Image adjusting method, system and device for dynamic signal loop-out optimization

Abstract

The invention relates to the technical field of image processing, and provides an image adjustment method, system and device for dynamic signal loop optimization, and the method comprises the steps: carrying out the feature extraction of an input image, and obtaining a signal change region distribution diagram; separating a candidate region image of the dynamic signal from the signal change region graph; judging the authenticity of the candidate area image according to the spatial consistency index and the accuracy index; carrying out clustering processing on the candidate area images which are judged to be true to obtain a core area image with changed signals; analyzing the dynamic signal continuity of the core image to obtain a continuous dynamic signal area image; and de-noising the continuous dynamic signal region image to obtain a dynamic signal feature map. According to the invention, the stability and accuracy of dynamic signal extraction in different scenes can be ensured.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, and in particular to an image adjustment method, system, and apparatus for dynamic signal loop-out optimization. Background Technology

[0002] In the field of modern image processing and signal optimization, the accurate extraction and adjustment of dynamic signals is a crucial technology, especially in applications with irreplaceable value in complex environments. Research in this area directly relates to the accuracy of signal recognition and the adaptability of systems, and has a profound impact on improving the performance of various image-related technologies. However, many current solutions often struggle to effectively distinguish between real signals and background interference when facing complex scenes, resulting in poor optimization performance. This is particularly true in environments with frequent signal changes or strong background noise, where signal features are often masked by noise, making it impossible to accurately extract dynamic signals. Therefore, ensuring the stability and accuracy of dynamic signal extraction in different scenarios is an important issue that the industry urgently needs to address. Summary of the Invention

[0003] In view of this, embodiments of this specification provide an image adjustment method for dynamic signal loop-out optimization. One or more embodiments of this specification also relate to an image adjustment system for dynamic signal loop-out optimization, a computing device, a computer-readable storage medium, and a computer program, to address technical deficiencies in the prior art.

[0004] According to a first aspect of the embodiments of this specification, an image adjustment method for dynamic signal loop-out optimization is provided, comprising: Feature extraction is performed on the input image to obtain a distribution map of signal variation regions; Candidate region images of dynamic signals are separated from the signal change region map; The authenticity of candidate region images is determined based on spatial consistency and accuracy indices; Clustering is performed on candidate region images that are determined to be true to obtain core region images of signal changes; By analyzing the persistence of dynamic signals in the aforementioned core images, images of regions with persistent dynamic signals can be obtained. Denoising is performed on the image of the continuous dynamic signal region to obtain the dynamic signal feature map.

[0005] According to a first aspect of the present invention, the image adjustment method for dynamic signal loop-out optimization further includes: Optimize dynamic signal feature maps: optimize dynamic signal feature maps based on one or more of the following requirements: image quality requirements, noise requirements, consistency requirements, and environmental adaptability requirements.

[0006] According to a first aspect of the invention, the step of optimizing the dynamic signal feature map includes one or more of the following steps: The brightness and contrast of the dynamic signal feature map are optimized based on the brightness threshold and contrast threshold. The dynamic signal feature map is filtered and equalized based on noise intensity and signal distribution uniformity. The image features of dynamic signal feature maps are optimized based on consistency parameter thresholds and environmental adaptability requirements; The image features of the dynamic signal feature map are optimized based on the consistency between the signal distribution characteristics and the preset optimization target.

[0007] According to a first aspect of the present invention, the step of extracting features from the input image to obtain a signal variation region distribution map includes: The input image is decomposed at multiple scales to separate image feature information at different levels and obtain multi-layer image feature maps. Extract the texture features of each image feature map layer, and use the texture features to characterize the signal change features, thereby obtaining multi-layer signal change feature maps; Extract the edge features of each layer of signal change feature map to obtain the boundary of the signal change features, thereby obtaining a multi-layer signal change region map; The signal variation region maps of multiple layers are fused to obtain the signal variation region distribution map.

[0008] According to a first aspect of the present invention, the step of clustering candidate region images determined to be true to obtain core region images of signal changes includes: Extract the boundary features of candidate regions that are determined to be true; Analyze the matching degree between the above boundary features and the signal change region distribution map, and take the real candidate region images with a matching degree higher than the matching degree threshold as potential core region images; Clustering is performed on potential core region images to obtain core region images.

[0009] According to a first aspect of the present invention, the step of analyzing the dynamic signal persistence of the aforementioned core image to obtain a persistent dynamic signal region image includes: Obtain pixel data of the core area image; Analyze the variation trend between adjacent frames by the difference in pixel data between adjacent frames of the core region image; Based on the analysis of the change trends between adjacent frames, motion persistence is obtained to obtain an image of the region with continuous dynamic signal.

[0010] According to a first aspect of the present invention, the step of denoising the image of a continuous dynamic signal region to obtain a dynamic signal feature map includes: Frequency domain transformation is performed on images of regions with continuous dynamic signals to obtain spectral distribution information; By comparing and analyzing the high-frequency and low-frequency components in the spectral distribution information, the frequency bands of background noise interference can be obtained. Frequency domain filtering is performed on the aforementioned background noise interference frequency band to obtain the dynamic signal feature map after noise removal.

[0011] According to a second aspect of the embodiments of this specification, an image adjustment system for dynamic signal loop-out optimization is provided, comprising: The distribution map acquisition module is configured to extract features from the input image to obtain a distribution map of signal change regions. The candidate region image acquisition module is configured to extract candidate region images of dynamic signals from the signal change region map obtained by the distribution map acquisition module. The candidate region authenticity determination module is set to determine the authenticity of the candidate region image obtained by the candidate region image acquisition module based on the spatial consistency index and the accuracy index. The core image acquisition module is configured to perform clustering processing on candidate region images that are determined to be true by the candidate region authenticity determination module to obtain the core region image of signal changes; The dynamic signal region image acquisition module is configured to analyze the dynamic signal persistence of the core image acquired by the core image acquisition module, thereby obtaining a continuous dynamic signal region image; The denoising module is configured to denoise the image of a continuous dynamic signal region to obtain a dynamic signal feature map.

[0012] According to a third aspect of the embodiments of this specification, a computing device is provided, comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions, which, when executed by the processor, implement the steps of the image adjustment method for dynamic signal loop-out optimization described above.

[0013] According to a fourth aspect of the embodiments of this specification, a computer-readable storage medium is provided that stores computer-executable instructions, which, when executed by a processor, implement the steps of the image adjustment method for dynamic signal loop-out optimization described above.

[0014] According to a fifth aspect of the embodiments of this specification, a computer program is provided, wherein when the computer program is executed in a computer, it causes the computer to perform the steps of the image adjustment method for dynamic signal loop-out optimization described above.

[0015] This invention extracts signal variation regions from the signal's graphic features, separates candidate regions from these regions, and determines the authenticity of candidate regions based on spatial consistency and accuracy indices, ensuring the adaptability and accuracy of candidate regions in dynamic environments. It also obtains core regions through clustering and extracts dynamic signal regions from these core regions, guaranteeing accurate identification of dynamic signal regions in different scenarios from multiple perspectives. Furthermore, based on accurate identification of dynamic signal regions, it distinguishes between real dynamic signals and noise through noise reduction processing, fundamentally ensuring the stability and accuracy of dynamic signal recognition in different scenarios. Attached Figure Description

[0016] Figure 1 This is a flowchart illustrating an embodiment of the image adjustment method for dynamic signal loop-out optimization described in this invention; Figure 2 This is a schematic block diagram of an embodiment of the image adjustment system for dynamic signal loop-out optimization described in this invention; Figure 3 This is a schematic block diagram illustrating an embodiment of the electronic device described in this invention. Detailed Implementation

[0017] Many specific details are set forth in the following description to provide a full understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar extensions without departing from the spirit of this specification. Therefore, this specification is not limited to the specific implementations disclosed below.

[0018] It should be understood that although terms such as first, second, step S1, step S2, etc. may be used to describe various information in one or more embodiments of this specification, such information should not be limited to these terms, for example, restrictions on the order.

[0019] In environments with frequent signal changes or strong background noise, signal features are often masked by noise, making it impossible to accurately extract dynamic signals for in-depth analysis. The core challenge lies in accurately capturing the key features of signal changes and making targeted adjustments. First, identifying regions of signal change in an image is a fundamental challenge; without accurately locating these regions, subsequent optimization and adjustments are impossible.

[0020] Figure 1 This is a flowchart illustrating an embodiment of the image adjustment method for dynamic signal loop-out optimization described in this invention, as follows: Figure 1 As shown, the image adjustment method for dynamic signal loop-out optimization includes: Step S1: Extract features from the input image to obtain a distribution map of signal change regions; Step S2: Separate the candidate region image of the dynamic signal from the signal change region map; Step S3: Determine the authenticity of the candidate region image based on the spatial consistency index and the accuracy index. The spatial consistency index includes pixel distribution uniformity and / or noise spatial dispersion. The accuracy index includes one or more of the following: mean signal strength, density resolution, and mean drift. Step S4: Perform clustering processing on the candidate region images that are determined to be true to obtain the core region images of signal changes; Step S5: Analyze the persistence of dynamic signals in the core image above to obtain a persistent dynamic signal region image; Step S6: Denoise the image of the continuous dynamic signal region to obtain the dynamic signal feature map.

[0021] Steps S1-S5 of this invention ensure accurate identification of signal change regions in dynamic signals from multiple aspects, including feature extraction, dynamic signal separation, spatial consistency index and accuracy index discrimination, clustering, and dynamic signal persistence. Then, denoising processing distinguishes dynamic signals from background noise, improving the dynamic signal optimization effect. This invention guarantees the accuracy and adaptability of dynamic signal identification in environments with frequent signal changes or strong background noise from multiple perspectives.

[0022] In an optional embodiment of the present invention, the above-described image adjustment method for dynamic signal loop-out optimization further includes: Step S7: Optimize one or more dynamic signal feature maps based on image quality requirements, noise requirements, consistency requirements, and environmental adaptability requirements.

[0023] The primary technical problem this invention aims to solve is how to accurately identify signal change regions by analyzing image features. To address this problem, in an optional embodiment of this invention, step S1, extracting features from the input image to obtain a signal change region distribution map, includes: Step S11: Perform multi-scale decomposition on the input image to separate image feature information at different levels and obtain multi-layer image feature maps; Step S12: Extract the texture features of each layer of image feature map, and use the texture features to characterize the signal change features, thereby obtaining multi-layer signal change feature maps; Step S13: Extract the edge features of each layer of signal change feature map to obtain the boundary of the signal change features, thereby obtaining a multi-layer signal change region map; Step S14: The multi-layer signal change region map is fused to obtain a signal change region distribution map. For example, the multi-layer signal change region map is weighted and combined to obtain a signal change region distribution map. Preferably, the weight is obtained according to the edge strength of the signal change region map. The greater the edge strength, the greater the weight.

[0024] This invention performs multi-scale decomposition on input image data to obtain image feature information at different levels. For each decomposed feature map, local texture and edge details are extracted to obtain a preliminary signal change region distribution map. Specifically, signal changes are captured through multi-scale decomposition, features characterizing signal changes are obtained through texture feature extraction, and the boundaries of signal changes are obtained through edge feature extraction. These three are combined to obtain the signal change region. Furthermore, this invention uses different weights to weight different layers based on edge intensity, fully considering image information and enhancing the adaptability and accuracy of the signal change region to the environment.

[0025] In a specific embodiment of the present invention, step S1 includes: The input image is a 512x512 pixel grayscale image. First, Discrete Wavelet Transform (DWT) is used with the Daubechies wavelet basis (db4) as the tool to decompose the image into 4 scale layers. Each layer contains low-frequency components (LL) and high-frequency components (LH, HL, HH). The low-frequency components represent the overall structure of the image, while the high-frequency components capture detailed information. After the first layer of decomposition, the size of the low-frequency components is 256x256, and the high-frequency components are also 256x256. This continues until the fourth layer, where the low-frequency components are 64x64. After multi-scale decomposition of the input image, local texture and edge details are extracted for each feature map layer. The Sobel operator is used to perform edge detection on the high-frequency components, and the edge detection results are normalized. The gradient threshold is set to 0.1 to filter out noise effects, and the edge intensity map of each layer is obtained: the average edge intensity of the high-frequency component LH in the first layer is 0.25, indicating that the details of this layer are relatively rich, while the average edge intensity of the fourth layer is only 0.05, indicating fewer details. The edge intensity maps of each layer are weighted and fused, with the weights set in descending order according to the layer: the weight of the first layer is 0.4, the weight of the second layer is 0.3, the weight of the third layer is 0.2, and the weight of the fourth layer is 0.1. The signal change area distribution map is generated by weighted summation.

[0026] This invention forms a complete chain from decomposition to feature extraction and then to distribution map generation through multi-scale decomposition, texture feature extraction and edge feature extraction, ensuring the coherence and accuracy of the technology implementation.

[0027] In one embodiment of the present invention, in step S2, one or more of the following methods can be used to separate candidate region images of dynamic signals from the signal change region map: a threshold-based segmentation method, a region growing-based localization method, a time-frequency analysis and signal decomposition method, and a deep learning method.

[0028] In an optional embodiment of the present invention, step S2 employs an adaptive threshold segmentation method to separate candidate region images of dynamic signals from the signal change region map.

[0029] In an optional embodiment of the present invention, step S2 includes: Image data is obtained from the signal variation region distribution map. An adaptive threshold segmentation method is used to analyze the signal intensity of each pixel in the image to obtain preliminary segmentation candidate regions. Preferably, a segmentation method based on local mean and standard deviation thresholds is used to obtain image data from the signal variation region distribution map.

[0030] In one embodiment of the present invention, step S3, determining the authenticity of the candidate region based on pixel distribution uniformity and signal intensity mean, specifically includes the following steps: Analyze the pixel distribution characteristics of the initial candidate region image to obtain the gray level, distribution uniformity and signal intensity mean of the pixels in the initial candidate region. The distribution uniformity can be one or more of the mean, standard deviation and coefficient of variation of gray level or color components. The threshold is obtained by linearly combining the uniformity of distribution and the mean signal strength. Pixels with gray values ​​higher than the threshold in the initial candidate region are classified into the true candidate region.

[0031] In one specific embodiment, step S3 includes: Construct a neighborhood window centered on each pixel of the initial candidate region image, for example, construct a 5x5 neighborhood window; Analyze the mean and standard deviation of the gray values ​​of the pixels within the neighborhood window, and set the threshold to the mean plus 1.5 times the standard deviation. For example, if the mean gray value of a pixel is 120 and the standard deviation is 20, then the threshold is 120 + 1.5 × 20 = 150. Pixels with gray values ​​higher than a threshold in the initial candidate region are assigned to the true candidate region. For example, pixels with gray values ​​higher than 150 are assigned to the true candidate region.

[0032] This invention uses spatial consistency and accuracy metrics to jointly determine the authenticity of candidate regions. Spatial consistency ensures the stability of candidate region feature matching and compensates for the sensitivity of accuracy metrics to local noise. Accuracy metrics ensure the reliability of candidate regions. This complementarity reduces misclassification and omission of candidate regions in complex scenarios and improves the generalization ability, accuracy and robustness of candidate region detection.

[0033] In an optional embodiment of the present invention, step S4 includes: Extract the boundary features of the candidate region image that is determined to be true. The boundary features include one or more of the following: gradient abrupt change points, boundary point curvature distribution, and boundary orientation. Analyze the matching degree between the above boundary features and the signal change area distribution map, and take the real candidate area images with a matching degree higher than the matching degree threshold as potential core area images. For example, match the signal change area distribution map according to the gradient abrupt change points and boundary direction of the above area contour to obtain the matching degree between the candidate area images and the signal change area distribution map. Take the candidate area images with a matching degree higher than 85% as potential core area images. Clustering (e.g., density clustering) is performed on potential core region images to obtain core region images. For example, using the DBSCAN algorithm, the radius parameter is set to 3 pixels and the minimum number of points is 5. If there is a cluster in a potential core region image, and there are more than 5 high grayscale pixels (grayscale value greater than 150) within a 3-pixel range around its center point, then the center of the cluster is regarded as the signal change core region. For example, in a specific embodiment, the center pixel coordinates of a cluster are (100, 150), and the number of cluster points around it is 8. If the condition is met, it is marked as a core region.

[0034] This invention effectively captures the geometric structure of the core region by matching the boundary features of the candidate region with the signal change area distribution map, reducing missegmentation caused by background interference or local occlusion. It also identifies fake candidate regions and noise interference, improving the authenticity of potential core regions and increasing detection accuracy. Furthermore, this invention combines clustering to adapt to targets of arbitrary shapes and optimizes adaptability in complex scenes, achieving higher robustness and accuracy in signal change recognition.

[0035] This invention extracts candidate and core regions from the signal variation distribution map, which can be further correlated with signal strength analysis. For example, if the average grayscale value of the core region exceeds 180, its priority is increased for subsequent resource allocation in the signal tracking module, ensuring that computing resources are concentrated in high-potential areas, forming a complete logical chain from segmentation to core region localization to priority evaluation. This approach not only improves signal detection accuracy but also optimizes system resource utilization efficiency.

[0036] In an optional embodiment of the present invention, step S5, obtaining the image of the continuous dynamic signal region from the core region image, includes: Obtain pixel data of the core area image; Analyze the variation trend between adjacent frames by the difference in pixel data between adjacent frames of the core region image; Based on the analysis of the change trends between adjacent frames, motion persistence is obtained to obtain an image of the region with continuous dynamic signal.

[0037] This invention analyzes motion persistence by changing trends between adjacent frames, effectively filtering out transient noise and retaining only dynamic signals of continuous motion. It is more adaptable to dynamic adjustments in motion states, avoids false detection and missed detection of motion signals, and avoids repeated calculations on static backgrounds, reducing computational redundancy.

[0038] In one embodiment of the present invention, step S5 includes: Pixel data within the core region of signal change is acquired, and each frame of the image is preprocessed to remove noise interference, resulting in a pre-cleaned pixel dataset. By extracting the data differences between adjacent frames from the initially cleaned pixel dataset, the trend of change between adjacent frames is obtained, and the continuity characteristics of signal changes in each region are determined. Based on the changing trends between adjacent frames, spatiotemporal correlation characteristics are analyzed, and a preset threshold is used to filter the changing trends to determine the region of continuous dynamic signal.

[0039] In one specific embodiment of the present invention, step S5 includes: The input is a continuous video frame sequence with a resolution of 512×512, each frame is a grayscale image with a pixel value range of 0-255 and a frame rate of 30fps; For the core region of signal change, a differential method is used to detect the change region: the pixel difference matrix is ​​analyzed for adjacent frames (t and t+1). , and They are time points and The image pixel matrix, The pixel difference result matrix at time t; set the threshold T=20, generate a binary mask M(t), where pixels with D(t)>T are set to 1, otherwise set to 0, to obtain the core change region; To calculate spatiotemporal correlation features, using pixels within a 3×3 neighborhood, for pixels with a value of 1 in the mask M(t), extract their grayscale value sequence across 5 frames from t-2 to t+2, forming a vector. And calculate the autocorrelation coefficient. ,in and Let V(p) be the mean and standard deviation, and let R(p) be close to 1 to indicate a strong correlation. To analyze the changing trends of adjacent frames, the optical flow algorithm (Farneback method) is used to calculate the optical flow vector field F(t) of the pixels in the core area. The magnitude ||F(t)|| represents the motion intensity. The threshold is set to 0.5 pixels / frame, and the proportion P(t) of pixels with ||F(t)||>0.5 in 3 consecutive frames is obtained. If P(t) > 0.7, then the region is considered to have continuous motion; Determine the characteristics of a continuous dynamic signal, and mark the region where R(p)>0.8 and P(t)>0.7 as the dynamic signal region, and output its coordinate range (e.g., x:100-150, y:200-250). If a region in a frame sequence meets the conditions for 10 frames, it is confirmed as a continuous dynamic signal region.

[0040] This invention forms a logical chain from change detection to dynamic confirmation through differential, optical flow, and autocorrelation analysis, and is applicable to scenarios such as video surveillance.

[0041] The present invention ensures accurate identification of dynamic signal change regions through steps S1-S5. Based on accurate identification, it effectively distinguishes between real dynamic signals and background noise, thereby further improving the optimization effect of dynamic signals.

[0042] In an optional embodiment of the present invention, the method for obtaining the frequency band of background noise interference in step S6 includes: Frequency domain transformation is performed on images of regions with continuous dynamic signals to obtain spectral distribution information; By comparing and analyzing the high-frequency and low-frequency components in the spectral distribution information, the frequency bands of background noise interference can be obtained. Frequency domain filtering is performed on the aforementioned background noise interference frequency band to obtain the dynamic signal feature map after noise removal.

[0043] In one embodiment of the present invention, the method for obtaining the frequency band of background noise interference in step S6 includes: The spectral distribution characteristics of the signal are obtained by applying Fast Fourier Transform to the continuous dynamic signal within the region. High-frequency and low-frequency components are extracted from the spectral distribution characteristics, and their energy ratios are analyzed to obtain the spectral difference distribution. If the proportion of high-frequency components in the spectral difference distribution exceeds a preset threshold, the high-frequency components are marked as the main noise frequency band to determine the high-frequency interference characteristics. Based on the high-frequency interference characteristics, an adaptive filtering algorithm is used to denoise the spectral distribution characteristics to obtain the denoised spectral data. By performing an inverse Fourier transform on the denoised spectral data, the dynamic signal is reconstructed, and the characteristics of the denoised signal are obtained. The time series variation trend is extracted from the characteristics of the denoised signal, and its time-frequency characteristics are analyzed by short-time Fourier transform to obtain the time-frequency distribution characteristics; Based on the time-frequency distribution characteristics, the power spectral density of the main frequency bands is analyzed to determine the stable frequency bands of background noise interference.

[0044] In one specific embodiment of the present invention, the method for obtaining the background noise interference frequency band includes: The acquired signal data was processed using the Fast Fourier Transform (FFT) algorithm. The signal sampling rate was 1000Hz, the acquisition time was 10 seconds, and a total of 10,000 sampling points were obtained. These time-domain data were input into the FFT algorithm to obtain the corresponding spectrum distribution information, where the frequency resolution was 0.1Hz and the spectrum range covered from 0 to 500Hz. Based on the spectral distribution information, the power spectral density of high-frequency components (e.g., 200Hz to 500Hz) and low-frequency components (e.g., 0Hz to 50Hz) was extracted. The total power of the high-frequency components was found to be 15.6 watts, and the total power of the low-frequency components was found to be 5.2 watts. The comparison showed that the power of the high-frequency components was significantly higher than that of the low-frequency components, indicating that there may be strong interference signals in the high-frequency band. Analysis of the power peaks in the spectrum revealed that the main peaks were concentrated around 300Hz, with a power value of 3.8 watts, accounting for 24.4% of the total high-frequency power. Based on the typical characteristics of background noise, the frequency band around 300Hz was determined to be the main frequency band of background noise interference. Signals within the range of 300Hz±10Hz were extracted using a bandpass filter, and their power proportion was analyzed again. It was found that they still dominated, confirming the accuracy of the main interference frequency band. This invention obtains the spectral distribution information of regions with continuous dynamic signal characteristics by performing frequency domain transformation processing. It then compares and analyzes the high-frequency and low-frequency components in the spectrum to determine the main frequency bands of background noise interference. From the time domain to the frequency domain conversion, power comparison analysis to peak location, a complete logical chain is formed to ensure the scientific nature of the interference frequency band determination. At the same time, the results can be applied to the design of subsequent noise suppression algorithms, such as the parameter adjustment of adaptive filters, to improve signal quality.

[0045] In one embodiment of the present invention, step S6, the method for obtaining a noise-removed dynamic signal feature map by performing frequency domain filtering on the frequency band of background noise interference, includes: The main frequency bands of background noise are obtained from the input signal to determine the noise spectrum distribution; The core region of the signal is converted into the frequency domain using a fast Fourier transform to obtain the frequency domain signal; Based on the main frequency band of the background noise, if the frequency of the frequency domain signal is located in the noise band, a band-stop filter is applied for denoising to obtain the denoised frequency domain signal. The denoised frequency domain signal is converted back to the time domain by inverse fast Fourier transform to obtain the denoised time domain signal; Extract signal features from the denoised time-domain signal to generate a signal feature map; According to the signal feature map, if the feature value exceeds the preset threshold, it is determined to be the main component of the real signal and the main component is retained. For the main components that are retained, the final signal feature map is generated, and the denoised signal features are output.

[0046] In one specific embodiment of the present invention, the above-mentioned noise reduction method includes: The input signal was sampled at a frequency of 44100Hz. A 5-second audio signal was collected, with a total of 220500 sampling points. The time-domain signal was converted to the frequency-domain signal using Fast Fourier Transform (FFT) to obtain the spectrum. It was found that the background noise was mainly concentrated in the frequency band of 500Hz to 2000Hz, while the core frequency range of the target signal was 3000Hz to 5000Hz. Through power spectral density analysis, the noise power accounted for about 60% of the total power, and this frequency band noise needs to be suppressed. Design a bandpass filter with a passband range of 2500Hz to 5500Hz and a stopband range of 0Hz to 2000Hz and above 6000Hz. The filter is a Butterworth filter with an order of 6 to ensure a steep transition band. After calculating the filter coefficients, the frequency domain signal is filtered to remove noise frequency bands and retain the main components of the target signal. After filtering, the noise power ratio is reduced to 15%, and the signal fidelity is improved to over 85%. The filtered frequency domain signal was subjected to inverse Fourier transform (IFFT) to restore it to the time domain signal. The short-time energy and zero-crossing rate of the signal were calculated, signal features were extracted, and a denoised signal feature map was generated. The feature map showed that the energy of the core signal was concentrated around 3.5kHz, and the signal change trend on the time axis was consistent with the original signal, which verified the denoising effect. To further optimize, the feature maps can be input into the subsequent machine learning model for signal classification, based on business needs. Assuming the classification task is speech recognition, the energy distribution and temporal characteristics of the feature maps can be used as input features. When training the model, the accuracy increased from 72% before denoising to 88%, demonstrating the positive impact of denoising on subsequent tasks.

[0047] This invention uses frequency domain filtering technology to denoise the core area of ​​signal variation based on the main frequency bands of background noise interference, obtaining a denoised signal feature map while retaining the main components of the real signal. Through the above method, a complete logic chain is formed from frequency domain filtering to feature extraction, ensuring the efficiency and accuracy of signal processing.

[0048] In an optional embodiment of the present invention, step S7, which denoises the image of the continuous dynamic signal region to obtain a dynamic signal feature map, includes one or more of the following steps: The brightness and contrast of the dynamic signal feature map are optimized based on the brightness threshold and contrast threshold. The dynamic signal feature map is filtered and equalized based on noise intensity and signal distribution uniformity. The image features of dynamic signal feature maps are optimized based on consistency parameter thresholds and environmental adaptability requirements; The image features of the dynamic signal feature map are optimized based on the consistency between the signal distribution characteristics and the preset optimization target.

[0049] In one embodiment of the present invention, step S7 includes: acquiring local contrast and brightness distribution information of the denoised dynamic signal feature map, and optimizing and adjusting it by comparing it with a preset threshold. Specifically, this includes: Image segmentation technology is used to divide the feature map of the denoised dynamic signal into regions, perform edge detection, and obtain local contrast. The brightness center value of each region was extracted using statistical analysis methods. Determine whether the local contrast is below the contrast threshold and the center brightness value is below the brightness threshold; If the local contrast is not lower than the contrast threshold, then reduce the local contrast within the contrast adjustment range and return to the step of extracting the brightness center value of each region through statistical analysis. If the local contrast is lower than the contrast threshold but the luminance center value is not lower than the luminance threshold, then increase the local contrast if the local contrast is lower than the contrast threshold but within the contrast adjustment range limit, and return to the step of extracting the luminance center value of each region through statistical analysis.

[0050] In one specific embodiment of the present invention, step S7 includes: The Laplacian operator is used to perform edge detection on the signal feature map. The gray-level gradient value in the 3x3 area around each pixel is calculated to obtain a local contrast map. The contrast value range is set to 0 to 1, and it is assumed that the average contrast value of a certain area is 0.3. The brightness distribution is statistically analyzed using grayscale histograms. The brightness value range is set to 0 to 255, and the pixel percentage of each brightness range is calculated. For example, it is found that the pixel percentage of brightness values ​​between 100 and 150 is 40%.

[0051] Next, the local contrast and brightness distribution information are compared with the preset signal strength threshold. Assuming the preset contrast threshold is 0.5 and the brightness center value threshold is 120, if the contrast of a certain area is lower than 0.5 and the brightness center value deviates from 120 by more than 20, it is marked as an area that needs optimization. For example, if the contrast of a certain area is 0.3 and the brightness center value is 90, it is determined that it needs to be adjusted. For the marked region, an adaptive histogram equalization algorithm (CLAHE) is used for optimization, limiting the contrast enhancement to 2.0 to ensure that it is not over-enhanced. At the same time, the contrast change before and after optimization is recorded, such as from 0.3 to 0.48, and the brightness center value is analyzed to see if it is close to 120. If it still deviates, the parameters are further adjusted according to business requirements (such as the signal recognition accuracy needing to reach 90%), forming a closed-loop optimization logic to ensure that the signal feature map meets the recognition requirements in subsequent processing.

[0052] This invention optimizes dynamic signal feature maps based on brightness and contrast thresholds, and significantly improves the robustness and accuracy of feature extraction by dynamically adapting to changes in signal characteristics and scene.

[0053] In one embodiment of the present invention, step S7 includes: A local enhancement algorithm is used to process the signal feature map to obtain enhanced image data. Edge details in the enhanced region are then smoothed to obtain the final optimized signal distribution map. Specifically, this includes: By analyzing the feature map of the dynamic signal, a preset region division method is used to identify the region range that needs to be optimized, and preliminary region division data is obtained. Based on the initially divided regional data, a local enhancement algorithm is used to process specific regions to improve the clarity of the image data and obtain the enhanced image content; For the enhanced image content, the edge details are identified, and the edge details are adjusted through a smoothing operation to generate smoothed image data; If noise interference still exists in the smoothed image data, a preset threshold is used to determine the noise intensity and obtain the image result after noise filtering. Based on the image results after noise filtering, the uniformity of signal distribution is detected. If the uniformity is lower than the preset standard, the distribution is optimized through local adjustment methods to obtain the adjusted distribution data. By adjusting the distribution data, a final optimized signal distribution map is generated, and the complete representation of signal characteristics is determined. A comparative analysis method is used to verify the difference between the final optimized signal distribution map and the original signal feature map, and to determine whether the optimization effect meets the preset requirements.

[0054] In one specific embodiment of the present invention, step S7 includes: The regions that need enhancement are identified. Assume that the input signal feature map is a two-dimensional grayscale image with a size of 512×512 pixels and a grayscale value range of 0-255. A local contrast enhancement algorithm is adopted, using adaptive histogram equalization (AHE), setting the window size to 32×32 pixels, and limiting the contrast enhancement factor to 0.1 to avoid excessive amplification of noise; Calculate the local histogram for each pixel, redistribute gray values, and generate an enhanced feature map. The signal strength in the enhanced region is increased by about 20%. For example, a pixel with an original gray value of 100 may be increased to 120. To enhance edge details in the region, a Gaussian smoothing filter is used with a kernel size of 5×5 and a standard deviation σ=1.0. The weighted average value of each pixel is calculated to smooth jagged edges and preserve key features. Analyzing the image after Gaussian filtering, the gradient value in the edge region is reduced by about 15%, such as the original gradient value of 50 being reduced to 42.5, ensuring that the edges are smooth but not excessively blurred; An optimized signal distribution map is generated, and the global signal uniformity is calculated. The standard deviation is used for evaluation. The original standard deviation is 25, which is reduced to 18 after optimization, indicating that the signal distribution is more uniform.

[0055] The optimization process described above in this invention can be achieved through matrix operations. It is an automatic process that requires no manual intervention. The processing logic for enhancing regions and smoothing edges ensures the prominence of signal features and the smoothness of their distribution, making it suitable for subsequent signal analysis tasks.

[0056] In one embodiment of the present invention, step S7 includes: For the final optimized signal distribution map, its overall consistency parameters are obtained. By comparing them with preset consistency standards, it is determined whether the optimization result meets the environmental adaptability requirements. Specifically, this includes: By performing preliminary processing on the signal distribution data, its distribution characteristic information is obtained, and a preliminary distribution characteristic description is obtained. Based on the distribution characteristics, statistical analysis methods are used to extract the overall consistency parameter and determine the quantitative value of the consistency parameter. The quantified value of the consistency parameter is compared with the preset standard. If the quantified value exceeds the threshold range of the preset standard, it is determined to be inconsistent, and a preliminary judgment conclusion is obtained. By further verifying the preliminary judgment conclusions with data, we can obtain data characteristics related to environmental adaptation and determine the basis for environmental adaptation assessment. Based on the environmental adaptability assessment criteria, a logistic regression model is used to analyze the matching degree between signal distribution and environmental requirements to determine whether the matching degree meets the adaptation requirements. If the matching degree does not meet the requirements, the new distribution feature data can be obtained by adjusting the parameter configuration of the signal distribution, and the optimized distribution adjustment scheme can be determined. For the optimized distribution adjustment scheme, the consistency parameters are repeatedly compared with the preset standards to obtain the final judgment result and determine whether it meets the requirements of overall consistency and environmental adaptability.

[0057] In one specific embodiment of the present invention, step S7 includes: The data of an optimized signal distribution map is stored in the form of a two-dimensional matrix with a size of 100x100. Each element represents a signal strength value, ranging from 0 to 1.

[0058] To analyze the overall consistency parameters, the standard deviation is used as a metric. Specifically, all elements in the matrix are traversed to obtain the average signal strength, for example, the average is 0.65. Then, the sum of squares of the differences between each element and the average is analyzed, and the square root is taken to obtain the standard deviation, for example, the standard deviation is 0.12. The smaller the standard deviation, the higher the consistency. The consistency parameter is compared with the preset consistency standard. For example, if the standard value is 0.15, and the standard deviation obtained above is less than or equal to the standard value, then the consistency is considered to meet the requirements; otherwise, it does not meet the requirements. By comparison, 0.12 is less than 0.15, indicating that the consistency parameter meets the standard. To determine whether the optimization results meet the environmental adaptability requirements, the standard deviation is used as a metric. If the standard deviation of consistency is less than the environmental noise threshold, the optimization results are considered to meet the environmental requirements. For example, if the environmental noise threshold is 0.13 and the standard deviation is 0.12, which is less than 0.13, the optimization results meet the environmental adaptability requirements. If the optimization results do not meet the consistency parameter requirements and / or environmental requirements, further business requirements can be considered, such as adjusting the weights of each layer in the multi-scale decomposition process, obtaining the signal change region distribution map matrix again, and performing consistency analysis again to ensure that the final results meet environmental requirements.

[0059] This invention forms a complete technical processing chain from data acquisition and parameter calculation to result judgment, all of which rely on information technology to achieve automated analysis.

[0060] In one embodiment of the present invention, step S7 includes: Based on the degree of conformity of the optimization results, the signal distribution map is iteratively adjusted to obtain the final adjusted image data. By analyzing the characteristics of the adjusted data, the final output result of the dynamic signal optimization is determined, specifically including: By using a pre-defined signal distribution model, the signal distribution characteristics are obtained from the input signal, and statistical analysis methods are used to obtain the distribution characteristic evaluation results. If the deviation between the distribution characteristic evaluation result and the preset optimization target exceeds the threshold, the signal distribution parameters are adjusted by the gradient descent algorithm to obtain the adjusted signal distribution characteristics. Based on the adjusted signal distribution characteristics, a convolutional neural network is used to generate the adjusted image, thus obtaining the adjusted image data. The frequency characteristics of the adjusted image data are analyzed using Fourier transform to obtain the image data characteristics. If the dynamic range of the image data characteristics is lower than a preset threshold, adaptive filtering is used to adjust the image data to obtain optimized image data characteristics. Based on the optimized image data characteristics, a decision tree algorithm is used to determine the optimized dynamic signal output, resulting in the final optimized signal output.

[0061] In one specific embodiment of the present invention, step S7 includes: The initial signal distribution data is evaluated for compliance. The signal strength values ​​of the initial distribution map range from 0 to 100. The compliance threshold is set to 80. The mean square error algorithm is used to calculate the deviation value of each signal point. For example, if the actual value of a point is 75 and the target value is 85, the deviation is 10. The adjusted value is obtained by iteratively adjusting the formula: new value = old value + deviation * 0.5. In the iterative adjustment phase, the gradient descent algorithm is used to optimize the distribution map. The learning rate is set to 0.01 and the number of iterations is 100. After each iteration, the intensity distribution of the signal points is recalculated to ensure that the variance of the overall distribution is reduced from the initial 15.3 to below the target of 5.2. The final adjusted image data is stored in matrix form, such as a 100x100 two-dimensional array, where each element represents the signal intensity. The characteristics of the adjusted data were analyzed, and the mean and standard deviation of the signal strength were calculated through statistical analysis. For example, the mean was 82.5 and the standard deviation was 4.8. Combined with spectrum analysis tools to extract the main frequency components, it was found that the main frequency was concentrated at 2.5Hz, indicating that the signal stability was enhanced. To determine the final output of dynamic signal optimization, based on the above characteristic analysis, the optimization target is set as a 20% improvement in signal stability. By comparing the data before and after adjustment, the stability improvement ratio is calculated to be 22.3%, which exceeds the target value. Therefore, the final optimization result is the adjusted signal distribution matrix, and an optimization report is generated, including mean, standard deviation, and main frequency data.

[0062] Preferably, the signal optimization results are also combined with subsequent business scenarios. For example, the optimized signal data is input into the communication system simulation module. The image processing method of this application reduces the bit error rate in the actual transmission of communication signals by 15%, from 0.05 to 0.0425, demonstrating the effectiveness of the invention in practical applications.

[0063] The optimization method described above in this invention forms a complete technical processing flow from data evaluation to final output.

[0064] Figure 2 This is a schematic block diagram of an embodiment of the image adjustment system for dynamic signal loop-out optimization described in this invention, as shown below. Figure 2 As shown, the image adjustment system for dynamic signal loop-out optimization includes: Distribution map acquisition module 1 is configured to extract features from the input image to obtain a distribution map of signal change regions. Candidate region image acquisition module 2 is configured to extract candidate region images of dynamic signals from the signal change region map obtained by distribution map acquisition module 1. Candidate region authenticity determination module 3 is configured to determine the authenticity of the candidate region image obtained by candidate region image acquisition module 2 based on spatial consistency index and accuracy index; The core image acquisition module 4 is configured to perform clustering processing on the candidate region images that are determined to be true by the candidate region authenticity determination module 3 to obtain the core region image of signal changes. The dynamic signal region image acquisition module 5 is configured to analyze the dynamic signal persistence of the core image acquired by the core image acquisition module 4, thereby obtaining a continuous dynamic signal region image. The denoising module 6 is configured to denoise the continuous dynamic signal region image acquired by the dynamic signal region image acquisition module 5 to obtain a dynamic signal feature map.

[0065] In a preferred embodiment of the present invention, the image adjustment system for dynamic signal loop-out optimization further includes an optimization module 7, which is configured to optimize the dynamic signal feature map obtained by the denoising processing module 6: one or more optimized dynamic signal feature maps based on image quality requirements, noise requirements, consistency requirements and environmental adaptability requirements.

[0066] Figure 3 This is a schematic block diagram illustrating an embodiment of the electronic device described in this invention, as shown below. Figure 3 As shown, the components of the computing device 100 include, but are not limited to, a memory 110 and a processor 120. The processor 120 is connected to the memory 110 via a bus 130, and the database 150 is used to store data.

[0067] The computing device 100 also includes an access device 140, which enables the computing device 100 to communicate via one or more networks 160. Examples of these networks include Public Switched Telephone Network (PSTN), Local Area Network (LAN), Wide Area Network (WAN), Personal Area Network (PAN), or combinations of communication networks such as the Internet. The access device 540 may include one or more of any type of wired or wireless network interface (e.g., a network interface card (NIC)), such as an IEEE 802.11 Wireless Local Area Network (WLAN) wireless interface, a Wi-MAX (Worldwide Interoperability for Microwave Access) interface, an Ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a Bluetooth interface, or a Near Field Communication (NFC) interface.

[0068] In one embodiment of this specification, the aforementioned components of the computing device 100 and Figure 3 Other components, not shown, can also be connected to each other, for example, via a bus. It should be understood that... Figure 3 The block diagram of the computing device shown is for illustrative purposes only and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0069] The computing device 100 can be any type of stationary or mobile computing device, including mobile computers or mobile computing devices (e.g., tablet computers, personal digital assistants, laptop computers, notebook computers, netbooks, etc.), mobile phones (e.g., smartphones), wearable computing devices (e.g., smartwatches, smart glasses, etc.) or other types of mobile devices, or stationary computing devices such as desktop computers or personal computers (PCs). The computing device 100 can also be a mobile or stationary server.

[0070] The processor 120 executes computer-executable instructions, which, when executed by the processor, implement the steps of the aforementioned intelligent traffic control method. The above is an illustrative scheme of a computing device according to this embodiment. It should be noted that the technical solution of this computing device and the technical solution of the aforementioned image adjustment method for dynamic signal loop-out optimization belong to the same concept. Details not described in detail in the technical solution of the computing device can be found in the description of the technical solution of the aforementioned intelligent traffic control method.

[0071] It should be noted that the aforementioned computing device 100 can be either hardware or software. When the computing device 100 is hardware, it can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or as a single server or a single terminal device. When the computing device 100 is software, it can be installed in the hardware devices listed above. It can be implemented as, for example, multiple software programs or software modules used to provide distributed services, or as a single software program or software module. No specific limitations are made here.

[0072] An embodiment of this specification also provides a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the image adjustment method for dynamic signal loop-out optimization described above.

[0073] The above is an illustrative scheme of a computer-readable storage medium according to this embodiment. It should be noted that the technical solution of this storage medium belongs to the same concept as the technical solution of the image adjustment method for dynamic signal loop-out optimization described above. For details not described in detail in the technical solution of the storage medium, please refer to the description of the technical solution of the intelligent traffic control method described above.

[0074] An embodiment of this specification also provides a computer program, wherein when the computer program is executed in a computer, it causes the computer to perform the steps of the image adjustment method for dynamic signal loop-out optimization described above.

[0075] The above is an illustrative example of a computer program in this embodiment. It should be noted that the technical solution of this computer program belongs to the same concept as the technical solution of the image adjustment method for dynamic signal loop-out optimization described above. Details not described in detail in the computer program's technical solution can be found in the description of the technical solution of the intelligent traffic control method described above.

[0076] The foregoing has described specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired result. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired result. In some embodiments, multitasking and parallel processing are possible or may be advantageous.

[0077] The computer instructions include computer program code, which may be in the form of source code, object code, executable file, or certain intermediate forms. The computer-readable medium may include any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium may be appropriately added to or subtracted according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media may not include electrical carrier signals and telecommunication signals.

[0078] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the embodiments in this specification are not limited to the described order of actions, because according to the embodiments in this specification, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in this specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to the embodiments in this specification.

[0079] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0080] The preferred embodiments disclosed above are merely illustrative of this specification. The optional embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the embodiments described herein. These embodiments are selected and specifically described in this specification to better explain the principles and practical applications of the embodiments, thereby enabling those skilled in the art to better understand and utilize this specification. This specification is limited only by the claims and their full scope and equivalents.

Claims

1. An image adjustment method for dynamic signal loop-out optimization, characterized in that, include: Feature extraction is performed on the input image to obtain a distribution map of signal variation regions; Candidate region images of dynamic signals are separated from the signal change region map; The authenticity of candidate region images is determined based on spatial consistency and accuracy indices; Clustering is performed on candidate region images that are determined to be true to obtain core region images of signal changes; By analyzing the persistence of dynamic signals in the aforementioned core images, images of regions with persistent dynamic signals can be obtained. Denoising is performed on the image of the continuous dynamic signal region to obtain the dynamic signal feature map.

2. The image adjustment method for dynamic signal loop-out optimization according to claim 1, characterized in that, Also includes: Optimize dynamic signal feature maps: optimize dynamic signal feature maps based on one or more of the following requirements: image quality requirements, noise requirements, consistency requirements, and environmental adaptability requirements.

3. The image adjustment method for dynamic signal loop-out optimization according to claim 2, characterized in that, The step of optimizing the dynamic signal feature map includes one or more of the following steps: The brightness and contrast of the dynamic signal feature map are optimized based on the brightness threshold and contrast threshold. The dynamic signal feature map is filtered and equalized based on noise intensity and signal distribution uniformity. The image features of dynamic signal feature maps are optimized based on consistency parameter thresholds and environmental adaptability requirements; The image features of the dynamic signal feature map are optimized based on the consistency between the signal distribution characteristics and the preset optimization target.

4. The image adjustment method for dynamic signal loop-out optimization according to claim 1, characterized in that, The step of extracting features from the input image to obtain a signal change region distribution map includes: The input image is decomposed at multiple scales to separate image feature information at different levels and obtain multi-layer image feature maps. Extract the texture features of each image feature map layer, and use the texture features to characterize the signal change features, thereby obtaining multi-layer signal change feature maps; Extract the edge features of each layer of signal change feature map to obtain the boundary of the signal change features, thereby obtaining a multi-layer signal change region map; The signal variation region maps of multiple layers are fused to obtain the signal variation region distribution map.

5. The image adjustment method for dynamic signal loop-out optimization according to claim 1, characterized in that, The step of clustering candidate region images that are determined to be true to obtain core region images of signal changes includes: Extract the boundary features of candidate regions that are determined to be true; Analyze the matching degree between the above boundary features and the signal change region distribution map, and take the real candidate region images with a matching degree higher than the matching degree threshold as potential core region images; Clustering is performed on potential core region images to obtain core region images.

6. The image adjustment method for dynamic signal loop-out optimization according to claim 1, characterized in that, The step of analyzing the dynamic signal persistence of the core image to obtain a persistent dynamic signal region image includes: Obtain pixel data of the core area image; Analyze the variation trend between adjacent frames by the difference in pixel data between adjacent frames of the core region image; Based on the analysis of the change trends between adjacent frames, motion persistence is obtained to obtain an image of the region with continuous dynamic signal.

7. The image adjustment method for dynamic signal loop-out optimization according to claim 1, characterized in that, The step of denoising the image of the continuous dynamic signal region to obtain the dynamic signal feature map includes: Frequency domain transformation is performed on images of regions with continuous dynamic signals to obtain spectral distribution information; By comparing and analyzing the high-frequency and low-frequency components in the spectral distribution information, the frequency bands of background noise interference can be obtained. Frequency domain filtering is performed on the aforementioned background noise interference frequency band to obtain the dynamic signal feature map after noise removal.

8. An image adjustment system for dynamic signal loop-out optimization, characterized in that, include: The distribution map acquisition module is configured to extract features from the input image to obtain a distribution map of signal change regions. The candidate region image acquisition module is configured to extract candidate region images of dynamic signals from the signal change region map obtained by the distribution map acquisition module. The candidate region authenticity determination module is set to determine the authenticity of the candidate region image obtained by the candidate region image acquisition module based on the spatial consistency index and the accuracy index. The core image acquisition module is configured to perform clustering processing on candidate region images that are determined to be true by the candidate region authenticity determination module to obtain the core region image of signal changes; The dynamic signal region image acquisition module is configured to analyze the dynamic signal persistence of the core image acquired by the core image acquisition module, thereby obtaining a continuous dynamic signal region image; The denoising module is configured to denoise the image of a continuous dynamic signal region to obtain a dynamic signal feature map.

9. A computing device, characterized in that, include: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions, which, when executed by the processor, implement the steps of the image adjustment method for dynamic signal loop-out optimization as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the image adjustment method for dynamic signal loop-out optimization as described in any one of claims 1 to 7.

Images