A method for evaluating shear zone quality in dangerous rock mass based on machine vision

Abstract

The application discloses a dangerous rock mass shear zone quality evaluation method based on machine vision, and relates to the technical field of dangerous rock mass monitoring and evaluation, and comprises the following steps: S1, arranging a high-resolution camera, adjusting the angle and focal length, regularly automatically collecting and transmitting image data to a server; S2, using a filter to denoise, adjusting the contrast and histogram equalization, and enhancing the image definition; S3, applying edge detection and feature point detection algorithms to extract key features and cover key areas; applying Canny edge detection and SIFT algorithms for feature extraction, using a convolutional neural network (CNN) for model training and cross-validation, real-time monitoring of shear zone changes and triggering of early warning, displaying analysis results through a heat map and other visualization tools and generating a standardized report, ensuring the standardization and consistency of the monitoring results, thereby improving the efficiency and accuracy of dangerous rock mass shear zone monitoring and effectively preventing geological disaster risks.

Description

Technical Field

[0001] The present invention relates to the technical field of dangerous rock mass monitoring and evaluation, and in particular to a dangerous rock mass shear zone quality evaluation method based on machine vision. Background Art

[0002] In the field of geological disaster prevention and control, dangerous rock masses refer to those whose structures have become loose, cracked, or imminently unstable and collapsed due to natural factors or human activities. The existence of dangerous rock masses poses a significant threat to human life and property, and therefore their monitoring and assessment has always been a key focus of geological disaster prevention and control. Traditional methods for monitoring dangerous rock masses rely primarily on manual observation and on-site testing, which is not only labor-intensive and inefficient, but also highly subjective and difficult to achieve continuous, real-time monitoring.

[0003] In recent years, with the rapid development of image processing and artificial intelligence technologies, machine vision-based monitoring methods have been widely applied in various fields. Machine vision technology uses cameras to capture image data and utilizes image processing algorithms for feature extraction and analysis, enabling efficient and accurate monitoring and assessment. In the monitoring of dangerous rock masses, machine vision technology can overcome the shortcomings of traditional methods. Through high-resolution cameras and intelligent analysis systems, it enables continuous, real-time monitoring of dangerous rock masses. Shear zones in dangerous rock masses are the most vulnerable to damage, and their quality is directly related to their stability. Shear zones are fractured or fractured zones formed within the rock mass due to shear stress. They are typically characterized by dense cracks, dispersed rock blocks, and a loose structure. Accurate quality assessment of shear zones in dangerous rock masses can promptly identify potential hazards and enable effective preventive measures to avert disasters.

[0004] Traditional methods for assessing the quality of shear zones in dangerous rock masses rely primarily on field surveys and laboratory testing. Field surveys require specialized personnel working at height, which carries certain safety risks; laboratory testing, on the other hand, requires sampling, a complex and time-consuming process. With the advancement of technology, shear zone quality assessment methods based on machine vision and artificial intelligence are gaining increasing attention. These methods capture shear zone images using cameras and utilize image processing and machine learning techniques for analysis and evaluation. This not only improves work efficiency but also ensures the objectivity and accuracy of monitoring results.

[0005] Currently, research has attempted to apply machine vision technology to the monitoring of dangerous rock masses. By detecting and analyzing surface features such as cracks and displacements, automated monitoring of dangerous rock masses has been initially achieved. However, these studies mostly focus on monitoring the rock surface, and their analysis of internal structural changes, particularly the quality assessment of shear zones, remains limited. Furthermore, due to the influence of external factors such as topography and lighting, machine vision technology faces numerous challenges in practical application, such as unstable image quality and difficulty in feature extraction. Therefore, a more comprehensive technical solution is urgently needed that can integrate machine vision and artificial intelligence technologies to conduct comprehensive and accurate quality assessments of shear zones in dangerous rock masses. Summary of the Invention

[0006] The present invention provides a method for evaluating the quality of shear zones in dangerous rock masses based on machine vision. The method comprises the following steps: arranging high-resolution cameras for image acquisition, using Gaussian filtering, histogram equalization and other technologies for image preprocessing, applying Canny edge detection and SIFT algorithm for feature extraction, adopting convolutional neural network (CNN) for model training and cross-validation, performing image segmentation and structural analysis, realizing intelligent evaluation of shear zone quality and risk identification, monitoring shear zone changes in real time and triggering early warnings, displaying analysis results through visualization tools such as heat maps and generating standardized reports, ensuring the standardization and consistency of monitoring results, thereby improving the efficiency and accuracy of shear zone monitoring in dangerous rock masses and effectively preventing geological disaster risks.

[0007] In order to achieve the above object, the present invention provides the following technical solution: a method for evaluating the quality of shear zones in dangerous rock masses based on machine vision, comprising the following steps:

[0008] S1. Arrange high-resolution cameras, adjust angles and focal lengths, and automatically collect and transmit image data to the server regularly;

[0009] S2, use filters to remove noise, adjust contrast and histogram equalization to enhance image clarity;

[0010] S3, apply edge detection and feature point detection algorithms to extract key features and cover key areas;

[0011] S4. Label the data and select a training model, using cross-validation to improve classification and segmentation accuracy;

[0012] S5, segment the image, analyze the structural characteristics of the shear band, assess the quality, and identify potential risk areas;

[0013] S6. Collect and analyze data in real time, identify shear zone changes, establish an early warning system, and promptly alert risks;

[0014] S7. Visualize the analysis results, generate standardized assessment reports regularly, and record the changes in shear bands.

[0015] Preferably, in step S1, a high-resolution camera is arranged in the shear zone area of ​​the dangerous rock mass, and the angle and focal length are adjusted to ensure a clear and complete image is obtained. Image data is regularly collected using automated acquisition software and transmitted to a central server via a network to ensure data continuity and integrity: ,in, For the The time of collection, is the initial acquisition time, is the collection interval time, For the Collection times.

[0016] Preferably, in step S2, the collected image is subjected to denoising processing, a Gaussian filter is used to reduce noise, the filter parameters are adjusted to balance the denoising effect and image detail retention, and contrast adjustment and histogram equalization techniques are used to enhance image clarity to ensure that key features are clearly visible: ,in, The Gaussian function value at position (x,y), is the standard deviation, which determines the width of the filter, The coordinates of the pixel; the histogram equalization technology is specifically manifested as: ,in, is the equalization value corresponding to the pixel value v, is the grayscale level, are the width and height of the image, is the number of pixels at gray level i.

[0017] Preferably, in step S3, the Canny edge detection algorithm is used to extract the edge features of the shear band in the image, and the detection threshold is adjusted to ensure accurate extraction; the SIFT algorithm is applied to extract the key feature points of the shear band, and the distribution and density of the feature points are evaluated to ensure coverage of the key area: the Canny edge detection formula is: ,in, is the edge detection result, Gaussian filter, is the input image, is a convolution operation; the SIFT key point descriptor is: ,in, is the feature point descriptor, is the first feature point vector A quantity, is the dimension of the feature point vector.

[0018] Preferably, in step S4, the image data is annotated to mark the cracks and rock blocks in the shear zone; a convolutional neural network (CNN) is selected for training, the performance of different models is evaluated, the optimal model is selected, the model is trained using the training data set, the model parameters are adjusted to improve the classification and segmentation accuracy, and the model performance is evaluated using cross-validation and test sets. The convolution operation: ,in, For output image at position The value of is the input image, is the convolution kernel, are the coordinates of the convolution kernel.

[0019] Preferably, in step S5, the trained model is used to segment the image, identify different parts of the shear zone, and evaluate the accuracy and completeness of the segmentation results; the structural characteristics of the shear zone are analyzed, and its integrity and stability are evaluated by combining geological knowledge and shear zone characteristics. The quality of the shear zone is comprehensively evaluated based on the structural analysis results, and potential risk areas are identified. Standardized evaluation indicators are used to ensure the objectivity and consistency of the results; fully connected layer: ,in, For output, weight matrix, is the input feature, Bias term; shear band quality score: ,in, Shear band quality score, Weight coefficient, Structural stability score, Crack density score, Score the rock size, Shear zone opening score, Score the shear band length, Score the shear band interface relief, Shear zone filling fragmentation score.

[0020] Preferably, in step S6, the image data of the shear band is collected in real time by a camera to ensure the timeliness and integrity of the data; the real-time data is analyzed using a trained model to identify changes in the shear band; an early warning system is established to issue an early warning signal based on the analysis results to alert monitoring personnel to potential risks and monitor indicators in real time: ,in, For in time Monitoring indicators The number of data points, For the Data points at time The characteristic value of; the early warning signal formula: ,in, As an early warning signal, Monitoring indicators, The specific operation method of the warning threshold is as follows: first, real-time image acquisition: the system regularly (e.g., once per second) collects image data of the shear band through the camera and transmits it to the central server. Then, data analysis: the real-time data is analyzed using the trained machine learning model to extract key features. , then calculate the monitoring indicators: use the formula Calculate the monitoring indicators at the current moment and finally trigger the warning: If the monitoring indicators Exceeding the warning threshold ,but , the system triggers an early warning signal to alert monitoring personnel to potential risks; if ,but .

[0021] Preferably, in step S7, the analysis results are displayed through visualization tools, such as heat maps, crack growth maps, etc., so that monitoring personnel can intuitively understand the shear zone status; a quality assessment report is generated regularly (e.g., once a week) to record the changes in the shear zone and the assessment results. If significant changes are found, they are marked as key monitoring areas, and standardized report templates and formats are used to ensure the standardization and consistency of the report content; Heat map generation: ,in, For heatmap at location The value of For the The weight of the feature, For the Features at location The value of is the number of features; report score summary: ,in, For the total score, is the number of time periods, : In time Quality rating.

[0022] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0023] The present invention provides a method for evaluating the quality of shear zones in dangerous rock masses based on machine vision. The method comprises the following steps: arranging high-resolution cameras for image acquisition, using Gaussian filtering, histogram equalization and other technologies for image preprocessing, applying Canny edge detection and SIFT algorithm for feature extraction, adopting convolutional neural network (CNN) for model training and cross-validation, performing image segmentation and structural analysis, realizing intelligent evaluation of shear zone quality and risk identification, monitoring shear zone changes in real time and triggering early warnings, displaying analysis results through visualization tools such as heat maps and generating standardized reports, ensuring the standardization and consistency of monitoring results, thereby improving the efficiency and accuracy of shear zone monitoring in dangerous rock masses and effectively preventing geological disaster risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction to the drawings required for use in the embodiments will be given below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0025] Figure 1 The module diagram of a method for evaluating the quality of shear zones in dangerous rock masses based on machine vision according to the present invention. DETAILED DESCRIPTION

[0026] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of this disclosure will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art.

[0027] The present invention provides Figure 1 A method for evaluating the quality of shear zones in dangerous rock masses based on machine vision is shown, comprising the following steps: S1, arranging a high-resolution camera, adjusting the angle and focal length, and regularly and automatically collecting and transmitting image data to a server;

[0028] S2, use filters to remove noise, adjust contrast and histogram equalization to enhance image clarity;

[0029] S3, apply edge detection and feature point detection algorithms to extract key features and cover key areas;

[0030] S4. Label the data and select a training model, using cross-validation to improve classification and segmentation accuracy;

[0031] S5, segment the image, analyze the structural characteristics of the shear band, assess the quality, and identify potential risk areas;

[0032] S6, real-time data collection and analysis, identify shear zone changes, establish early warning system, timely risk prompt;

[0033] S7, visual display of analysis results, regular generation of standardized evaluation reports, record of shear zone changes; in step S1, high-resolution cameras are arranged in the shear zone area of the dangerous rock mass, the angle and focal length are adjusted to ensure clear and complete images, automatic acquisition software is used to regularly collect image data, and the data is transmitted to the central server through the network to ensure continuous and complete data: , wherein, is the time of the th acquisition, is the initial acquisition time, is the acquisition interval time, is the th acquisition; high-resolution cameras are arranged in the shear zone area of the dangerous rock mass, and the angle and focal length of the cameras are precisely adjusted to cover and clearly capture the images of the entire shear zone. Automatic acquisition software regularly collects image data, usually in seconds, for example, one acquisition per second. Each acquisition image is transmitted to the central server through the network to ensure data continuity and integrity. During data transmission, redundant transmission and data encryption technology are used to ensure data security and reliability. The position of the camera should be selected considering the terrain conditions and the specific situation of the shear zone to ensure comprehensive coverage of the monitoring area and avoid blind spots. At the same time, in order to cope with different weather and lighting conditions, the camera should have night vision and waterproof function. In addition, to ensure the stability of data acquisition, an automatic correction function is set in the system to calibrate the camera regularly to ensure the consistency and accuracy of image acquisition. Through the above measures, the image acquisition process can efficiently and accurately obtain real-time image data of the shear zone, providing a reliable data basis for subsequent image preprocessing and analysis.

[0034] In step S2, the collected images are denoised, using a Gaussian filter to reduce noise, adjusting the filter parameters to balance the denoising effect and image detail preservation, using contrast adjustment and histogram equalization techniques to enhance image clarity, ensuring that key features are clearly visible: , wherein, is the value of the Gaussian function at position (x, y), is the standard deviation, which determines the width of the filter, is the coordinate of the pixel; histogram equalization technology specifically embodies: , wherein, is the equalization value corresponding to the pixel value v, is the number of gray levels, is the width and height of the image, The captured image is preprocessed, first performing denoising. Common denoising methods include Gaussian filtering and mean filtering. Gaussian filtering effectively removes high-frequency noise from the image, while mean filtering reduces the impact of noise by smoothing the image. Selecting appropriate filter parameters is crucial, striking a balance between denoising and preserving image detail. Next, the image undergoes contrast adjustment and histogram equalization to enhance image clarity and legibility. Contrast adjustment can make brightness differences more pronounced, while histogram equalization redistributes grayscale values ​​to increase overall contrast. When performing histogram equalization, it is important to ensure that the adjusted image is undistorted and that key features are more prominent. In the final step of image preprocessing, image enhancement techniques such as sharpening and edge enhancement are used to further improve image quality and the visibility of key features. The goal of all these steps is to produce a high-quality preprocessed image, ensuring that key information in the image is not obscured by noise and low contrast during feature extraction and analysis, providing a clear and accurate foundation for subsequent steps.

[0035] In step S3, the Canny edge detection algorithm is used to extract the edge features of the shear band in the image, and the detection threshold is adjusted to ensure accurate extraction. The SIFT algorithm is applied to extract the key feature points of the shear band, and the distribution and density of the feature points are evaluated to ensure that the key area is covered. The Canny edge detection formula is: ,in, is the edge detection result, Gaussian filter, is the input image, is a convolution operation; the SIFT key point descriptor is: ,in, is the feature point descriptor, is the first feature point vector A quantity, The Canny edge detection algorithm is used to extract shear zone edge features from the preprocessed image, where the dimension of the feature point vector is . This algorithm effectively detects edges in images, including key features such as shear zone outlines and cracks. Canny edge detection calculates the image's gradient to identify areas of dramatic change, thereby extracting image edges. When applying this algorithm, an appropriate threshold must be set to ensure that the extracted edges are complete and accurate. Subsequently, the SIFT algorithm is applied to extract key feature points from the image. The SIFT algorithm, based on scale-invariant feature transforms, can extract stable feature points at different scales and rotations. The extracted feature points include key points in the shear zone, such as the starting and ending points of cracks. The distribution and density of the feature points are evaluated to ensure that they cover all key areas of the shear zone. Other image processing techniques, such as image segmentation and morphological operations, are combined during feature extraction to further enhance the extraction performance. The combined application of multiple algorithms ensures accurate and comprehensive extraction of key shear zone features, providing rich and accurate data support for subsequent machine learning model training.

[0036] In step S4, the image data is annotated to mark the fractures and rock blocks in the shear zone; a convolutional neural network (CNN) is selected for training, the performance of different models is evaluated, the optimal model is selected, the model is trained using the training dataset, the model parameters are adjusted to improve the classification and segmentation accuracy, and the model performance is evaluated using cross-validation and test sets. Convolution operation: ,in, For output image at position The value of is the input image, is the convolution kernel, where are the coordinates of the convolution kernel. After feature extraction, the image data is annotated to highlight key areas of the shear zone, such as fractures and rock blocks. This annotated data will serve as the training set for the machine learning model. A convolutional neural network (CNN) was chosen as the primary model, as CNNs offer significant advantages in processing image data. First, the network architecture is designed, including the input layer, convolutional layers, pooling layers, and fully connected layers. The network architecture needs to be tailored to the specific characteristics of the shear zone image to ensure the model can fully extract and understand the key information in the image. Next, the annotated training data is fed into the network for model training. During training, network parameters such as the learning rate and convolution kernel size are adjusted to improve model accuracy and convergence speed. Cross-validation is used to evaluate the model. Through repeated training and testing, model parameters are continuously optimized to ensure generalization. In the final stage of model training, an independent test set is used to evaluate the model and verify its performance on unseen data. Through multiple iterations and parameter adjustments, a high-performance convolutional neural network model was finally obtained, which can accurately classify and segment shear band images, providing strong support for structural analysis and quality assessment.

[0037] In step S5, the trained model is used to segment the image, identify different parts of the shear zone, and evaluate the accuracy and completeness of the segmentation results. The structural characteristics of the shear zone are analyzed, and its integrity and stability are evaluated by combining geological knowledge and shear zone characteristics. The quality of the shear zone is comprehensively evaluated based on the structural analysis results, and potential risk areas are identified. Standardized evaluation indicators are used to ensure the objectivity and consistency of the results. Fully connected layer: ,in, For output, weight matrix, is the input feature, Bias term; shear band quality score: ,in, Shear band quality score, Weight coefficient, Structural stability score, Crack density score, Score the rock size, Shear zone opening score, Score the shear band length, Score the shear band interface relief, To score the fragmentation of shear zone fillings, after feature extraction, the image data is annotated to identify key areas within the shear zone, such as fractures and rock fragments. This annotated data serves as the training set for the machine learning model. A convolutional neural network (CNN) was selected as the primary model, as CNNs offer significant advantages in processing image data. First, the network architecture is designed, including the input layer, convolutional layers, pooling layers, and fully connected layers. The network architecture needs to be tailored to the specific characteristics of the shear zone images to ensure the model can fully extract and understand the key information within them. Next, the annotated training data is fed into the network for model training. During training, network parameters, such as the learning rate and convolution kernel size, are adjusted to improve model accuracy and convergence speed. Cross-validation is used to evaluate the model. Through repeated training and testing, model parameters are continuously optimized to ensure generalization. In the final stage of model training, an independent test set is used to evaluate the model and verify its performance on unseen data. After multiple iterations and parameter adjustments, a high-performance convolutional neural network model was ultimately developed. This model accurately classifies and segments shear zone images, providing strong support for structural analysis and quality assessment. Subsequently, the structural characteristics of the shear zone were analyzed in depth, and their integrity and stability were assessed by combining geological knowledge and specific conditions. The analysis focused on the following factors: Shear zone aperture: This refers to the degree of crack opening within the shear zone. A larger aperture indicates lower strength and poorer stability. Therefore, accurate measurement and analysis of shear zone aperture is crucial for assessing shear zone stability. Shear zone length: This length is also an important indicator for assessing stability. Longer shear zones may affect the rock mass structure over a wider area, increasing the risk of instability. Using image segmentation and feature extraction techniques, the shear zone length was accurately measured and incorporated into the assessment model. Shear zone interface undulation: This undulation reflects the complexity of the internal structure of the shear zone. Higher undulations typically indicate more irregularities and weaknesses within the shear zone, reducing its overall stability. We will use edge detection and morphological processing techniques to extract and quantify the shear band interface undulations. Shear band filling thickness: Filling refers to the material that fills the shear band cracks. Filling thickness has a significant impact on shear band strength. Thicker fillings generally indicate more material deposition within the shear band, potentially reducing its stability. Image processing techniques will be used to measure and analyze filling thickness. Shear band filling fragmentation: The fragmentation of the filling reflects the physical state and stability of the filling. Fillings with high fragmentation are often loose and lack sufficient support, which in turn affects the stability of the shear band. Filling fragmentation will be assessed using image detail enhancement and feature analysis techniques.

[0038] In step S6, the camera collects image data of the shear zone in real time to ensure the timeliness and integrity of the data; the trained model is used to analyze the real-time data to identify changes in the shear zone; an early warning system is established to issue early warning signals based on the analysis results, alerting monitoring personnel to potential risks and real-time monitoring indicators: ,in, For in time Monitoring indicators The number of data points, For the Data points at time The characteristic value of; the early warning signal formula: ,in, As an early warning signal, Monitoring indicators, The specific operation method of the warning threshold is as follows: first, real-time image acquisition: the system regularly (e.g., once per second) collects image data of the shear band through the camera and transmits it to the central server. Then, data analysis: the real-time data is analyzed using the trained machine learning model to extract key features. , then calculate the monitoring indicators: use the formula Calculate the monitoring indicators at the current moment and finally trigger the warning: If the monitoring indicators Exceeding the warning threshold ,but , the system triggers an early warning signal to alert monitoring personnel to potential risks; if ,but The system uses cameras to collect real-time image data of shear zones, ensuring data timeliness and integrity. This real-time data is transmitted via the network to a central server, where a trained convolutional neural network model analyzes the data, extracts key features, and calculates current monitoring indicators. These indicators are calculated by analyzing information such as crack changes and rock movement in the images, reflecting the real-time status of the shear zone. If a monitoring indicator exceeds a warning threshold, the system automatically triggers an early warning signal, alerting monitoring personnel to potential risks. Warning signals are communicated to monitoring personnel via various channels, including text messages, emails, and alerts on the monitoring platform. The system incorporates a multi-level early warning mechanism, issuing different levels of warning signals based on the specific monitoring indicators. For example, if a monitoring indicator slightly exceeds the threshold, a level one warning is issued, prompting monitoring personnel to take immediate action; if a monitoring indicator significantly exceeds the threshold, a level two warning is issued, requiring immediate preventive measures. This real-time monitoring and early warning mechanism enables timely detection of abnormal changes in shear zones, prompting rapid response and effective measures to mitigate potential geological hazards, thereby improving the timeliness and reliability of dangerous rock mass monitoring and management.

[0039] In step S7, the analysis results are displayed through visualization tools such as heat maps, crack growth maps, etc., so that the monitoring personnel can intuitively understand the shear zone conditions; quality assessment reports are generated regularly (e.g., once a week) to record the changes in the shear zone and evaluation results, and if significant changes are found, the area is marked as a key monitoring area, and standardized report templates and formats are used to ensure the standardization and consistency of the report content; heat map generation: wherein, is the value of the heat map at position , is the weight of the th feature, is the value of the th feature at position , is the number of features; report score aggregation: wherein, is the total score, is the number of time periods, : quality score at time ; the analysis results are displayed through visualization tools such as heat maps, crack growth maps, etc., so that the monitoring personnel can intuitively understand the shear zone conditions. The heat map displays the high-risk areas in the image, with color changes representing the risk level, with red indicating high-risk areas and blue indicating low-risk areas. The crack growth map records the changes in the cracks, including the starting point, end point, and growth rate of the cracks. Quality assessment reports are generated regularly (e.g., once a week) to record the changes in the shear zone and evaluation results. The report includes data sources, analysis methods, result display, key monitoring areas, etc., to ensure the standardization and consistency of the report. If significant changes are found, the area is marked as a key monitoring area and the monitoring frequency and analysis intensity of the area are suggested to be increased. The report uses standardized templates for comparison and analysis of reports from different time periods. Through the generation and display of the report, the monitoring personnel can fully understand the conditions of the shear zone, discover potential problems in a timely manner, and take appropriate measures. In addition, the data and analysis results in the report can also provide reference for subsequent geological research and engineering decision-making, improving the scientificity and effectiveness of dangerous rock mass monitoring and management.

[0040] The above embodiments may be implemented in whole or in part via software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When loaded or executed on a computer, the processes or functions described in the embodiments of this application are fully or partially performed. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired connection (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium may be any available medium accessible by a computer, or a data storage device such as a server or data center that contains a collection of one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, tapes), optical media (e.g., DVDs), or semiconductor media. Semiconductor media may include solid-state drives.

[0041] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0042] Those skilled in the art will clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices and units described above refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0043] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., located in one place or distributed across multiple network units. Some or all of the units may be selected to achieve the purpose of this embodiment according to actual needs.

[0044] In addition, each functional unit in each embodiment of the present application is integrated into one processing unit, each unit exists physically separately, or two or more units are integrated into one unit.

[0045] If the functions are implemented in the form of software function units and sold or used as independent products, they are stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts of the prior art that make contributions or parts of the technical solutions are embodied in the form of software products, which are stored in a storage medium and include instructions for making a computer device (personal computer, server, or network device, etc.) execute all or part of the steps of the methods described in the embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), magnetic disk or optical disk, and various storage program code media.

[0046] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application.

Claims

1. A method for evaluating the quality of shear zones in dangerous rock masses based on machine vision, characterized in that: The following steps are involved: S1. Arrange high-resolution cameras, adjust angles and focal lengths, and automatically collect and transmit image data to the server regularly; S2, use filters to remove noise, adjust contrast and histogram equalization to enhance image clarity; S3, apply edge detection and feature point detection algorithms to extract key features and cover key areas; S4. Label the data and select a training model, using cross-validation to improve classification and segmentation accuracy; S5, segment the image, analyze the structural characteristics of the shear band, assess the quality, and identify potential risk areas; S6. Collect and analyze data in real time, identify shear zone changes, establish an early warning system, and promptly alert risks; S7. Visualize the analysis results and regularly generate standardized assessment reports to record shear band changes; In step S5, the trained model is used to segment the image, identify different parts of the shear band, and evaluate the accuracy and completeness of the segmentation results; Analyze the structural characteristics of the shear zone, evaluate its integrity and stability by combining geological knowledge and shear zone characteristics, comprehensively assess the shear zone quality based on the structural analysis results, identify potential risk areas, and use standardized assessment indicators to ensure the objectivity and consistency of the results; Fully connected layer: ,in, For output, is the weight matrix, is the input feature, is the offset term; shear band quality score: ,in, Score the shear band quality, is the weight coefficient, Score the structural stability. Score the crack density, Score the rock size, Score the shear zone aperture, Score the shear band length, Score the shear band interface relief, Score the degree of fragmentation of shear zone fillings; In step S6, first, real-time image acquisition: the system regularly collects image data of the shear band through the camera and transmits it to the central server. Then, data analysis: the real-time data is analyzed using the trained machine learning model to extract key features. , then calculate the monitoring indicators: use the formula Calculate the monitoring indicators at the current moment and finally trigger the warning: If the monitoring indicators Exceeding the warning threshold ,but , the system triggers an early warning signal to alert monitoring personnel to potential risks; if ,but ,in, For in time monitoring indicators, the number of data points, For the Data points at time The eigenvalue of .

2. The method for evaluating the quality of shear zones in dangerous rock masses based on machine vision according to claim 1, characterized in that: In step S1, a high-resolution camera is placed in the shear zone of the dangerous rock mass. The angle and focal length are adjusted to ensure a clear and complete image. Image data is collected regularly using automated acquisition software and transmitted to a central server via the network to ensure data continuity and integrity: ,in, For the The time of collection, is the initial acquisition time, is the collection interval time, For the Collection times.

3. The method for evaluating the quality of shear zones in dangerous rock masses based on machine vision according to claim 1, characterized in that: In step S2, the collected image is denoised by using a Gaussian filter to reduce noise. The filter parameters are adjusted to balance the denoising effect and image detail preservation. Contrast adjustment and histogram equalization techniques are used to enhance image clarity and ensure that key features are clearly visible: ,in, For the location (x,y) The Gaussian function value at is the coordinate of the pixel; the histogram equalization technology is specifically embodied as follows: ,in, is the equalization value corresponding to the pixel value v, is the grayscale level, are the width and height of the image, Grayscale i The number of pixels.

4. The method for evaluating the quality of shear zones in dangerous rock masses based on machine vision according to claim 1, wherein: In step S4, the image data is annotated to mark the cracks and rock blocks in the shear zone, and the length and spacing of the internal cracks in the shear zone, the undulation of the shear zone interface, and the size of the internal filling rock blocks are obtained; a convolutional neural network is selected for training, the performance of different models is evaluated, the optimal model is selected, and the model is trained using the training data set. The model parameters are adjusted to improve the classification and segmentation accuracy. The model performance is evaluated using cross-validation and test sets. Convolution operation: ,in, For output image at position The value of is the input image, is the convolution kernel, are the coordinates of the convolution kernel.

5. The method for evaluating the quality of shear zones in dangerous rock masses based on machine vision according to claim 1, characterized in that: In step S7, the analysis results are displayed through a heat map to enable monitoring personnel to intuitively understand the shear zone status; quality assessment reports are generated regularly to record the changes in the shear zone and the assessment results. If significant changes are found, they are marked as key monitoring areas, and standardized report templates and formats are used to ensure the standardization and consistency of the report content; Heat map generation: ,in, For heatmap at location The value of For the The weight of the feature, For the Features at location The value of is the number of features; report score summary: ,in, For the total score, is the number of time periods, For in time Quality rating.

Images