Remote Diagnosis Method for the Operating Status of Water Quality Automatic Monitoring System Based on Video Images

Abstract

The present disclosure provides a remote diagnosis method for the operating state of a water quality automatic monitoring system based on video images, belonging to the field of detection technology. The method includes: obtaining a first health assessment value based on device images; adjusting the first health assessment value based on environmental data to obtain a second health assessment value; and determining a remote diagnosis result for the operating state of the water quality automatic monitoring system based on the second health assessment value. The remote diagnosis method for the operating state of the water quality automatic monitoring system based on video images provided by the present disclosure can achieve real-time and accurate detection of the water quality automatic monitoring system.

Description

Technical Field

[0001] The present disclosure belongs to the field of detection technology, and more specifically, relates to a remote diagnosis method for the operating status of a water quality automatic monitoring system based on video images. Background Art

[0002] With the increasing global attention to environmental quality and the strengthening of the requirements for sustainable development, ensuring water quality has become an important task. Governments, research institutions, and related enterprises have begun to explore more effective methods to monitor water quality changes and respond promptly to potential pollution problems. Advances in fields such as cloud computing, big data analysis, the Internet of Things (IoT), and video image processing technology have made data collection, transmission, processing, and analysis more efficient and accurate. Water quality automatic monitoring stations can continuously and quickly collect water quality data and obtain high-precision water quality parameter information, such as pH value, dissolved oxygen, turbidity, etc., which helps to promptly detect pollution problems and take corresponding measures. Automatic monitoring stations reduce manual participation and lower the possibility of data errors or omissions caused by human factors.

[0003] In order to maintain the accuracy and stability of the data of the automatic monitoring station, it is necessary to regularly check and repair sensors and other hardware devices. However, the maintenance and monitoring frequencies for different water quality monitoring stations are different. Whether the hardware devices need to be repaired or replaced mainly depends on the experience of on-site personnel. For remote areas or monitoring points with complex geographical locations, it is difficult for on-site maintenance personnel to arrive quickly and perform repairs in a timely manner. Summary of the Invention

[0004] The purpose of the present disclosure is to provide a remote diagnosis method for the operating status of a water quality automatic monitoring system based on video images to achieve real-time and accurate detection of the water quality automatic monitoring system.

[0005] In the first aspect of the embodiments of the present disclosure, a remote diagnosis method for the operating status of a water quality automatic monitoring system based on video images is provided, including:

[0006] Obtaining a first health assessment value based on the device image;

[0007] Adjusting the first health assessment value based on the environmental data to obtain a second health assessment value;

[0008] Determining the remote diagnosis result of the operating status of the water quality automatic monitoring system based on the second health assessment value.

[0009] In the second aspect of the embodiments of the present disclosure, a remote diagnosis device for the operating status of a water quality automatic monitoring system based on video images is provided, including:

[0010] A first processing module for obtaining a first health assessment value based on the device image;

[0011] A second processing module, configured to adjust the first health assessment value based on environmental data to obtain a second health assessment value;

[0012] A result output module, configured to determine a remote diagnosis result of the operation status of the water quality automatic monitoring system based on the second health assessment value.

[0013] In a third aspect of the embodiments of the present disclosure, there is provided an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, the steps of the above-mentioned remote diagnosis method for the operation status of the water quality automatic monitoring system based on video images are implemented.

[0014] In a fourth aspect of the embodiments of the present disclosure, there is provided a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned remote diagnosis method for the operation status of the water quality automatic monitoring system based on video images are implemented.

[0015] The beneficial effects of the remote diagnosis method for the operation status of the water quality automatic monitoring system based on video images provided by the embodiments of the present disclosure are as follows:

[0016] In the embodiments of the present disclosure, by collecting device images and analyzing the device images to obtain the first health assessment value of the water quality automatic monitoring system, remote real-time detection of the water quality automatic monitoring system is realized, eliminating the need for on-site inspections by personnel, greatly saving labor and time costs, and avoiding the problem of untimely detection in manual inspections.

[0017] At the same time, the embodiments of the present disclosure consider the influence of environmental factors (temperature, humidity, rainfall, etc.) on the health status of the device, and adjust the first health assessment value in combination with environmental data to make the diagnosis result more comprehensive and objective. Description of the Drawings

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present disclosure. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0019] Figure 1 It is a flowchart of a remote diagnosis method for the operation status of a water quality automatic monitoring system based on video images provided by an embodiment of the present disclosure;

[0020] Figure 2 It is a structural block diagram of a remote diagnosis device for the operation status of a water quality automatic monitoring system based on video images provided by an embodiment of the present disclosure;

[0021] Figure 3 Schematic block diagram of an electronic device provided in an embodiment of the present disclosure. Detailed implementation manners

[0022] In the following description, specific details such as specific system architectures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present disclosure. However, those skilled in the art should understand that the present disclosure can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present disclosure.

[0023] To make the objectives, technical solutions, and advantages of the present disclosure clearer, the following will be described through specific embodiments in conjunction with the accompanying drawings.

[0024] Please refer to Figure 1 , Figure 1 Schematic flowchart of a remote diagnosis method for the operating status of a water quality automatic monitoring system based on video images provided in an embodiment of the present disclosure. The method includes:

[0025] S101: Obtain a first health assessment value based on device images.

[0026] In this embodiment, the devices in the water quality automatic monitoring system mainly include a sampling unit, an instrument control unit, a pretreatment unit, and an auxiliary unit, etc. Among them, the sampling unit includes a sampler, a sampling pipeline, and a filter, etc., which are used to collect and transport water samples and remove impurities; the instrument control unit includes analytical and detection instruments (such as water quality five-parameter monitors, various pollutant analyzers, etc.), a data acquisition and processing system, and a control system, which are used to measure different water quality parameters to reflect the water body condition and control and manage the entire water quality automatic monitoring system; the pretreatment unit includes a water distribution unit, a digestion device, and a cleaning device. Among them, the water distribution unit is used to distribute and preprocess water samples, the digestion device is used for water sample digestion before specific parameter detection, and the cleaning device is used to prevent impurity accumulation to ensure the normal operation of the system; the auxiliary unit includes functions such as meteorological monitoring, heat management, and air purging, which are used to provide a suitable working environment and conditions for the system.

[0027] Images of each device in the water quality automatic monitoring system can be obtained regularly using a camera or other image acquisition devices installed at the monitoring site, and features related to the health status of the devices are extracted from the images, such as color features (whether the appearance color of the device is normal, whether there is discoloration or corrosion signs), shape features (whether the device is deformed, damaged, etc.), texture features (whether the surface texture of the device is uniform, whether there are abnormal textures), etc. According to the extracted image features, an evaluation model is established to determine the first health assessment value.

[0028] The evaluation model can be a rule-based method. For example, specific feature thresholds are set, and when the image features exceed the thresholds, they correspond to different health status levels. It can also be a machine learning-based method, using a trained classifier or regression model to perform a health assessment on the image and output a numerical health assessment value.

[0029] S102: Adjust the first health assessment value based on the environmental data to obtain a second health assessment value.

[0030] In this embodiment, it is considered that the health status of the device will be affected by environmental data. For example, a high-temperature and high-humidity environment may accelerate the aging and damage of the device. When the rainfall is large, the content of sediment, debris, etc. in the water body may increase, bringing a greater burden to the sampling system. For example, the filter may be more likely to become blocked and need to be cleaned or replaced more frequently.

[0031] Therefore, in this embodiment, the first health assessment value is adjusted based on the environmental data. Specifically, an adjustment model between the environmental data and the first health assessment value can be established, and the first health assessment value is adjusted according to the environmental data and the adjustment model to obtain a second health assessment value. For example, if the environmental data shows that the current environmental conditions are relatively harsh, the first health assessment value of the device may be reduced; conversely, if the environmental data is good, the first health assessment value of the device may be increased.

[0032] S103: Determine the remote diagnosis result of the operation status of the water quality automatic monitoring system based on the second health assessment value.

[0033] In this embodiment, according to actual requirements and experience, different health status thresholds are set, and the second health assessment value is divided into different health status levels. For example, based on fuzzy control, the operation status of the water quality automatic monitoring system is discriminated. When the second health assessment value is between 90 and 100 points, it is healthy; between 80 and 90 points, it is excellent; between 60 and 80 points, it is good; between 40 and 60 points, it is medium; between 20 and 40 points, it is poor; and below 20 points, it is faulty. And it is judged whether to repair the water quality automatic monitoring system according to the operation status discrimination result (that is, the diagnosis result).

[0034] It can be concluded from the above that in this embodiment, by collecting device images and analyzing the device images, the first health assessment value of the water quality automatic monitoring system is obtained, thereby realizing the remote real-time detection of the water quality automatic monitoring system. There is no need for on-site inspection by personnel, which greatly saves labor and time costs and avoids the problem of untimely detection in manual inspection.

[0035] At the same time, this embodiment considers the influence of environmental factors (temperature, humidity, rainfall, etc.) on the health status of the device, and adjusts the first health assessment value in combination with the environmental data, making the diagnosis result more comprehensive and objective.

[0036] In one embodiment of the present disclosure, obtaining a first health assessment value based on device images includes:

[0037] Obtaining a plurality of device images continuously captured within a set time period;

[0038] Extracting a first key frame image from the plurality of device images; determining the first health assessment value based on the information entropy of the first key frame image; wherein, the information entropy and the first health assessment value are in a negative correlation relationship.

[0039] In this embodiment, starting from the brand-new state of the device, a camera or other image acquisition device installed near the device can be used to continuously capture images to obtain a plurality of device images. Then, compare the feature differences between two adjacent images among the plurality of device images, and extract the image with larger changes as the first key frame image. For example, if a certain image has larger feature differences compared to its previous image, then this image is used as the first key frame image. The first key frame image can be used to judge the specific state of the device.

[0040] According to the experimental research of the inventors, during the entire life cycle of the device from brand-new to faulty, the information entropy of the device images is an increasing process. That is, when the device is in the brand-new state, the information entropy of the device images is small, and when the device is in the faulty state, the information entropy of the device images is large. Therefore, the first health assessment value can be calculated based on the information entropy of the first key frame image and the above negative correlation relationship. The specific calculation process may include:

[0041] First, determine the possible value range of the information entropy. For grayscale images, the maximum value of the information entropy appears when all gray-level probabilities are equal. Let represent brand-new, represent faulty, where L is the possible number of gray levels (for 8-bit images, L = 256).

[0042] Design a mapping function f(H) to map the information entropy H to the score range [0, 100]. A simple linear mapping function can be:

[0043]

[0044] This function gives the minimum score 0 (representing faulty) when H = Hmax, and H = gives the maximum score 100 (representing brand-new).

[0045] According to actual requirements, adjust the mapping function f(H) to more accurately reflect the health state of the device.

[0046] It can be concluded from the above that in this embodiment, the first key frame image is extracted from multiple device images. The first key frame image represents the important state or change point of the device. Based on the first key frame image, the first health assessment value is determined, which can achieve accurate detection of the device state. At the same time, in this embodiment, the first health assessment value is quantified based on information entropy, making the evaluation result more intuitive and easy to understand.

[0047] In an embodiment of the present disclosure, extracting the first key frame image from multiple device images includes:

[0048] Extracting color features, texture features, and shape features from each device image;

[0049] Based on the change amounts of the color features, texture features, and shape features in each device image, screening the second key frame image from multiple device images;

[0050] Performing clustering analysis on the second key frame image, determining the clustering center obtained by the clustering analysis as the third key frame image, and determining the third key frame image as the first key frame image.

[0051] In this embodiment, the key frame can be identified and extracted by analyzing features such as the color, texture, and shape of the device image. The specific process may include:

[0052] 1) Preprocessing: Scaling multiple device images to a unified size and normalizing the device images.

[0053] 2) Color feature extraction: Calculating the color histogram and statistical features of each device image, such as mean, standard deviation, etc.

[0054] 3) Texture feature extraction: Calculating the gray-level co-occurrence matrix (GLCM) to obtain texture information and extracting local binary pattern (LBP) features.

[0055] 4) Shape feature extraction: Using an edge detection algorithm (such as the Canny algorithm) to identify the significant edges in each device image, and using a contour tracking algorithm to identify and extract the contours of the objects in each device image.

[0056] 5) Feature comparison: Calculating the differences between each device image (consecutive frames) based on color, texture, and shape features, obtaining the change amounts of each device image based on the differences, and selecting the device images with larger change amounts as the second key frame images.

[0057] Specifically, the differences between each device image and its previous device image can be calculated based on color, texture, and shape features. Taking two adjacent device images, the first image and the second image, as an example, in chronological order, the first image is before the second image. At this time, the corresponding feature vectors can be determined based on the color, texture, and shape features of the first image and the second image respectively, and then the similarity between the two feature vectors can be calculated based on the Euclidean distance. If the similarity is greater than the second similarity threshold, it indicates that the difference between the first image and the second image is small. Otherwise, if the similarity is less than or equal to the second similarity threshold, it indicates that the difference between the first image and the second image is large, and the change amount of the second image is large. Then the second image is used as the second key frame image.

[0058] In addition, the color change amount, texture change amount, and shape change amount of the first image and the second image can be calculated respectively, and the color change amount, texture change amount, and shape change amount are compared with the corresponding thresholds. If the change amounts of two or three of the features (including color feature, texture feature, and shape feature) are greater than the corresponding thresholds, it indicates that the difference between the first image and the second image is large, and the change amount of the second image is large. Then the second image is used as the second key frame image.

[0059] 6) Secondary screening of key frames: Based on the acquisition time corresponding to each second key image frame, uniform sampling of each second key frame image is performed in different time periods to ensure that the key frames cover the entire set time period. The clustering algorithm (such as K-means) is used to group the extracted features, and the clustering center of each group can be used as the third key frame, and the third key frame is used as the first key frame image.

[0060] It can be concluded from the above that in this embodiment, two-level screening is performed based on the change amounts of the color feature, texture feature, and shape feature in each device image to obtain the first key frame image, which can effectively extract the important change information in the device image and provide valuable key frame images for the monitoring and diagnosis of the device.

[0061] In an embodiment of the present disclosure, screening the second key frame images from multiple device images based on the change amounts of the color feature, texture feature, and shape feature in each device image includes:

[0062] If the change amount of the color feature, texture feature, or shape feature in any device image is greater than the corresponding first threshold, determine that any such device image is the second key frame image.

[0063] In this embodiment, considering that the feature change amount between adjacent images is small, in order to effectively screen out the device images that have changed, when screening the second key frame images, as long as the change amount of any one of the three features of a device image is greater than the corresponding first threshold, it can be considered that the change amount of this device image is large, and this device image is used as the second key frame image.

[0064] It can be concluded from the above that starting from the three features of color, texture, and shape in this embodiment, the changes in device images can be captured in a timely manner, improving the monitoring sensitivity to device state changes.

[0065] In an embodiment of the present disclosure, the remote diagnosis method for the operating state of the water quality automatic monitoring system based on video images further includes:

[0066] Remove the images with a similarity greater than the first similarity threshold from the third key frame images to obtain the first key frame images.

[0067] In this embodiment, on the basis of obtaining the third key frame images, the key frame images with relatively high similarity can be removed from them to reduce redundancy, ensure the uniform distribution of key frame images in time, and maintain the coherence of the scene.

[0068] Among them, when calculating the similarity between two third key frame images, the feature vectors of the two third key frame images can be extracted respectively, and then the similarity between the two feature vectors is calculated based on the Euclidean distance.

[0069] In an embodiment of the present disclosure, adjusting the first health assessment value based on environmental data includes:

[0070] Fitting the first adjustment parameter based on multiple groups of sample data; each group of sample data includes environmental data and the measured value of the corresponding first adjustment parameter;

[0071] Adjust the first health assessment value based on the first adjustment parameter.

[0072] In this embodiment, the first adjustment parameter is used to characterize the influence degree of environmental data on the first assessment value, and the measured value of the first adjustment parameter can be determined according to the historical operation data of the water quality automatic monitoring system. For example, the operation status of the water quality automatic monitoring system under various environmental factor conditions can be collected, the operation status is scored for the device health status to obtain the measured value of the second assessment value; at the same time, the first assessment value of the device state is obtained based on the analysis of device images, and then the measured value of the first adjustment parameter is obtained by dividing the second assessment value by the first assessment value.

[0073] Furthermore, the first adjustment parameter and contemporaneous environmental factor data, such as temperature, humidity, rainfall, etc., can be collected to obtain multiple sets of sample data. The data can be cleaned to handle missing values and outliers to ensure data quality.

[0074] Based on multiple sets of sample data, a multiple linear regression model is established:

[0075]

[0076] where Y represents the first adjustment parameter, represents the regression coefficient, represents the environmental data, is the random error term.

[0077] Through data fitting, the estimated value of the regression coefficient can be obtained. Based on the estimated value of the regression coefficient the estimated value of the first adjustment parameter is obtained, and then the residual is calculated. The weight coefficient is determined according to the magnitude of the residual, and the formula is as follows:

[0078]

[0079] Based on the weights determined above, weighted least squares estimation is performed on the multiple linear regression model, with the goal of minimizing the weighted residual sum of squares , and data fitting is performed accordingly to obtain the weighted estimated value of the regression coefficient, thus completing the solution process of the multiple linear regression model.

[0080] According to the above multiple linear regression model, the first adjustment parameter can be obtained, and multiplying the first adjustment parameter by the first evaluation value can obtain the second evaluation value.

[0081] It can be concluded from the above that in this embodiment, by fitting the first adjustment parameter with multiple sets of sample data, the influence of environmental data on the health state of the device can be more accurately reflected, so that the obtained second health evaluation value is more in line with the actual operation of the device.

[0082] In an embodiment of the present disclosure, the device image includes an image of the water intake unit and an image of the instrument control unit; determining the remote diagnosis result of the operation state of the water quality automatic monitoring system based on the second health evaluation value includes:

[0083] Weighted summing the second health evaluation value corresponding to the image of the water intake unit and the second health evaluation value corresponding to the image of the instrument control unit to obtain a third health evaluation value;

[0084] Based on the third health evaluation value, the remote diagnosis result of the operation state of the water quality automatic monitoring system is determined.

[0085] In this embodiment, considering that in the water quality automatic monitoring system, in the water quality automatic monitoring station, the water sampling unit and the instrument control unit are key nodes. Therefore, it is possible to focus on collecting the device images of the water sampling unit and the instrument control unit, and calculating the first health assessment value based on the device images of the water sampling unit and the instrument control unit, which is beneficial to reducing the calculation amount.

[0086] Specifically, the corresponding second health assessment value can be obtained based on the device image of the water sampling unit, and then the corresponding second health assessment value can be obtained based on the device image of the instrument control unit. The second health assessment values of the above two devices are weighted and averaged to obtain the third health assessment value. The third health assessment value can be used to evaluate the operation status of the entire water quality automatic monitoring system.

[0087] Corresponding to the method for remotely diagnosing the operation status of the water quality automatic monitoring system based on video images in the above embodiment, Figure 2 is a structural block diagram of a device for remotely diagnosing the operation status of a water quality automatic monitoring system based on video images provided by an embodiment of the present disclosure. For the sake of convenience of description, only the parts related to the embodiments of the present disclosure are shown. Refer to Figure 2 The device 20 for remotely diagnosing the operation status of the water quality automatic monitoring system based on video images includes: a first processing module 21, a second processing module 22, and a result output module 23.

[0088] Among them, the first processing module 21 is used to obtain the first health assessment value based on the device image;

[0089] The second processing module 22 is used to adjust the first health assessment value based on the environmental data to obtain the second health assessment value;

[0090] The result output module 23 is used to determine the remote diagnosis result of the operation status of the water quality automatic monitoring system based on the second health assessment value.

[0091] In an embodiment of the present disclosure, the first processing module 21 is specifically used for:

[0092] Obtain a plurality of device images continuously captured within a set time period;

[0093] Extract the first key frame image from the plurality of device images; determine the first health assessment value based on the information entropy of the first key frame image; wherein, the information entropy and the first health assessment value are in a negative correlation relationship.

[0094] In an embodiment of the present disclosure, the first processing module 21 is specifically used for:

[0095] Extract the color features, texture features, and shape features in each device image;

[0096] Screen the second key frame images from multiple device images based on the variation amounts of color features, texture features, and shape features in the device images;

[0097] Perform clustering analysis on the second key frame images, determine the clustering centers obtained from the clustering analysis as the third key frame images, and determine the third key frame images as the first key frame images.

[0098] In an embodiment of the present disclosure, the first processing module 21 is further specifically configured to:

[0099] If the variation amount of color features, the variation amount of texture features, or the variation amount of shape features in any device image is greater than the corresponding first threshold, determine the any device image as the second key frame image.

[0100] In an embodiment of the present disclosure, the first processing module 21 is further specifically configured to:

[0101] Remove the images with a similarity greater than the first similarity threshold from the third key frame images to obtain the first key frame images.

[0102] In an embodiment of the present disclosure, the second processing module 22 is specifically configured to:

[0103] Fit the first adjustment parameter based on multiple groups of sample data; each group of sample data includes environmental data and the measured value of the corresponding first adjustment parameter;

[0104] Adjust the first health assessment value based on the first adjustment parameter.

[0105] In an embodiment of the present disclosure, the result output module 23 is specifically configured to:

[0106] Perform weighted summation on the second health assessment value corresponding to the water sampling unit image and the second health assessment value corresponding to the instrument control unit image to obtain the third health assessment value;

[0107] Determine the remote diagnosis result of the operation state of the water quality automatic monitoring system based on the third health assessment value.

[0108] See Figure 3 , Figure 3 is a schematic block diagram of an electronic device provided in an embodiment of the present disclosure. As Figure 3The electronic device 300 in the present embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The above-mentioned processors 301, input devices 302, output devices 303, and memories 304 communicate with each other through a communication bus 305. The memory 304 is used to store a computer program, and the computer program includes program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. Among them, the processor 301 is configured to call the program instructions to execute the functions of each module / unit in the above device embodiments, for example Figure 2 the functions of the modules 21 to 23 shown.

[0109] It should be understood that in the embodiments of the present disclosure, the so-called processor 301 may be a central processing unit (CPU), and this processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or this processor may also be any conventional processor, etc.

[0110] The input device 302 may include a touchpad, a fingerprint acquisition sensor (for acquiring the fingerprint information and the direction information of the fingerprint of the user), a microphone, etc., and the output device 303 may include a display (such as an LCD), a speaker, etc.

[0111] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A part of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.

[0112] In specific implementation, the processors 301, input devices 302, and output devices 303 described in the embodiments of the present disclosure may execute the implementation manners described in the first embodiment and the second embodiment of the remote diagnosis method for the operating state of the water quality automatic monitoring system based on video images provided by the embodiments of the present disclosure, and may also execute the implementation manner of the electronic device described in the embodiments of the present disclosure, which will not be elaborated here.

[0113] In another embodiment of the present disclosure, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and the computer program includes program instructions. When the program instructions are executed by a processor, all or part of the processes in the methods of the above embodiments are implemented. It can also be completed by instructing related hardware through the computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above various method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0114] The computer-readable storage medium can be an internal storage unit of the electronic device in any of the foregoing embodiments, such as the hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device. Further, the computer-readable storage medium can also include both the internal storage unit and the external storage device of the electronic device. The computer-readable storage medium is used to store the computer program and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store the data that has been output or will be output.

[0115] Those of ordinary skill in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. To clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been generally described according to their functions in the above description. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present disclosure.

[0116] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described electronic devices and units can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated herein.

[0117] In several embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed couplings or direct couplings or communication connections to each other can be indirect couplings or communication connections through some interfaces or units, or can also be electrical, mechanical or other forms of connection.

[0118] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiments of the present disclosure.

[0119] In addition, each functional unit in various embodiments of the present disclosure can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0120] The above is only the specific implementation manner of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present disclosure can easily think of various equivalent modifications or substitutions, and these modifications or substitutions should all be covered within the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be subject to the protection scope of the claims.

Claims

1. A remote diagnosis method for the operation status of an automatic water quality monitoring system based on video images, characterized in that: include: Acquire a first health assessment value based on the device image; Adjusting the first health assessment value based on the environmental data to obtain a second health assessment value; Determine a remote diagnosis result of the operation status of the automatic water quality monitoring system based on the second health assessment value; The obtaining of a first health assessment value based on a device image includes: Acquire multiple device images taken continuously within a set period of time; A first key frame image is extracted from a plurality of device images; and the first health assessment value is determined based on the information entropy of the first key frame image; wherein the information entropy and the first health assessment value are negatively correlated.

2. The remote diagnosis method for the operation status of the water quality automatic monitoring system based on video images according to claim 1 is characterized in that: The step of extracting a first key frame image from a plurality of device images comprises: Extract color features, texture features and shape features from each device image; Selecting a second key frame image from the plurality of device images based on the amount of change in the color features, texture features, and shape features in each device image; Performing cluster analysis on the second key frame image, determining a cluster center obtained by the cluster analysis as a third key frame image, and determining the third key frame image as the first key frame image.

3. The remote diagnosis method for the operation status of the water quality automatic monitoring system based on video images according to claim 2 is characterized in that: The step of selecting a second key frame image from a plurality of device images based on the amount of change of color features, texture features, and shape features in each device image comprises: If the amount of change in color features, texture features or shape features in any device image is greater than the corresponding first threshold, the device image is determined as the second key frame image.

4. The remote diagnosis method for the operation status of the water quality automatic monitoring system based on video images according to claim 2 is characterized in that: Also includes: The images whose similarity is greater than a first similarity threshold are removed from the third key frame images to obtain the first key frame image.

5. The remote diagnosis method for the operation status of the water quality automatic monitoring system based on video images according to claim 1 is characterized in that: The adjusting the first health assessment value based on the environmental data includes: Fitting a first adjustment parameter based on multiple groups of sample data; each group of sample data includes environmental data and a corresponding measured value of the first adjustment parameter; The first health assessment value is adjusted based on the first adjustment parameter.

6. The remote diagnosis method for the operation status of the water quality automatic monitoring system based on video images according to claim 1 is characterized in that: The equipment image includes a water sampling unit image and an instrument control unit image; the remote diagnosis result of the operation status of the automatic water quality monitoring system determined based on the second health assessment value includes: Performing a weighted summation of the second health assessment value corresponding to the water sampling unit image and the second health assessment value corresponding to the instrument control unit image to obtain a third health assessment value; The remote diagnosis result of the operating status of the automatic water quality monitoring system is determined based on the third health assessment value.

7. A remote diagnosis device for the operation status of an automatic water quality monitoring system based on video images, characterized in that: include: A first processing module, configured to obtain a first health assessment value based on a device image; A second processing module, configured to adjust the first health assessment value based on environmental data to obtain a second health assessment value; A result output module, used to determine a remote diagnosis result of the operation status of the automatic water quality monitoring system based on the second health assessment value; The first processing module is specifically used for: Acquire multiple device images taken continuously within a set period of time; A first key frame image is extracted from a plurality of device images; a first health assessment value is determined based on the information entropy of the first key frame image; wherein the information entropy and the first health assessment value are negatively correlated.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: 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 storing 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