Intelligent routing inspection method and system for raw water pipeline

Abstract

The invention belongs to the technical field of intelligent water supply, and provides an intelligent inspection method and system for a raw water pipeline. The method comprises the following steps: constructing an intelligent inspection model, wherein the intelligent inspection model comprises a personnel abnormity inspection model and an instrument state inspection model; starting intelligent online inspection, receiving a real-time video shot by a video monitoring system arranged on the periphery of the raw water pipeline by an intelligent inspection model, and performing personnel behavior analysis and instrument state extraction on the real-time video according to a set frequency; and if the personnel behavior abnormity and / or the instrument state abnormity exist, outputting early warning information. According to the scheme of the invention, intelligent inspection of the raw water pipeline can be realized, only few managers are needed to deal with abnormal conditions in the monitoring center, and there is no need to configure too many on-site inspectors, so that the cost and pressure of inspection of the raw water pipeline can be greatly reduced.

Description

Technical Field

[0001] The present invention relates to the field of smart water supply technology, and in particular to a raw water pipeline smart inspection method and system. Background Art

[0002] The raw water pipeline refers to the water pipeline system from the water source to the water treatment plant. It is responsible for transporting untreated natural water (such as river water, lake water, groundwater, etc.) to the water treatment plant for purification. The raw water pipeline is an important part of the urban water supply system, and its safety and reliability are crucial to ensuring water supply safety.

[0003] Video surveillance systems are installed along the raw water pipelines, and the real-time status of the raw water pipelines can be monitored through the video surveillance systems. However, the video surveillance system captures too many video images, making it difficult to complete the online inspection of the raw water pipelines through manual browsing. Therefore, how to realize the intelligent transformation of the online inspection of the raw water pipeline is a technical problem that needs to be solved urgently. Summary of the invention

[0004] In order to solve at least one of the above technical problems, the present invention specifically provides a raw water pipeline intelligent inspection method, system, electronic equipment, computer storage medium and computer program product.

[0005] The present invention provides a raw water pipeline intelligent inspection method, comprising the following steps: Constructing a smart inspection model, which includes a personnel abnormal inspection model and an instrument status inspection model; Start smart online inspection. The smart inspection model receives real-time video captured by the video surveillance system arranged around the raw water pipeline, and performs personnel behavior analysis and instrument status extraction on the real-time video at a set frequency; If there is abnormal personnel behavior and / or abnormal instrument status, an early warning message will be output.

[0006] Furthermore, the performing of personnel behavior analysis and instrument status extraction on the real-time video at a set frequency includes: Controlling the personnel abnormal inspection model to perform personnel behavior analysis on the real-time video according to a first set frequency to obtain personnel behavior analysis result data; Controlling the instrument status inspection model to perform instrument status analysis on the real-time video at a second set frequency to obtain instrument status analysis result data; The first set frequency is lower than the second set frequency.

[0007] Further, the controlling the personnel abnormal inspection model to perform personnel behavior analysis on the real-time video according to the first set frequency to obtain personnel behavior analysis result data includes: Controlling the personnel abnormal inspection model to perform personnel behavior analysis on the real-time video according to a third set frequency to obtain first personnel behavior analysis result data; Extracting the personnel behavior abnormality from the first personnel behavior analysis result data, and if the personnel behavior abnormality is higher than the abnormal threshold, controlling the personnel abnormal inspection model to perform personnel behavior analysis on the real-time video at a fourth set frequency to obtain second personnel behavior analysis result data; wherein the fourth set frequency is higher than the third set frequency; The first personnel behavior analysis result data and the second personnel behavior analysis result data are used as the personnel behavior analysis result data.

[0008] Furthermore, the fourth set frequency is determined by: ; In the above formula, is the fourth set frequency, The third set frequency; is the first adjustment coefficient corresponding to the abnormality of the personnel behavior that is higher than the abnormal threshold, ; is the second adjustment coefficient corresponding to the abnormality of human behavior obtained based on the analysis of several other geographically adjacent real-time videos, , The number of real-time videos for other geographically nearby locations.

[0009] Furthermore, a number of other geographically adjacent real-time videos are determined in the following manner: Obtaining historical inspection records corresponding to the real-time video, calculating the average abnormality of personnel behavior according to the historical inspection records, and determining an associated geographic analysis area according to the average abnormality of personnel behavior; wherein the size of the associated geographic analysis area is negatively correlated with the average abnormality of personnel behavior; The real-time videos belonging to the associated geographic analysis area are determined to be other geographically adjacent real-time videos.

[0010] Further, the controlling the instrument status inspection model to perform instrument status analysis on the real-time video according to a second set frequency to obtain instrument status analysis result data includes: The instrument status inspection model is controlled to perform instrument status analysis on the real-time video at a second set frequency to obtain analysis results corresponding to a number of designated inspection items, and each of the analysis results is integrated into the instrument status analysis result data.

[0011] The present invention also provides a raw water pipeline intelligent inspection system, the system comprising a model building module, an inspection analysis module, and an early warning module; The model building module is used to build a smart inspection model, which includes a personnel abnormal inspection model and an instrument status inspection model; The inspection analysis module is used to control the smart inspection model to receive the real-time video captured by the video surveillance system arranged around the raw water pipeline after the smart online inspection is started, and perform personnel behavior analysis and instrument status extraction on the real-time video according to the set frequency; The warning module is used to output warning information if there is abnormal personnel behavior and / or abnormal instrument status.

[0012] The present invention also provides an electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute the method as described in any of the preceding items.

[0013] The present invention also provides a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, any of the above methods is executed.

[0014] The present invention also provides a computer program product, which includes computer program instructions. When the computer program instructions are executed by a processor of an electronic device, any of the methods described above is implemented.

[0015] The beneficial effect of the present invention is that the solution of the present invention can realize intelligent inspection of raw water pipelines, and only a small number of management personnel are needed to deal with abnormal situations in the monitoring center, without the need to configure too many on-site inspection personnel, which can greatly reduce the cost and pressure of raw water pipeline inspections. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 It is a flow chart of a method for intelligent inspection of raw water pipelines provided by an embodiment of the present invention; Figure 2 It is a schematic diagram of the model structure of the personnel abnormal inspection model and the instrument status inspection model provided in the embodiment of the present invention; Figure 3It is a structural schematic diagram of a raw water pipeline intelligent inspection system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0019] See also Figure 1 As shown, an embodiment of the present invention provides a raw water pipeline intelligent inspection method, comprising the following steps: Constructing a smart inspection model, which includes a personnel abnormal inspection model and an instrument status inspection model; Start smart online inspection. The smart inspection model receives real-time video captured by the video surveillance system arranged around the raw water pipeline, and performs personnel behavior analysis and instrument status extraction on the real-time video at a set frequency; If there is abnormal personnel behavior and / or abnormal instrument status, an early warning message will be output.

[0020] Compared with the manual online inspection method in the background technology, the present invention designs the above-mentioned intelligent online inspection scheme. Specifically, firstly, a smart inspection model is constructed, which includes a personnel abnormal inspection model and an instrument status inspection model. After starting the smart online inspection, the smart inspection model begins to receive the real-time video captured by the video surveillance system arranged around the raw water pipeline, and performs online inspection on the real-time video according to the set frequency, that is, the personnel abnormal inspection model extracts the personnel behavior from the real-time video, and the instrument status inspection model extracts the instrument status from the real-time video. If there is abnormal personnel behavior and / or abnormal instrument status, the warning information can be output on the monitoring interface for management personnel to intervene and deal with.

[0021] It can be seen that the solution of the present invention can realize intelligent inspection of raw water pipelines, and only requires fewer management personnel to deal with abnormal situations in the monitoring center. There is no need to configure too many on-site inspection personnel, which can greatly reduce the cost and pressure of raw water pipeline inspections.

[0022] The above-mentioned video monitoring system includes multiple groups of monitoring cameras, which are respectively arranged at certain key positions of the raw water pipeline to achieve monitoring coverage of the raw water pipeline. The present invention does not limit the specific arrangement interval distance of the monitoring cameras.

[0023] Furthermore, the performing of personnel behavior analysis and instrument status extraction on the real-time video at a set frequency includes: Controlling the personnel abnormal inspection model to perform personnel behavior analysis on the real-time video according to a first set frequency to obtain personnel behavior analysis result data; Controlling the instrument status inspection model to perform instrument status analysis on the real-time video at a second set frequency to obtain instrument status analysis result data; The first set frequency is lower than the second set frequency.

[0024] In this embodiment, by analyzing the real-time video, the personnel abnormal inspection model and the instrument status inspection model respectively analyze the personnel behavior analysis result data and the instrument status analysis result data from the real-time video. Among them, the frequency of the above analysis of the real-time video by the personnel abnormal inspection model and the instrument status inspection model is different. Specifically, since the layout environment of the raw water pipeline is generally far away from the residential area, the probability of the appearance of personnel is generally small, and whether the status of the instrument is normal is crucial to the raw water pipeline system, and it is also the most important inspection content. Therefore, the present invention sets the analysis frequency of the instrument status to be higher than the analysis frequency of the personnel behavior. Such a setting can reduce the processing load of the personnel abnormal inspection model, which is conducive to improving the overall inspection efficiency.

[0025] Among them, the personnel abnormal inspection model and the instrument status inspection model are preferably based on the lightweight network YOLOv4 algorithm model. The structural states of the two models are as follows: Figure 2 shown.

[0026] Further, the controlling the personnel abnormal inspection model to perform personnel behavior analysis on the real-time video according to the first set frequency to obtain personnel behavior analysis result data includes: Controlling the personnel abnormal inspection model to perform personnel behavior analysis on the real-time video according to a third set frequency to obtain first personnel behavior analysis result data; Extracting the personnel behavior abnormality from the first personnel behavior analysis result data, and if the personnel behavior abnormality is higher than the abnormal threshold, controlling the personnel abnormal inspection model to perform personnel behavior analysis on the real-time video at a fourth set frequency to obtain second personnel behavior analysis result data; wherein the fourth set frequency is higher than the third set frequency; The first personnel behavior analysis result data and the second personnel behavior analysis result data are used as the personnel behavior analysis result data.

[0027] In this embodiment, in the initial state, the personnel abnormal inspection model is set to perform personnel behavior analysis on the real-time video at a lower third inspection frequency to obtain the first personnel behavior analysis result data, which includes the personnel behavior feature data and the personnel behavior abnormality obtained by analysis. If the personnel behavior abnormality is higher than the abnormal threshold, the inspection frequency of the personnel abnormal inspection model is appropriately increased to the fourth set frequency to obtain the second personnel behavior analysis result data. The first personnel behavior analysis result data and the second personnel behavior analysis result data are integrated into the personnel behavior analysis result data.

[0028] With the above settings of this embodiment, when it is initially determined that the behavior of a person is obviously abnormal, the frequency of analyzing the behavior of the person in the real-time video can be appropriately increased, that is, a higher frequency of tracking of the potential abnormal person can be achieved, so as to timely discover and confirm his abnormal behavior, and thus issue a warning in time; and if it is initially determined that the behavior of a person is not obviously abnormal, the initial third inspection frequency can still be used to track and identify the person. With such settings, a balance can be achieved between ensuring the timeliness of identifying abnormal personnel and processing load.

[0029] The warning methods include both remote warning at the monitoring center and warning at the scene of the video monitoring system. For example, the video monitoring system also includes a warning loudspeaker, which can warn abnormal personnel through the warning loudspeaker when abnormal behavior or trends are confirmed.

[0030] The personnel behavior characteristic data corresponds to a variety of different abnormal behaviors of personnel, including but not limited to pipeline damage, smoking, falling, etc.

[0031] Furthermore, the fourth set frequency is determined by: ; In the above formula, is the fourth set frequency, The third set frequency; is the first adjustment coefficient corresponding to the abnormality of the personnel behavior that is higher than the abnormal threshold, ; is the second adjustment coefficient corresponding to the abnormality of human behavior obtained based on the analysis of several other geographically adjacent real-time videos, , The number of real-time videos for other geographically nearby locations.

[0032] Referring to the above formula, the fourth set frequency in the present invention is an appropriate amplification of the third set frequency, and the method degree of determining the fourth set frequency is from two aspects. Pre-configure corresponding adjustment coefficients for different abnormalities of personnel behavior , adjustment coefficient It is positively correlated with the abnormality of personnel behavior. That is, the higher the abnormality of personnel behavior detected, the higher the adjustment coefficient is set. At the same time, the video surveillance system deployed around the raw water pipeline includes multiple distributed cameras. The real-time videos shot by the geographically adjacent cameras constitute the above-mentioned other geographically adjacent real-time videos. By analyzing these geographically adjacent real-time videos in the same way, the corresponding abnormality of personnel behavior can also be obtained, thereby determining the corresponding second adjustment coefficient. The average value of the second adjustment coefficients is calculated, and the average value is added to the first adjustment coefficient obtained above, and the sum is used for overall adjustment of the amplification of the third set frequency.

[0033] Among them, other cameras around a certain camera also captured situations where the abnormality of human behavior is higher than the abnormal threshold, indicating that there is a high probability of abnormality in the area. At this time, the frequency of personnel analysis of the real-time video images taken by the camera can be increased to discover and confirm personnel abnormalities more timely.

[0034] Furthermore, a number of other geographically adjacent real-time videos are determined in the following manner: Obtaining historical inspection records corresponding to the real-time video, calculating the average abnormality of personnel behavior according to the historical inspection records, and determining an associated geographic analysis area according to the average abnormality of personnel behavior; wherein the size of the associated geographic analysis area is negatively correlated with the average abnormality of personnel behavior; The real-time videos belonging to the associated geographic analysis area are determined to be other geographically adjacent real-time videos.

[0035] In this embodiment, when determining other geographically adjacent real-time videos, it is necessary to use the geographical location of the camera that shoots the real-time video as a benchmark, determine other cameras within the appropriate range of the benchmark as geographically adjacent cameras, and determine the real-time videos shot by them as other geographically adjacent real-time videos. At the same time, it is also necessary to determine the appropriate range. Specifically, the present invention retrieves the historical inspection records of the real-time video shot by the camera, and the historical inspection records contain the abnormal behavior of the personnel in the real-time video shot by the camera, and the average abnormality of the personnel behavior is calculated based on this; when the average abnormality of the personnel behavior is higher, it means that the raw water pipeline area where the camera is located is more likely to have abnormal personnel, and there is no need to rely heavily on other geographically adjacent real-time videos. At this time, the associated geographical analysis area is set to be smaller; on the contrary, it is necessary to rely heavily on other geographically adjacent real-time videos to conduct a comprehensive analysis of multiple real-time videos to ensure the rationality of the fourth set frequency determined, and correspondingly, the associated geographical analysis area is set to be larger.

[0036] However, the present invention is not limited to the expression formula of the above negative correlation.

[0037] Further, the controlling the instrument status inspection model to perform instrument status analysis on the real-time video according to a second set frequency to obtain instrument status analysis result data includes: The instrument status inspection model is controlled to perform instrument status analysis on the real-time video at a second set frequency to obtain analysis results corresponding to a number of designated inspection items, and each of the analysis results is integrated into the instrument status analysis result data.

[0038] In this embodiment, the abnormal conditions of various instruments on the raw water pipeline mainly include abnormal knob switch position, abnormal indicator light status, abnormal meter data, etc. Based on this, the present invention presets a corresponding number of designated inspection items, controls the instrument status inspection model to analyze the above-mentioned designated inspection items on the real-time video, thereby obtaining corresponding analysis results, and then integrates the analysis results.

[0039] According to the analysis of the instrument status inspection model, the real-time video should be processed, mainly to control the corresponding camera to adjust the shooting angle and focal length to obtain a closer instrument image, which is conducive to improving the accuracy of the above analysis results.

[0040] See also Figure 3 As shown, a raw water pipeline intelligent inspection system according to an embodiment of the present invention includes a model building module, an inspection analysis module, and an early warning module; The model building module is used to build a smart inspection model, which includes a personnel abnormal inspection model and an instrument status inspection model; The inspection analysis module is used to control the smart inspection model to receive the real-time video captured by the video surveillance system arranged around the raw water pipeline after the smart online inspection is started, and perform personnel behavior analysis and instrument status extraction on the real-time video according to the set frequency; The warning module is used to output warning information if there is abnormal personnel behavior and / or abnormal instrument status.

[0041] An embodiment of the present invention further discloses an electronic device, comprising: a memory storing executable program code; a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute the method described in the above embodiment.

[0042] The embodiment of the present invention further discloses a computer storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method described in the above embodiment is executed.

[0043] An embodiment of the present invention further discloses a computer program product, which includes computer program instructions. When the computer program instructions are executed by a processor of an electronic device, any of the above methods is implemented.

[0044] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0045] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable load balancing device, so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0046] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0047] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0048] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A method for intelligent inspection of raw water pipelines, characterized in that: The steps include: Constructing a smart inspection model, which includes a personnel abnormal inspection model and an instrument status inspection model; Start smart online inspection. The smart inspection model receives real-time video captured by the video surveillance system arranged around the raw water pipeline, and performs personnel behavior analysis and instrument status extraction on the real-time video at a set frequency; If there is abnormal personnel behavior and / or abnormal instrument status, an early warning message will be output.

2. The intelligent inspection method for raw water pipeline according to claim 1 is characterized by: Performing personnel behavior analysis and instrument status extraction on the real-time video at a set frequency, including: Controlling the personnel abnormal inspection model to perform personnel behavior analysis on the real-time video according to a first set frequency to obtain personnel behavior analysis result data; Controlling the instrument status inspection model to perform instrument status analysis on the real-time video at a second set frequency to obtain instrument status analysis result data; The first set frequency is lower than the second set frequency.

3. The intelligent inspection method for raw water pipeline according to claim 2 is characterized by: Controlling the personnel abnormal inspection model to perform personnel behavior analysis on the real-time video according to a first set frequency to obtain personnel behavior analysis result data, including: Controlling the personnel abnormal inspection model to perform personnel behavior analysis on the real-time video according to a third set frequency to obtain first personnel behavior analysis result data; Extracting the personnel behavior abnormality from the first personnel behavior analysis result data, and if the personnel behavior abnormality is higher than the abnormal threshold, controlling the personnel abnormal inspection model to perform personnel behavior analysis on the real-time video at a fourth set frequency to obtain second personnel behavior analysis result data; wherein the fourth set frequency is higher than the third set frequency; The first personnel behavior analysis result data and the second personnel behavior analysis result data are used as the personnel behavior analysis result data.

4. The intelligent inspection method for raw water pipeline according to claim 3 is characterized by: The fourth set frequency is determined by: ; In the above formula, is the fourth set frequency, The third set frequency; is the first adjustment coefficient corresponding to the abnormality of the personnel behavior that is higher than the abnormal threshold, ; is the second adjustment coefficient corresponding to the abnormality of human behavior obtained based on the analysis of several other geographically adjacent real-time videos, , The number of real-time videos for other geographically nearby locations.

5. The intelligent inspection method for raw water pipeline according to claim 4 is characterized by: Several other geographically nearby real-time videos are determined as follows: Obtaining historical inspection records corresponding to the real-time video, calculating the average abnormality of personnel behavior according to the historical inspection records, and determining an associated geographic analysis area according to the average abnormality of personnel behavior; wherein the size of the associated geographic analysis area is negatively correlated with the average abnormality of personnel behavior; The real-time videos belonging to the associated geographic analysis area are determined to be other geographically adjacent real-time videos.

6. The intelligent inspection method for raw water pipeline according to claim 5 is characterized in that: Controlling the instrument status inspection model to perform instrument status analysis on the real-time video according to a second set frequency to obtain instrument status analysis result data, including: The instrument status inspection model is controlled to perform instrument status analysis on the real-time video at a second set frequency to obtain analysis results corresponding to a number of designated inspection items, and each of the analysis results is integrated into the instrument status analysis result data.

7. A raw water pipeline intelligent inspection system, the system comprising a model building module, an inspection analysis module, and an early warning module; characterized in that: The model building module is used to build a smart inspection model, which includes a personnel abnormal inspection model and an instrument status inspection model; The inspection analysis module is used to control the smart inspection model to receive the real-time video captured by the video surveillance system arranged around the raw water pipeline after the smart online inspection is started, and perform personnel behavior analysis and instrument status extraction on the real-time video according to the set frequency; The warning module is used to output warning information if there is abnormal personnel behavior and / or abnormal instrument status.

8. An electronic device, comprising: A memory storing executable program code; A processor coupled to the memory; characterized in that: the processor calls the executable program code stored in the memory to execute the method according to any one of claims 1-6.

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

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

Images