Bird identification algorithm for power transmission line based on big data analysis

Abstract

The application discloses a bird identification algorithm for a power transmission line based on big data analysis and relates to the technical field of big data analysis. Specifically, the application comprises the following steps: collecting data, collecting high-resolution images of a power transmission line in real time to obtain collected data; preprocessing the collected data to obtain preprocessed data, so as to improve the accuracy of the data; extracting bird features according to the preprocessed data; based on the extracted bird features, adopting a machine learning algorithm to construct a bird identification model, training the extracted bird features; inputting real-time collected data into the constructed bird identification model to identify the species and behavior of the birds, so as to realize real-time monitoring of the power transmission line. Through the data preprocessing step, the machine learning model is trained to enhance the generalization ability of the model, and the algorithm design based on big data analysis improves the safety and reliability of the power transmission line.

Description

Technical Field

[0001] This invention relates to the field of big data analytics, specifically to a big data analytics-based algorithm for bird identification on power transmission lines. Background Technology

[0002] With the rapid development of big data technology, deep learning, the Internet of Things (IoT), and cloud computing, a big data analytics-based algorithm for bird identification on power transmission lines provides data processing capabilities and algorithmic support for bird identification. Big data technology makes the collection and processing of massive amounts of image and video data possible, and breakthroughs in deep learning, especially convolutional neural networks (CNNs), in image recognition have laid the foundation for accurate bird species identification. IoT technology ensures real-time data acquisition and transmission, while cloud computing provides powerful computing resources to support the training and deployment of complex models.

[0003] However, despite the enormous potential that technological advancements have brought to bird identification, several problems and challenges remain. Acquired images and videos may be affected by noise, blur, or occlusion, compromising identification accuracy and data quality. Due to the limited generalization ability of models, well-trained models may perform poorly when faced with new environments or bird species. Processing large amounts of data requires efficient algorithms and sufficient computing resources, and data cannot be updated in real time. Furthermore, the complex environment of power transmission lines, such as weather changes and lighting conditions, can also impact the performance of identification algorithms.

[0004] To overcome these problems, it is necessary to continuously optimize algorithms, improve data quality, enhance the generalization ability of models, and explore more efficient and economical solutions. Summary of the Invention

[0005] The purpose of this invention is to provide a bird identification algorithm for power transmission lines based on big data analysis. By collecting and analyzing bird activity data around power transmission lines, it enables real-time monitoring and identification of bird behavior to prevent the impact of bird activity on power transmission line safety. This algorithm utilizes high-resolution cameras, infrared sensors, and sound recognition devices to collect data, and processes and analyzes the data through machine learning models to identify different bird species, behavioral patterns, and their potential threats to power transmission lines, thereby solving the problems mentioned in the background section.

[0006] To address the aforementioned technical problems, this invention provides the following technical solution: a bird identification algorithm for power transmission lines based on big data analysis, specifically including:

[0007] Step S1: Collect data using a high-resolution camera, infrared sensor, and sound recognition device to acquire high-resolution images of the transmission line in real time and obtain the collected data;

[0008] Step S2: Preprocess the data collected in step S1 to obtain preprocessed data, which is used to improve the accuracy of the data.

[0009] Step S3: The preprocessed data obtained in the fundamental step S2 is used for bird feature extraction.

[0010] Step S4: Based on the bird features extracted in step S3, a bird recognition model is constructed using a machine learning algorithm. The model is trained on the extracted bird features, specifically as follows:

[0011] S41. Extract n features from the bird features described in step S3, denoted as x = [x1, x2, ... x]. n ], where x i It is the i-th eigenvalue;

[0012] S42. Normalize the extracted data and divide it into training, validation, and test sets. The calculation formula is as follows:

[0013]

[0014] Among them, u i and σ i These are the mean and standard deviation of the i-th feature, respectively;

[0015] S43. Select the Support Vector Machine algorithm to construct a bird recognition model. The model formula is as follows:

[0016]

[0017] The constraints are:

[0018] y i (w·x j +b)≥1―ξ j ,ξj ≥ 0;

[0019] Where w is the weight vector, b is the bias term, and ξ is the bias term. j C is the slack variable, and C is the regularization parameter.

[0020] S44. Using the gradient descent optimization algorithm, train the SVM model with the training set to minimize the loss function. The calculation formula is as follows:

[0021]

[0022] Where η is the learning rate and L(w,b) is the loss function;

[0023] S45. The trained SVM model is evaluated using the validation set and the test set to determine the reliability and stability of the SVM model.

[0024] S46. Based on the evaluation results of the SVM model, adjust the hyperparameters and feature selection of the SVM model to ensure the accuracy of the SVM model evaluation;

[0025] Step S5: Input the real-time collected data into the constructed bird identification model to identify bird species and behaviors, thereby achieving real-time monitoring of the power transmission line.

[0026] Furthermore, the model evaluation in step S45 includes the evaluation of accuracy, precision, recall, and F1 score, specifically:

[0027] S451, The formula for calculating accuracy is:

[0028]

[0029] in, ∏ is the label predicted by the model, and ∏ is the indicator function;

[0030] S452, The formula for calculating accuracy is:

[0031]

[0032] Among them, TP is the true positive example and FP is the false positive example;

[0033] S453, The formula for calculating recall rate is:

[0034]

[0035] Where FN is a false negative;

[0036] The formulas for calculating S454 and F1 scores are as follows:

[0037]

[0038] Furthermore, step S2 further comprises:

[0039] S21. Gaussian filtering is used for noise reduction to decrease or eliminate noise in the image and improve image quality. The specific calculation formula is as follows:

[0040] I filtered (x,y)=∑ (i,j)∈Ω I(i,j)·G(i―x,j―y);

[0041] Where G(i―x,j―y) is the Gaussian kernel function, representing the influence weight of pixel (i,j) on the center pixel (x,y);

[0042] S22. Enhance the high-frequency components of the acquired image through sharpening to make the edges and details of the image clearer. The calculation formula is as follows:

[0043] I enhanced (x,y)=I(x,y)+λ(I(x,y)―I blurred (x,y));

[0044] Among them, I blurred( x,y) is the blurred image, and λ is the sharpening intensity parameter;

[0045] S23. Image segmentation is performed using edge detection, and the calculation formula is as follows:

[0046]

[0047] Where E(x,y) is the edge strength. and It is the gradient of the image in the x and y directions.

[0048] Furthermore, step S3 further comprises:

[0049] S31. Extract the color distribution in the image using a color histogram to distinguish different bird species. The specific calculation formula is as follows:

[0050] H(i)=∑ x,y δ(I(x,y)―i);

[0051] Where H(i) is the value of the i-th bin of the color histogram, I(x,y) is the color value of the image at position (x,y), and δ is the Kronecker delta function;

[0052] S32. The shape of the bird is obtained through Hu moment calculation to identify the morphological characteristics of the bird;

[0053] S33. By calculating the gray-level co-occurrence matrix, extract the texture statistical features of birds to identify the texture features of bird feathers;

[0054] S34. The Canny edge detection algorithm is used to extract edge information to identify the outline of birds.

[0055] Furthermore, step S5 further comprises:

[0056] By integrating the results of bird identification and behavior analysis into the detection system of power transmission lines, real-time identification and monitoring of power transmission lines can be achieved.

[0057] Detecting the presence and activity of birds to assess the threat posed to power transmission lines;

[0058] The test results are fed back to the system in real time so that measures can be taken to protect the transmission lines.

[0059] The beneficial effects of this invention are as follows: By performing denoising, sharpening, and segmentation on the acquired images and videos through data preprocessing steps, the impact of noise, blur, and occlusion on recognition accuracy can be effectively reduced, thereby improving data quality; training with machine learning models can improve the model's adaptability to different environments and bird species, enhance the model's generalization ability, and make it perform better when facing new environments or new bird species; the algorithm design based on big data analysis can efficiently process large amounts of data, ensure real-time data updates and processing, improve data processing efficiency, and through continuous optimization of algorithms and models, enable them to adapt to complex environments, improve the stability and accuracy of recognition algorithms, and improve overall performance. Attached Figure Description

[0060] Figure 1 This is a schematic diagram of the overall process of the present invention.

[0061] Figure 2 This is a schematic diagram of step S2 of the present invention.

[0062] Figure 3 This is a schematic diagram of step S4 of the present invention. Detailed Implementation

[0063] In the following description, numerous specific details are set forth in order to provide a more thorough understanding of the invention. However, it will be apparent to those skilled in the art that the invention can be practiced without one or more of these details. In other instances, certain technical features well-known in the art have not been described in order to avoid obscuring the invention.

[0064] The bird identification algorithm for power transmission lines provided in this solution, based on big data analysis, refers to... Figure 1 The specific steps are as follows:

[0065] Step S1: Collect data using a high-resolution camera, infrared sensor, and sound recognition device to acquire high-resolution images of the transmission line in real time and obtain the collected data;

[0066] Step S2: Preprocess the data collected in step S1 to obtain preprocessed data, which is used to improve the accuracy of the data.

[0067] Step S3: Based on the preprocessed data obtained in step S2, extract bird features;

[0068] Step S4: Based on the bird features extracted in step S3, a bird recognition model is constructed using a machine learning algorithm, and the extracted bird features are trained.

[0069] Step S5: Input the real-time collected data into the constructed bird identification model to identify bird species and behaviors, thereby achieving real-time monitoring of the power transmission line.

[0070] In this embodiment, automated data collection and processing reduce the need for manual monitoring, greatly improving monitoring efficiency and coverage. Preprocessing data and feature extraction steps ensure the quality of data input into the machine learning model, thereby improving the accuracy of bird identification. By collecting and analyzing data in real time, bird species and behaviors can be identified promptly, which helps to respond quickly to potential safety threats or environmental changes, helps prevent birds from coming into contact with power transmission lines, reduces power outages or equipment damage caused by birds, and thus improves the safety of the entire power system.

[0071] In a further embodiment, the collected data is preprocessed to obtain preprocessed data. This mainly involves improving the data quality through denoising, sharpening, and segmentation. Specifically:

[0072] S21. During the data collection process using high-resolution cameras, infrared sensors, and voice recognition devices, various types of noise, such as Gaussian noise and salt-and-pepper noise, will be encountered. Therefore, it is necessary to select a denoising method according to the noise type to remove random noise in the image while preserving the edge and detail information of the image as much as possible. In this solution, Gaussian filtering is used for denoising to reduce or eliminate noise in the image and improve image quality. The specific calculation formula is as follows:

[0073] I filtered (x,y)=∑ (i,j)∈Ω I(i,j)·G(i―x,j―y);

[0074] Where G(i―x,j―y) is the Gaussian kernel function, representing the influence weight of pixel (i,j) on the center pixel (x,y);

[0075] S22. Sharpening can enhance the edges and details of an image, making it appear clearer and more vivid. This solution enhances the high-frequency components of the acquired image through sharpening, making the edges and details of the image clearer. The calculation formula is as follows:

[0076] I enhanced (x,y)=I(x,y)+λ(I(x,y)―I blurred (x,y));

[0077] Among them, I blurred (x,y) is the blurred image, and λ is the sharpening intensity parameter;

[0078] S23. The process of dividing an image into multiple regions or objects is crucial for subsequent feature extraction and recognition. In this scheme, an edge detection segmentation method is used to segment the image, identify and separate different objects or regions in the image. The calculation formula is as follows:

[0079]

[0080] Where E(x,y) is the edge strength. and It is the gradient of the image in the x and y directions.

[0081] Based on the acquired preprocessed data, bird features are extracted as follows:

[0082] S31. Extract the color distribution in the image using a color histogram to distinguish different bird species. The specific calculation formula is as follows:

[0083] H(i)=∑ x,y δ(I(x,y)―i);

[0084] Where H(i) is the value of the i-th bin of the color histogram, I(x,y) is the color value of the image at position (x,y), and δ is the Kronecker delta function;

[0085] S32. The shape of the bird is obtained through Hu moment calculation to identify its morphological characteristics, specifically:

[0086] The formula for calculating Hu moment is:

[0087]

[0088] Where, η pq It is the normalized central moment, μ pq It is the central moment, μ 00 It is the zeroth moment;

[0089] S33. Extract the texture statistical features of birds through gray-level co-occurrence matrix calculation to identify the texture features of bird feathers. The calculation formula is as follows:

[0090] P(i,j│Δx,Δy)=∑ x,y δ(I(x,y)―i)δ(I(x+Δx,y+Δy)―j);

[0091] Where P(i,j│Δx,Δu) are elements of the gray-level co-occurrence matrix, representing the frequency at which gray values ​​i and j appear simultaneously at a distance of (Δx,Δy);

[0092] S34. The Canny edge detection algorithm is used to extract edge information to identify the outline of birds, specifically:

[0093] S341. Calculate the weight matrix of the Gaussian filter using the following formula:

[0094]

[0095] Where σ is the standard deviation of the Gaussian distribution, and x and y are the pixel positions;

[0096] S342. Calculate the gradient of the image using the Sobel operator. The Sobel operator in the horizontal direction G... x and vertical direction G y The convolution kernels are as follows:

[0097]

[0098] The formulas for calculating the gradient intensity M(x,y) and direction θ(x,y) are as follows:

[0099]

[0100]

[0101] S343. Perform non-maximum suppression in the gradient direction to refine the edges;

[0102] S344. Set two thresholds, the higher threshold T H and low threshold T L Gradient strength greater than T H Pixels are considered strong edges, with gradient strength at T L and T H Pixels between strong edges are considered weak edges, strong edges are preserved directly, and weak edges are only preserved when they are connected to strong edges.

[0103] In this embodiment, denoising, sharpening, and segmentation can significantly improve the quality of the collected data, remove noise and interference, and enhance image features, thereby providing a clearer and more accurate data foundation for subsequent analysis and identification. Through feature extraction, key bird features such as shape, texture, and color can be effectively extracted from the preprocessed data, distinguishing different bird species and behaviors, which helps to build a more accurate identification model. Preprocessing and feature extraction can reduce false alarms and missed alarms, improving the reliability of the monitoring system, which is of great significance for ensuring the safe operation of transmission lines and reducing unnecessary human resource investment.

[0104] In a further embodiment, a machine learning algorithm is used to construct a bird recognition model, and the extracted bird features are trained, specifically as follows:

[0105] S41. Extract n features from bird characteristics, represented as x = [x1, x2, ... xn].n ], where x i It is the i-th eigenvalue;

[0106] S42. Normalize the extracted data and divide it into training, validation, and test sets. The calculation formula is as follows:

[0107]

[0108] Among them, u i and σ i These are the mean and standard deviation of the i-th feature, respectively;

[0109] S43. Select the Support Vector Machine algorithm to construct a bird recognition model. The model formula is as follows:

[0110]

[0111] The constraints are:

[0112] y i (w·x j +b)≥1―ξ j ,ξ j ≥0;

[0113] Where w is the weight vector, b is the bias term, and ξ is the bias term. j C is the slack variable, and C is the regularization parameter.

[0114] S44. Using the gradient descent optimization algorithm, train the SVM model with the training set to minimize the loss function. The calculation formula is as follows:

[0115]

[0116] Where η is the learning rate and L(w,b) is the loss function;

[0117] S45. The trained SVM model is evaluated using the validation set and the test set to determine the reliability and stability of the SVM model.

[0118] The model evaluation in step S45 includes the evaluation of accuracy, precision, recall, and F1 score, specifically:

[0119] S451, The formula for calculating accuracy is:

[0120]

[0121] in, ∏ is the label predicted by the model, and ∏ is the indicator function;

[0122] S452, The formula for calculating accuracy is:

[0123]

[0124] Among them, TP is the true positive example and FP is the false positive example;

[0125] S453, The formula for calculating recall rate is:

[0126]

[0127] Where FN is a false negative;

[0128] The formulas for calculating S454 and F1 scores are as follows:

[0129]

[0130] S46. Based on the SVM model evaluation results, adjust the hyperparameters and feature selection of the SVM model to ensure the accuracy of the SVM model evaluation, specifically as follows:

[0131] S461. Choosing a linear function

[0132] The regularization parameter C controls the degree of penalty for misclassification. The larger C is, the greater the penalty for misclassification, which may lead to overfitting; the smaller C is, the smaller the penalty for misclassification, which may lead to underfitting. Kernel function parameters are used to determine hyperparameters.

[0133] S462. Select Bayesian optimization to guide parameter search;

[0134] S463. Through correlation analysis, calculate the Pearson correlation coefficient between the eigenvalues ​​and the target variable. The formula is:

[0135]

[0136] S464. Evaluate the model's accuracy, recall, and F1 score, perform model evaluation, and conduct K-fold cross-validation.

[0137] The real-time collected data is input into the constructed bird identification model to identify bird species and behaviors, thereby enabling real-time monitoring of power transmission lines. Specifically:

[0138] The shape, texture, color, and behavioral characteristics of birds obtained from bird identification and behavior analysis are integrated into the detection system of power transmission lines for behavior analysis. The formula is as follows:

[0139] B pred =behaviorAnalysis(y pred ,y);

[0140] Among them, Bpred is a predicted bird behavior, which enables real-time identification and monitoring of power transmission lines;

[0141] The threat level to power transmission lines is assessed based on bird species and behavior, using the following formula:

[0142] T = ThratAssessment(y pred B pred );

[0143] Among them, T is the threat level score, which detects the degree of threat posed to the transmission line by the presence of birds, i.e., abnormal activity.

[0144] The test results are fed back to the system in real time, and measures such as adjusting the operating parameters of the transmission lines, dispatching personnel for inspection, and installing protective devices are taken to protect the transmission lines.

[0145] In this embodiment, a highly accurate bird identification model can be trained by constructing a machine learning model based on extracted bird features. This model can effectively distinguish different bird species and behaviors based on features, thereby improving identification accuracy. Real-time collected data is input into the trained bird identification model to achieve real-time monitoring of transmission lines, enabling timely detection and response to potential threats posed by bird activities. The bird identification model constructed through machine learning algorithms allows the system to automatically process and analyze large amounts of real-time data, reducing the need for manual intervention and improving monitoring efficiency and intelligence. The automated real-time monitoring system can reduce the demand for human resources and lower operating costs. At the same time, by timely identifying and responding to bird activities, transmission line faults caused by birds can be reduced, further lowering maintenance costs, improving the safety and reliability of transmission lines, and reducing power outages and equipment damage caused by bird activities.

[0146] As described above, although the invention has been shown and described with reference to specific preferred embodiments, it should not be construed as limiting the invention itself. Various changes in form and detail may be made without departing from the spirit and scope of the invention as defined in the appended claims.

Claims

1. A bird identification algorithm for power transmission lines based on big data analysis, characterized in that, Specifically, it includes: Step S1: Collect data using a high-resolution camera, infrared sensor, and sound recognition device to acquire high-resolution images of the transmission line in real time and obtain the collected data; Step S2: Preprocess the data collected in step S1 to obtain preprocessed data, which is used to improve the accuracy of the data. Step S3: The preprocessed data obtained in the fundamental step S2 is used for bird feature extraction. Step S4: Based on the bird features extracted in step S3, a bird recognition model is constructed using a machine learning algorithm. The model is trained on the extracted bird features, specifically as follows: S41. Extract n features from the bird features described in step S3, denoted as x = [x1, x2, ... x]. n ], where x i It is the i-th eigenvalue; S42. Normalize the extracted data and divide it into training, validation, and test sets. The calculation formula is as follows: Among them, u i and σ i These are the mean and standard deviation of the i-th feature, respectively; S43. Select the Support Vector Machine algorithm to construct a bird recognition model. The model formula is as follows: The constraints are: y i (w x j +b)≥1-ξ j ,x j ≥0; Where w is the weight vector, b is the bias term, and ξ is the bias term. j C is the slack variable, and C is the regularization parameter. S44. Using the gradient descent optimization algorithm, train the SVM model with the training set to minimize the loss function. The calculation formula is as follows: Where η is the learning rate and L(w,b) is the loss function; S45. The trained SVM model is evaluated using the validation set and the test set to determine the reliability and stability of the SVM model. S46. Based on the evaluation results of the SVM model, adjust the hyperparameters and feature selection of the SVM model to ensure the accuracy of the SVM model evaluation; Step S5: Input the real-time collected data into the constructed bird identification model to identify bird species and behaviors, thereby achieving real-time monitoring of the power transmission line.

2. The big data analysis-based bird identification algorithm for power transmission lines according to claim 1, characterized in that, The model evaluation in step S45 includes the evaluation of accuracy, precision, recall, and F1 score, specifically: S451, The formula for calculating accuracy is: in, ∏ is the label predicted by the model, and ∏ is the indicator function; S452, The formula for calculating accuracy is: Among them, TP is the true positive example and FP is the false positive example; S453, The formula for calculating recall rate is: Where FN is a false negative; The formulas for calculating S454 and F1 scores are as follows:

3. The big data analysis-based bird identification algorithm for power transmission lines according to claim 1, characterized in that, Step S2 further comprises: S21. Gaussian filtering is used for noise reduction to decrease or eliminate noise in the image and improve image quality. The specific calculation formula is as follows: I filtered (x,y)=∑ (ij)∈Ω I(i,j)·G(i-x,j-y); Where G(ix, jy) is the Gaussian kernel function, representing the influence weight of pixel (i, j) on the center pixel (x, y); S22. Enhance the high-frequency components of the acquired image through sharpening to make the edges and details of the image clearer. The calculation formula is as follows: I enhanced (x,y)=I(x,y)+λ(I(x,y)-I blurred (x,y)); Among them, I blurred (x,y) is the blurred image, and λ is the sharpening intensity parameter; S23. Image segmentation is performed using edge detection, and the calculation formula is as follows: Where E(x,y) is the edge strength. and It is the gradient of the image in the x and y directions.

4. The big data analysis-based bird identification algorithm for power transmission lines according to claim 1, characterized in that, Step S3 further includes: S31. Extract the color distribution in the image using a color histogram to distinguish different bird species. The specific calculation formula is as follows: H(i)=∑ x,y δ(I(x,y)-i); Where H(i) is the value of the i-th bin of the color histogram, I(x,y) is the color value of the image at position (x,y), and δ is the Kronecker delta function; S32. The shape of the bird is obtained through Hu moment calculation to identify the morphological characteristics of the bird; S33. By calculating the gray-level co-occurrence matrix, extract the texture statistical features of birds to identify the texture features of bird feathers; S34. The Canny edge detection algorithm is used to extract edge information to identify the outline of birds.

5. The big data analysis-based bird identification algorithm for power transmission lines according to claim 1, characterized in that, Step S5 further includes: By integrating the results of bird identification and behavior analysis into the detection system of power transmission lines, real-time identification and monitoring of power transmission lines can be achieved. Detecting the presence and activity of birds to assess the threat posed to power transmission lines; The test results are fed back to the system in real time so that measures can be taken to protect the transmission lines.

Images