Photovoltaic-based biodiversity monitoring method and system

Abstract

The invention discloses a photovoltaic-based biodiversity monitoring method and system, and the method comprises the steps: setting a video data obtaining device based on regional photovoltaic equipment, and obtaining a regional video image based on the video data obtaining device; carrying out image extraction on the region video image to obtain an extracted image, and carrying out region division based on the extracted image to obtain a region annotation image; constructing a feature recognition model, and training the feature recognition model based on the biological features to obtain a biological recognition model; and inputting the region labeling image into the biological recognition model for recognition, and storing the region labeling image into a database to obtain a biological diversity monitoring result. By using the electric quantity of the photovoltaic equipment, the energy problem during biodiversity monitoring is reduced, meanwhile, the biodiversity of a region can be effectively monitored, and ecological protection can be taken into consideration while clean power generation is achieved.

Description

Technical Field

[0001] The present invention belongs to the field of biodiversity monitoring, and in particular relates to a photovoltaic-based biodiversity monitoring method and system. Background Art

[0002] Photovoltaic, or photovoltaic power generation system, is a power generation system that uses the photovoltaic effect of semiconductor materials to convert solar radiation energy into electrical energy. The energy of the photovoltaic power generation system comes from inexhaustible solar energy, which is a clean, safe and renewable energy source. The photovoltaic power generation process does not pollute the environment or damage the ecology. Photovoltaic power generation systems are divided into independent photovoltaic systems and grid-connected photovoltaic systems. Photovoltaic power generation systems are composed of solar cell arrays, battery packs, charge and discharge controllers, inverters, AC distribution cabinets, solar tracking control systems and other equipment.

[0003] However, due to the large-scale installation of photovoltaic equipment, the organisms in the area are unable to obtain sufficient sunlight, reducing the biodiversity of the area. At the same time, the biodiversity of the areas where photovoltaic equipment is installed has not been monitored. At the same time, since the resources of the photovoltaic system are required to be used efficiently, users need to use high-efficiency load equipment, which has caused biological and economic burdens in the region. Summary of the invention

[0004] The purpose of the present invention is to provide a photovoltaic-based biodiversity monitoring method and system to solve the problems existing in the above-mentioned prior art.

[0005] To achieve the above object, the present invention provides a photovoltaic-based biodiversity monitoring method, comprising:

[0006] Setting a video data acquisition device based on regional photovoltaic equipment, and acquiring regional video images based on the video data acquisition device;

[0007] Performing image extraction on the video image of the region to obtain an extracted image, performing region division based on the extracted image to obtain a region annotated image;

[0008] Constructing a feature recognition model, and training the feature recognition model based on biological features to obtain a biological recognition model;

[0009] The region-marked image is input into the biometric recognition model for recognition and stored in a database to obtain a biodiversity monitoring result.

[0010] Preferably, the process of acquiring the regional video image includes:

[0011] Acquire equipment data of regional photovoltaic equipment, and set the video data acquisition device based on the equipment data;

[0012] The video data acquisition devices are evenly arranged based on the regional terrain to acquire images, thereby obtaining the regional video image.

[0013] Preferably, the process of setting the video data acquisition device based on the device data includes:

[0014] Acquire the real-time power and current changes of regional photovoltaic equipment, and set the daytime operation plan of the video data acquisition device based on the highest point power data and current changes in the real-time power;

[0015] A nighttime operation plan of the video data acquisition device is set based on the lowest point power data and current changes in the real-time power.

[0016] Preferably, the process of acquiring the extracted image includes: setting a similarity threshold, deduplicating the image data in the regional video image based on the similarity threshold to obtain a biological key change image, and clarifying the biological key change image to obtain the extracted image.

[0017] Preferably, the process of obtaining the region-annotated image includes:

[0018] The convolutional neural network is trained based on the environmental features to obtain an image classifier;

[0019] Based on the image classifier, the environmental features in the extracted image are divided into regions and annotated to obtain the region annotated image.

[0020] Preferably, the process of obtaining the biometric recognition model includes:

[0021] Build a neural network model;

[0022] Acquire a historical biodiversity dataset, and input the historical biodiversity dataset into the neural network model for training to obtain a training model;

[0023] The training model is optimized based on biological parameters to obtain the biological recognition model.

[0024] Preferably, the process of obtaining biodiversity monitoring results includes:

[0025] Inputting the region-annotated image into the biometric recognition model for recognition to obtain a biometric monitoring result;

[0026] The biological monitoring results are optimized based on a standardized method and stored in a database to obtain the biodiversity monitoring results.

[0027] To achieve the above object, the present invention also provides a photovoltaic-based biodiversity monitoring system, comprising:

[0028] Photovoltaic equipment, video data acquisition device, image processing module, model building module, monitoring module;

[0029] The photovoltaic device is used to supply power;

[0030] The video data acquisition device is electrically connected to the photovoltaic device and is used to acquire regional video images;

[0031] The image processing module is connected to the video data acquisition device and is used to extract the image from the video image of the region, obtain the extracted image, divide the region based on the extracted image, and obtain the region annotation image;

[0032] The model building module is connected to the image processing module and is used to build a feature recognition model, train the feature recognition model based on biological features, and obtain a biological recognition model;

[0033] The monitoring module is connected to the model building module and is used to input the region annotation image into the biometric recognition model for identification and storage in a database to obtain biodiversity monitoring results.

[0034] The technical effects of the present invention are:

[0035] 1. The present invention reduces the energy problem in monitoring biodiversity by using the power of photovoltaic equipment, and can effectively monitor the biodiversity of the region, while generating clean electricity and taking into account ecological protection;

[0036] 2. The present invention reduces the economic burden on users of photovoltaic equipment. Meanwhile, after the biological monitoring system of the present invention is built, only a small number of staff are required to perform regular inspection and maintenance of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0038] Figure 1 is a flow chart of a biodiversity monitoring method in an embodiment of the present invention;

[0039] Figure 2 Schematic diagram of a biodiversity monitoring system in an embodiment of the present invention. DETAILED DESCRIPTION

[0040] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0041] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0042] Embodiment 1

[0043] like Figure 1 As shown, this embodiment provides a photovoltaic-based biodiversity monitoring method, including:

[0044] Setting a video data acquisition device based on regional photovoltaic equipment, and acquiring regional video images based on the video data acquisition device;

[0045] Performing image extraction on the video image of the region to obtain an extracted image, performing region division based on the extracted image to obtain a region annotated image;

[0046] Constructing a feature recognition model, and training the feature recognition model based on biological features to obtain a biological recognition model;

[0047] The region-marked image is input into the biometric recognition model for recognition and stored in a database to obtain a biodiversity monitoring result.

[0048] In this embodiment, the photovoltaic device supplies power to the video data acquisition device;

[0049] In this embodiment, the video data acquisition device is a high-definition camera;

[0050] To further optimize the solution, the process of obtaining regional video images includes:

[0051] Acquire equipment data of regional photovoltaic equipment, and set the video data acquisition device based on the equipment data;

[0052] The video data acquisition devices are evenly arranged based on the regional terrain to acquire images, thereby obtaining the regional video image.

[0053] Further optimizing the solution, the process of setting the video data acquisition device based on the device data includes:

[0054] Acquire the real-time power and current changes of regional photovoltaic equipment, and set the daytime operation plan of the video data acquisition device based on the highest point power data and current changes in the real-time power;

[0055] A nighttime operation plan of the video data acquisition device is set based on the lowest point power data and current changes in the real-time power.

[0056] According to a further optimization scheme, the process of obtaining the extracted image includes: setting a similarity threshold, deduplicating the image data in the video image of the area based on the similarity threshold, obtaining a biological key change image, and clarifying the biological key change image to obtain the extracted image.

[0057] Further optimizing the solution, the process of obtaining the region annotation image includes:

[0058] The convolutional neural network is trained based on the environmental features to obtain an image classifier;

[0059] Based on the image classifier, the environmental features in the extracted image are divided into regions and annotated to obtain the region annotated image.

[0060] Further optimizing the scheme, the process of obtaining the biometric recognition model includes:

[0061] Build a neural network model;

[0062] Acquire a historical biodiversity dataset, and input the historical biodiversity dataset into the neural network model for training to obtain a training model;

[0063] The training model is optimized based on biological parameters to obtain the biological recognition model.

[0064] Specifically: Determine the network structure: Determine the number of input, hidden and output layers and the number of nodes required based on actual needs.

[0065] Initialize weights and biases: Weights and biases are the core parameters of the neural network and need to be randomly initialized to a small value. Weights and biases control the strength and direction of signal transmission between neurons.

[0066] Forward propagation calculation: Starting from the input layer, the prediction result is calculated by calculating the weighted sum of each neuron and passing it to the next layer.

[0067] Define the loss function: The loss function is used to measure the difference between the predicted result and the actual result. Commonly used loss functions include mean squared error (MSE) and cross-entropy. This embodiment uses the cross-entropy loss function;

[0068] Back-propagation optimization: The back-propagation algorithm is used to calculate the contribution of each parameter to the loss function, and then the values ​​of weights and biases are updated according to the gradient descent algorithm to minimize the loss function.

[0069] Repeated iteration: Through multiple forward propagation and back propagation optimization, the values ​​of weights and biases are continuously updated until the loss function converges.

[0070] Further optimizing the scheme, the process of obtaining biodiversity monitoring results includes:

[0071] Inputting the region-annotated image into the biometric recognition model for recognition to obtain a biometric monitoring result;

[0072] The biological monitoring results are optimized based on a standardized method and stored in a database to obtain the biodiversity monitoring results.

[0073] Z-score standardization, also known as standard deviation standardization, is a commonly used data standardization method. It converts the original data into values ​​with a standard normal distribution for better comparison and analysis. The following are the steps to achieve Z-score standardization:

[0074] Calculate mean and standard deviation: For a given data set x, calculate its mean μ and standard deviation σ.

[0075] Normalize the data: For each data point xi, normalize it using the following formula:

[0076] z=(xi-μ) / σ

[0077] Among them, z represents the standardized value and xi represents the original value.

[0078] Apply standardization: In this way, the data is scaled to a range with a mean of 0 and a standard deviation of 1. The standardized data can better reflect the relationship between the data and facilitate further statistical analysis.

[0079] At the same time, the database in this application is in xml format;

[0080] Building an XML database usually requires the following steps:

[0081] Determine the data structure based on the requirements of the microgravity environment: The data in the XML database is stored in the form of XML documents, so it is necessary to determine the data structure and define a document type definition (DTD) or XML schema (XSD) to describe the format and rules of the data. These templates include elements, attributes, namespaces, etc.

[0082] Design document template: Create and design XML document template based on data structure, that is, define the elements, attributes and the relationships between them in the XML document.

[0083] Determine the storage solution: Select a suitable XML database system according to application requirements, such as eXist-db, BaseX, or MarkLogic. Some database management systems also support data import and query in XML format, such as Oracle and Microsoft SQL Server.

[0084] Insert and query data: Use the provided API or query language, such as XQuery or XPath, to insert data into the database, and retrieve and query data from the database. It should be noted here that the XML data saved in the database should comply with the pre-defined DTD or XSD specifications.

[0085] Perform maintenance and optimization: Periodically back up and maintain the database, and optimize query statements and indexes to improve index efficiency and query speed.

[0086] Embodiment 2

[0087] like Figure 2 As shown, this embodiment provides a photovoltaic-based biodiversity monitoring system, including:

[0088] Photovoltaic equipment, video data acquisition device, image processing module, model building module, monitoring module;

[0089] The photovoltaic device is used to supply power;

[0090] The video data acquisition device is electrically connected to the photovoltaic device and is used to acquire regional video images;

[0091] The image processing module is connected to the video data acquisition device and is used to extract the image from the video image of the region, obtain the extracted image, divide the region based on the extracted image, and obtain the region annotation image;

[0092] The model building module is connected to the image processing module and is used to build a feature recognition model, train the feature recognition model based on biological features, and obtain a biological recognition model;

[0093] The monitoring module is connected to the model building module and is used to input the region annotation image into the biometric recognition model for identification and storage in a database to obtain biodiversity monitoring results.

[0094] The above is only a preferred specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A photovoltaic-based biodiversity monitoring method, characterized in that: The following steps are involved: Setting a video data acquisition device based on regional photovoltaic equipment, and acquiring regional video images based on the video data acquisition device; Performing image extraction on the video image of the region to obtain an extracted image, performing region division based on the extracted image to obtain a region annotated image; Constructing a feature recognition model, and training the feature recognition model based on biological features to obtain a biological recognition model; The region-marked image is input into the biometric recognition model for recognition and stored in a database to obtain a biodiversity monitoring result.

2. The photovoltaic-based biodiversity monitoring method according to claim 1, characterized in that: The process of acquiring regional video images includes: Acquire equipment data of regional photovoltaic equipment, and set the video data acquisition device based on the equipment data; The video data acquisition devices are evenly arranged based on the regional terrain to acquire images, thereby obtaining the regional video image.

3. The photovoltaic-based biodiversity monitoring method according to claim 2, characterized in that: The process of setting the video data acquisition device based on the device data includes: Acquire the real-time power and current changes of regional photovoltaic equipment, and set the daytime operation plan of the video data acquisition device based on the highest point power data and current changes in the real-time power; A nighttime operation plan of the video data acquisition device is set based on the lowest point power data and current changes in the real-time power.

4. The photovoltaic-based biodiversity monitoring method according to claim 1, characterized in that: The process of obtaining the extracted image includes: setting a similarity threshold, deduplicating the image data in the regional video image based on the similarity threshold to obtain a biological key change image, and clarifying the biological key change image to obtain the extracted image.

5. The photovoltaic-based biodiversity monitoring method according to claim 1, characterized in that: The process of obtaining the region annotation image comprises: The convolutional neural network is trained based on the environmental features to obtain an image classifier; Based on the image classifier, the environmental features in the extracted image are divided into regions and annotated to obtain the region annotated image.

6. The photovoltaic-based biodiversity monitoring method according to claim 1, characterized in that: The process of obtaining the biometric recognition model comprises: Build a neural network model; Acquire a historical biodiversity dataset, and input the historical biodiversity dataset into the neural network model for training to obtain a training model; The training model is optimized based on biological parameters to obtain the biological recognition model.

7. The photovoltaic-based biodiversity monitoring method according to claim 1, characterized in that: The process of obtaining biodiversity monitoring results includes: Inputting the region-annotated image into the biometric recognition model for recognition to obtain a biometric monitoring result; The biological monitoring results are optimized based on a standardized method and stored in a database to obtain the biodiversity monitoring results.

8. A photovoltaic-based biodiversity monitoring system, characterized in that: include: Photovoltaic equipment, video data acquisition device, image processing module, model building module, monitoring module; The photovoltaic device is used to supply power; The video data acquisition device is electrically connected to the photovoltaic device and is used to acquire regional video images; The image processing module is connected to the video data acquisition device and is used to extract the image from the video image of the region, obtain the extracted image, divide the region based on the extracted image, and obtain the region annotation image; The model building module is connected to the image processing module and is used to build a feature recognition model, train the feature recognition model based on biological features, and obtain a biological recognition model; The monitoring module is connected to the model building module and is used to input the region annotation image into the biometric recognition model for identification and storage in a database to obtain biodiversity monitoring results.

Images