Transformer substation monitoring image noise reduction method and device and electronic equipment
Through the methods of texture separation, frequency domain analysis, sparse coding and rank space projection, the shortcomings of the substation video monitoring system in noise processing are solved, effective noise removal and real-time monitoring are achieved, adapting to the noise characteristics of different environments, and improving the substation security management.
Patent Information
- Application Number
- CN202410984048.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-22
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-07-22
AI Technical Summary
The existing substation video surveillance system has poor effect in processing noise, cannot effectively remove noise, has slow processing speed, cannot meet real-time monitoring needs, and has poor adaptability, so it cannot adapt to the noise characteristics of different substation environments.
By using texture separation, frequency domain analysis, sparse encoding and rank space projection, the texture characteristics of the substation monitoring image are acquired, converted to the frequency domain, sparse encoding of high-frequency and low-frequency components are carried out, and the noise is identified and removed. , adapt to the noise characteristics of different environments and ensure real-time monitoring.
Effectively remove noise, retain key information and details of the video, adapt to the noise characteristics of different substation environments, meet real-time monitoring needs, and improve the support capabilities of substation safety production and operation and maintenance management.
Smart Images

Figure CN118941459A_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the field of substation automation technology, and in particular relates to a substation monitoring image noise reduction method, device and electronic equipment. Background Art
[0002] With the rapid development of substation automation technology, the functionality of integrated substation automation systems has become increasingly sophisticated, primarily used to monitor substation production and operation conditions. However, in practice, while these systems enable real-time monitoring of various substation operating parameters, they still struggle to maintain a secure operating environment for equipment within the substation. This is particularly true for video surveillance. Due to the complexity and diversity of substation environments, surveillance videos are often subject to interference from various noise sources, such as electromagnetic and mechanical noise. This degrades video quality and prevents a clear display of equipment operating status and personnel operations, posing significant challenges to substation safety and operation and maintenance management.
[0003] Existing substation video surveillance systems typically use traditional image processing methods for video noise reduction. However, these methods often suffer from the following technical drawbacks: First, the noise reduction effect is suboptimal and cannot effectively remove noise from the video; second, the processing speed is slow, which cannot meet the needs of real-time monitoring; and third, the adaptability is poor and cannot adapt to the noise characteristics of different substation environments. These technical shortcomings limit the application of substation video surveillance systems in production safety and operation and maintenance management. Summary of the Invention
[0004] The purpose of this application is to propose a method, device and electronic equipment for substation monitoring image noise reduction, which are used to at least solve or alleviate one of the technical problems existing in the prior art.
[0005] To achieve the above object, the present invention adopts the following technical solutions:
[0006] In a first aspect, the present invention provides a method for reducing noise in substation monitoring images, comprising:
[0007] Acquire a substation monitoring image to be processed, and perform texture separation on the substation monitoring image to be processed to obtain texture features;
[0008] Converting the texture features into a frequency domain space to determine a high-frequency component cluster and a low-frequency component cluster in the frequency domain space;
[0009] Performing sparse coding on the high-frequency component cluster and the low-frequency component cluster respectively to obtain a high-frequency sparse coding array and a low-frequency sparse coding matrix;
[0010] Projecting the high-frequency sparse coding array and the low-frequency sparse coding matrix into the rank space to obtain corresponding high-frequency rank vector distribution and low-frequency rank vector distribution;
[0011] According to the high-frequency rank vector distribution and the low-frequency rank vector distribution, noise in the substation monitoring image to be processed is determined and removed.
[0012] In a second aspect, the present invention provides a device for reducing noise in substation monitoring images, comprising:
[0013] A texture separation unit is used to obtain a substation monitoring image to be processed, and perform texture separation on the substation monitoring image to be processed to obtain texture features;
[0014] A texture conversion unit, configured to convert the texture features into a frequency domain space, so as to determine a high-frequency component cluster and a low-frequency component cluster in the frequency domain space;
[0015] a sparse coding unit, configured to perform sparse coding on the high-frequency component cluster and the low-frequency component cluster respectively to obtain a high-frequency sparse coding array and a low-frequency sparse coding matrix;
[0016] A projection unit, configured to project the high-frequency sparse coding array and the low-frequency sparse coding matrix into a rank space to obtain a corresponding high-frequency rank vector distribution and a low-frequency rank vector distribution;
[0017] The noise removal unit is used to determine and remove the noise in the substation monitoring image to be processed according to the high-frequency rank vector distribution and the low-frequency rank vector distribution.
[0018] According to a third aspect of the present invention, there is provided an electronic device comprising:
[0019] one or more processors;
[0020] A computer readable medium configured to store one or more programs,
[0021] When the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the method described in any embodiment.
[0022] In the present application, the texture information in the video is distinguished from the structural information through the above-mentioned texture separation, so as to facilitate the subsequent noise identification in the frequency domain space. Furthermore, the image or video signal is converted from the spatial domain to the frequency domain through frequency domain analysis, so as to facilitate the identification and processing of high-frequency noise components. Furthermore, by sparsely coding the high-frequency component clusters and the low-frequency component clusters, the information that best represents the image or video features can be extracted, while removing redundancy and noise. Sparse coding captures the main features of the data through a small number of non-zero elements. In video denoising, it can retain key information while removing noise. Finally, the sparse coding array and matrix are projected into the rank space to obtain the corresponding high-frequency rank vector distribution and low-frequency rank vector distribution. Based on the rank space projection, key information is further extracted, and the data dimension is reduced, making it easier to distinguish between noise and useful information. According to the high-frequency rank vector distribution and the low-frequency rank vector distribution, the specific location and characteristics of the noise in the video can be determined, so that the noise can be effectively removed while retaining the key information and details of the video. Finally, because it is based on sparse coding and rank space projection, it can adapt to the noise characteristics of different substation environments, and ensure the realization of real-time monitoring needs, ensuring that the safe production and operation and maintenance management of the substation are supported in a timely and effective manner. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] Hereinafter, some specific embodiments of the present application will be described in detail in an exemplary and non-limiting manner with reference to the accompanying drawings. The same reference numerals in the drawings indicate the same or similar components or parts. It should be understood by those skilled in the art that these drawings are not necessarily drawn to scale. In the drawings:
[0024] Figure 1 This is a flow chart of a method for noise reduction of substation monitoring images according to an embodiment of the present application;
[0025] Figure 2 A schematic structural diagram of a substation monitoring image noise reduction device is provided for an embodiment of the present application;
[0026] Figure 3 Schematic diagram of the structure of the electronic device of this embodiment;
[0027] Figure 4 This is the hardware structure of the electronic device in this embodiment. DETAILED DESCRIPTION
[0028] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field should fall within the scope of protection of the embodiments of the present application.
[0029] In the present application, the texture information in the video is distinguished from the structural information through the above-mentioned texture separation, so as to facilitate the subsequent noise identification in the frequency domain space. Furthermore, the image or video signal is converted from the spatial domain to the frequency domain through frequency domain analysis, so as to facilitate the identification and processing of high-frequency noise components. Furthermore, by sparsely coding the high-frequency component clusters and the low-frequency component clusters, the information that best represents the image or video features can be extracted, while removing redundancy and noise. Sparse coding captures the main features of the data through a small number of non-zero elements. In video denoising, it can retain key information while removing noise. Finally, the sparse coding array and matrix are projected into the rank space to obtain the corresponding high-frequency rank vector distribution and low-frequency rank vector distribution. Based on the rank space projection, key information is further extracted, and the data dimension is reduced, making it easier to distinguish between noise and useful information. According to the high-frequency rank vector distribution and the low-frequency rank vector distribution, the specific location and characteristics of the noise in the video can be determined, so that the noise can be effectively removed while retaining the key information and details of the video. Finally, because it is based on sparse coding and rank space projection, it can adapt to the noise characteristics of different substation environments, and ensure the realization of real-time monitoring needs, ensuring that the safe production and operation and maintenance management of the substation are supported in a timely and effective manner.
[0030] Figure 1 This is a flow chart of a method for noise reduction of substation monitoring images according to an embodiment of the present application. Figure 1 As shown, it includes:
[0031] S101, obtaining a substation monitoring image to be processed, and performing texture separation on the substation monitoring image to be processed to obtain texture features;
[0032] In this embodiment, the substation monitoring image to be processed may be obtained, for example, from an image acquisition device. The image acquisition device includes but is not limited to a camera, a scanner, or other image acquisition devices. Alternatively, the image may be obtained from an image database, such as by direct download.
[0033] In substation monitoring images, texture information may contain key information about the surface condition, stains, wear, etc. of the equipment, but it may also contain noise. Therefore, separating texture information from structural information (such as edges, shapes, etc.) is crucial for subsequent image noise reduction and enhancement. To this end, optionally, in this embodiment, the texture separation of the substation monitoring image to be processed to obtain texture features includes:
[0034] Obtaining the R channel value, G channel value, and B channel value of each pixel on the substation monitoring image to be processed;
[0035] Convert the R channel value, the G channel value, and the B channel value into a brightness channel value and a color difference channel value;
[0036] According to the brightness channel values and the color difference channel values corresponding to all pixels, texture separation is performed on the substation monitoring image to be processed to obtain texture features.
[0037] The following is an example code of the above technical processing:
[0038] import cv2
[0039] import numpy as np
[0040] def get_channel_values(image):
[0041] #Get the R channel value, G channel value, and B channel value of each pixel
[0042] r_channel=image[:,:,0]
[0043] g_channel=image[:,:,1]
[0044] b_channel=image[:,:,2]
[0045] return r_channel,g_channel,b_channel
[0046] def convert_to_yuv(image):
[0047] #Convert RGB image to YUV image
[0048] yuv_image=cv2.cvtColor(image,cv2.COLOR_BGR2YUV)
[0049] #Get the brightness channel value and color difference channel value
[0050] y_channel=yuv_image[:,:,0]
[0051] u_channel=yuv_image[:,:,1]
[0052] v_channel=yuv_image[:,:,2]
[0053] return y_channel,u_channel,v_channel
[0054] def texture_separation(image):
[0055] #Get channel value
[0056] r_channel,g_channel,b_channel=get_channel_values(image)
[0057] #Convert to brightness and color difference channel values
[0058] y_channel,u_channel,v_channel=convert_to_yuv(image)
[0059] #Texture separation of brightness channel value
[0060] #Any texture separation algorithm can be used here, such as wavelet transform, texture filtering, etc.
[0061] #Here is an example of using Gaussian filtering for texture separation
[0062] texture_y=cv2.GaussianBlur(y_channel,(5,5),0)
[0063] #Merge texture features into the brightness channel of the original image
[0064] enhanced_y=cv2.addWeighted(y_channel,0.5,texture_y,0.5,0)
[0065] #Merge texture features into the RGB channels of the original image
[0066] enhanced_image=cv2.merge((enhanced_y,u_channel,v_channel))
[0067] #Convert the image from YUV color space back to RGB color space
[0068] enhanced_image=cv2.cvtColor(enhanced_image,cv2.COLOR_YUV2BGR)
[0069] return enhanced_image
[0070] #Read the substation monitoring image to be processed
[0071] image=cv2.imread("image.jpg")
[0072] #Perform texture separation
[0073] result_image=texture_separation(image)
[0074] # Display the result image
[0075] cv2.imshow("Result Image",result_image)
[0076] cv2.waitKey(0)
[0077] cv2.destroyAllWindows()
[0078] Optionally, in this embodiment, the step of performing texture separation on the substation monitoring image to be processed to obtain texture features further includes:
[0079] Obtaining the horizontal coordinate and vertical coordinate of each pixel on the substation monitoring image to be processed;
[0080] Projecting the horizontal coordinate and the vertical coordinate of each pixel into the orthogonal space to perform an orthogonal transformation on the pixel to obtain an orthogonal horizontal coordinate and an orthogonal vertical coordinate;
[0081] Determining a texture separation step size based on the orthogonal abscissa and the orthogonal ordinate;
[0082] The step of performing texture separation on the substation monitoring image to be processed to obtain texture features according to the brightness channel values and the color difference channel values corresponding to all pixels includes:
[0083] Based on the texture separation step, multi-scale features of brightness channel values and color difference channel values corresponding to all pixels are counted;
[0084] According to the multi-scale features, texture separation is performed on the substation monitoring image to be processed to obtain texture features. To this end, the above-mentioned texture separation of the substation monitoring image to obtain texture features has the following technical advantages:
[0085] (1) By projecting the horizontal and vertical coordinates of the pixels into the orthogonal space and performing an orthogonal transformation, the orthogonal horizontal and vertical coordinates can be obtained. The orthogonal transformation can eliminate the redundant information in the original coordinate system, making the spatial relationship between pixels clearer, thereby improving the accuracy of texture feature extraction.
[0086] (2) After determining the texture separation step size, the multi-scale features of the brightness channel values and color difference channel values corresponding to all pixels are counted based on this step size. Multi-scale features can capture texture details at different scales, thereby more comprehensively describing the texture information of the image. This texture separation method based on multi-scale features can more effectively extract texture features from substation monitoring images.
[0087] (3) Since there may be many different texture types in substation monitoring images, such as equipment surface texture, cable texture, etc., the multi-scale feature extraction method can enhance the algorithm's adaptability to different texture types. Both rough and fine textures can be effectively extracted.
[0088] (4) Through the automated texture separation process, the need for manual intervention can be greatly reduced, and the degree of automation of image analysis can be improved. This is of great significance for the rapid processing and real-time analysis of substation monitoring images, which helps to improve the safety and reliability of substation operation.
[0089] (5) The extracted texture features can serve as the basis for subsequent image processing and analysis, such as target detection, anomaly recognition, etc. By utilizing these texture features, the accuracy and efficiency of image processing algorithms can be further improved.
[0090] To this end, the exemplary implementation code of the above technical processing is as follows:
[0091]
[0092]
[0093] Optionally, in this embodiment, based on the texture separation step size, multi-scale features of the brightness channel values and the color difference channel values corresponding to all pixels are counted, for example, including: extracting characteristic values from the brightness channel values and the color difference channel values corresponding to all pixels; based on the texture separation step size, multi-scale features of the characteristic values of the brightness channel values and the color difference channel values corresponding to all pixels are counted.
[0094] To this end, based on the technical solution provided above, in the process of texture separation of substation monitoring images, the multi-scale features of the brightness channel value and the color difference channel value are statistically analyzed, which has the following technical advantages:
[0095] (1) By extracting the eigenvalues from the brightness and color difference channels and combining them with multi-scale statistics, we can obtain richer texture information. This information includes not only the brightness and color information of the pixel itself, but also the texture structure information at different scales, thus enabling a more comprehensive description of the texture characteristics of the image.
[0096] (2) The extraction of multi-scale features makes the algorithm robust to scale changes of textures. Textures may exhibit different characteristics at different scales. By counting the feature values of multiple scales, the algorithm can adapt to texture changes at different scales and improve the generalization ability of the algorithm.
[0097] (3) By selecting an appropriate texture separation step size, the amount of computation can be reduced to a certain extent, thus improving the computational efficiency of the algorithm. At the same time, the statistics of multi-scale features can also reduce the interference of redundant information to a certain extent, making the extracted texture features more accurate and effective.
[0098] (4) The extracted multi-scale texture features can serve as the basis for subsequent image processing and analysis, such as target detection, anomaly recognition, etc. These features can provide more accurate and comprehensive information support for subsequent algorithms, thereby improving the accuracy and efficiency of the algorithms.
[0099] The following is an example implementation code for extracting multi-scale features of brightness channel values and color difference channel values:
[0100]
[0101] S102, converting the texture features into a frequency domain space to determine a high-frequency component cluster and a low-frequency component cluster in the frequency domain space;
[0102] Optionally, the method further includes: constructing a filter, the filter including a conversion module, a high-frequency filtering module and a low-frequency filtering module, the conversion module being cascaded with the high-frequency filtering module and the low-frequency filtering module respectively.
[0103] The converting the texture features into a frequency domain space to determine a high-frequency component cluster and a low-frequency component cluster in the frequency domain space includes:
[0104] Inputting the texture features into the conversion module, converting the texture features into frequency domain signals and inputting the signals into the high-frequency filtering module and the low-frequency filtering module;
[0105] The high-frequency filtering module extracts all high-frequency components in the frequency domain signal to form the high-frequency component cluster;
[0106] The low-frequency filtering module extracts all low-frequency components in the frequency domain signal to form the low-frequency component cluster.
[0107] Optionally, the high-frequency filtering module extracts all high-frequency components in the frequency domain signal to form the high-frequency component cluster, including:
[0108] The high-frequency filtering module divides the frequency domain signal into spatial frequency distribution and calculates the entropy of each spatial frequency distribution area to extract the frequency domain signal covered by the spatial frequency distribution area when the entropy is greater than the set entropy threshold to form the high-frequency component cluster.
[0109] To this end, the frequency domain processing technology and filter construction method involved in the above-mentioned substation monitoring image processing solution have the following technical advantages:
[0110] (1) By converting texture features into frequency domain space for analysis, the system can more effectively identify and separate high-frequency and low-frequency components in the image. In the frequency domain space, the details and structure of the texture are clearly reflected in the different frequency components, making the analysis more intuitive and accurate.
[0111] (2) Frequency domain processing has a natural inhibitory effect on noise and redundant information. The high-frequency filtering module can extract high-frequency details in the image, while the low-frequency filtering module retains the image's outline and basic structural information. This helps eliminate or reduce noise in the image and extract key information useful for subsequent processing.
[0112] (3) By constructing a filter consisting of a conversion module, a high-frequency filtering module, and a low-frequency filtering module, the system can achieve rapid frequency domain conversion and component extraction of texture features. This modular design makes the processing flow clearer and more efficient, reducing unnecessary computational overhead.
[0113] (4) The high-frequency and low-frequency filter modules in the filter can be customized and adjusted according to specific needs. For example, the high-frequency filter module can set different entropy thresholds according to different texture types and application scenarios to achieve more accurate high-frequency component extraction. This flexibility enables the system to adapt to a wider range of monitoring scenarios and application needs.
[0114] (5) By extracting high-frequency component clusters through spatial frequency distribution division and entropy calculation, the system can more accurately identify key texture information in the image. This method is highly robust to interference factors such as lighting changes and occlusion, ensuring the stability and reliability of the algorithm under different conditions.
[0115] (6) The extracted high-frequency component clusters and low-frequency component clusters can provide strong support for subsequent image processing and analysis. For example, high-frequency component clusters can be used for tasks such as detail enhancement and edge detection, while low-frequency component clusters can be used for tasks such as image reconstruction and target recognition. This multi-scale information processing method helps improve the performance and efficiency of the entire monitoring system.
[0116] To this end, an exemplary code for implementing the above scheme is also provided below: a Python-based library (such as OpenCV and numpy) will be used to simulate the process of filter construction and frequency domain analysis, showing how to build a filter containing a conversion module (Fourier transform), a high-frequency filtering module, and a low-frequency filtering module, and use these modules to separate the high-frequency and low-frequency components in texture features.
[0117]
[0118] low_freq[high_freq!=0]=0#Set the high frequency part to zero to get the low frequency part
[0119] return low_freq
[0120] #Convert texture features (image here) into frequency domain signals
[0121] fshift=fourier_transform(image)
[0122] #Set entropy threshold
[0123] entropy_threshold=2
[0124] #Extract high frequency components
[0125] high_freq_components=high_frequency_filter(fshift,entropy_threshold)
[0126] #Extract low frequency components
[0127] low_freq_components=low_frequency_filter(fshift)
[0128] high_freq_image=np.fft.ifftshift(high_freq_components)
[0129] high_freq_image=np.abs(np.fft.ifft2(high_freq_image))
[0130] high_freq_image=(high_freq_image-np.min(high_freq_image)) /
[0131] (np.max(high_freq_image)-np.min(high_freq_image))*255
[0132] high_freq_image=np.uint8(high_freq_image)
[0133] low_freq_image=np.fft.ifftshift(low_freq_components)
[0134] low_freq_image=np.abs(np.fft.ifft2(low_freq_image))
[0135] low_freq_image=(low_freq_image-np.min(low_freq_image)) /
[0136] (np.max(low_freq_image)-np.min(low_freq_image))*255
[0137] low_freq_image=np.uint8(low_freq_image)
[0138] # Display the results
[0139] cv2.imshow('Original Image',image)
[0140] Optionally, the low-frequency filtering module extracts all low-frequency components in the frequency domain signal to form the low-frequency component cluster, including:
[0141] The low-frequency filtering module divides the frequency domain signal into spatial frequency distribution and calculates the entropy of each spatial frequency distribution area to extract the frequency domain signal covered by the spatial frequency distribution area when the entropy is less than the set entropy threshold to form the low-frequency component cluster.
[0142] In this embodiment, by dividing the frequency domain signal into spatial frequency distribution regions and calculating the entropy of each spatial frequency distribution region, it is possible to extract spatial frequency distribution regions with entropy less than a set entropy threshold. The frequency domain signals corresponding to these spatial frequency distribution regions represent the low-frequency components of the image and contain the overall structure and background information of the image. Furthermore, as mentioned above, high-frequency signals generally correspond to high-frequency information such as detail and texture in the image, while low-frequency signals correspond to smooth areas and background in the image, thereby ensuring overall denoising accuracy.
[0143] S103, performing sparse coding on the high-frequency component cluster and the low-frequency component cluster respectively to obtain a high-frequency sparse coding array and a low-frequency sparse coding matrix;
[0144] Optionally, in this embodiment, sparse coding the high-frequency component cluster and the low-frequency component cluster to obtain a high-frequency sparse coding array and a low-frequency sparse coding matrix includes:
[0145] Vectorizing the high-frequency component cluster and the low-frequency component cluster respectively to obtain corresponding high-frequency component vectors and low-frequency component vectors;
[0146] Based on the linear combination vector of the set basis function, the high-frequency component vector and the low-frequency component vector are sparsely coded respectively to obtain a high-frequency sparse coding array and a low-frequency sparse coding matrix.
[0147] Therefore, in the aforementioned image processing or feature representation tasks, sparse coding of high-frequency component clusters and low-frequency component clusters achieves effective feature extraction and dimensionality reduction, which has the following technical benefits:
[0148] (1) Through sparse coding, high-frequency and low-frequency component clusters can be transformed into a more compact and robust representation. This representation is more robust to noise and local deformation because only a few basis functions are activated to reconstruct the input data during sparse coding, which makes the representation less sensitive to the specific details of the input data.
[0149] (2) Sparse coding converts the original high-dimensional data (such as high-frequency component clusters and low-frequency component clusters) into a low-dimensional sparse coding array or matrix. This dimensionality reduction process can greatly reduce the computational complexity of subsequent processing steps (such as classification and recognition), and improve the computational efficiency of the overall system.
[0150] (3) Since sparse coding approximates the original data based on a linear combination of basis functions, it is possible to select discriminative basis functions to enhance the discriminative ability of features. In the sparse coding process of high-frequency and low-frequency component clusters, basis functions that can capture the key information in high-frequency and low-frequency features can be selected respectively, thereby enhancing the discriminativeness of the encoded features.
[0151] (4) By sparse coding the high-frequency and low-frequency component clusters separately, two independent sparse code arrays or matrices can be obtained. These two sparse codes can be conveniently fused to combine the information in the high-frequency and low-frequency features. This fusion can be achieved through simple splicing, weighting, or more complex fusion strategies, providing more information input for subsequent processing steps.
[0152] The above exemplary code is as follows:
[0153] import numpy as np
[0154] # Sample data of high-frequency component clusters and low-frequency component clusters
[0155] high_freq_clusters=np.array([[1,2,3],[4,5,6],[7,8,9]])
[0156] low_freq_clusters=np.array([[10,20,30],[40,50,60]])
[0157] #Vectorize high-frequency component clusters and low-frequency component clusters
[0158] high_freq_vector=high_freq_clusters.flatten()
[0159] low_freq_vector=low_freq_clusters.flatten()
[0160] #Set the linear combination vector of basis functions
[0161] basis_functions=np.array([[1,0,0],[0,1,0],[0,0,1]])
[0162] #Sparsely encode the high-frequency component vector
[0163] high_freq_sparse_code=np.linalg.lstsq(basis_functions,high_freq_vector,rcond=None)[0]
[0164] #Sparsely encode the low-frequency component vector
[0165] low_freq_sparse_code=np.linalg.lstsq(basis_functions,low_freq_vector,rcond=None)[0]
[0166] print("High frequency sparse coding array:", high_freq_sparse_code)
[0167] print("Low frequency sparse coding matrix:",low_freq_sparse_code)
[0168] In the above code, we first define sample data for high-frequency and low-frequency component clusters. We then use the flatten() function to flatten the cluster data into a one-dimensional vector. Next, we define a vector of linear combinations of basis functions, basis_functions, assuming that the basis functions are unit vectors. Finally, we use the np.linalg.lstsq() function to sparsely encode the high-frequency and low-frequency vectors, producing a high-frequency sparse encoding array and a low-frequency sparse encoding matrix.
[0169] S104, projecting the high-frequency sparse coding array and the low-frequency sparse coding matrix into a rank space to obtain corresponding high-frequency rank vector distribution and low-frequency rank vector distribution;
[0170] Optionally, in this embodiment, projecting the high-frequency sparse coding array and the low-frequency sparse coding matrix into a rank space to obtain corresponding high-frequency rank vector distribution and low-frequency rank vector distribution includes:
[0171] Projecting the high-frequency sparse coding array and the low-frequency sparse coding matrix into the rank space to obtain corresponding high-frequency rank tensor and low-frequency rank tensor;
[0172] According to the high-frequency rank tensor and the low-frequency rank tensor, the high-frequency rank vector distribution and the low-frequency rank vector distribution are counted.
[0173] To this end, during image processing or feature analysis, the high-frequency sparse coding array and the low-frequency sparse coding matrix are projected into the rank space to obtain the high-frequency rank vector distribution and the low-frequency rank vector distribution, which has the following technical benefits:
[0174] (1) By projecting sparse coding arrays and matrices into the rank space, the original high-dimensional data can be compressed into a low-dimensional rank tensor. This dimensionality reduction process not only reduces the storage and transmission costs of the data, but also reduces the computational complexity of subsequent analysis.
[0175] (2) Rank space projection can preserve key structural information in the original data. The high-frequency rank tensor mainly reflects detailed information such as edges and textures in the image, while the low-frequency rank tensor mainly reflects structural information such as the overall shape and contour of the image. This retention of characteristic structure helps in feature extraction and recognition in subsequent tasks.
[0176] (3) By converting the rank tensor into a rank vector distribution, the distribution of high-frequency and low-frequency features in the rank space can be more intuitively displayed. This statistical distribution helps to analyze the overall characteristics and local differences of images or data.
[0177] (3) Since the rank space projection and statistical distribution calculation are based on the overall data, this method is robust to local noise and outliers. Even if there are some noise or outliers in the original data, the rank tensor and rank vector distribution after projection can still remain relatively stable, providing reliable feature representation for subsequent processing.
[0178] (4) By projecting the high-frequency and low-frequency components into the rank space respectively, feature representations at different scales can be obtained. This multi-scale analysis helps to more comprehensively understand the structure and content of images or data, and provides rich feature information for subsequent tasks such as image recognition and object detection.
[0179] The statistical distribution of high-frequency rank vectors and low-frequency rank vectors can be achieved by using a histogram. In a specific application scenario, for example, the histogram is drawn using Python's Matplotlib library:
[0180] import numpy as np
[0181] import matplotlib.pyplot as plt
[0182] #Example data of high-frequency rank vectors and low-frequency rank vectors
[0183] high_freq_rank_vectors=np.array([1,2,3,4,5])
[0184] low_freq_rank_vectors=np.array([10,20,30,40,50])
[0185] #Statistical high frequency rank vector distribution
[0186] high_freq_rank_hist,high_freq_rank_bins=np.histogram(high_freq_rank_vectors,bins=10)
[0187] #Statistical low-frequency rank vector distribution
[0188] low_freq_rank_hist,low_freq_rank_bins=np.histogram(low_freq_rank_vectors,bins=10)
[0189] #Draw a histogram of the high-frequency rank vector distribution
[0190] plt.bar(high_freq_rank_bins[:-1],high_freq_rank_hist,
[0191] width=np.diff(high_freq_rank_bins),align='edge')
[0192] plt.xlabel('high frequency rank vector')
[0193] plt.ylabel('Frequency')
[0194] plt.title('High-frequency rank vector distribution histogram')
[0195] plt.show()
[0196] #Draw a histogram of the low-frequency rank vector distribution
[0197] plt.bar(low_freq_rank_bins[:-1],low_freq_rank_hist,width=np.diff(low_freq_rank_bins),align='edge')
[0198] plt.xlabel('low frequency rank vector')
[0199] plt.ylabel('Frequency')
[0200] plt.title('Histogram of low-frequency rank vector distribution')
[0201] plt.show()
[0202] In the above code, the np.histogram() function is used to calculate the distribution of the vector, where the bins parameter specifies the number of bins in the histogram. In addition, the plt.bar() function of the Matplotlib library is used to plot the histogram of the high-frequency rank vector distribution and the low-frequency rank vector distribution.
[0203] S105 . Determine and remove noise in the substation monitoring image to be processed based on the high-frequency rank vector distribution and the low-frequency rank vector distribution.
[0204] Optionally, determining and removing noise in the substation monitoring image to be processed based on the high-frequency rank vector distribution and the low-frequency rank vector distribution includes:
[0205] Projecting the high-frequency rank vector distribution and the low-frequency rank vector distribution into Gaussian space to obtain corresponding Gaussian distributions;
[0206] The maximum likelihood estimation value of the Gaussian distribution corresponding to the high-frequency rank vector distribution and the low-frequency rank vector distribution is determined, and compared with a set maximum likelihood threshold to determine and remove the noise in the substation monitoring image to be processed.
[0207] To this end, the high-frequency rank vector distribution and the low-frequency rank vector distribution are projected into Gaussian space, and the maximum likelihood estimate of the Gaussian distribution is used to determine and remove noise in the substation monitoring image. This has the following technical benefits:
[0208] (1) By projecting the rank vector distribution onto Gaussian space, the characteristics of the Gaussian distribution can be used to accurately detect noise. Ideally, noise-free data will exhibit a certain Gaussian distribution pattern, while noisy data may deviate from this distribution pattern. Therefore, by comparing the maximum likelihood estimate of the Gaussian distribution corresponding to the rank vector distribution with the set threshold, noisy data can be effectively identified.
[0209] (2) This method has a certain degree of adaptability. By setting the maximum likelihood threshold, the sensitivity of noise detection can be adjusted according to different application scenarios and data characteristics. This is of great significance for processing substation monitoring images with different noise levels.
[0210] (3) Since this method performs noise detection based on the distribution of high-frequency and low-frequency rank vectors, it can retain the image details while removing noise. High-frequency components usually contain image details and texture information, while low-frequency components reflect the overall structure and contour of the image. By processing high-frequency and low-frequency components separately, it is possible to remove noise while maintaining the clarity and details of the image.
[0211] The following is a simple example implementation code to illustrate how to project the rank vector distribution into Gaussian space and perform noise detection:
[0212] import numpy as np
[0213] from scipy.stats import norm
[0214] #High frequency rank vector and low frequency rank vector
[0215] high_freq_vectors = np.random.randn(1000) # high frequency rank vector
[0216] low_freq_vectors = np.random.randn(1000) # low frequency rank vector
[0217] #Project the rank vector into Gaussian space
[0218] #Mean and standard deviation of Gaussian distribution
[0219] mean_high=np.mean(high_freq_vectors)
[0220] std_high=np.std(high_freq_vectors)
[0221] mean_low=np.mean(low_freq_vectors)
[0222] std_low=np.std(low_freq_vectors)
[0223] #Calculate the maximum likelihood estimate (for Gaussian distribution, it is the value of the probability density function)
[0224] def gaussian_likelihood(x,mean,std):
[0225] return norm.pdf(x,mean,std)
[0226] #For high frequency rank vector
[0227] high_freq_likelihoods=gaussian_likelihood(high_freq_vectors,mean_high,std_high)
[0228] #Set the maximum likelihood threshold for noise detection
[0229] max_likelihood_threshold=norm.pdf(mean_high,mean_high,std_high)*0.1#The threshold is 10% of the probability density at the mean
[0230] #Detect and remove noise
[0231] high_freq_vectors_cleaned=
[0232] high_freq_vectors[high_freq_likelihoods>max_likelihood_threshold]
[0233] Exemplarily, for example, the high-frequency rank vector distribution and the low-frequency rank vector distribution are projected into the Gaussian space to obtain the corresponding Gaussian distribution, for example, including: merging the high-frequency rank vector distribution and the low-frequency rank vector distribution into a matrix, with each vector as a row of the matrix, and performing a mean operation on the merged matrix, that is, subtracting the mean of each dimension from the mean of the entire dimension; calculating the covariance matrix of the merged matrix; performing eigenvalue decomposition on the covariance matrix to obtain eigenvalues and corresponding eigenvectors. Sort the eigenvectors according to the size of the eigenvalues, and select the first N eigenvectors as principal components. Multiply the merged matrix with the selected principal components to obtain a projected data matrix. The projected data matrix is the representation of the high-frequency rank vector distribution and the low-frequency rank vector distribution in the Gaussian space, which can be regarded as the corresponding Gaussian distribution.
[0234] To this end, projecting the high-frequency rank vector distribution and the low-frequency rank vector distribution into Gaussian space and using principal component analysis (PCA) to obtain their representation in Gaussian space is an effective feature extraction and dimensionality reduction technique with the following technical benefits:
[0235] (1) By combining the high-frequency rank vectors and the low-frequency rank vectors into a matrix and applying PCA, we can project the data from the original high-dimensional space into a low-dimensional principal component space. This greatly reduces the dimensionality of the data and reduces the amount of computation and storage space required.
[0236] (2) PCA is an unsupervised learning method that performs dimensionality reduction based on the statistical properties of the data (e.g., the covariance matrix). Since noise often manifests as random fluctuations in the data, PCA may treat these noise components as secondary features and ignore them during the projection process, thereby achieving the effect of suppressing noise.
[0237] (3) By selecting the first N principal components, we are actually selecting the most important features in the data. These features usually contain most of the information in the original data, while noise and other irrelevant information are eliminated or weakened.
[0238] The following example implementation code is used to project the high-frequency rank vector distribution and the low-frequency rank vector distribution into Gaussian space (by PCA dimensionality reduction):
[0239] import numpy as np
[0240] from sklearn.decomposition import PCA
[0241] #High frequency rank vector and low frequency rank vector
[0242] high_freq_vectors=np.random.randn(100,10)
[0243] low_freq_vectors=np.random.randn(100,5)
[0244] #Merge the high-frequency rank vector and the low-frequency rank vector into a matrix
[0245] # Expand the low-frequency rank vector to the same dimension as the high-frequency rank vector (for example, by filling with 0 or interpolation)
[0246] low_freq_vectors_padded=np.pad(low_freq_vectors,((0,0),(0,5)),'constant',constant_values=0)
[0247] combined_vectors=np.concatenate((high_freq_vectors,low_freq_vectors_padded),axis=0)
[0248] #Perform PCA dimensionality reduction on the merged matrix
[0249] pca=PCA(n_components=5) #Assume that the first 5 principal components are selected
[0250] projected_data=pca.fit_transform(combined_vectors)
[0251] #The projected data matrix is the representation of the high-frequency rank vector distribution and the low-frequency rank vector distribution in Gaussian space
[0252] #Show the data after dimensionality reduction
[0253] print(projected_data)
[0254] #import matplotlib.pyplot as plt
[0255] #plt.scatter(projected_data[:,0],projected_data[:,1])
[0256] #plt.show()
[0257] Note that the low_freq_vectors_padded method in the above code is a hypothetical padding method to expand the dimensions of the low-frequency rank vectors to the same as the high-frequency rank vectors. In practice, you can choose an appropriate padding or interpolation method based on the specific data structure and task requirements.
[0258] Optionally, in this embodiment, determining the maximum likelihood estimate of the Gaussian distribution corresponding to the high-frequency rank vector distribution and the low-frequency rank vector distribution includes, for example: calculating the Gaussian distribution probability density function value corresponding to the gradient amplitude of each pixel point based on the estimated Gaussian distribution parameters of the high-frequency rank vector and the low-frequency rank vector to obtain the corresponding maximum likelihood estimate, and comparing it with the set maximum likelihood threshold.
[0259] To this end, when the maximum likelihood estimate of the Gaussian distribution is used to determine and remove noise in the image, especially the Gaussian distribution parameters based on the high-frequency rank vector and the low-frequency rank vector, the following technical benefits are achieved:
[0260] (1) By calculating the Gaussian distribution probability density function value corresponding to the gradient amplitude of each pixel, a quantitative indicator can be obtained to measure whether the pixel is noise. This probability-based method can detect noise more accurately, especially when the noise distribution is complex or the noise level is high.
[0261] (2) Using Gaussian distribution parameters (mean and variance) to describe the distribution of pixel values makes the model more flexible and adaptable. These parameters can be automatically estimated in a data-driven manner without manual setting, thereby improving the automation and robustness of the algorithm.
[0262] (3) By setting the maximum likelihood threshold, the sensitivity of noise detection can be controlled. Depending on the specific application scenario and requirements, the threshold can be adjusted to achieve different degrees of noise removal effect.
[0263] (4) Since this method performs noise detection based on the Gaussian distribution of high-frequency rank vectors and low-frequency rank vectors, it can retain the image details while removing noise. High-frequency components usually contain image details and texture information, while low-frequency components reflect the overall structure and contour of the image. By processing high-frequency and low-frequency components separately, it is possible to remove noise while maintaining the clarity and details of the image.
[0264] The following is an example implementation code for calculating the maximum likelihood estimate of the Gaussian distribution for each pixel and performing noise detection:
[0265]
[0266] # Treat pixels below the threshold as noise and set them to zero
[0267] denoised_image_gradients=np.where(likelihoods_high>max_likelihood_threshold,image_gradients,0)
[0268] #denoised_image_gradients contains the gradient magnitude after denoising
[0269] Figure 2 This is a schematic diagram of the structure of a substation monitoring image noise reduction device according to an embodiment of the present application. Figure 2 As shown, it includes:
[0270] The texture separation unit 201 is used to obtain a substation monitoring image to be processed, and perform texture separation on the substation monitoring image to be processed to obtain texture features;
[0271] A texture conversion unit 202 is configured to convert the texture features into a frequency domain space to determine a high frequency component cluster and a low frequency component cluster in the frequency domain space;
[0272] A sparse coding unit 203 is configured to perform sparse coding on the high-frequency component cluster and the low-frequency component cluster respectively to obtain a high-frequency sparse coding array and a low-frequency sparse coding matrix;
[0273] A projection unit 204 is configured to project the high-frequency sparse coding array and the low-frequency sparse coding matrix into a rank space to obtain a corresponding high-frequency rank vector distribution and a low-frequency rank vector distribution;
[0274] The noise removal unit 205 is configured to determine and remove noise in the substation monitoring image to be processed based on the high-frequency rank vector distribution and the low-frequency rank vector distribution.
[0275] Figure 3 This is a schematic diagram of the structure of an electronic device according to this embodiment; the electronic device may include:
[0276] One or more processors 301;
[0277] The computer readable medium 302 may be configured to store one or more programs,
[0278] When the one or more programs are executed by the one or more processors, the one or more processors implement the method described in the above embodiments.
[0279] Figure 4 The hardware structure of the electronic device of this embodiment is as follows; Figure 4 As shown, the hardware structure of the electronic device may include: a processor 401, a communication interface 402, a computer-readable medium 403 and a communication bus 404;
[0280] The processor 401, the communication interface 402, and the computer-readable medium 403 communicate with each other via a communication bus 404;
[0281] Optionally, the communication interface 402 may be an interface of a communication module, such as an interface of a GSM module;
[0282] Among them, the processor 401 can be specifically configured to: obtain the substation monitoring image to be processed, and perform texture separation on the substation monitoring image to be processed to obtain texture features; convert the texture features to the frequency domain space to determine the high-frequency component cluster and the low-frequency component cluster in the frequency domain space; perform sparse coding on the high-frequency component cluster and the low-frequency component cluster respectively to obtain a high-frequency sparse coding array and a low-frequency sparse coding matrix; project the high-frequency sparse coding array and the low-frequency sparse coding matrix into the rank space to obtain the corresponding high-frequency rank vector distribution and low-frequency rank vector distribution; determine the noise in the substation monitoring image to be processed and remove it according to the high-frequency rank vector distribution and the low-frequency rank vector distribution.
[0283] The processor 401 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component. It can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor.
[0284] The computer-readable medium 403 may be, but is not limited to, a random access memory (RAM), a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), etc.
[0285] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code configured to execute the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part, and / or installed from a removable medium. When the computer program is executed by a central processing unit (CPU), the above-mentioned functions defined in the method of the present application are executed. It should be noted that the computer-readable medium described in the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable medium can be, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage medium, a magnetic storage medium, or any suitable combination thereof. In this application, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including, but not limited to, an electromagnetic signal, an optical signal, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transfer a program configured for use by or in conjunction with an instruction execution system, apparatus, or device. Program code embodied on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
[0286] Computer program code configured to perform the operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).
[0287] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of the systems, methods, and computer program products according to various embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or part of the code, which contains one or more executable instructions configured to implement the specified logical functions. There are specific sequential relationships in the above-mentioned specific embodiments, but these sequential relationships are only exemplary. When implementing the specific embodiments, these steps may be fewer, more, or the execution order may be adjusted. That is, in some alternative implementations, the functions marked in the boxes may also occur in an order different from that marked in the accompanying drawings. For example, two boxes shown in succession can actually be executed substantially in parallel, or they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, as well as the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified functions or operations, or can be implemented using a combination of dedicated hardware and computer instructions.
[0288] As another aspect, the present application further provides a computer-readable medium having a computer program stored thereon, which implements the method described in the above embodiment when the program is executed by a processor.
[0289] As another aspect, the present application also provides a computer-readable medium, which may be included in the device described in the above embodiment; or it may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by the device, the device: obtains the substation monitoring image to be processed, and performs texture separation on the substation monitoring image to be processed to obtain texture features; converts the texture features into the frequency domain space to determine high-frequency component clusters and low-frequency component clusters in the frequency domain space; performs sparse coding on the high-frequency component clusters and the low-frequency component clusters respectively to obtain a high-frequency sparse coding array and a low-frequency sparse coding matrix; projects the high-frequency sparse coding array and the low-frequency sparse coding matrix into the rank space to obtain corresponding high-frequency rank vector distribution and low-frequency rank vector distribution; determines and removes the noise in the substation monitoring image to be processed based on the high-frequency rank vector distribution and the low-frequency rank vector distribution.
[0290] The terms "first," "second," "the first," or "the second" used in various embodiments of the present disclosure may modify various components regardless of order and / or importance, but these terms do not limit the corresponding components. The above terms are configured solely for the purpose of distinguishing an element from other elements. For example, a first user device and a second user device represent different user devices, even though both are user devices. For example, a first element may be referred to as a second element, and similarly, a second element may be referred to as a first element without departing from the scope of the present disclosure.
[0291] When one element (for example, a first element) is referred to as being “(operably or communicably) coupled” or “(operably or communicably) coupled to” or “connected to” another element (for example, a second element), it should be understood that the one element is directly connected to the other element or that the one element is indirectly connected to the other element via yet another element (for example, a third element). Conversely, it should be understood that when an element (for example, a first element) is referred to as being “directly connected” or “directly coupled” to another element (the second element), there is no element (for example, a third element) interposed therebetween.
[0292] The above description is merely a preferred embodiment of the present application and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in this application is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but also encompasses other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned inventive concept. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this application.
Claims
1. A method for noise reduction of substation monitoring images, characterized in that: include: Acquire a substation monitoring image to be processed, and perform texture separation on the substation monitoring image to be processed to obtain texture features; Converting the texture features into a frequency domain space to determine a high frequency component cluster and a low frequency component cluster in the frequency domain space; Performing sparse coding on the high-frequency component cluster and the low-frequency component cluster respectively to obtain a high-frequency sparse coding array and a low-frequency sparse coding matrix; Projecting the high-frequency sparse coding array and the low-frequency sparse coding matrix into the rank space to obtain corresponding high-frequency rank vector distribution and low-frequency rank vector distribution; According to the high-frequency rank vector distribution and the low-frequency rank vector distribution, the noise in the substation monitoring image to be processed is determined and removed.
2. The method according to claim 1, characterized in that The step of performing texture separation on the substation monitoring image to be processed to obtain texture features includes: Obtaining the R channel value, G channel value, and B channel value of each pixel on the substation monitoring image to be processed; Convert the R channel value, the G channel value, and the B channel value into a brightness channel value and a color difference channel value; According to the brightness channel values and the color difference channel values corresponding to all pixels, texture separation is performed on the substation monitoring image to be processed to obtain texture features.
3. The method according to claim 1, characterized in that The method further comprises: Constructing a filter, the filter comprising a conversion module, a high-frequency filtering module and a low-frequency filtering module, wherein the conversion module is cascaded with the high-frequency filtering module and the low-frequency filtering module respectively; The step of converting the texture features into a frequency domain space to determine a high frequency component cluster and a low frequency component cluster in the frequency domain space comprises: Inputting the texture features into the conversion module, converting the texture features into frequency domain signals and inputting the signals into the high frequency filtering module and the low frequency filtering module; The high-frequency filtering module extracts all high-frequency components in the frequency domain signal to form the high-frequency component cluster; The low-frequency filtering module extracts all low-frequency components in the frequency domain signal to form the low-frequency component cluster.
4. The method according to claim 3, characterized in that The high-frequency filtering module extracts all high-frequency components in the frequency domain signal to form the high-frequency component cluster, including: The high-frequency filtering module divides the frequency domain signal into spatial frequency distribution and calculates the entropy of each spatial frequency distribution area to extract the frequency domain signal covered by the spatial frequency distribution area when the entropy is greater than the set entropy threshold to form the high-frequency component cluster.
5. The method according to claim 3, characterized in that: The low-frequency filtering module extracts all low-frequency components in the frequency domain signal to form the low-frequency component cluster, including: The low-frequency filtering module divides the frequency domain signal into spatial frequency distribution and calculates the entropy of each spatial frequency distribution area to extract the frequency domain signal covered by the spatial frequency distribution area when the entropy is less than the set entropy threshold to form the low-frequency component cluster.
6. The method according to any one of claims 1 to 5, characterized in that: The sparse coding of the high-frequency component cluster and the low-frequency component cluster is performed respectively to obtain a high-frequency sparse coding array and a low-frequency sparse coding matrix, including: Vectorizing the high-frequency component cluster and the low-frequency component cluster respectively to obtain corresponding high-frequency component vectors and low-frequency component vectors; Based on the linear combination vector of the set basis function, the high-frequency component vector and the low-frequency component vector are sparsely encoded respectively to obtain a high-frequency sparse coding array and a low-frequency sparse coding matrix.
7. The method according to claim 6, characterized in that The projecting the high-frequency sparse coding array and the low-frequency sparse coding matrix into the rank space to obtain the corresponding high-frequency rank vector distribution and low-frequency rank vector distribution includes: Projecting the high-frequency sparse coding array and the low-frequency sparse coding matrix into the rank space to obtain a corresponding high-frequency rank tensor and a low-frequency rank tensor; According to the high-frequency rank tensor and the low-frequency rank tensor, the high-frequency rank vector distribution and the low-frequency rank vector distribution are statistically analyzed.
8. The method according to claim 7, characterized in that The step of determining and removing noise in the substation monitoring image to be processed according to the high-frequency rank vector distribution and the low-frequency rank vector distribution includes: Projecting the high-frequency rank vector distribution and the low-frequency rank vector distribution into Gaussian space to obtain corresponding Gaussian distribution; The maximum likelihood estimation value of the Gaussian distribution corresponding to the high-frequency rank vector distribution and the low-frequency rank vector distribution is determined, and compared with the set maximum likelihood threshold to determine and remove the noise in the substation monitoring image to be processed.
9. A substation monitoring image noise reduction device, characterized in that: include: A texture separation unit, used for acquiring a substation monitoring image to be processed, and performing texture separation on the substation monitoring image to be processed to obtain texture features; A texture conversion unit, used for converting the texture feature into a frequency domain space to determine a high frequency component cluster and a low frequency component cluster in the frequency domain space; A sparse coding unit, used to perform sparse coding on the high-frequency component cluster and the low-frequency component cluster respectively to obtain a high-frequency sparse coding array and a low-frequency sparse coding matrix; A projection unit, used to project the high-frequency sparse coding array and the low-frequency sparse coding matrix into a rank space to obtain a corresponding high-frequency rank vector distribution and a low-frequency rank vector distribution; The noise removal unit is used to determine and remove the noise in the substation monitoring image to be processed according to the high-frequency rank vector distribution and the low-frequency rank vector distribution.
10. An electronic device, characterized in that: include: one or more processors; A computer readable medium configured to store one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 8.
Citation Information
Patent Citations
Multi-scale combined wavelet image denoising method
CN110349101A
Method and system for automatically selecting optimal wavelet denoising parameter
CN117093833A
Video denoising method
WO2018227881A1
