Environmental disaster monitoring method, system and equipment based on deep learning

Abstract

The invention relates to the technical field of environment disaster monitoring and evaluation, in particular to an environment disaster monitoring method, system and device based on deep learning, and the method comprises the steps: obtaining environment monitoring image data; preprocessing the environment monitoring image data to obtain a preprocessed environment monitoring image; identifying an environment disaster site in the environment monitoring image through a deep learning model to obtain an identification result; and analyzing and evaluating the risk based on the identification result and the historical meteorological data. Therefore, according to the scheme of the invention, the efficiency and accuracy of environmental disaster monitoring and evaluation can be greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of environmental disaster monitoring and assessment, and in particular to an environmental disaster monitoring method, system and device based on deep learning. Background Art

[0002] In the power industry and other high-risk industries, disasters such as icing pose a threat to the safety of equipment and infrastructure. Traditional disaster monitoring technologies usually rely on sensors or manual inspections, which cannot fully and comprehensively understand the disaster situation in real time.

[0003] For example, Chinese invention patent CN118629159A discloses a method and system for early warning of collapsed poles of ice-covered distribution towers, which uses sensors to collect temperature, humidity, wind speed and tilt angle data, and then analyzes and judges the data, confirms danger and issues early warnings. Although early warnings can be achieved, only collapsed poles of ice-covered distribution towers can be judged, and real-time early warnings cannot be achieved. Another example is Chinese invention patent CN115278578A discloses a digital twin system for disaster prevention and mitigation of substations, which monitors natural monitoring data related to damage to substations caused by natural disasters through a wireless monitoring sensor network, and determines the type of disaster through correlation analysis; and analyzes the damage to substations caused by natural disasters based on natural monitoring data and constructed fulcrum string models, rigid body models, etc. through a physical analysis module for disasters in substations. Although the early warning efficiency can be improved to a certain extent, it is still impossible to achieve real-time early warnings, and it is impossible to fully grasp the actual disaster situation. Moreover, the above schemes all require the early arrangement of various sensors, and the operation and implementation are complicated. Therefore, there is an urgent need for a method that is easy to implement, can achieve real-time early warnings, and can help staff fully grasp the disaster situation. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide an environmental disaster monitoring method, system and device based on deep learning to overcome the problems of low efficiency and poor accuracy in the current disaster monitoring field.

[0005] To achieve the above objectives, the present invention adopts the following technical solutions:

[0006] In a first aspect, an embodiment of the present application provides an environmental disaster monitoring method based on deep learning, comprising:

[0007] Acquire environmental monitoring image data;

[0008] Preprocessing the environmental monitoring image data to obtain a preprocessed environmental monitoring image;

[0009] Using a deep learning model, identifying the environmental disaster scene in the environmental monitoring image to obtain an identification result;

[0010] Based on the identification results and historical meteorological data, the risks are analyzed and assessed.

[0011] Furthermore, in some embodiments of the present application, the step of acquiring environmental monitoring image data includes:

[0012] The environmental monitoring image data is obtained from a preset environmental monitoring system, and the environmental monitoring image data is obtained through one or more devices including satellite remote sensing equipment, unmanned aerial vehicles or surveillance cameras.

[0013] Furthermore, in some embodiments of the present application, the preprocessing of the environment monitoring image data to obtain the preprocessed environment monitoring image includes:

[0014] The environmental monitoring image data is subjected to denoising, image enhancement and size standardization processing in sequence;

[0015] Among them, denoising processing includes denoising processing through Gaussian filtering and mean filtering; image enhancement processing includes using histogram equalization technology to enhance the contrast of image data; size standardization processing includes scaling the image data to the input size required by the preset deep learning model.

[0016] Furthermore, in some embodiments of the present application, identifying the environmental disaster scene in the environmental monitoring image by a deep learning model to obtain an identification result includes:

[0017] Performing semantic segmentation on the environmental monitoring image through a deep learning model based on PSPNet to identify disaster areas in the environmental monitoring image;

[0018] The PSPNet-based deep learning model is generated by a transfer learning strategy and pre-trained model parameters.

[0019] Furthermore, in some embodiments of the present application, the risk analysis and assessment based on the identification result and historical meteorological data includes:

[0020] Based on historical meteorological data and the recognition results of the deep learning model, a rule-based target learning model is used to analyze and evaluate potential risks.

[0021] Furthermore, in some embodiments of the present application, the risk analysis and assessment based on the identification result and historical meteorological data further includes:

[0022] Based on the identification results, historical disaster records and equipment importance, a comprehensive risk score is generated.

[0023] Furthermore, in some embodiments of the present application, the analyzing and assessing risk based on the identification result and historical meteorological data also includes: issuing a warning based on the result of the risk assessment and the comprehensive risk score.

[0024] In a second aspect, an embodiment of the present application provides an environmental disaster monitoring system based on deep learning, comprising:

[0025] An image acquisition module, used to acquire environmental monitoring image data;

[0026] An image preprocessing module, used to preprocess the environmental monitoring image data to obtain a preprocessed environmental monitoring image;

[0027] A deep learning model analysis module, used to identify the environmental disaster scene in the environmental monitoring image through a deep learning model to obtain an identification result;

[0028] The risk assessment module is used to analyze and assess risks based on the identification results and historical meteorological data.

[0029] Furthermore, in some embodiments of the present application, an early warning module is also included, and the early warning module is used to issue an early warning based on the assessment result of the risk assessment module.

[0030] In a third aspect, an embodiment of the present application provides an environmental disaster monitoring device based on deep learning, including a processor and a memory, wherein the processor is connected to the memory:

[0031] Wherein, the processor is used to call and execute the program stored in the memory;

[0032] The memory is used to store the program, and the program is at least used to execute the above-mentioned environmental disaster monitoring method based on deep learning.

[0033] The present invention relates to the technical field of environmental disaster monitoring and assessment, and in particular to a method, system and device for environmental disaster monitoring based on deep learning, the method comprising acquiring environmental monitoring image data; preprocessing the environmental monitoring image data to obtain a preprocessed environmental monitoring image; identifying the environmental disaster site in the environmental monitoring image through a deep learning model to obtain an identification result, including identifying ice cover in the environmental monitoring image based on the identification result and historical meteorological data, and analyzing and assessing the risk. In this way, through the scheme of the present invention, the efficiency and accuracy of environmental disaster monitoring and assessment can be greatly improved. Its beneficial effects are specifically embodied in the following aspects: 1. Through the deep learning model, real-time monitoring can be achieved and monitoring efficiency can be improved. 2. Environmental monitoring images can be obtained from the existing environmental monitoring system without additional hardware costs, easy to operate and strong in feasibility. 3. Disaster monitoring and early warning for various infrastructures susceptible to disasters, such as power lines and transportation facilities, can be achieved by adjusting the environmental monitoring image data. 4. Through the preprocessing of environmental monitoring image data and the use of deep learning models, the accuracy of monitoring and assessment can be greatly improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0035] Figure 1 It is a flow chart of the deep learning-based environmental disaster monitoring method provided in an embodiment of the present application.

[0036] Figure 2 It is a structural diagram of the PPM of the deep learning model in the deep learning-based environmental disaster monitoring method provided in an embodiment of the present application.

[0037] Figure 3 It is a structural diagram of the deep learning-based environmental disaster monitoring system provided in an embodiment of the present application.

[0038] Figure 4 It is a structural diagram of an environmental disaster monitoring device based on deep learning provided in an embodiment of the present application. DETAILED DESCRIPTION

[0039] To make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described in detail below. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other implementation methods obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0040] Figure 1 is a flow chart of an environmental disaster monitoring method based on deep learning provided in an embodiment of the present application, such as Figure 1 As shown, the environmental disaster monitoring method based on deep learning provided by the embodiment of the present application may at least include the following steps:

[0041] S101. Acquire environmental monitoring image data.

[0042] Specifically, in the present application, environmental monitoring image data can be directly acquired from an existing environmental monitoring system.

[0043] S102: Preprocess the environmental monitoring image data to obtain a preprocessed environmental monitoring image.

[0044] Specifically, it may include performing denoising, image enhancement and size standardization processing on the acquired environmental monitoring image data in sequence.

[0045] Among them, denoising processing includes denoising processing through Gaussian filtering and mean filtering; image enhancement processing includes using histogram equalization technology to enhance the contrast of image data; size standardization processing includes scaling the image data to the input size required by the preset deep learning model, thereby obtaining a preprocessed environmental monitoring image.

[0046] It should be noted that by using denoising techniques such as Gaussian filtering and mean filtering to denoise the acquired environmental monitoring image data, the noise interference in the image data can be reduced and the image quality can be improved. By using image enhancement techniques such as histogram equalization, the contrast of the image data can be improved, and the features of the ice-covered area in the image data can be made more obvious. By scaling the processed image data to the input size required by the deep learning model (for example: 256×256 pixels), the input consistency of the deep learning model can be ensured and the model recognition accuracy can be improved.

[0047] S103. Identify the environmental disaster scene in the environmental monitoring image through a deep learning model to obtain an identification result.

[0048] Specifically, the environmental monitoring images obtained after the above preprocessing are input into the deep learning model, and the environmental disaster scenes including ice cover are identified through the deep learning model to obtain identification results (such as whether ice cover exists and the severity, etc.).

[0049] S104. Analyze and assess risks based on identification results and historical meteorological data.

[0050] Specifically, after obtaining the recognition results of the deep learning model, we combine historical meteorological data to analyze and evaluate the potential risks brought by the disaster.

[0051] The deep learning-based environmental disaster monitoring method provided by the present invention obtains environmental monitoring image data; preprocesses the environmental monitoring image data to obtain a preprocessed environmental monitoring image; identifies the environmental disaster site in the environmental monitoring image through a deep learning model to obtain an identification result; and analyzes and evaluates risks based on the identification result and historical meteorological data, thereby greatly improving the efficiency and accuracy of environmental disaster monitoring and evaluation.

[0052] Furthermore, in the present application, for environmental monitoring image data, image data can be obtained from existing environmental monitoring systems. For example, these image data can come from various sources such as satellite remote sensing, drone aerial photography, surveillance cameras, etc., and can cover infrastructure that is vulnerable to disasters, such as power lines and transportation facilities.

[0053] In addition, the acquired historical environmental monitoring image data can also be applied to processes such as the training of deep learning models. For this purpose, environmental monitoring image data can be obtained from an existing image database or historical image acquisition system, where the data types include image data taken under different weather conditions, thereby ensuring that ice cover can be effectively identified in various environments in the future.

[0054] In this application, for the deep learning model, this application first selects the PSPNet (Pyramid SceneParsing Network) basic deep learning model, which performs well in image segmentation and recognition tasks, and is especially suitable for environmental monitoring with complex backgrounds. On this basis, a large number of annotated ice-covered image data sets are used for model training to ensure that the final deep learning model has good generalization capabilities. Among them, in the training process of the deep learning model, the solution of this application includes the use of a transfer learning strategy, which is applied through pre-trained model parameters, and targeted training to further improve the recognition accuracy of the model. The PPM structure diagram of the deep learning model is shown below. Figure 2 As shown (its principle is consistent with the basic principle of the deep learning model in the prior art, and can be understood by referring to the deep learning model in the prior art, and will not be described in detail here).

[0055] After the deep learning model is obtained through preliminary training, the environmental monitoring image data obtained during actual monitoring is input into the deep learning model after preprocessing. The deep learning model can perform semantic segmentation on the image, identify the ice-covered area, and obtain the recognition result.

[0056] After obtaining the identification results, combined with historical meteorological data, rule-based algorithms or machine learning models (such as decision trees and random forests) are used to analyze and evaluate potential risks in order to analyze and evaluate risks (i.e. analyze the potential risks that may be caused by icing) and issue warnings based on the evaluation results. For example, the evaluation results can be used in early warning systems or modules to provide reference for relevant decision makers.

[0057] In addition, after obtaining the above-mentioned identification results, a comprehensive risk score can be generated based on various factors, such as the identification results of the ice-covered area obtained based on the above-mentioned deep learning model, historical disaster records, and equipment importance, etc. (in some embodiments, it can also include the results of analyzing and evaluating potential risks by the above-mentioned rule-based algorithm or machine learning model) to assist decision makers in making response measures.

[0058] Based on the same inventive concept, the present application also provides an environmental disaster monitoring system based on deep learning. Figure 3 is a schematic diagram of the structure of the environmental disaster monitoring system based on deep learning provided in the embodiment of the present application, such as Figure 3 As shown, the environmental disaster monitoring system based on deep learning also provided by this application includes:

[0059] An image acquisition module 21 is used to acquire environmental monitoring image data; an image preprocessing module 22 is used to preprocess the environmental monitoring image data to obtain a preprocessed environmental monitoring image; a deep learning model analysis module 23 is used to identify environmental disaster sites in environmental monitoring images through a deep learning model to obtain identification results; wherein, identifying environmental disaster sites in environmental monitoring images includes identifying ice cover in environmental monitoring images; a risk assessment module 24 is used to analyze and assess risks based on the identification results and historical meteorological data.

[0060] Furthermore, in some embodiments of the present application, the environmental disaster monitoring system also includes an early warning module, which is used to issue an early warning based on the assessment results of the risk assessment module.

[0061] It should be noted that the environmental disaster monitoring system based on deep learning provided by this application adopts a modular design, and the above modules can transmit data through the API interface to ensure the flexibility and scalability of the system. At the same time, the environmental disaster monitoring system based on deep learning also provides a user interface for providing a friendly user interface, through which users can view real-time monitoring data, identification results and risk assessment reports. The system can be applied to multiple fields such as the power industry, transportation, and meteorological monitoring, and provide decision support for relevant units through real-time monitoring and evaluation.

[0062] In addition, as introduced in the above method embodiment, the deep learning-based environmental disaster monitoring system provided by the present application can utilize existing monitoring equipment and image data without additional hardware costs. At the same time, the environmental disaster monitoring system can also be integrated into the existing environmental monitoring system for disaster warning and real-time monitoring in the power industry, transportation facilities and other high-risk scenarios, and has strong feasibility.

[0063] Regarding the deep learning-based environmental disaster monitoring system in the above-mentioned embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the deep learning-based environmental disaster monitoring method, and will not be elaborated here.

[0064] Based on the same inventive concept, the present application also provides an environmental disaster monitoring device based on deep learning. Figure 4 is a schematic diagram of the structure of an environmental disaster monitoring device based on deep learning provided in an embodiment of the present application, such as Figure 4 As shown, the device may include: a processor 31 and a memory 32, wherein the processor 31 is connected to the memory 32: wherein the processor 31 is used to call and execute a program stored in the memory 32; the memory 32 is used to store a program, which is at least used to execute the above-mentioned deep learning-based environmental disaster monitoring method.

[0065] It can be understood that the same or similar parts of the above embodiments can be referenced to each other, and the contents not described in detail in some embodiments can refer to the same or similar contents in other embodiments.

[0066] It should be noted that, in the description of the present invention, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of the present invention, unless otherwise specified, the meaning of "plurality" refers to at least two.

[0067] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code that includes one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present invention belong.

[0068] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0069] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0070] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0071] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0072] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0073] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A method for monitoring environmental disasters based on deep learning, characterized in that: include: Acquire environmental monitoring image data; Preprocessing the environmental monitoring image data to obtain a preprocessed environmental monitoring image; Using a deep learning model, identifying the environmental disaster scene in the environmental monitoring image to obtain an identification result; Based on the identification results and historical meteorological data, the risks are analyzed and assessed.

2. The environmental disaster monitoring method based on deep learning according to claim 1 is characterized in that: The step of acquiring environmental monitoring image data comprises: The environmental monitoring image data is obtained from a preset environmental monitoring system, and the environmental monitoring image data is obtained through one or more devices including satellite remote sensing equipment, unmanned aerial vehicles or surveillance cameras.

3. The environmental disaster monitoring method based on deep learning according to claim 1 is characterized in that: The preprocessing of the environmental monitoring image data to obtain a preprocessed environmental monitoring image includes: The environmental monitoring image data is subjected to denoising, image enhancement and size standardization processing in sequence; Among them, denoising processing includes denoising processing through Gaussian filtering and mean filtering; image enhancement processing includes using histogram equalization technology to enhance the contrast of image data; size standardization processing includes scaling the image data to the input size required by the preset deep learning model.

4. The environmental disaster monitoring method based on deep learning according to claim 1 is characterized in that: The identifying of the environmental disaster scene in the environmental monitoring image by the deep learning model to obtain the identification result includes: Performing semantic segmentation on the environmental monitoring image through a deep learning model based on PSPNet to identify disaster areas in the environmental monitoring image; The PSPNet-based deep learning model is generated by a transfer learning strategy and pre-trained model parameters.

5. The environmental disaster monitoring method based on deep learning according to claim 1 is characterized in that: The risk analysis and assessment based on the identification results and historical meteorological data includes: Based on historical meteorological data and the recognition results of the deep learning model, a rule-based target learning model is used to analyze and evaluate potential risks.

6. The environmental disaster monitoring method based on deep learning according to claim 5 is characterized in that: The analyzing and assessing risk based on the identification result and historical meteorological data also includes: Based on the identification results, historical disaster records and equipment importance, a comprehensive risk score is generated.

7. The environmental disaster monitoring method based on deep learning according to claim 6 is characterized in that: The analyzing and assessing risk based on the identification result and historical meteorological data also includes: issuing a warning based on the result of the risk assessment and / or the comprehensive risk score.

8. An environmental disaster monitoring system based on deep learning, characterized in that: include: An image acquisition module, used to acquire environmental monitoring image data; An image preprocessing module, used to preprocess the environmental monitoring image data to obtain a preprocessed environmental monitoring image; A deep learning model analysis module, used to identify the environmental disaster scene in the environmental monitoring image through a deep learning model to obtain an identification result; The risk assessment module is used to analyze and assess risks based on the identification results and historical meteorological data.

9. The deep learning-based environmental disaster monitoring system according to claim 8, characterized in that: It also includes an early warning module, which is used to issue an early warning based on the assessment result of the risk assessment module.

10. An environmental disaster monitoring device based on deep learning, characterized in that: The invention comprises a processor and a memory, wherein the processor is connected to the memory: Wherein, the processor is used to call and execute the program stored in the memory; The memory is used to store the program, and the program is at least used to execute the deep learning-based environmental disaster monitoring method described in any one of claims 1-7.

Images