Intelligent recognition method and system for ground objects in power grid infrastructure project scenes based on AI technology

Abstract

The present application relates to the field of scene intelligent recognition technology, and specifically discloses a method and system for intelligent recognition of ground objects in power grid infrastructure project scenes based on AI technology. The method mainly includes: obtaining remote sensing images of power grid infrastructure project scenes; using a convolutional neural network model to identify the ground object type in the remote sensing image. In the initial stage, the convolutional neural network model activates a preset number of convolution layers and pooling layers. If there is an unknown ground object type, the number and depth of the convolution layers and pooling layers are further activated to extract more ground object features. The present application can dynamically adjust the depth and number of extracted features according to the ground object situation in the image, so as to better adapt to different types of remote sensing images, separate the tasks of ground object type recognition and coordinate positioning, effectively reduce the computational complexity, and improve the efficiency and speed of the model, so as to better identify various ground object types and bring significant economic and social benefits.

Description

Technical Field

[0001] The present application relates to the field of scene intelligent recognition technology, and in particular to a method for intelligent recognition of ground objects in power grid infrastructure projects based on AI technology. Background Art

[0002] Power grid infrastructure projects involve the planning, design, construction, and renovation of power systems to meet electricity supply needs. Using static satellite remote sensing data for power grid infrastructure planning provides detailed basic information such as topography, land use, and vegetation cover. This supports preliminary facility location and route selection, reduces decision-makers' uncertainty about environmental and geographical conditions, and improves planning accuracy and reliability.

[0003] Although existing technologies have made certain progress in identifying land features in power grid infrastructure project scenarios, the static model structure cannot flexibly increase the network depth when faced with unknown land feature types, which limits the model's adaptability and generalization capabilities. It also shows limitations in responding to real-time changes and dynamic demands in power grid infrastructure planning, and cannot effectively cope with the diversity and variability of land feature types. Summary of the Invention

[0004] This application provides an AI-based method and system for intelligently identifying ground objects in power grid infrastructure project scenarios. This method addresses the existing problem of static model structures being unable to flexibly increase network depth when faced with unknown ground object types. It can dynamically adjust the depth and number of extracted features based on the ground object conditions in the image, thereby better adapting to different types of remote sensing imagery. This reduces resource consumption when processing common ground objects, saving storage and processing resources while maintaining efficiency and accuracy in complex image processing.

[0005] The present application provides an AI-based method for intelligently identifying ground objects in power grid infrastructure project scenes, which includes the following steps: acquiring a remote sensing image of a power grid infrastructure project scene; using a convolutional neural network model to identify the ground object type in the remote sensing image, including: the convolutional neural network model uses stacked convolution layers and pooling layers, in the initial stage, the convolutional neural network model activates a preset number of convolution layers and pooling layers, and after extracting ground object features in the remote sensing image, transfers the extracted ground object features to a connection layer to obtain a ground object type probability value; determines whether the ground object type probability value is greater than a preset judgment probability, and identifies ground object types with probability values ​​greater than and less than the judgment probability as known ground object types and unknown ground object types, respectively; if an unknown ground object type exists, further activates the number and depth of convolution layers and pooling layers to extract more ground object features, and identifies the ground object type probability value of the unknown ground object type based on the ground object features, until a feature map of all known ground object types is obtained; and outputs a result, which includes a remote sensing image marked with a known ground object type.

[0006] By increasing the number and depth of convolutional and pooling layers, and optimizing feature extraction strategies, the depth and number of extracted features can be dynamically adjusted according to the terrain conditions in the image. When processing unknown terrain types, the network structure can be dynamically adjusted to better identify various terrain types, providing a more accurate and efficient terrain identification solution for power grid infrastructure projects.

[0007] Furthermore, the output remote sensing image also has coordinates of known land feature types.

[0008] Furthermore, the convolutional neural network model also includes an additional fully connected layer, the feature map of the known land feature type is converted into a one-dimensional vector through a shape transformation matrix, the one-dimensional vector is input into the fully connected layer, and a linear transformation is performed through the weight matrix to obtain an intermediate output, an activation function is applied to the intermediate output, and the activated output is used as the input of the output layer to obtain the coordinates of the known land feature type.

[0009] Furthermore, the number of activation layers of the convolution layer and the pooling layer when identifying all specified objects is obtained, and the number of activation layers is used as the stacking number of the convolution layer and the pooling layer.

[0010] Furthermore, further activating the number and depth of convolutional layers and pooling layers specifically includes: obtaining the maximum value of the feature type probability value of all unknown feature types, dividing the maximum value of the feature type probability value of all unknown feature types into a specified number of clusters according to the numerical value; and determining the number of times the convolutional layers and pooling layers are activated based on the number of clusters.

[0011] Furthermore, a clustering algorithm based on data density is used to determine the number of clusters.

[0012] Furthermore, determining the number of clusters specifically includes: taking the maximum value of the feature type probability value of the unknown feature type as the data point, defining parameters ε and MinPts, ε represents the distance threshold of the neighborhood, and MinPts represents the minimum number of data points in the ε neighborhood; visiting each data point, randomly selecting an unvisited data point each time, calculating the number of data points in the ε neighborhood of the point, and if it is greater than or equal to MinPts, marking the point as a core point; starting from the core point, adding its density-reachable points to the same cluster in a density-reachable manner, and adding points that do not belong to any cluster to the nearest cluster.

[0013] Furthermore, each cluster corresponds to the number of activation layers n i , n i For: n i =a i ·(Ls); Where n i represents the number of activation layers corresponding to the i-th cluster, a irepresents the length ratio of the i-th cluster, L represents the number of stacked convolutional layers and pooling layers, s represents the number of convolutional layers and pooling layers activated in the initial stage, and A represents the number of clusters.

[0014] Furthermore, the feature characteristics include edge characteristics, texture characteristics, shape characteristics, spectral characteristics, spatial distribution characteristics and context characteristics.

[0015] In the second aspect, the present application provides an AI-based intelligent ground object recognition system for power grid infrastructure project scenes, which adopts the AI-based intelligent ground object recognition method for power grid infrastructure project scenes as described in the first aspect, and includes: an image acquisition module and a ground object recognition module. The image acquisition module is used to acquire remote sensing images of power grid infrastructure project scenes; the land object identification module is used to use a convolutional neural network model to identify the land object type of the remote sensing image, including: the convolutional neural network model uses stacked convolution layers and pooling layers. In the initial stage, the convolutional neural network model activates a preset number of convolution layers and pooling layers. After extracting the land object features of the remote sensing image, the extracted land object features are transferred to the connection layer to obtain the land object type probability value; it is judged whether the land object type probability value is greater than the preset judgment probability, and the land object types with probability values ​​greater than and less than the judgment probability are respectively identified as known land object types and unknown land object types. If an unknown land object type exists, the number and depth of the convolution layers and pooling layers are further activated to extract more land object features, and the land object type probability value of the unknown land object type is identified based on the land object features until a feature map of all known land object types is obtained; and the result is output, which includes a remote sensing image marked with a known land object type.

[0016] In a third aspect, the present application provides an AI-based device for intelligently identifying objects in power grid infrastructure project scenes, including a memory and a processor; the memory is used to store computer programs; and the processor is used to implement the steps of the AI-based method for intelligently identifying objects in power grid infrastructure project scenes as in the first aspect when executing the computer program.

[0017] The technical solution provided by this application has at least the following technical effects or advantages:

[0018] By increasing the number and depth of convolutional layers and pooling layers, and optimizing the feature extraction strategy, the problem in the existing technology that the static model structure cannot flexibly increase the network depth when facing unknown land object types is effectively solved. The depth and number of extracted features can be dynamically adjusted according to the land object conditions in the image, so as to better adapt to different types of remote sensing images, separate the tasks of land object type identification and coordinate positioning, effectively reduce the computational complexity, and improve the efficiency and speed of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1This is a flow chart of the method for intelligently identifying objects in power grid infrastructure project scenarios based on AI technology in this application;

[0020] Figure 2 For this application Figure 1 Flowchart of the number of further activation convolutional and pooling layers in . DETAILED DESCRIPTION

[0021] This application can solve the defect in the existing technology that the static model structure cannot flexibly increase the network depth when facing unknown land object types. It can dynamically adjust the depth and number of extracted features according to the land object conditions in the image. When processing unknown land object types, it can dynamically adjust the network structure and separate the tasks of land object type identification and coordinate positioning, effectively reducing the computational complexity and improving the efficiency and speed of the model, thereby better identifying various land object types and bringing significant economic and social benefits.

[0022] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0023] Example 1

[0024] An AI-based method for intelligently identifying ground objects in power grid infrastructure project scenarios includes the following steps:

[0025] S100. Acquire remote sensing images of power grid infrastructure project scenes.

[0026] The acquisition and analysis of remote sensing imagery plays a key role in power grid infrastructure projects. Remote sensing images, acquired through various methods such as satellite remote sensing, aerial remote sensing, and ground-based measurements, provide detailed geographic information. These images provide digitized multi-band data, including visible light, infrared, and radar bands, as well as corresponding geospatial coordinate information. Remote sensing images should have appropriate resolution and sensor information. This data provides a rich source of information for convolutional neural network (CNN) models, enabling them to accurately identify and classify different types of land features, thereby helping decision makers understand and manage the status and environmental impact of power grid infrastructure.

[0027] S200. Use convolutional neural network model to identify the type of ground objects in remote sensing images.

[0028] Object features refer to visual features extracted from remote sensing images, specifically edge features, texture features, shape features, spectral features, spatial distribution features, and contextual features. Texture features include building wall texture and road pavement texture, shape features include building outlines and road shapes, spectral features include the characteristics of different object types in visible and infrared bands, spatial distribution features include the dense distribution of buildings and the distribution patterns of water bodies, and contextual features include the relative positions and interactions between different object types.

[0029] Construct a convolutional neural network model. The input data is high-resolution, multi-band remote sensing image data, and the label data is the ground feature type label of each image. Use the convolution kernel to perform convolution operation on the input data and calculate the output feature map of the convolution layer. For the kth convolution kernel, the convolution calculation is: In the formula, F represents the size of the convolution kernel, S represents the stride, and b k Represents bias; perform nonlinear transformation on the output of the convolutional layer and apply the ReLU activation function ReLU. The activation function is calculated as: A i,j,k =max(0,Z i,j,k ); perform pooling on the feature map to reduce the size of the feature map and reduce the computational complexity. For maximum pooling, the pooling calculation is: Where F represents the size of the pooling window; the output of the pooling layer is flattened into a one-dimensional vector, the flattened feature map is matrix multiplied with the weight matrix of the fully connected layer, a bias is added, and an activation function is applied. The full connection is calculated as: O = ReLU(W·X+b), where W represents the weight matrix and b represents the bias; the output of the fully connected layer is converted into a probability distribution, representing the predicted probability of each category, and the Softmax function is calculated as: Where, O k Represents the output value of the kth category, K represents the total number of categories; calculate the loss: the difference between the prediction of the evaluation model and the actual label, the cross entropy loss function is calculated as: Where Y i,k represents the true label of the i-th sample, P i,k Represents the probability predicted by the model; calculates the gradient of the loss function with respect to each parameter (weight, bias), and updates the parameters using an optimization algorithm (such as gradient descent); selects an optimization algorithm such as stochastic gradient descent (SGD) or Adam, and adjusts the learning rate and parameters according to the gradient update rule.

[0030] S210. The convolutional neural network model uses stacked convolutional layers and pooling layers. In the initial stage, the convolutional neural network model activates a preset number of convolutional layers and pooling layers. After extracting the ground object features of the remote sensing image, the extracted ground object features are passed to the connection layer to obtain the ground object type probability value.

[0031] The convolution layer is the core component for extracting features from remote sensing images. Each convolution layer consists of multiple convolution kernels. Each convolution kernel slides on the image and calculates the dot product with its overlapping area to produce a feature map. The output of each convolution layer is a set of feature maps. Each feature map contains multiple features detected in the input image. As the depth of the network increases, the complexity and abstraction of the convolution kernel also increase, and more advanced and abstract features can be extracted.

[0032] In the initial stage, a preset number of convolutional and pooling layers are activated to extract feature information. These convolutional and pooling layers use filters to extract features from the image, such as edge features, texture features, shape features, spectral features, spatial distribution features, and contextual features. Downsampling is performed through the pooling layer to retain the main features. The feature information extracted by the convolutional and pooling layers is flattened and passed to the connection layer, which is responsible for mapping the extracted features to feature type probability values. In the connection layer, the activation function performs a nonlinear transformation on the features to increase the network's expressive power and learn nonlinear features. These nonlinearly transformed features are then used to predict the probability of feature types. The features output by the connection layer are processed by the softmax function to obtain the probability values ​​of each feature type.

[0033] By stacking multiple convolutional and pooling layers, the model extracts features of objects in remote sensing imagery at different levels of abstraction. This hierarchical structure allows the model to gradually capture features ranging from simple to complex, such as edges and textures, to more advanced object structures and shapes. The number of layers can be adjusted to the specific task and data complexity. Initially, the model can use fewer convolutional and pooling layers to quickly extract basic features for preliminary object type prediction.

[0034] S220. Determine whether the probability value of the feature type is greater than the preset judgment probability, and identify the feature types with probability values ​​greater than and less than the judgment probability as known feature types and unknown feature types respectively. If an unknown feature type exists, further activate the number and depth of the convolution layer and the pooling layer to extract more feature features, and identify the feature type probability value of the unknown feature type based on the feature features, until the feature maps of all known feature types are obtained.

[0035] For each feature type probability value, determine whether it is greater than the preset judgment probability. If the probability value is greater than the judgment probability, the feature type is identified as a known feature type. If the probability value is less than the judgment probability, the feature type is identified as an unknown feature type. If there is an unknown feature type, based on the existing unknown feature type, it is necessary to further activate the number and depth of convolutional layers and pooling layers to extract more feature features. This can be achieved by activating more convolutional layers and pooling layers. The adjusted convolutional neural network extracts more feature features and then passes them to the connection layer again. This iterative judgment is used to obtain the feature type probability value of the unknown feature type until the feature map of all known feature types is obtained.

[0036] The feature types with probability values ​​greater than and less than the judgment probability are identified as known feature types and unknown feature types respectively, so that some features that are difficult to identify accurately can be identified. For the processing of unknown feature types, further activating the number and depth of convolutional layers and pooling layers can help the system to extract more feature features in a targeted manner, which helps to make up for the deficiencies that may exist in the initial feature extraction stage. In addition, the system can also continuously optimize and improve the recognition results of unknown feature types during the recognition process, thereby improving the overall recognition accuracy.

[0037] S300. Output results, including remote sensing images marked with known land feature types.

[0038] By using an appropriate number of convolutional and pooling layers to identify feature types in the initial phase, the model can dynamically increase network depth when encountering unknown feature types to extract richer features while maintaining rapid recognition of known feature types. This improves overall adaptability and recognition accuracy, and dynamically adjusts the depth and number of extracted features based on the features in the image, better adapting to different types of remote sensing imagery. This reduces resource consumption when processing common features, saving storage and processing resources while maintaining efficiency and accuracy in complex image processing.

[0039] The output remote sensing image also has the coordinates of known land feature types.

[0040] The combination of coordinate information of known land feature types with data such as terrain and land use can help accurately assess terrain and resource distribution, optimize line layout, reduce environmental impact, ensure safe and stable operation of the power grid, and reduce construction costs.

[0041] S230. The convolutional neural network model also includes an additional fully connected layer. The feature map of the known feature type is converted into a one-dimensional vector through a shape transformation matrix. The one-dimensional vector is input into the fully connected layer and linearly transformed through the weight matrix to obtain an intermediate output. An activation function is applied to the intermediate output, and the activated output is used as the input of the output layer to obtain the coordinates of the known feature type.

[0042] When training this additional fully connected layer, the weight matrix W and bias vector b are randomly initialized. During the forward propagation, the feature maps of all known terrain types are converted into one-dimensional vectors: flatten(X k )=X k ⊙reshape(I), where X k Represents the feature maps of all known feature types, reshape(I) represents a shape transformation matrix, which is used to convert the feature maps of all known feature types into one-dimensional vectors and calculate the intermediate output: intermediate_output = W·flatten(X k )+b, apply an activation function to the intermediate output, such as ReLU, and use the mean squared error (MSE) as the loss function during backpropagation. Calculate the gradient of the loss function and use gradient descent or other optimization algorithms to update the weights and biases until the maximum number of iterations is reached or the loss function converges.

[0043] After obtaining the feature maps of all known object types, they are converted into one-dimensional vectors through a shape transformation matrix reshape(I), and the one-dimensional vectors are mapped to the predicted values ​​of the object coordinates. The coordinates are predicted through two neurons to obtain the output: output = [output x output y ], where output x and output y The coordinates obtained through the activation function realize the precise positioning of the position of known landform types.

[0044] In conventional CNNs, identifying object types and coordinates is usually handled as a joint task. This means that the CNN architecture includes convolution and pooling layers to extract rich features from remote sensing images, followed by classification (identifying object types) and regression (obtaining object coordinates) through fully connected layers. Therefore, in this case, multiple convolution and pooling operations are indeed required throughout the network in order to fully extract and utilize the information in the image to complete these two tasks simultaneously.

[0045] In S210, the convolutional neural network mainly extracts the ground object features of the remote sensing image through stacked convolutional layers and pooling layers. S220 classifies the extracted features, determines the ground object type, and determines the known ground object type and unknown ground object type. These two steps mainly focus on the feature extraction and ground object type determination process of the convolutional neural network model, focusing on the extraction and classification of ground object features in the remote sensing image. However, steps S210 and S220 provide ground object feature and classification information to S230, and S230 converts the feature map of the known ground object type into a one-dimensional vector and inputs it into the fully connected layer for processing, ultimately obtaining the specific location of the known ground object type in the image. This embodiment adopts a simplified processing flow by separating the tasks of ground object type identification and coordinate positioning. First, multiple convolution and pooling operations are used to extract key features for ground object type identification. This step effectively reduces the computational complexity. When performing coordinate positioning, S230 avoids repeated convolution and pooling and directly processes on the extracted features, thereby further improving the efficiency and speed of the model.

[0046] Get the number of activation layers of the convolution layer and pooling layer when identifying all specified objects, and use the activation number as the number of stacked layers of the convolution layer and pooling layer.

[0047] Regarding the number of stacked convolutional and pooling layers, the types of features to be identified can be selected as specified features during the model training phase. The number of activation layers of the convolutional and pooling layers when identifying all specified features can be used as the number of stacked convolutional and pooling layers. If there are difficult-to-identify feature types among the features to be identified, these difficult-to-identify feature types can be removed from the specified known feature types to ensure that the model can identify all specified known feature types.

[0048] In S220, further activating the number and depth of convolutional layers and pooling layers specifically includes: obtaining the maximum value of the feature type probability value of all unknown feature types, dividing the maximum value of the feature type probability value of all unknown feature types into a specified number of clusters according to the numerical value; and determining the number of times to activate the convolutional layer and the pooling layer based on the number of clusters.

[0049] The probability values ​​reflect the model's confidence in different feature types, and the number of clusters determines the number of layers activated in the convolutional neural network. Each cluster is associated with a set of convolutional and pooling layer operations in the network, enabling more efficient feature extraction and recognition of similar feature types. The number and depth of convolutional and pooling layers are dynamically determined based on actual data, allowing the model to be optimized based on the characteristics and complexity of each feature type. This dynamic adaptability helps improve the model's generalization and accuracy, while also reducing computational load while maintaining recognition speed, thereby improving overall operational efficiency.

[0050] A clustering algorithm based on data density is used to determine the number of clusters, specifically including: taking the maximum value of the feature type probability value of the unknown feature type as the data point, defining the parameters ε and MinPts, where ε represents the distance threshold of the neighborhood and MinPts represents the minimum number of data points in the ε neighborhood; visiting each data point, randomly selecting an unvisited data point each time, and calculating the number of data points in the ε neighborhood of the point. If it is greater than or equal to MinPts, the point is marked as a core point; starting from the core point, the points that are density-reachable are added to the same cluster in a density-reachable manner, and the points that do not belong to any cluster are added to the nearest cluster.

[0051] The selection of the two parameters ε and MinPts will affect the clustering results and can be adjusted according to the specific problem and data characteristics. The core points represent areas with higher data density. Points densely connected to the core points are classified into the same category to form clusters. The DBSCAN algorithm does not require the pre-specification of the number of clusters, but determines the number of clusters by the density of the data. Therefore, it has good applicability for determining the number of clusters of unknown landform types.

[0052] The number of activation layers n corresponding to the cluster i For: n i =a i ·(Ls); Where n i represents the number of activation layers corresponding to the i-th cluster, a i represents the length ratio of the i-th cluster, L represents the number of stacked convolutional layers and pooling layers, s represents the number of convolutional layers and pooling layers activated in the initial stage, and A represents the number of clusters.

[0053] Because different feature types have different length ratios, dynamically determining the number of layers activated at each time can be adjusted based on the complexity of the category. This makes the network more targeted and adaptable when processing different feature types, thereby improving classification accuracy. For longer categories, more layers are allocated for feature extraction and recognition; for shorter categories, the number of activated layers can be reduced, allocating network resources more rationally and avoiding using the same number of layers for all categories, thereby reducing the risk of overfitting. For shorter categories, reducing the number of activated layers can save computing resources and improve network efficiency.

[0054] Example 2:

[0055] This embodiment provides an AI-based intelligent ground object recognition system for power grid infrastructure project scenes, which adopts the AI-based intelligent ground object recognition method for power grid infrastructure project scenes as described in Example 1, and includes: an image acquisition module and a ground object recognition module.

[0056] The image acquisition module is used to acquire remote sensing images of power grid infrastructure project scenes; the land object recognition module is used to use a convolutional neural network model to identify the land object type of the remote sensing image, including: the convolutional neural network model uses stacked convolution layers and pooling layers. In the initial stage, the convolutional neural network model activates a preset number of convolution layers and pooling layers. After extracting the land object features of the remote sensing image, the extracted land object features are transferred to the connection layer to obtain the land object type probability value; it is judged whether the land object type probability value is greater than the preset judgment probability, and the land object types with probability values ​​greater than and less than the judgment probability are respectively identified as known land object types and unknown land object types. If an unknown land object type exists, the number and depth of the convolution layers and pooling layers are further activated to extract more land object features, and the land object type probability value of the unknown land object type is identified based on the land object features until a feature map of all known land object types is obtained; the output result includes a remote sensing image marked with a known land object type.

[0057] This embodiment has all the advantages of the method for intelligently identifying ground objects in power grid infrastructure project scenes based on AI technology in Example 1, and can automatically implement all steps of the method for intelligently identifying ground objects in power grid infrastructure project scenes based on AI technology.

[0058] Example 3:

[0059] This embodiment provides an AI-based device for intelligently identifying objects in power grid infrastructure project scenes, including a memory and a processor. The memory is used to store computer programs; the processor is used to implement the steps of the AI-based method for intelligently identifying objects in power grid infrastructure project scenes as described in Example 1 when executing the computer program.

[0060] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0061] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1The present invention is described in detail below. ...

Claims

1. An AI-based method for intelligently identifying ground objects in power grid infrastructure projects, characterized by: Acquire remote sensing images of power grid infrastructure project scenes; The convolutional neural network model is used to identify the types of objects in remote sensing images, including: The convolutional neural network model uses stacked convolutional layers and pooling layers. In the initial stage, the convolutional neural network model activates a preset number of convolutional layers and pooling layers. After extracting the ground feature features of the remote sensing image, the extracted ground feature features are passed to the connection layer to obtain the ground feature type probability value; Determine whether the probability value of the feature type is greater than the preset judgment probability, and identify the feature types with probability values ​​greater than and less than the judgment probability as known feature types and unknown feature types respectively. If an unknown feature type exists, further activate the number and depth of the convolutional layer and pooling layer to extract more feature features, including: Obtain the maximum value of the feature type probability value of all unknown feature types, and divide the maximum value of the feature type probability value of all unknown feature types into a specified number of clusters according to the value size; Determining the number of times to activate convolutional layers and pooling layers based on the number of clusters; Determining the number of clusters using a clustering algorithm based on data density, and identifying feature type probability values ​​of unknown feature types based on the feature characteristics, until feature maps of all known feature types are obtained; Output results, including remote sensing images marked with known land feature types.

2. The method for intelligently identifying ground objects in power grid infrastructure projects based on AI technology according to claim 1, characterized in that: The output remote sensing image also has the coordinates of known land feature types.

3. The method for intelligently identifying ground objects in power grid infrastructure projects based on AI technology according to claim 2, characterized in that: The convolutional neural network model also includes an additional fully connected layer. The feature map of the known land feature type is converted into a one-dimensional vector through a shape transformation matrix. The one-dimensional vector is input into the fully connected layer and linearly transformed through a weight matrix to obtain an intermediate output. An activation function is applied to the intermediate output, and the activated output is used as the input of the output layer to obtain the coordinates of the known land feature type.

4. The method for intelligently identifying ground objects in power grid infrastructure projects based on AI technology according to claim 1, characterized in that: Get the number of activation layers of the convolution layer and pooling layer when identifying all specified objects, and use this activation number as the number of stacked layers of the convolution layer and pooling layer.

5. The method for intelligently identifying ground objects in power grid infrastructure projects based on AI technology according to claim 1, characterized in that: Determining the number of clusters specifically involves: The maximum value of the feature type probability value of the unknown feature type is taken as the data point, and the parameters ε and MinPts are defined. ε represents the distance threshold of the neighborhood, and MinPts represents the minimum number of data points in the ε neighborhood. Visit each data point, randomly select an unvisited data point each time, calculate the number of data points in the ε neighborhood of the point, and if it is greater than or equal to MinPts, mark the point as a core point; starting from the core point, add its density-reachable points to the same cluster through density-reachable methods, and add points that do not belong to any cluster to the nearest cluster.

6. The method for intelligently identifying ground objects in power grid infrastructure projects based on AI technology according to claim 1, characterized in that: Each cluster corresponds to the number of activation layers n i , n i for: n i =a i ·(L-s) Where n i represents the number of activation layers corresponding to the i-th cluster, a i represents the length ratio of the i-th cluster, L represents the number of stacked convolutional layers and pooling layers, s represents the number of convolutional layers and pooling layers activated in the initial stage, and A represents the number of clusters.

7. The method for intelligently identifying ground objects in power grid infrastructure projects based on AI technology according to claim 1, characterized in that: The feature of the ground object includes edge feature, texture feature, shape feature, spectral feature, spatial distribution feature and context feature.

8. The AI-based intelligent ground feature recognition system for power grid infrastructure projects is characterized by: include: An image acquisition module, which is used to acquire remote sensing images of power grid infrastructure project scenes; The object recognition module is used to identify the object type in remote sensing images using a convolutional neural network model, including: The convolutional neural network model uses stacked convolutional layers and pooling layers. In the initial stage, the convolutional neural network model activates a preset number of convolutional layers and pooling layers. After extracting the ground feature features of the remote sensing image, the extracted ground feature features are passed to the connection layer to obtain the ground feature type probability value; Determine whether the probability value of the feature type is greater than the preset judgment probability, and identify the feature types with probability values ​​greater than and less than the judgment probability as known feature types and unknown feature types respectively. If an unknown feature type exists, further activate the number and depth of the convolutional layer and pooling layer to extract more feature features, including: Obtain the maximum value of the feature type probability value of all unknown feature types, and divide the maximum value of the feature type probability value of all unknown feature types into a specified number of clusters according to the value size; Determining the number of activations of the convolution layer and the pooling layer based on the number of clusters; and identifying the object type probability value of the unknown object type based on the object features until a feature map of all known object types is obtained; Output results, including remote sensing images marked with known land feature types.

Images