Power Corridor Vegetation Management Method and System Based on Spectral Images and Laser Point Clouds

Abstract

The present invention relates to a method and system for power corridor vegetation management based on spectral images and laser point clouds, including collecting laser point cloud data and multi-spectral image data within the power corridor by means of an unmanned aerial vehicle, and generating a fused point cloud containing vegetation spatial and spectral features through a dynamic non-linear spectral band selection mechanism; extracting vegetation features from the fused point cloud through a multi-scale graph convolutional network, constructing a time series and training a growth model using bidirectional LSTM and self-attention mechanism to predict the growth trend of the vegetation; based on the spatial information and growth trend of the vegetation, comprehensively evaluating the contact risk between the vegetation and the power line by means of fuzzy logic, and generating a visualization model and operation and maintenance instructions. The visualization model and operation and maintenance instructions generated by the present invention significantly enhance the automation and intelligence level of power corridor vegetation management, effectively reduce the contact risk between the vegetation and the power line, and ensure the safe operation of the power system.

Description

Technical Field

[0001] The present invention belongs to the technical field of spectral images and laser point clouds, and particularly relates to a power corridor vegetation management method and system based on spectral images and laser point clouds. Background Art

[0002] With the continuous expansion of the power grid, power corridor vegetation management has become an important link in ensuring the safe operation of the power system. The overgrowth of vegetation may come into contact with power lines, leading to risks such as short circuits, power outages, and even fires. Therefore, it is necessary to monitor and evaluate the spatial distribution and growth trend of vegetation. In recent years, unmanned aerial vehicle (UAV) technology combined with lidar and multispectral imaging technology has been widely used in vegetation management. LiDAR point cloud data can provide three-dimensional spatial information of vegetation, while multispectral image data can reflect the spectral characteristics and health status of vegetation, providing a basis for vegetation classification and growth analysis. However, existing technologies still have deficiencies in data fusion, feature extraction, and risk assessment.

[0003] In terms of data fusion, traditional vegetation monitoring methods mostly use simple superposition of point cloud and spectral data, without fully considering the dynamic selectivity of spectral bands, resulting in limited accuracy in characterizing vegetation features in the fusion results. In terms of feature extraction and growth prediction, conventional methods usually rely on single-scale spatial analysis or statistical models based on static data, making it difficult to capture the dynamic change characteristics of vegetation in multi-scale spatial and temporal dimensions. In addition, existing technologies mostly use deterministic threshold judgment in risk assessment, ignoring the ambiguity and complex interaction relationships among multiple variables such as vegetation height, distance, and growth rate, and the evaluation results often lack comprehensiveness and robustness. These problems limit the automation and intelligence level of power corridor vegetation management and are difficult to meet the requirements of efficient operation and maintenance of large-scale power grids.

[0004] In recent years, artificial intelligence technologies such as graph convolutional networks, long short-term memory networks (LSTM), and fuzzy logic have shown potential in related fields. For example, graph convolutional networks can be used to process the spatial relationships of point cloud data, LSTM is suitable for time series modeling, and fuzzy logic can handle uncertainty problems. However, how to combine these technologies with multispectral image and LiDAR point cloud data to construct a complete vegetation management solution is still a difficult point in current research. In view of the above problems, it is necessary to develop a method that can achieve dynamic fusion of multi-source data, multi-scale feature extraction, time series growth prediction, and comprehensive risk assessment based on fuzzy logic, so as to improve the accuracy and practicality of power corridor vegetation management and provide technical support for the safe operation of the power system. Summary of the Invention

[0005] The purpose of the present invention is to provide a method and system for power corridor vegetation management based on spectral images and laser point clouds, so as to solve the problem of low automation and intelligence in the existing technology for power corridor vegetation management.

[0006] To achieve one of the above-mentioned invention purposes, an embodiment of the present invention provides a method for power corridor vegetation management based on spectral images and laser point clouds, which is characterized in that it includes:

[0007] Collecting laser point cloud data and multi-spectral image data in the power corridor by using an unmanned aerial vehicle, and generating a fused point cloud containing vegetation spatial and spectral features through a dynamic non-linear spectral band selection mechanism;

[0008] Extracting vegetation features from the fused point cloud through a multi-scale graph convolutional network, constructing a time series and training a growth model using a bidirectional LSTM and a self-attention mechanism to predict the growth trend of the vegetation;

[0009] Based on the spatial information and growth trend of the vegetation, comprehensively evaluating the contact risk between the vegetation and the power line by using fuzzy logic, and generating a visualization model and operation and maintenance instructions.

[0010] As a further improvement of an embodiment of the present invention, the method further includes that the generating a fused point cloud containing vegetation spatial and spectral features through a dynamic non-linear spectral band selection mechanism includes:

[0011] Defining the laser point cloud data in the power corridor as , where is the three-dimensional coordinate of the i-th point, and n is the number of points;

[0012] Defining the multi-spectral image data as , where is the reflection value of point i in band j, and k is the number of bands;

[0013] Inferring the vegetation type c and growth stage s from the multi-spectral image data S through a pre-trained classification model;

[0014] Calculating the weight of each spectral band j, and the formula is:

[0015] .

[0016] Where is the standard deviation of band j, is a scalar representation of vegetation characteristics and time dynamics, τ is the data acquisition timestamp, is band specificity, and are pre-trained embedding vectors, is a balance parameter, is a scaling factor;

[0017] Calculate the spectral features of each point, and the formula is:

[0018] .

[0019] Wherein, is the weight of band j, is the mean value of band j, is a non-linear transformation function;

[0020] Generate a fused point cloud representation as:

[0021] .

[0022] As a further improvement of an embodiment of the present invention, the method further includes that the extraction of vegetation features from the fused point cloud by the multi-scale graph convolutional network includes,

[0023] Construct a graph structure from the fused point cloud , wherein the vertex set represents all points in the fused point cloud, and E is the edge set;

[0024] Calculate the edge weight used to characterize the spatial relationship between points i and l;

[0025] Wherein, is a preset distance attenuation parameter for controlling the neighborhood range;

[0026] Define multiple scales , wherein represents the neighborhood range of the p-th scale, and the neighborhood of point i at scale is ;

[0027] Extract local features at each scale , and the formula is:

[0028] .

[0029] Wherein, is neighborhood aggregation, and are the learnable weight matrix and bias at the p-th scale;

[0030] Aggregate global features through max pooling and represent them as:

[0031] .

[0032] Output the final feature representation of point i as:

[0033] .

[0034] Among them, represents the result of mapping the original features to a high-dimensional space through a multi-layer perceptron.

[0035] As a further improvement of an embodiment of the present invention, the method further includes that the construction of the time series and the training of the growth model using bidirectional LSTM and self-attention mechanism include,

[0036] Collecting vegetation features at multiple time points to construct a time series , where is the feature at the t-th moment;

[0037] Processing using bidirectional LSTM , calculating the forward hidden state and the backward hidden state ;

[0038] Combining the forward and backward hidden states to obtain the bidirectional hidden state ;

[0039] By introducing the self-attention mechanism and based on the hidden state matrix , calculating the query matrix , the key matrix , and the value matrix ;

[0040] Among them, are the weights of the corresponding matrices respectively;

[0041] Calculating the attention weight matrix and the context representation matrix ;

[0042] Among them, is the dimension of the key vector for scaling.

[0043] As a further improvement of an embodiment of the present invention, the method further includes that the prediction of the growth trend of the vegetation includes,

[0044] Predicting the vegetation height at the next time point through the formula ;

[0045] Among them, is the t-th column of the context representation matrix C, corresponding to the weighted context information at the t-th time step, aligned with the hidden state in the time dimension; are the predicted weight matrix and bias respectively;

[0046] Calculating the growth rate , where To predict the change in height at consecutive time points, is the time interval;

[0047] When training the model, historical height data is used as the supervision signal, and the model parameters are adjusted by optimizing the loss function, which is expressed as:

[0048] .

[0049] Among them, is the true vegetation height at time step t, is the predicted vegetation height at time step t, is the total number of time steps in the time series.

[0050] As a further improvement of an embodiment of the present invention, the method further includes that the comprehensive evaluation of the contact risk between the vegetation and the power line by using fuzzy logic includes,

[0051] Defining input variables, including the height difference , the closest distance d between the vegetation canopy points and the power line in the horizontal plane, and the growth rate v;

[0052] Among them, is the power line height, and d is extracted from the laser point cloud P;

[0053] Establishing the membership relationship of the fuzzy sets of the input variables through fuzzy membership functions to quantify the fuzzy characteristics of the height difference , the horizontal distance d, and the growth rate v, specifically including,

[0054] For each input variable, defining a membership function , mapping the input variable to fuzzy sets, including fuzzy semantic levels such as the safety level, transition level, and danger level; the membership function is determined based on the physical meaning of the input variable and the actual requirements of power corridor management;

[0055] Among them, X represents , d, or v;

[0056] Based on the membership relationship of the fuzzy sets, configuring fuzzy inference rules between the input variables and the risk levels; the fuzzy inference rules express the influence of the input variables , d, or v on the contact risk;

[0057] Combining the membership relationship of the fuzzy sets of the input variables with the fuzzy inference rules, determining the activation degree of the fuzzy inference rules, and generating a corresponding fuzzy output subset;

[0058] The activation degree of each rule is expressed as:

[0059] .

[0060] Among them, is the activation degree of the q-th rule; is the membership degree at the input value , indicating the degree of belonging to a certain fuzzy level; is the membership degree of d at the input value , indicating the degree of d belonging to a certain fuzzy level; is the membership degree of v at the input value , indicating the degree of v belonging to a certain fuzzy level;

[0061] The corresponding fuzzy output subset is expressed as:

[0062] .

[0063] Among them, is the clipped output subset of the q-th rule, is the output membership function of the q-th rule, is the risk value range variable;

[0064] Aggregate the output subsets of all rules and generate a comprehensive membership function through the maximum operation, which is expressed as:

[0065] .

[0066] Among them, N is the total number of rules;

[0067] Defuzzify the comprehensive membership function and generate a scalar risk value using the weighted average method, which is expressed as:

[0068] .

[0069] Among them, is the risk value;

[0070] Classify the contact risk according to the risk value r and the predetermined standard to determine the potential contact threat degree between the vegetation and the power line.

[0071] As a further improvement of an embodiment of the present invention, the method further includes that the generation of the visualization model and the operation and maintenance instructions include,

[0072] Generate a visual three-dimensional model based on the vegetation growth trend and the contact risk, and mark the risk area in the form of a heat map in the visual three-dimensional model to intuitively display the analysis results;

[0073] Automatically generate operation and maintenance instructions according to the risk level; when the risk level is high, trigger the instruction to trim the vegetation and specify the coordinate range to be trimmed;

[0074] Transmit the visualization model and operation and maintenance instructions to the operation and maintenance terminal to ensure that the analysis results are applied to the power corridor management in real time.

[0075] To achieve one of the above invention purposes, an embodiment of the present invention further provides a power corridor vegetation management system based on spectral images and laser point clouds, which is characterized in that it includes a data fusion module, a growth prediction module, and a risk assessment module;

[0076] The data fusion module is used to collect laser point cloud data and multi-spectral image data in the power corridor by using an unmanned aerial vehicle, and fuse and generate a fused point cloud containing vegetation spatial and spectral features through a dynamic non-linear spectral band selection mechanism;

[0077] The growth prediction module is used to extract vegetation features from the fused point cloud through a multi-scale graph convolutional network, construct a time series, and train a growth model by using a bidirectional LSTM and a self-attention mechanism to predict the growth trend of the vegetation;

[0078] The risk assessment module is used to comprehensively evaluate the contact risk between the vegetation and the power line based on the spatial information and growth trend of the vegetation by using fuzzy logic, and generate a visualization model and operation and maintenance instructions.

[0079] To achieve one of the above invention purposes, an embodiment of the present invention further provides an electronic device, including a memory and a processor, characterized in that a computer program that can run on the processor is stored in the memory, and when the program is executed on the processor, the steps in the above-mentioned power corridor vegetation management method based on spectral images and laser point clouds are implemented.

[0080] To achieve one of the above invention purposes, an embodiment of the present invention further provides a storage medium, the storage medium stores a computer program, characterized in that when the computer program is executed by a processor, the steps in the above-mentioned power corridor vegetation management method based on spectral images and laser point clouds are implemented.

[0081] Compared with the prior art, a power corridor vegetation management method and system based on spectral images and laser point clouds provided by the present invention fuse multispectral images and laser point cloud data through a dynamic non-linear spectral band selection mechanism, improving the accuracy of vegetation feature extraction; adopt a multi-scale graph convolutional network and bidirectional LSTM combined with a self-attention mechanism to achieve accurate prediction of vegetation growth trends; a comprehensive risk assessment method based on fuzzy logic fully considers the uncertainty of multi-variable interaction, improving the robustness of contact risk assessment. The finally generated visualization model and operation and maintenance instructions significantly enhance the automation and intelligence level of power corridor vegetation management, effectively reducing the contact risk between vegetation and power lines and ensuring the safe operation of the power system. Description of the Drawings

[0082] Figure 1 is the overall flowchart of the power corridor vegetation management method based on spectral images and laser point clouds according to the present invention.

[0083] Figure 2 is the schematic diagram of the architecture of the power corridor vegetation management system based on spectral images and laser point clouds according to the present invention. Detailed Embodiments

[0084] The present invention will be described in detail below in conjunction with the specific embodiments shown in the drawings. However, these embodiments do not limit the present invention, and any structural, method, or functional transformation made by those of ordinary skill in the art based on these embodiments is included in the protection scope of the present invention.

[0085] The embodiments of the present invention will be described in detail below. Examples of the embodiments are shown in the drawings, where the same or similar reference numerals represent the same or similar elements or elements with the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and are only used to explain the present invention and should not be construed as limiting the present invention.

[0086] In the first embodiment of the present invention, the present invention provides a power corridor vegetation management method based on spectral images and laser point clouds, as Figure 1 shown, the method includes,

[0087] S1: Collect laser point cloud data and multispectral image data in the power corridor through an unmanned aerial vehicle, and fuse them through a dynamic non-linear spectral band selection mechanism to generate a fused point cloud containing vegetation spatial and spectral features;

[0088] S2: Extract vegetation features from the fused point cloud through a multi-scale graph convolutional network, construct a time series, and use a bidirectional LSTM and a self-attention mechanism to train a growth model to predict the growth trend of vegetation;

[0089] S3: Based on the spatial information and growth trend of vegetation, comprehensively evaluate the contact risk between vegetation and power lines using fuzzy logic, and generate a visualization model and operation and maintenance instructions.

[0090] In a specific embodiment of the present invention, a fused point cloud containing vegetation spatial and spectral features is generated through a dynamic non-linear spectral band selection mechanism. Specifically,

[0091] Define the laser point cloud data within the power corridor as , where is the three-dimensional coordinate of the i-th point, and n is the number of points;

[0092] Define the multispectral image data as , where is the reflection value of point i in band j, and k is the number of bands;

[0093] Infer the vegetation type c and growth stage s from the multispectral image data S through a pre-trained classification model;

[0094] Calculate the weight of each spectral band j, and the formula is:

[0095] .

[0096] Where is the standard deviation of band j, is a scalar representation of vegetation characteristics and temporal dynamics, τ is the data acquisition timestamp, is the band specificity, and are pre-trained embedding vectors, is the balance parameter, is the scaling factor;

[0097] Calculate the spectral characteristics of each point, and the formula is:

[0098] .

[0099] Where is the weight of band j, is the mean of band j, is the non-linear transformation function;

[0100] Generate the fused point cloud and represent it as:

[0101] .

[0102] It should be noted that through the dynamic non-linear band selection mechanism, the present invention fuses the laser point cloud data P and the multispectral image data S collected by the drone through the formula to generate a fused point cloud containing vegetation spatial information and spectral characteristics for subsequent feature extraction, growth prediction, and risk assessment. The formula generates adaptive weights by integrating vegetation type, growth stage, and temporal dynamics. Compared with traditional fixed band selection, it can optimize spectral information extraction according to environmental changes, improve fusion accuracy, and is particularly suitable for mixed vegetation scenarios. The formula generates spectral features through weighted sum and non-linear transformation, enhancing the spectral expression of vegetation and providing high-quality input for multi-scale feature extraction. Fusing point cloud combines spatial coordinates and spectral features as the input of the subsequent graph convolutional network, connecting data fusion and feature extraction.

[0103] Furthermore, the system collects laser point cloud data P to describe the three-dimensional spatial structure of vegetation and its surrounding environment. The number of points is determined by the collection range and device resolution. At the same time, it collects multi-spectral image data S to obtain the spectral reflection characteristics of vegetation, covering bands such as visible light and near-infrared. The number of points is the same as that of the laser point cloud to ensure spatial-spectral correspondence. The system infers the vegetation type c and growth stage s through a pre-trained classification model, providing input for weight calculation.

[0104] Furthermore, the system calculates the band weights , integrating the standard deviation , vegetation characteristics , and band specificity , optimized by balance parameters and scaling factors. The standard deviation , where reflects the information content of the band. Vegetation characteristics , using a lightweight MLP (input layer dimension is the number of types + 2, hidden layer has 64 neurons, ReLU activation, output layer has 1 neuron, Sigmoid activation), trained with labeled data to capture growth period or seasonal changes. Band specificity extracts the embedding vector (dimension 32) through the spectral feature library and classification model, normalizes it to [0,1], and quantifies the correlation between the band and vegetation type.

[0105] Furthermore, based on the weights , the system calculates the spectral features , where enhances the dynamic range and suppresses noise. Fusing point cloud combines spatial and spectral information to support subsequent multi-scale extraction.

[0106] In a specific embodiment of the present invention, vegetation features are extracted from the fused point cloud through a multi-scale graph convolutional network. Specifically,

[0107] constructs a graph structure from the fused point cloud , where the vertex set Denote all points in the fused point cloud, and \(E\) is the edge set;

[0108] Calculate the edge weights which is used to characterize the spatial relationship between points \(i\) and \(l\);

[0109] where is a preset distance decay parameter used to control the neighborhood range;

[0110] Define multiple scales , where represents the neighborhood range of the \(p\)-th scale, and the neighborhood of point \(i\) at scale is ;

[0111] Extract local features at each scale , and the formula is:

[0112] .

[0113] where is neighborhood aggregation, and are the learnable weight matrix and bias at the \(p\)-th scale;

[0114] Aggregate the global features through max pooling and represent them as:

[0115] .

[0116] Output the final feature representation of point \(i\) as:

[0117] .

[0118] where represents the result of mapping the original features to a high-dimensional space through a multi-layer perceptron.

[0119] It should be noted that the present invention uses a multi-scale graph convolutional network to extract vegetation features from the fused point cloud, providing a high-quality representation for time series construction and growth prediction. The formula calculates the edge weights through an exponential decay function, dynamically quantifies the proximity based on the spatial distance, and is more adaptable to the uneven distribution of point cloud density than the fixed neighborhood method, suitable for the complex vegetation scenarios of power corridors. The formula extracts local features through weighted aggregation at multiple scales, captures the spatial characteristics from branches and leaves to the canopy, and significantly improves the robustness and classification accuracy compared with the single-scale method. The formula \(g\) generates global features through max pooling, providing the overall context. The formula integrates the global features, the original feature mapping, and the multi-scale local features to form a comprehensive representation, supporting time series analysis.

[0120] Furthermore, the system transforms the fused point cloud into a graph structure G to represent the spatial and feature relationships between points. The vertex set V contains all points, and each vertex carries three-dimensional coordinates and spectral features; the edge set E is constructed based on spatial distance to adapt to the irregular distribution of the point cloud. The edge weight , calculated by the Euclidean distance and the distance decay parameter, highlights the association of neighboring points and optimizes the feature extraction in complex vegetation scenes.

[0121] Furthermore, the system defines multi-scale neighborhoods and extracts local features. Set an increasing sequence of neighborhood radii , and each point contains neighboring points with a distance less than at scale . Calculate the local features through graph convolution , weighted aggregation of neighborhood features, and the independent weight matrix and bias enhance scale specificity and capture local texture and overall geometry.

[0122] Furthermore, the system generates a global feature g through max pooling to extract the most significant features of the point cloud, reflecting the canopy height or spectral peak. The final feature integrates the global feature, the non-linear mapping of the original feature (MLP containing a multi-layer neural network), and the multi-scale local features to form a comprehensive representation to support time series prediction.

[0123] In a specific embodiment of the present invention, a time series is constructed and a growth model is trained using bidirectional LSTM and self-attention mechanism. Specifically,

[0124] Vegetation features are collected at multiple time points to construct a time series , where is the feature at the t-th moment;

[0125] Processed using bidirectional LSTM , calculate the forward hidden state and the backward hidden state ;

[0126] Merge the forward and backward hidden states to obtain the bidirectional hidden state ;

[0127] By introducing the self-attention mechanism and based on the hidden state matrix , calculate the query matrix , the key matrix , and the value matrix ;

[0128] where are the weights of the corresponding matrices respectively;

[0129] Calculate the attention weight matrix and the context representation matrix ;

[0130] Wherein, is the dimension of the key vector for scaling.

[0131] It should be noted that the present invention models the vegetation feature time series through bidirectional LSTM and self-attention mechanism , and captures the growth dynamics. Formula merges the forward and backward hidden states of bidirectional LSTM, comprehensively captures the temporal context, and models the non-linear trend more accurately than unidirectional LSTM. Formulas Q, K, V, A, and C calculate the time step correlation through the self-attention mechanism, dynamically highlight key time steps such as the rapid growth period, and enhance the prediction stability. In implementation, Q, K, and V are linearly transformed from the hidden state matrix H, A is calculated using scaled dot product attention, and C is weighted and summed to highlight important features.

[0132] Furthermore, the system constructs a time series based on multi-scale graph convolution features . Feature data, including canopy height, spectral characteristics, etc., are collected at fixed intervals (such as weekly), arranged in chronological order as a high-dimensional vector sequence, and unified format is ensured to have consistent dimensions, covering multiple growth cycles. The length of the time series is determined by the number of collected points, supporting long-term trend modeling.

[0133] Furthermore, bidirectional LSTM processes the time series to generate hidden states . The forward LSTM processes features from the start of the sequence, capturing the trend from the past to the present; the backward LSTM processes from the end, reflecting future constraints. Each time step updates the memory unit through a gating mechanism, generating forward and backward hidden states, which are concatenated into , retaining the complete context and supporting non-linear dynamic modeling.

[0134] Furthermore, the self-attention mechanism enhances the expression of key time steps. All constitute the matrix H, and Q, K, and V are generated through the weight matrix. The attention weight A and the context representation C highlight the features of the rapid growth period, supporting high-precision prediction.

[0135] Furthermore, the system optimizes the model parameters to ensure performance. Bidirectional LSTM sets a medium-dimensional hidden state, the forget gate bias is initialized to a positive value, and a single-layer or double-layer structure adapts to the sequence length. The attention mechanism adds dropout to prevent overfitting, and the scaling factor is based on the dimension of the key vector. Training uses batch processing and gradient clipping, and distributed computing accelerates the processing of long sequences.

[0136] In a specific embodiment of the present invention, predicting the growth trend of vegetation, specifically,

[0137] Predict the vegetation height at the next time point through the formula ;

[0138] wherein, is the t-th column of the context representation matrix C, corresponding to the weighted context information at the t-th time step, and is aligned with the hidden state in the time dimension; are the predicted weight matrix and bias respectively;

[0139] Calculate the growth rate , wherein, is the change in the predicted height at consecutive time points, is the time interval;

[0140] When training the model, historical height data is used as the supervision signal, and the model parameters are adjusted by optimizing the loss function, and the loss function is expressed as:

[0141] .

[0142] wherein, is the true vegetation height at time step t, is the predicted vegetation height at time step t, is the total number of time steps in the time series.

[0143] It should be noted that the formula predicts the vegetation height by fusing the bidirectional hidden state and the context representation , combines the temporal dynamics and key time step information, and captures complex growth patterns more accurately than linear regression. The formula v calculates the growth rate based on the continuous height difference, quantifies the dynamic threat, and provides a basis for risk assessment. The formula L optimizes the model through the mean square error to ensure the prediction accuracy and generalization ability. In implementation, is calculated through linear transformation, v reflects the growth trend, and L uses gradient descent for optimization.

[0144] Furthermore, the system predicts the height and calculates the growth rate based on and . The input features integrate (forward and backward temporal information) and (weighted key time steps), and are linearly mapped to through the weight matrix and the bias , retaining the dynamic characteristics. The growth rate v is calculated through the difference between adjacent time points, and smoothing processing (such as weighted average) reduces noise to ensure stability. The time interval is based on the acquisition period, and the consistent unit is convenient for risk comparison.

[0145] Furthermore, the system optimizes the model through supervised learning. Historical height data (from lidar point clouds or field measurements) serves as the supervision signal, covering the growth cycle. The loss function L calculates the mean squared error between the prediction and the true height, and the Adam optimizer is used to update 、 and the aforementioned model parameters. Regularization prevents overfitting. The training is divided into rounds, and the validation set is used to evaluate the performance, and the learning rate is adjusted for convergence.

[0146] Furthermore, the system adopts optimization strategies to improve efficiency. Batch processing inputs sequences in batches and dynamically adjusts the batch size. Gradient clipping limits the norm to prevent numerical instability. Incremental learning gradually updates the model to adapt to new data. Feature selection prioritizes key dimensions such as canopy height to reduce complexity and accelerate prediction.

[0147] In a specific embodiment of the present invention, fuzzy logic is used to comprehensively evaluate the contact risk between vegetation and power lines. Specifically,

[0148] Input variables are defined, including the height difference , the minimum distance d between the vegetation canopy points and the power line in the horizontal plane, and the growth rate v;

[0149] wherein, is the height of the power line, and d is extracted from the lidar point cloud P;

[0150] It should be noted that by analyzing the spatial and dynamic characteristics, the basic data required for risk assessment is generated. These data describe the relative position and potential threat trend between the vegetation and the power line, providing quantitative inputs for subsequent analysis.

[0151] Furthermore, the fuzzy set membership relationship of the input variables is established through fuzzy membership functions to quantify the fuzzy characteristics of the height difference , the horizontal distance d, and the growth rate v. Specifically,

[0152] For each input variable, a membership function is defined to map the input variable to fuzzy sets, including fuzzy semantic levels such as the safe level, the transitional level, and the dangerous level; the form of the membership function is determined based on the physical meaning of the input variable and the actual requirements of power corridor management;

[0153] wherein, X represents , d, or v;

[0154] Preferably, the membership function adopted in an embodiment of the present invention is a triangular membership function, specifically expressed as:

[0155] .

[0156] Among them, is the center of the fuzzy set, is the width of the fuzzy set, corresponding to the three levels of safe, excessive, and dangerous respectively. Safe level: indicating low risk, the center is based on safety standards (such as the minimum height requirement of the power line). Transitional level: indicating medium risk, the center is at the intermediate value between safe and dangerous. Dangerous level: indicating high risk, the center is close to the threat threshold.

[0157] It should be noted that by converting precise data into fuzzy semantics, it is convenient to handle uncertainty. The data is mapped to risk descriptions at different levels, providing input for subsequent decision-making rules.

[0158] Furthermore, based on the membership relationship of the fuzzy set, configure the fuzzy inference rules between the input variables and the risk levels; the fuzzy inference rules express the influence of the input variables , d or v on the contact risk;

[0159] It should be noted that by associating the fuzzified data with the risk levels, a decision-making basis is formed. The rules map the combination of data to the risk levels, simulating expert judgment to ensure that the comprehensive influence is quantified.

[0160] Furthermore, combining the membership relationship of the fuzzy set of the input variables with the fuzzy inference rules, determine the activation degree of the fuzzy inference rules, and generate the corresponding fuzzy output subset;

[0161] The activation degree of each rule is expressed as:

[0162] .

[0163] Among them, is the activation degree of the q-th rule; is the membership degree at the input value , indicating the degree of belonging to a certain fuzzy level; is the membership degree of d at the input value , indicating the degree of d belonging to a certain fuzzy level; is the membership degree of v at the input value , indicating the degree of v belonging to a certain fuzzy level;

[0164] The corresponding fuzzy output subset is expressed as:

[0165] .

[0166] Among them, is the cropped output subset of the q-th rule, is the output membership function of the q-th rule, is the risk value range variable;

[0167] It should be noted that the activation degree quantifies the triggering intensity of each rule, depending on the inference rule and the output of the membership function. The fuzzy output subset combines the activation degree of the rule with the output risk level, providing a basis for subsequent aggregation. The formula 's minimum value operation ensures the logical consistency of the rule, and the formula 's cropping operation preserves the accuracy of the rule contribution.

[0168] Furthermore, aggregate the output subsets of all rules and generate a comprehensive membership function through the maximum value operation, expressed as:

[0169] .

[0170] where N is the total number of rules;

[0171] It should be noted that by integrating the outputs of all rules, a unified fuzzy risk distribution is formed. The maximum value operation retains the strongest contribution of each rule, ensuring that high-risk scenarios are not diluted and providing accurate input for defuzzification.

[0172] Furthermore, defuzzify the comprehensive membership function and generate a scalar risk value using the weighted average method, expressed as:

[0173] .

[0174] where, is the risk value;

[0175] Classify the contact risk according to the risk value r and the predetermined standard to determine the potential contact threat degree between the vegetation and the power line.

[0176] It should be noted that converting the fuzzy risk distribution into a single numerical value facilitates decision-making. The numerical risk index provides input for subsequent classification.

[0177] In a specific embodiment of the present invention, a visualization model and an operation and maintenance instruction are generated. Specifically,

[0178] generate a visual three-dimensional model based on the vegetation growth trend and the contact risk, and mark the risk area in the form of a heat map in the visual three-dimensional model to intuitively display the analysis results;

[0179] automatically generate an operation and maintenance instruction according to the risk level; when the risk level is high risk, trigger the instruction to trim the vegetation and specify the coordinate range to be trimmed;

[0180] Transfer the visualization model and operation and maintenance instructions to the operation and maintenance terminal to ensure that the analysis results are applied to the power corridor management in real time.

[0181] It should be noted that the heat map maps the risk value r to the vegetation points through linear interpolation, and uses a gradient of cold and warm colors (blue for low risk, red for high risk) to represent the risk level. It supports transparency adjustment to retain the details of the 3D model and is more intuitive than the 2D report. The operation and maintenance instructions are generated based on the comparison between the risk value and the safety standard. In high-risk areas, pruning instructions are triggered, coordinates are extracted, and a specified range is determined in combination with the safety distance. The priorities are dynamically sorted to optimize resource allocation. Compared with traditional methods, the heat map and automated instructions significantly improve risk visualization and management efficiency.

[0182] Furthermore, the system constructs a 3D visualization model based on the fused point cloud, predicted height, and risk value. The spatial coordinates of the point cloud reconstruct the vegetation canopy, align the positions of the power lines, and dynamically incorporate the predicted height and growth rate to reflect the future form. The heat map marks the risk areas, the color assignment is aligned with the risk level, and the transparency is dynamically adjusted to highlight the high-risk points without obscuring the geometric details.

[0183] Furthermore, the system generates operation and maintenance instructions according to the risk level. In high-risk areas, pruning instructions are generated through threshold judgment, specifying the coordinate range (extracted by point cloud indexing), and the boundary meets the safety distance. Monitoring or observation instructions are generated for medium- and low-risk areas. The instructions include the operation type, priority, and time range, and the heat map distribution guides precise positioning.

[0184] Furthermore, the system transfers the model and instructions to the operation and maintenance terminal. The model is stored in a compressed 3D format, and the instructions are structured data. The encrypted transmission supports real-time or periodic updates. The terminal decodes the model, displays the risk distribution, integrates the instructions to generate a task list, supports perspective adjustment and area query, and guides on-site management.

[0185] Preferably, the system optimizes the visualization and instruction generation efficiency. The point cloud downsampling simplifies the model and retains key information; the long corridor is segmented for processing to reduce the computational complexity; the high-risk areas are sorted according to the risk value, and resources are preferentially allocated; the transmission adds status monitoring to ensure reliable reception by the terminal.

[0186] In the second embodiment of the present invention, the present invention provides a power corridor vegetation management system based on spectral images and laser point clouds, as Figure 2 shown, the system includes a data fusion module 1, a growth prediction module 2, and a risk assessment module 3;

[0187] The data fusion module 1 is used to collect laser point cloud data and multi-spectral image data in the power corridor through an unmanned aerial vehicle, and fuse them through a dynamic non-linear spectral band selection mechanism to generate a fused point cloud containing vegetation spatial and spectral characteristics;

[0188] The growth prediction module 2 is used to extract vegetation features from the fused point cloud through a multi-scale graph convolutional network, construct a time series, and train a growth model using a bidirectional LSTM and a self-attention mechanism to predict the growth trend of vegetation;

[0189] The risk assessment module 3 is used to comprehensively evaluate the contact risk between vegetation and power lines based on the spatial information and growth trend of vegetation using fuzzy logic, and generate a visualization model and operation and maintenance instructions.

[0190] In the third embodiment of the present invention, an electronic device is provided, including a memory and a processor, characterized in that a computer program that can run on the processor is stored in the memory, and when the program is executed on the processor, the steps in the above-mentioned power corridor vegetation management method based on spectral images and laser point clouds are implemented.

[0191] In the fourth embodiment of the present invention, a storage medium is provided, and the storage medium stores a computer program, characterized in that when the computer program is executed by a processor, the steps in the above-mentioned power corridor vegetation management method based on spectral images and laser point clouds are implemented.

[0192] In summary, the power corridor vegetation management method and system based on spectral images and laser point clouds provided by the present invention fuse multi-spectral images and laser point cloud data through a dynamic non-linear spectral band selection mechanism, improving the accuracy of vegetation feature extraction; using a multi-scale graph convolutional network and a bidirectional LSTM combined with a self-attention mechanism to achieve accurate prediction of the vegetation growth trend; a comprehensive risk assessment method based on fuzzy logic fully considers the uncertainty of multi-variable interaction, improving the robustness of the contact risk assessment. The finally generated visualization model and operation and maintenance instructions significantly enhance the automation and intelligence level of power corridor vegetation management, effectively reducing the contact risk between vegetation and power lines and ensuring the safe operation of the power system.

[0193] It should be understood that although this specification is described according to embodiments, not each embodiment only contains an independent technical solution. This narrative way of the specification is only for clarity. Those skilled in the art should regard the specification as a whole, and the technical solutions in each embodiment can also be appropriately combined to form other embodiments that can be understood by those skilled in the art.

[0194] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes of the above-described modules can refer to the corresponding processes in the foregoing method embodiments and will not be repeated here.

[0195] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0196] In addition, the functional modules in each embodiment of this application can be integrated into one processing module, or each module can exist physically alone, or two or more modules can be integrated into one module. The above integrated modules can be implemented in the form of hardware or in the form of a combination of hardware and software functional modules.

[0197] The above integrated modules implemented in the form of software functional modules can be stored in a computer-readable storage medium. The above software functional modules stored in a storage medium include several instructions to enable a computer system (which can be a personal computer, a server, or a network system, etc.) or a processor to execute some steps of the methods described in each embodiment of this application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0198] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application and are not intended to limit them; although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of each embodiment of this application.

Claims

1. A method for power corridor vegetation management based on spectral images and laser point clouds, characterized in that: including collecting laser point cloud data and multi - spectral image data in the power corridor by drones, and generating a fused point cloud containing vegetation spatial and spectral features through a dynamic non - linear spectral band selection mechanism, where Define the laser point cloud data in the power corridor as , where is the three-dimensional coordinate of the i-th point, and n is the number of points; Define the multispectral image data as , where is the reflection value of point i in band j, and k is the number of bands; inferring the vegetation type \(c\) and growth stage \(s\) from the multi - spectral image data \(S\) through a pre - trained classification model; calculating the weight of each spectral band \(j\), with the formula: ， wherein, is the standard deviation of band j, is a scalar representation of vegetation characteristics and temporal dynamics, τ is the data acquisition timestamp, is band specificity, and are pre-trained embedding vectors, is a balance parameter, is a scaling factor; calculating the spectral features of each point, with the formula: ， wherein, is the weight of band j, is the mean value of band j, is a non-linear transformation function; generating the fused point cloud represented as: ； extracting vegetation features from the fused point cloud through a multi - scale graph convolutional network, constructing a time series and training a growth model using bidirectional LSTM and self - attention mechanism to predict the growth trend of vegetation; based on the spatial information and growth trend of vegetation, comprehensively evaluating the contact risk between vegetation and power lines using fuzzy logic, and generating a visualization model and operation and maintenance instructions.

2. The method for managing vegetation in a power corridor based on spectral images and laser point clouds according to claim 1, wherein: The extracting of vegetation features from the fused point cloud through the multi - scale graph convolutional network includes Constructing a graph structure from the fused point cloud , where the vertex set represents all points in the fused point cloud, and E is the edge set; Calculate edge weights used to characterize the spatial relationship between point i and l; Among them, is a preset distance attenuation parameter for controlling the neighborhood range; Define multiple scales , where represents the neighborhood range of the p-th scale, and the neighborhood of point i at scale is ; Extract local features at each scale The formula is as follows: ， Among them, is neighborhood aggregation, and are the learnable weight matrix and bias at the p-th scale; aggregating global features through max - pooling represented as: ， outputting the final feature representation of point \(i\) as: ， Among them, represents the result of mapping the original features to a high-dimensional space through a multi-layer perceptron.

3. The method for power corridor vegetation management based on spectral images and laser point clouds according to claim 2, wherein: The constructing of a time series and training a growth model using bidirectional LSTM and self - attention mechanism includes Collect vegetation characteristics at multiple time points to construct a time series , where is the characteristic at the t-th moment; Process using bidirectional LSTM , calculate the forward hidden state and the backward hidden state ; Merge the forward and backward hidden states to obtain the bidirectional hidden state ; By introducing the self-attention mechanism and based on the hidden state matrix , calculate the query matrix , the key matrix , and the value matrix ; Among them, are the weights of the corresponding matrices respectively; Calculate the attention weight matrix and the context representation matrix ; Among them, is the dimension of the key vector and is used for scaling.

4. The method for managing vegetation in a power corridor based on spectral images and laser point clouds according to claim 3, wherein: The predicting of the growth trend of vegetation includes Predict the vegetation height at the next time point through the formula ​ where, is the t-th column of the context representation matrix C, corresponding to the weighted context information at the t-th time step, and is aligned with the hidden state in the time dimension; are the predicted weight matrix and bias respectively; Calculate the growth rate , where is the change in the predicted height at consecutive time points, is the time interval; when training the model, using historical height data as a supervision signal, and adjusting the model parameters by optimizing the loss function, where the loss function is represented as: ， Among them, is the true vegetation height at time step t, is the predicted vegetation height at time step t, is the total number of time steps in the time series.

5. The method for power corridor vegetation management based on spectral images and laser point clouds according to claim 4, characterized in that: The comprehensively evaluating the contact risk between vegetation and power lines using fuzzy logic includes Define the input variables, including the height difference , the closest distance d between the vegetation canopy points and the power line in the horizontal plane, and the growth rate v; Among them, is the height of the power line, and d is extracted from the laser point cloud P; The fuzzy set membership relationship of the input variables is established through the fuzzy membership function, which is used to quantify the fuzzy characteristics of the height difference , the horizontal distance d, and the growth rate v. Specifically, For each input variable, define a membership function , which maps the input variable to a fuzzy set, including fuzzy semantic levels of safety level, transition level, and danger level; the membership function is determined based on the physical meaning of the input variable and the actual requirements of power corridor management; wherein, X represents , d or v; Configure fuzzy inference rules between input variables and risk levels based on the membership relationship of the fuzzy sets; the fuzzy inference rules express the influence of input variables , d, or v on the contact risk; combining the membership relationship of the fuzzy sets of the input variables and the fuzzy inference rules, determining the activation degree of the fuzzy inference rules, and generating corresponding fuzzy output subsets; The activation degree of each rule is represented as: ， Among them, is the activation degree of the q-th rule; is the membership degree at the input value , indicating the degree of belonging to a certain fuzzy level; is the membership degree of d at the input value , indicating the degree of d belonging to a certain fuzzy level; is the membership degree of v at the input value , indicating the degree of v belonging to a certain fuzzy level; The corresponding fuzzy output subset is represented as: ， Among them, is the cropped output subset of the q-th rule, is the output membership function of the q-th rule, is the risk value range variable; aggregating the output subsets of all rules, and generating a comprehensive membership function through the maximum operation, represented as: ， where \(N\) is the total number of rules; defuzzifying the comprehensive membership function, and generating a scalar risk value using the weighted average method, represented as: ， Among them, is the risk value; classifying the contact risk into levels according to the risk value \(r\) and a predetermined standard to determine the potential contact threat degree between vegetation and power lines.

6. The method for power corridor vegetation management based on spectral images and laser point clouds according to claim 1, characterized in that: The generating of the visualization model and operation and maintenance instructions includes generating a visualization 3D model based on the vegetation growth trend and contact risk, and annotating the risk area in the form of a heat map in the visualization 3D model to intuitively display the analysis results; automatically generating operation and maintenance instructions according to the risk level; when the risk level is high - risk, triggering an instruction to trim vegetation and specifying the coordinate range to be trimmed; transmitting the visualization model and operation and maintenance instructions to the operation and maintenance terminal to ensure that the analysis results are applied to the power corridor management in real - time.

7. A power corridor vegetation management system based on spectral images and laser point clouds, which is applied to the power corridor vegetation management method based on spectral images and laser point clouds as described in claim 1, and is characterized in that: including a data fusion module, a growth prediction module, and a risk assessment module; The data fusion module is used to collect laser point cloud data and multi - spectral image data in the power corridor by drones, and generate a fused point cloud containing vegetation spatial and spectral features through a dynamic non - linear spectral band selection mechanism; The growth prediction module is used to extract vegetation features from the fused point cloud through a multi - scale graph convolutional network, construct a time series and train a growth model using bidirectional LSTM and self - attention mechanism to predict the growth trend of vegetation; The risk assessment module is used to comprehensively evaluate the contact risk between vegetation and power lines based on the spatial information and growth trend of vegetation by using fuzzy logic, and generate a visualization model and operation and maintenance instructions.

8. An electronic device, comprising a memory and a processor, characterized in that: The memory stores a computer program that can run on the processor, and when the program is executed on the processor, the steps in the power corridor vegetation management method based on spectral images and laser point clouds according to any one of claims 1-6 are implemented.

9. A storage medium storing a computer program, characterized in that: When the computer program is executed by the processor, the steps in the power corridor vegetation management method based on spectral images and laser point clouds according to any one of claims 1-6 are implemented.

Images