipeline edge model and the initial form of the pipeline exceeds a preset overlap threshold;

[0118] If the overlap between the pipeline edge model and the initial shape of the pipeline exceeds a preset overlap threshold, an abnormal prompt is generated;

[0119] If the overlap between the pipeline edge model and the initial shape of the pipeline does not exceed a preset overlap threshold, a normal prompt is generated.

[0120] In one embodiment, when the processor executes the computer program, the processor further implements the following steps: obtaining temperature information;

[0121] Prompt information is generated according to the visual recognition model, the temperature information and the overlap degree.

[0122] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, any one of the steam pipeline network intelligent visual perception and early warning methods in the above embodiments is implemented.

[0123] Obtain image information of leaking pipeline;

[0124] Performing frame interpolation processing on the image information to obtain steam cloud data;

[0125] Extract target features from the steam cloud data to generate a visual recognition model;

[0126] The current pipeline image is identified according to the visual recognition model, and prompt information is generated.

[0127] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: interpolating adjacent frame images to obtain interpolation results;

[0128] Perform background interpolation operation according to the interpolation result to obtain a background interpolation result;

[0129] The steam cloud data is obtained by performing an OR operation based on the interpolation result and the background interpolation result.

[0130] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: performing dimensionality reduction processing on the steam cloud data to obtain a dimensionality reduction space sequence;

[0131] The target features are extracted from the reduced-dimensional space sequence, and a supervised learning SVM network is built to generate a visual recognition model.

[0132] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: segmenting the pipeline from the environmental background in the image information to obtain a pipeline edge model;

[0133] Prompt information is generated according to the degree of overlap between the pipeline edge model and the initial shape of the pipeline.

[0134] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: detecting whether the overlap between the pipeline edge model and the initial form of the pipeline exceeds a preset overlap threshold;

[0135] If the overlap between the pipeline edge model and the initial shape of the pipeline exceeds a preset overlap threshold, an abnormal prompt is generated;

[0136] If the overlap between the pipeline edge model and the initial shape of the pipeline does not exceed a preset overlap threshold, a normal prompt is generated.

[0137] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining temperature information;

[0138] Prompt information is generated according to the visual recognition model, the temperature information and the overlap degree.

[0139] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0140] Obtain image information of leaking pipeline;

[0141] Performing frame interpolation processing on the image information to obtain steam cloud data;

[0142] Extract target features from the steam cloud data to generate a visual recognition model;

[0143] The current pipeline image is identified according to the visual recognition model, and prompt information is generated.

[0144] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: interpolating adjacent frame images to obtain interpolation results;

[0145] Perform background interpolation operation according to the interpolation result to obtain a background interpolation result;

[0146] The steam cloud data is obtained by performing an OR operation based on the interpolation result and the background interpolation result.

[0147] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: performing dimensionality reduction processing on the steam cloud data to obtain a dimensionality reduction space sequence;

[0148] The target features are extracted from the reduced-dimensional space sequence, and a supervised learning SVM network is built to generate a visual recognition model.

[0149] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: segmenting the pipeline from the environmental background in the image information to obtain a pipeline edge model;

[0150] Prompt information is generated according to the degree of overlap between the pipeline edge model and the initial shape of the pipeline.

[0151] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: detecting whether the overlap between the pipeline edge model and the initial form of the pipeline exceeds a preset overlap threshold;

[0152] If the overlap between the pipeline edge model and the initial shape of the pipeline exceeds a preset overlap threshold, an abnormal prompt is generated;

[0153] If the overlap between the pipeline edge model and the initial shape of the pipeline does not exceed a preset overlap threshold, a normal prompt is generated.

[0154] In one embodiment, when the computer program is executed by the processor, the following steps are also implemented: obtaining temperature information;

[0155] Prompt information is generated according to the visual recognition model, the temperature information and the overlap degree.

[0156] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0157] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0158] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0159] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A steam pipe network intelligent visual perception and early warning method, characterized in that: The method comprises: Obtain image information of leaking pipeline; Performing frame interpolation processing on the image information to obtain steam cloud data; Extract target features from the steam cloud data to generate a visual recognition model; The current pipeline image is identified according to the visual recognition model, and prompt information is generated.

2. The method according to claim 1, characterized in that: The image information is interpolated to obtain steam cloud data include: Wherein, the image information includes a plurality of continuous frame images; Perform interpolation processing on adjacent frame images to obtain interpolation results; Perform background interpolation operation according to the interpolation result to obtain a background interpolation result; The steam cloud data is obtained by performing an OR operation based on the interpolation result and the background interpolation result.

3. The method according to claim 2, characterized in that The extracting target features from the steam cloud data to generate a visual recognition model comprises: Performing dimensionality reduction processing on the steam cloud data to obtain a dimensionality reduction space sequence; The target features are extracted from the reduced-dimensional space sequence, and a supervised learning SVM network is built to generate a visual recognition model.

4. The method according to claim 1, characterized in that The step of obtaining the image information of the leaking pipeline includes: Segmenting the pipeline from the environmental background in the image information to obtain a pipeline edge model; Prompt information is generated according to the degree of overlap between the pipeline edge model and the initial shape of the pipeline.

5. The method according to claim 4, characterized in that The prompt information is generated according to the overlap between the pipeline edge model and the initial shape of the pipeline. include: Among them, the prompt information includes abnormal prompts and normal prompts; Detecting whether the overlap between the pipeline edge model and the initial shape of the pipeline exceeds a preset overlap threshold; If the overlap between the pipeline edge model and the initial shape of the pipeline exceeds a preset overlap threshold, an abnormal prompt is generated; If the overlap between the pipeline edge model and the initial shape of the pipeline does not exceed a preset overlap threshold, a normal prompt is generated.

6. The method according to claim 5, characterized in that The method comprises: Get temperature information; Prompt information is generated according to the visual recognition model, the temperature information and the overlap degree.

7. An intelligent visual perception and early warning device for a steam pipe network, characterized in that: The device comprises: An image acquisition module, used to acquire image information of the leaking pipeline; A frame insertion processing module, used for performing frame insertion processing on the image information to obtain steam cloud data; A model generation module, used for extracting target features from the steam cloud data and generating a visual recognition model; The information prompt module is used to identify the current pipeline image according to the visual recognition model and generate prompt information.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images