A roadway crack identification method and system based on image recognition

Abstract

The present invention relates to the field of image recognition technology, and in particular, to a roadway crack recognition method and system based on image recognition. The method includes the following steps: obtaining roadway structure data; performing regional camera deployment according to the roadway structure data to obtain roadway camera deployment data; collecting roadway images according to the roadway camera deployment data to generate a roadway time-series image set; performing roadway morphological change analysis on the roadway time-series image set to generate roadway time-series change data; identifying the surface crack area of the roadway time-series image set through the roadway time-series change data to generate a roadway surface crack area image; and performing surface crack trend analysis on the roadway surface crack area image to generate surface crack texture trend data. The present invention improves the accuracy and comprehensiveness of recognition through dynamic change detection, hidden crack recognition, crack classification and analysis, and crack age deduction.

Description

Technical Field

[0001] The present invention relates to the technical field of image recognition, and in particular, to a roadway crack recognition method and system based on image recognition. Background Art

[0002] Initially, the detection of roadway cracks relied on manual inspections. This method was not only time-consuming and laborious but also easily affected by subjective factors, making it impossible to ensure the consistency and accuracy of the detection. With the development of computer vision technology, image recognition technology has gradually been introduced into the field of crack detection. Early image recognition methods mainly relied on simple edge detection and image segmentation techniques, which showed certain limitations when dealing with complex crack morphologies. After entering the 21st century, the breakthrough of deep learning technology has greatly promoted the development of image recognition technology. The emergence of convolutional neural networks (CNNs) has made automatic feature extraction possible, improving the accuracy and robustness of crack detection. A crack detection system based on CNNs can automatically identify various crack types and morphologies by training a large number of labeled images, significantly improving the detection efficiency and accuracy. In addition, with the enhancement of computing power and the application of big data technology, the crack recognition system can process larger-scale datasets and achieve real-time detection and monitoring. However, currently, traditional roadway cracks usually only focus on surface cracks, ignoring potential hidden cracks, and at the same time, it is impossible to accurately infer the formation period and age of the cracks, which affects the prediction of the future development trend of the cracks, and thus leads to lower accuracy and comprehensiveness in recognition. Summary of the Invention

[0003] Based on this, it is necessary to provide a roadway crack recognition method and system based on image recognition to solve at least one of the above technical problems.

[0004] To achieve the above object, a roadway crack recognition method based on image recognition, the method includes the following steps:

[0005] Step S1: Obtain roadway structure data; deploy area cameras according to the roadway structure data to obtain roadway camera deployment data; collect roadway images according to the roadway camera deployment data to generate a roadway time-series image set; analyze the morphological changes of the roadway in the roadway time-series image set to generate roadway time-series change data; identify the surface crack area of the roadway time-series image set through the roadway time-series change data to generate a roadway surface crack area image;

[0006] Step S2: Analyze the surface crack trend of the roadway surface crack area image to generate surface crack texture trend data; perform depth map conversion based on the roadway surface crack area image to generate the depth map of the roadway surface crack area; analyze the crack ductility of the roadway surface crack area depth map to generate surface crack ductility data; use the surface crack texture trend data and the surface crack ductility data to confirm the hidden roadway crack area of the roadway surface crack area image to obtain the hidden roadway crack area image;

[0007] Step S3: Integrate the roadway hidden crack area image and the roadway surface crack area image to obtain the crack type area image; perform crack thermal balance analysis on the crack type area image to generate roadway crack thermal balance data; perform crack spectrum analysis on the crack type area image according to the roadway crack thermal balance data to generate roadway crack spectrum analysis data;

[0008] Step S4: Divide the crack formation period based on the roadway crack thermal balance data and the roadway crack spectrum analysis data to generate crack period data; deduce and label the crack age of the crack type area image through the crack period data to generate crack age deduction data; adjust the monitoring frequency of the roadway camera deployment data according to the crack age deduction data to perform dynamic monitoring operations for roadway crack identification.

[0009] The present invention provides a basis for subsequent camera deployment and image acquisition through accurate roadway structure data, ensuring the comprehensiveness and accuracy of the data. Deploying cameras according to the roadway structure data enables image acquisition to cover all key areas, improving the coverage rate of crack detection. By generating a time-series image set through continuous image acquisition, the changing trend of cracks can be tracked to ensure the timely discovery of the dynamic development of cracks. Analyzing the morphological changes of the roadway in the time-series image set can identify the growth and expansion of cracks and their impact on the surrounding environment, improving the accuracy of crack identification. By analyzing the roadway time-series change data to identify the surface crack area and generating a crack area image, accurate basic data is provided for subsequent in-depth analysis and hidden crack identification. By analyzing the trend data of the crack orientation, understanding the direction and pattern of crack expansion helps predict the future development direction of cracks and optimize the maintenance strategy. Converting the crack area image into a depth map can extract the depth information of the cracks and identify potential hidden cracks, which is often difficult to achieve in traditional image recognition. Analyzing the crack ductility in the depth map to understand the ductility and stability of the cracks provides data support for the long-term monitoring and repair of cracks. Combining the crack texture trend data and the crack ductility data to confirm the hidden crack area improves the comprehensiveness of crack detection and reduces the risk of missed detection. Integrating the hidden crack and surface crack area images provides a comprehensive crack type image for convenient comprehensive analysis and management. Conducting a thermal balance analysis on the crack type area image reveals the thermal characteristics and formation reasons of the cracks, helping to identify the thermal influencing factors of the cracks. Based on the thermal balance data, performing a crack spectrum analysis can identify the composition and material properties of the cracks, improving the meticulousness and accuracy of crack detection and providing guidance for further crack repair and maintenance. Using the crack thermal balance and spectrum analysis data to divide the crack formation period helps understand the historical background and development process of the cracks and supports long-term maintenance planning. Deducing and annotating the age of the cracks to predict the future development trend of the cracks, optimizing the maintenance strategy and resource allocation, and reducing potential safety risks. Adjusting the monitoring frequency of the camera according to the crack age deduction data ensures the dynamic adaptability of the monitoring work, improves the response speed and accuracy to crack changes, and enhances the monitoring effect of roadway cracks. Therefore, the present invention improves the accuracy and comprehensiveness of identification through dynamic change detection, hidden crack identification, crack classification and analysis, and crack age deduction.

[0010] Preferably, step S1 includes the following steps:

[0011] Step S11: Obtain roadway structure data by using laser scanning;

[0012] Step S12: Divide the roadway into regions according to the roadway structure data to generate roadway structure division data; deploy cameras based on the roadway structure division data to obtain roadway camera deployment data;

[0013] Step S13: Based on a preset time interval, collect roadway images according to the roadway camera deployment data to generate a set of roadway time-series images; perform image preprocessing on the set of roadway time-series images to generate a set of standard roadway time-series images, where the image preprocessing includes image filtering, image brightness enhancement, and image normalization;

[0014] Step S14: Perform roadway morphological change analysis on the set of standard roadway time-series images to generate roadway time-series change data; identify the surface crack area of the set of standard roadway time-series images through the roadway time-series change data to generate a roadway surface crack area image.

[0015] The present invention can provide high-precision roadway structure data through laser scanning technology. These data depict in detail the spatial structure and geometric features of the roadway, providing a reliable basis for subsequent area division and analysis. Laser scanning can generate detailed three-dimensional point cloud data, which helps to comprehensively understand the spatial layout of the roadway and supports accurate area division and equipment deployment. According to the roadway structure data for area division, the generated roadway structure division data helps to identify and manage different areas in the roadway, improving the efficiency of monitoring and management. Based on the area division for camera deployment, it can ensure that important areas and blind spots in the roadway are fully covered, improving the monitoring effect and the comprehensiveness of data collection. The set of roadway images collected at preset time intervals can provide dynamic change information of the roadway, capture the states at different moments, and support subsequent time-series analysis and monitoring. Performing image preprocessing (such as filtering, brightness enhancement, and normalization) on the set of roadway time-series images can eliminate noise and improve image quality, generating a set of standard roadway time-series images. These standardized image data provide clear and accurate input for subsequent analysis. Performing morphological change analysis on the set of standard roadway time-series images can detect deformations, wear, or other structural changes of the roadway. This helps to monitor the health status of the roadway and timely discover potential problems. Identifying the crack area of the image through the roadway morphological change data, the generated crack area image helps to accurately locate the cracks in the roadway. This information is crucial for subsequent maintenance and safety assessment. The implementation of the whole step ensures the comprehensiveness and accuracy from data collection to analysis, providing a solid foundation for the monitoring and maintenance of the roadway. Through the collection and analysis of the time-series image set, the state of the roadway can be dynamically monitored, and potential problems can be timely discovered and addressed. The optimization of area division and camera deployment improves the efficiency of roadway management and the monitoring effect, helping to prevent and handle potential risks in advance.

[0016] Preferably, step S14 includes the following steps:

[0017] Step S141: Identify feature points in the standard roadway time-series image set to generate standard roadway time-series image feature points; use the standard roadway time-series image feature points to unify the image perspectives of the standard roadway time-series image set to generate a unified perspective roadway image set;

[0018] Step S142: Extract multi-dimensional morphological features from the unified perspective roadway image set to obtain roadway multi-dimensional morphological feature data, where the multi-dimensional morphological feature extraction includes edge line extraction, surface texture extraction, and geometric contour extraction; calculate the morphological change amount of the unified perspective roadway image set based on the roadway multi-dimensional morphological feature data to generate roadway time-series morphological change amount data;

[0019] Step S143: Use the roadway time-series morphological change amount data to segment the abnormal roadway change area of the unified perspective roadway image set to generate an abnormal roadway change area image; perform crack feature matching on the abnormal roadway change area image to generate crack feature matching data;

[0020] Step S144: Label the surface crack area of the abnormal roadway change area image according to the crack feature matching data to generate a roadway surface crack area image.

[0021] Through the identification of feature points in the standard roadway time-series image set, the present invention can accurately extract key feature points in the image. These feature points provide a stable reference, making subsequent image processing more consistent and reliable. Using the identified feature points to unify the image perspectives, the generated unified perspective roadway image set eliminates the influence of perspective differences on image analysis. This consistency helps to more accurately compare and analyze roadway changes at different time points, improving the comparability of data. By extracting multi-dimensional morphological features from the unified perspective roadway image set, information on the edge lines, surface textures, and geometric contours of the roadway can be comprehensively obtained. These feature data provide a rich information basis for subsequent morphological change analysis. Calculating the morphological change amount based on the extracted multi-dimensional morphological feature data can accurately measure the degree of change of the roadway at different times. This can effectively detect minor changes in the roadway structure and timely discover potential deformations or damages. Using the roadway time-series morphological change amount data to segment the abnormal change area can accurately identify abnormal areas in the roadway. This helps to quickly locate areas that need to be focused on, improving the response speed to abnormal situations. Performing crack feature matching on the segmented abnormal area can refine the crack feature data and help identify and classify the types and severity of cracks. This can provide accurate data support for subsequent maintenance and repair work. Labeling the surface crack area of the abnormal roadway change area image according to the crack feature matching data, the generated roadway surface crack area image can clearly identify the location and scope of the cracks. This is very important for further analysis and decision-making and helps to formulate targeted maintenance plans.

[0022] Preferably, step S2 includes the following steps:

[0023] Step S21: Extract the surface crack patterns from the image of the roadway surface crack area to obtain the surface crack pattern distribution data; analyze the pattern orientation of the surface crack pattern distribution data to generate the surface crack pattern orientation data; perform a crack trend analysis on the surface crack pattern distribution data according to the surface crack pattern orientation data to generate the surface crack texture trend data;

[0024] Step S22: Perform a depth map conversion based on the image of the roadway surface crack area to generate a depth map of the roadway surface crack area; measure the crack width and crack depth of the depth map of the roadway surface crack area to obtain the surface crack width data and the surface crack depth data;

[0025] Step S23: Perform a crack ductility analysis through the surface crack width data and the surface crack depth data to generate the surface crack ductility data;

[0026] Step S24: Use the surface crack texture trend data and the surface crack ductility data to confirm the hidden roadway crack area in the image of the roadway surface crack area to obtain the hidden roadway crack area image.

[0027] By extracting the surface crack patterns from the images of the roadway surface crack areas, the present invention can obtain detailed data on the crack pattern distributions. This provides the basic data for subsequent crack analysis and helps to understand the basic shapes and distributions of the cracks. By analyzing the orientations of the surface crack patterns in the distribution data, the main directions of the crack patterns can be revealed. This information is of great significance for judging the formation mechanisms of the cracks and their potential impacts. By performing trend analysis on the crack directions based on the orientation data, the generated crack texture trend data can help identify the expansion directions and patterns of the cracks. This is very useful for predicting the future development directions of the cracks and their affected areas. By converting the images of the roadway surface crack areas into depth maps, three-dimensional information of the cracks can be obtained. This provides accurate spatial data support for measuring the depths and widths of the cracks. By measuring the widths and depths of the cracks in the depth maps, the generated surface crack width data and depth data provide detailed geometric parameters of the cracks. These data help to evaluate the severities and safety risks of the cracks. By performing crack ductility analysis using the surface crack width data and depth data, the generated crack ductility data can evaluate the expansion potentials and trends of the cracks. This helps to predict the growth ranges and speeds of the cracks, thus enabling preventive measures to be taken in advance. Using the crack texture trend data and crack ductility data to confirm the latent crack areas in the images of the roadway surface crack areas can identify those crack areas that have not yet appeared or are difficult to detect. This is very important for comprehensively understanding the crack conditions of the roadway and helps to discover hidden safety hazards. Through crack pattern extraction, depth measurement, and ductility analysis, the crack conditions in the roadway can be comprehensively detected and predicted, providing a scientific basis for subsequent maintenance and management. Providing detailed crack data, including width, depth, and ductility, helps to evaluate the impacts of the cracks on the roadway structure, thus enhancing safety. By confirming the latent crack areas, cracks that have not yet appeared can be detected early, which helps to take timely repair measures to prevent potential safety problems.

[0028] Preferably, step S24 includes the following steps:

[0029] Step S241: Perform crack segmentation fitting on the images of the roadway surface crack areas according to the surface crack ductility data to generate crack extension speed evaluation data;

[0030] Step S242: Perform crack texture line direction vector fitting on the images of the roadway surface crack areas according to the surface crack texture trend data to generate crack extension direction evaluation data;

[0031] Step S243: Perform latent crack correlation analysis through the crack extension speed evaluation data and the crack extension direction evaluation data to generate latent crack correlation data;

[0032] Step S244: Based on the implicit crack correlation data, perform stress field simulation on the image of the crack area on the roadway surface to generate the image of the implicit crack area on the roadway.

[0033] Through crack segment fitting on the image of the crack area on the roadway surface, the present invention can obtain the evaluation data of the crack extension speed. This helps to understand the crack propagation speed, thereby predicting the growth of cracks in the future time period. This is crucial for preventing potential structural risks. Crack segment fitting provides the ability to dynamically monitor crack changes, helps to timely warn of structural safety hazards, ensures timely maintenance measures are taken to prevent accidents. By fitting the direction vectors of the crack texture lines according to the crack texture trend data, the evaluation data of the crack extension direction can be generated. This helps to understand the main crack propagation direction and supports the prediction of the future development trend of cracks. By identifying the crack extension direction, the potential implicit crack area can be accurately located, thus more effectively carrying out structural maintenance and repair. Through the implicit crack correlation analysis using the crack extension speed evaluation data and the crack extension direction evaluation data, the implicit cracks that are invisible in the current image but potentially related to the identified cracks can be identified. This is crucial for comprehensively evaluating the safety of the roadway structure. The implicit crack correlation data provides important information for evaluating the overall safety of the structure, helping to formulate more comprehensive maintenance and repair strategies. Based on the implicit crack correlation data, perform stress field simulation on the image of the crack area on the roadway surface to generate the image of the implicit crack area. This provides detailed spatial information for further crack analysis, helping to accurately identify potential implicit crack areas. The stress field simulation results can help formulate specific maintenance strategies for implicit cracks, thereby improving the safety and stability of the roadway structure and preventing the risks brought by crack propagation. Through the evaluation of the crack extension speed and direction, the real-time monitoring and prediction of the dynamic changes of cracks are realized, improving the timeliness of structural safety management. Through correlation analysis and stress field simulation, the implicit crack area can be identified, providing detailed data support for structural maintenance and preventing potential safety hazards. A comprehensive evaluation of the cracks and their propagation trends is provided, helping to optimize the safety monitoring and maintenance strategies of the roadway and improve the safety and reliability of the overall structure.

[0034] Preferably, step S3 includes the following steps:

[0035] Step S31: Integrate the image of the implicit crack area on the roadway and the image of the crack area on the roadway surface to obtain the image of the crack type area; based on the infrared thermal imaging technology, collect the crack temperature change of the image of the crack type area to generate the image of the roadway crack temperature change;

[0036] Step S32: Calculate the adjacent temperature difference of the roadway fissure temperature change image to obtain the roadway fissure temperature difference data; calculate the temperature difference change rate of the roadway fissure temperature difference data to obtain the temperature difference change rate data;

[0037] Step S33: Conduct fissure thermal balance analysis on the roadway fissure temperature change image through the roadway fissure temperature difference data and the temperature difference change rate data to generate roadway fissure thermal balance data;

[0038] Step S34: Based on the spectral analysis technology, conduct fissure spectral analysis on the fissure type area image according to the roadway fissure thermal balance data to generate roadway fissure spectral analysis data.

[0039] In the present invention, by integrating the image of the hidden fissure area of the roadway with the image of the surface fissure area of the roadway, a detailed fissure type area image can be obtained. This integration helps to comprehensively understand the distribution of various types of fissures in the roadway. Using infrared thermal imaging technology to collect the temperature change of the fissure type area image can generate the roadway fissure temperature change image. This helps to detect the temperature change at the fissure part, provide information on the thermal state of the fissure, and assist in evaluating the thermal anomaly of the fissure. By calculating the adjacent temperature difference of the roadway fissure, the roadway fissure temperature difference data can be obtained. The temperature difference data helps to identify whether there is a significant thermal anomaly at the fissure, which indicates the potential problems or change trends of the fissure. Calculating the temperature difference change rate can generate the temperature difference change rate data. By evaluating the temperature difference change rate, the dynamic change of the fissure thermal balance can be understood, the intensification or mitigation of the temperature difference can be identified, which helps to better understand the thermal behavior of the fissure. Conducting fissure thermal balance analysis through the roadway fissure temperature difference data and the temperature difference change rate data can generate the roadway fissure thermal balance data. This helps to evaluate the stability of the fissure in the thermal environment and identify whether there is a problem of thermal imbalance. The fissure thermal balance data can be used to identify abnormal thermal phenomena and prevent further expansion or structural damage of the fissure due to thermal stress changes. Conducting fissure spectral analysis on the fissure type area image based on the spectral analysis technology can generate the roadway fissure spectral analysis data. This helps to identify the chemical composition and physical characteristics of the fissure and provide in-depth information about the nature of the fissure. The fissure spectral analysis data helps to diagnose the type of the fissure, the formation reason and its impact on the overall structure of the roadway, and supports the formulation of targeted repair and maintenance strategies. By integrating different technologies (such as infrared thermal imaging, spectral analysis), the thermal state and chemical characteristics of the fissure can be comprehensively evaluated, and the accuracy of fissure monitoring can be improved. Temperature difference calculation and change rate analysis provide dynamic information on the thermal behavior of the fissure, which helps to monitor the change trend of the fissure and timely discover potential problems. Fissure thermal balance analysis and spectral analysis provide a scientific basis for formulating effective maintenance and repair strategies, and enhance the safety and stability of the roadway structure.

[0040] Preferably, step S34 includes the following steps:

[0041] Step S341: Based on the spectral analysis technology, Raman spectra of the fissure type area image are collected according to the roadway fissure thermal balance data to obtain a roadway fissure spectrogram;

[0042] Step S342: Analyze the elements in the fissure environment of the roadway fissure spectrogram to generate fissure environment element data; identify the chemical substance components of the fissure type area data through the fissure environment element data to generate fissure environment chemical substance data;

[0043] Step S343: Analyze the oxidation state of the fissure material in the roadway fissure spectrogram to generate fissure material oxidation state data; analyze the oxidation degree of the fissure type area data according to the fissure material oxidation state data to generate fissure oxidation degree data;

[0044] Step S344: Analyze the time-varying characteristics of the fissure spectrum of the roadway fissure spectrogram through the fissure environment chemical substance data and the fissure oxidation degree data to generate roadway fissure spectrum analysis data.

[0045] The spectral map of roadway fissures generated by Raman spectroscopy acquisition in the present invention provides detailed spectral information of the fissure area. This helps to accurately identify the material composition and chemical structure in the fissures, revealing the microscopic characteristics of the fissures. Raman spectroscopy technology can detect the vibration modes of the fissures, providing high-resolution spectral data for the chemical and physical properties of the fissure materials. This supports an in-depth understanding of the formation causes and material properties of the fissures. Through the analysis of the environmental elements in the fissures, the generated fissure environmental element data helps to identify the environmental components in the fissure area, such as minerals and pollutants. This is crucial for understanding the formation and expansion mechanisms of the fissures. Using the environmental element data for the identification of chemical substance components, the fissure environmental chemical substance data is generated. It can reveal the chemical components in the fissures, evaluate the impact of the environment on the fissures, and support accurate maintenance and treatment measures. The fissure material oxidation state data generated by the analysis of the oxidation state of the fissure materials provides information on the degree of oxidation of the fissure materials. This is crucial for evaluating the deterioration and corrosion degrees of the fissure materials. Through the analysis of the degree of oxidation, the impact of the oxidation of the fissures on the structure can be evaluated, helping to predict the further development of the fissures and their impact on the overall structure, and formulating appropriate repair strategies. Through the fissure environmental chemical substance data and the fissure oxidation degree data, the time-series change analysis of the spectral characteristics of the fissures is carried out to generate the roadway fissure spectral analysis data. It can monitor the change trend of the fissure characteristics over time, providing a dynamic understanding of the fissure progress. Analyzing the time-series changes of the spectral characteristics of the fissures helps to comprehensively evaluate the evolution process of the fissures, identify potential risk factors, and thus support more scientific maintenance and repair decisions. Combining Raman spectroscopy data and environmental analysis can accurately diagnose the chemical and physical properties of the fissures, providing a scientific basis for fissure evaluation and repair. The time-series change analysis of the spectral characteristics enables the assessment of the dynamic risks of the fissures, helping to foresee the future development trend of the fissures. By comprehensively analyzing the environmental impact and material state of the fissures, it supports the formulation of effective maintenance and repair plans, improving the safety and stability of the roadway structure.

[0046] Preferably, step S4 includes the following steps:

[0047] Step S41: Divide the formation period of the fissures based on the roadway fissure thermal balance data and the roadway fissure spectral analysis data to generate fissure period data;

[0048] Step S42: Deduce and label the fissure age for the fissure type area image through the fissure period data to generate fissure age deduction data;

[0049] Step S43: Compare the inferred fracture age data with the preset fracture age range. When the inferred fracture age data is less than the preset fracture age range, mark the corresponding fracture type area image as a newly formed fracture image; when the inferred fracture age data is within the preset fracture age range, mark the corresponding fracture type area image as a stable fracture image; when the inferred fracture age data is greater than the preset fracture age range, mark the corresponding fracture type area image as an aging fracture image;

[0050] Step S44: Conduct fracture age image discrimination on the annotated fracture type area image. When it is confirmed that the fracture type area image is a newly formed fracture image, perform high-frequency monitoring on the roadway camera deployment data. When it is confirmed that the fracture type area image is a stable fracture image, perform medium-frequency monitoring on the roadway camera deployment data. When it is confirmed that the fracture type area image is an aging fracture image, perform low-frequency monitoring on the roadway camera deployment data to carry out dynamic monitoring operations for roadway fracture identification.

[0051] By dividing the fracture formation period based on fracture thermal equilibrium data and spectral analysis data, the present invention can accurately determine the formation time of fractures. This is crucial for understanding the evolution process of fractures and their impact on structures. The generated fracture period data provides a classification basis for fracture management in the time dimension, which helps formulate maintenance and treatment strategies for different stages. The generated fracture period data provides a classification basis for fracture management in the time dimension, which helps formulate maintenance and treatment strategies for different stages. The generated fracture period data provides a classification basis for fracture management in the time dimension, which helps formulate maintenance and treatment strategies for different stages. By comparing the fracture age deduction data with the preset age range, fractures can be classified into newly formed period, stable period or aging period. This classification helps evaluate the risk level of fractures and their impact on structural safety. Classifying according to the age stage of fractures can prioritize the treatment of high-risk fractures in maintenance and repair work to ensure the most effective use of resources. According to the age stage of the fracture type area image, adjust the monitoring frequency of the roadway camera. For newly formed fractures, high-frequency monitoring can be carried out to track their development and changes in real time; for stable fractures, medium-frequency monitoring can be carried out to continuously monitor their status; for aging fractures, low-frequency monitoring can be carried out to reduce unnecessary monitoring work. This dynamic adjustment helps optimize the allocation of monitoring resources. By implementing different monitoring frequencies for different fracture age stages, the monitoring efficiency can be improved, redundant data collection can be reduced, and potential risks can be more effectively warned. According to the age and development stage of fractures, formulate targeted maintenance and repair measures to improve the safety and stability of the roadway. Through classification and phased monitoring, effectively identify and control the risks of fractures and ensure the structural safety of the roadway. Dynamically adjust the monitoring frequency, optimize the resource allocation according to the actual state of fractures, and improve the efficiency and effect of monitoring. Through classification and phased monitoring, effectively identify and control the risks of fractures and ensure the structural safety of the roadway.

[0052] Preferably, step S42 includes the following steps:

[0053] Step S421: Extract fracture period features from the fracture period data through a preset fracture period feature database to obtain fracture period feature data;

[0054] Step S422: Divide the fracture period feature data into datasets to generate a model training set and a model test set; use the support vector machine algorithm to train the model training set to generate a fracture age deduction pre-model;

[0055] Step S423: Optimize and iterate the fracture age deduction pre-model through the model test set to generate a fracture age deduction model; import the fracture type area image into the fracture age deduction model for fracture age deduction and annotation to generate a fracture type area annotation image.

[0056] The present invention extracts fracture period feature data through a preset fracture period feature database, which helps to accurately extract the time features of fractures, thereby providing more detailed information for subsequent analysis. Feature extraction provides an in-depth understanding of the fracture period, laying a solid foundation for model training and deduction, and improving the prediction accuracy of the model. The fracture period feature data is divided into a model training set and a model test set, and trained using the support vector machine algorithm, which can generate an efficient pre-model for fracture age deduction. The support vector machine algorithm has excellent classification ability and generalization performance and can handle complex data patterns. The pre-model for fracture age deduction is optimized and iterated through the model test set to ensure that the model can accurately reflect the actual situation, effectively deduce different fracture ages, and improve the reliability and prediction accuracy of the model. Importing the fracture type region image into the fracture age deduction model can achieve accurate deduction and annotation of the fracture age. This method not only improves the accuracy of deduction but also provides a scientific basis for subsequent maintenance and repair work. The generated fracture type region annotation image provides a clear fracture age classification, which helps to quickly identify fractures of different ages and facilitates the hierarchical management and treatment of fractures. Through scientific feature extraction and model training, the accuracy of fracture age deduction can be improved, providing reliable data support for the fracture management of roadways. Accurate fracture age deduction helps to formulate more effective maintenance strategies, prioritize according to the actual age of fractures, and improve the pertinence and efficiency of maintenance work. Providing detailed fracture age data enables decision-makers to make scientific and reasonable decisions based on the data, thereby optimizing the safety management and maintenance work of roadways.

[0057] In this specification, a roadway fracture identification system based on image recognition is provided for performing the above-mentioned roadway fracture identification method based on image recognition. The roadway fracture identification system based on image recognition includes:

[0058] A surface fracture region identification module, configured to obtain roadway structure data; deploy area cameras according to the roadway structure data to obtain roadway camera deployment data; collect roadway images according to the roadway camera deployment data to generate a roadway time-series image set; perform roadway morphology change analysis on the roadway time-series image set to generate roadway time-series change data; identify the surface fracture region of the roadway time-series image set through the roadway time-series change data to generate a roadway surface fracture region image;

[0059] The recessive fissure area recognition module is used to analyze the surface fissure trend of the roadway surface fissure area image, generate surface fissure texture trend data; convert the depth map based on the roadway surface fissure area image to generate the roadway surface fissure area depth map; analyze the fissure ductility of the roadway surface fissure area depth map to generate surface fissure ductility data; use the surface fissure texture trend data and the surface fissure ductility data to confirm the recessive roadway fissure area of the roadway surface fissure area image to obtain the recessive roadway fissure area image;

[0060] The fissure feature recognition module is used to integrate the recessive fissure area image of the roadway and the roadway surface fissure area image to obtain the fissure type area image; analyze the fissure thermal balance of the fissure type area image to generate the roadway fissure thermal balance data; perform fissure spectral analysis on the fissure type area image according to the roadway fissure thermal balance data to generate the roadway fissure spectral analysis data;

[0061] The monitoring frequency adjustment module is used to divide the fissure formation period based on the roadway fissure thermal balance data and the roadway fissure spectral analysis data to generate fissure period data; deduce and label the fissure age of the fissure type area image through the fissure period data to generate fissure age deduction data; adjust the monitoring frequency of the roadway camera deployment data according to the fissure age deduction data to perform dynamic monitoring operations for roadway fissure recognition.

[0062] The beneficial effects of the present invention are as follows: By obtaining roadway structure data and deploying cameras, the structural layout of the roadway can be comprehensively understood, ensuring that data collection covers the entire roadway area and guaranteeing the comprehensiveness and accuracy of subsequent analysis. Analyzing the time-series image set of the roadway can monitor changes in the roadway morphology, identify potential surface crack areas, and provide key data support for the timely discovery and treatment of cracks. Through the analysis of morphological changes and the identification of surface crack areas, crack areas can be effectively distinguished, laying a foundation for subsequent crack feature analysis and evaluation. Analyzing the trend of the surface crack orientation can understand the expansion direction of the cracks, providing valuable information for further crack management and repair. Through depth map conversion and crack ductility analysis, the width and depth of the cracks can be accurately measured, the ductility of the cracks can be evaluated, and the impact of the cracks on the roadway structure can be helped to be evaluated. Combining the crack orientation trend data and ductility data to confirm the hidden crack areas helps to discover those cracks that are not easily detectable, so as to carry out maintenance in advance and avoid potential risks. Integrating the images of the hidden crack areas with the images of the surface crack areas provides a comprehensive image of the crack type areas, which helps to better understand the distribution and nature of the cracks. Through crack thermal balance analysis, the thermal characteristics of the cracks can be understood, which helps to reveal the formation mechanism of the cracks and their impact on the roadway structure. Conducting spectral analysis on the cracks can detect the chemical components and material properties in the cracks, providing an in-depth understanding of the crack formation causes and providing a scientific basis for formulating repair strategies. Dividing the crack formation periods according to the crack thermal balance data and spectral analysis data can determine the age of the cracks, understand the evolution process of the cracks, and provide timeliness information for crack management. Through crack age deduction and annotation, the age status of different cracks can be accurately understood, and corresponding maintenance strategies can be formulated according to the actual situation of the cracks. Adjusting the monitoring frequency of the roadway cameras according to the crack age deduction data can achieve targeted dynamic monitoring, improve the monitoring efficiency and effect, and ensure the timely discovery and treatment of new crack problems. Therefore, the present invention improves the accuracy and comprehensiveness of identification through dynamic change detection, hidden crack identification, crack classification and analysis, and crack age deduction. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 It is a schematic diagram of the step flow of a roadway crack identification method based on image recognition;

[0064] Figure 2 For Figure 1 It is a schematic diagram of the detailed implementation step flow of step S2 in

[0065] Figure 3 For Figure 1 It is a schematic diagram of the detailed implementation step flow of step S3 in

[0066] Figure 4 For Figure 1Schematic diagram of the detailed implementation steps of step S4 in

[0067] The realization, functional characteristics and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. Specific implementation manners

[0068] The technical method of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0069] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus their repeated description will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor methods and / or microcontroller methods.

[0070] It should be understood that although terms such as "first" and "second" may be used here to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used here includes any and all combinations of one or more of the listed related items.

[0071] To achieve the above object, please refer to Figures 1 to 4 , a roadway crack identification method based on image recognition, the method includes the following steps:

[0072] Step S1: Obtain roadway structure data; deploy area cameras according to the roadway structure data to obtain roadway camera deployment data; collect roadway images according to the roadway camera deployment data to generate a roadway time-series image set; perform roadway morphology change analysis on the roadway time-series image set to generate roadway time-series change data; identify the surface crack area of the roadway time-series image set through the roadway time-series change data to generate a roadway surface crack area image;

[0073] Step S2: Analyze the trend of the surface crack orientation in the image of the roadway surface crack area to generate surface crack texture orientation trend data; perform depth map conversion based on the image of the roadway surface crack area to generate a depth map of the roadway surface crack area; analyze the crack ductility of the depth map of the roadway surface crack area to generate surface crack ductility data; use the surface crack texture orientation trend data and the surface crack ductility data to confirm the hidden roadway crack area in the image of the roadway surface crack area to obtain an image of the hidden roadway crack area;

[0074] Step S3: Integrate the image of the hidden crack area of the roadway and the image of the roadway surface crack area to obtain an image of the crack type area; perform crack thermal balance analysis on the image of the crack type area to generate roadway crack thermal balance data; perform crack spectral analysis on the image of the crack type area according to the roadway crack thermal balance data to generate roadway crack spectral analysis data;

[0075] Step S4: Divide the crack formation period based on the roadway crack thermal balance data and the roadway crack spectral analysis data to generate crack period data; deduce and label the crack age of the crack type area image through the crack period data to generate crack age deduction data; adjust the monitoring frequency of the roadway camera deployment data according to the crack age deduction data to perform dynamic monitoring operations for roadway crack identification.

[0076] The present invention provides a basis for subsequent camera deployment and image acquisition through accurate roadway structure data, ensuring the comprehensiveness and accuracy of the data. Deploying cameras according to the roadway structure data enables image acquisition to cover all key areas, improving the coverage rate of crack detection. Generating a time-series image set through continuous image acquisition can track the change trend of cracks, ensuring the timely discovery of the dynamic development of cracks. Conducting roadway morphology change analysis on the time-series image set can identify the growth and expansion of cracks and their impact on the surrounding environment, improving the accuracy of crack identification. Identifying the surface crack area by analyzing the roadway time-series change data and generating a crack area image provides accurate basic data for subsequent in-depth analysis and hidden crack identification. By analyzing the trend data of the crack orientation, understanding the direction and pattern of crack expansion helps predict the future development direction of cracks and optimize the maintenance strategy. Converting the crack area image into a depth map can extract the depth information of cracks and identify potential hidden cracks, which is often difficult to achieve in traditional image recognition. Conducting crack ductility analysis on the depth map to understand the ductility and stability of cracks provides data support for the long-term monitoring and repair of cracks. Combining the crack texture trend data and crack ductility data to confirm the hidden crack area improves the comprehensiveness of crack detection and reduces the risk of missed detection. Integrating the hidden crack and surface crack area images provides a comprehensive crack type image for convenient comprehensive analysis and management. Conducting thermal balance analysis on the crack type area image reveals the thermal characteristics and formation reasons of cracks, helping to identify the thermal influencing factors of cracks. Based on the thermal balance data, conducting crack spectrum analysis can identify the composition and material properties of cracks, improving the detail and accuracy of crack detection, and providing guidance for further crack repair and maintenance. Using the crack thermal balance and spectrum analysis data to divide the crack formation period helps understand the historical background and development process of cracks and supports long-term maintenance planning. Deducing and annotating the age of cracks to predict the future development trend of cracks, optimizing the maintenance strategy and resource allocation, and reducing potential safety risks. Adjusting the monitoring frequency of the camera according to the crack age deduction data ensures the dynamic adaptability of the monitoring work, improves the response speed and accuracy to crack changes, and enhances the monitoring effect of roadway cracks. Therefore, the present invention improves the accuracy and comprehensiveness of identification through dynamic change detection, hidden crack identification, crack classification and analysis, and crack age deduction.

[0077] In an embodiment of the present invention, referring to Figure 1 as described, it is a schematic diagram of the step process of a roadway crack identification method based on image recognition according to the present invention. In this example, the roadway crack identification method based on image recognition includes the following steps:

[0078] Step S1: Obtain roadway structure data; deploy area cameras according to the roadway structure data to obtain roadway camera deployment data; collect roadway images based on the roadway camera deployment data to generate a set of roadway time-series images; perform roadway morphological change analysis on the set of roadway time-series images to generate roadway time-series change data; identify the surface crack area of the set of roadway time-series images through the roadway time-series change data to generate a roadway surface crack area image;

[0079] In the embodiment of the present invention, the geometric structure, geological characteristics, and other relevant information of the roadway are obtained through laser scanning, geological surveys, or existing engineering drawings. The collected raw data is converted into a structured format, such as a 3D model or a digital topographic map, to ensure the accuracy and integrity of the data. According to the structural characteristics of the roadway and the key monitoring areas, the optimal positions of the cameras are planned to ensure that all areas to be monitored are covered. Cameras are installed at the planned positions, including fixing devices and cable wiring, to ensure that the cameras can work stably and have a good viewing angle. The shooting parameters of the cameras are set, including resolution, frame rate, exposure, etc., to adapt to the lighting and environmental conditions of the roadway. The cameras are started to take continuous or timed shots to generate a set of roadway time-series images. If necessary, image collection can be carried out at different time points to capture the changes in the roadway. The set of roadway time-series images is preprocessed, such as denoising, enhancing contrast, correcting distortion, etc. Image processing algorithms (such as background modeling, change detection algorithms) are applied to analyze the changes in the image sequence to generate roadway time-series change data. Common methods include differential images, optical flow analysis, etc. Deep learning or traditional image processing techniques (such as edge detection, region growing) are used to analyze the set of roadway time-series images to identify the surface crack area. A convolutional neural network (CNN) can be used for more accurate crack detection to generate a roadway surface crack area image, highlighting the crack area and providing data support for subsequent analysis and processing.

[0080] Step S2: Perform surface crack trend analysis on the roadway surface crack area image to generate surface crack texture trend data; perform depth map conversion based on the roadway surface crack area image to generate a roadway surface crack area depth map; perform crack ductility analysis on the roadway surface crack area depth map to generate surface crack ductility data; use the surface crack texture trend data and the surface crack ductility data to confirm the hidden roadway crack area of the roadway surface crack area image to obtain a hidden roadway crack area image;

[0081] In the embodiments of the present invention, by preprocessing the image of the fissure area on the roadway surface, including image denoising, contrast enhancement, etc., the detection accuracy of the fissure trend is improved. Texture analysis algorithms (such as gray-level co-occurrence matrix, local binary pattern, etc.) are used to extract the fissure texture features. Methods such as histogram of oriented gradients (HOG) and edge detection are applied to analyze the trend of the fissure, and the surface fissure texture trend data is generated. Machine learning methods (such as SVM, decision tree) can be combined to further optimize the detection result of the fissure trend. Based on the image of the fissure area on the roadway surface, stereo vision technology or deep learning methods (such as monocular depth estimation network) are used to generate the depth map of the fissure area on the roadway surface. Stereo vision technology requires at least two images at different angles for depth calculation, while deep learning methods directly estimate the depth from a single image through a trained network. Post-processing is performed on the generated depth map, such as smoothing, noise removal, and interpolation, to improve the quality of the depth map. The geometric features of the fissure are extracted from the depth map, including the width, depth, length, etc. of the fissure. Geometric analysis algorithms (such as fissure propagation model, fracture mechanics model) are applied to analyze the ductility of the fissure, and the surface fissure ductility data is generated, specifically including the potential propagation direction, distribution range, etc. of the fissure. Combining the surface fissure texture trend data and the surface fissure ductility data, data fusion technology (such as weighted average, decision fusion) is used to deeply analyze the fissure area on the roadway surface. By analyzing the fissure trend and ductility, the existing hidden fissure areas are identified. These areas are not easily found in the existing images, but their existence can be confirmed through data analysis, generating the image of the hidden roadway fissure area, highlighting the potential hidden fissure areas, and providing detailed fissure propagation information.

[0082] Step S3: Integrate the image of the hidden roadway fissure area and the image of the fissure area on the roadway surface to obtain the fissure type area image; perform fissure thermal balance analysis on the fissure type area image to generate the roadway fissure thermal balance data; perform fissure spectral analysis on the fissure type area image according to the roadway fissure thermal balance data to generate the roadway fissure spectral analysis data;

[0083] In the embodiments of the present invention, by preparing the images of the latent fracture regions and the surface fracture regions of the roadway, their resolutions and alignments are ensured to be consistent. Image registration techniques can be used to align the images. Image processing algorithms (such as region segmentation, edge detection) are used to identify the fracture regions, and the latent fracture regions and the surface fracture regions are classified and labeled. The identified fracture regions are combined into a comprehensive fracture type region image. Image fusion techniques (such as weighted fusion, pixel-level fusion) can be used to combine the fracture region images of different types to generate a complete fracture type region image. A thermal imaging device is used to photograph the roadway to obtain the thermal image data of the fracture regions. These data can reflect the thermal characteristics and thermal distribution of the fractures. A thermal analysis model (such as a heat conduction model, a heat balance equation) is applied to perform a heat balance analysis on the fracture type region image. The thermal distribution, heat flux density, and heat balance state of the fracture regions are calculated to generate the roadway fracture heat balance data. The consistency between the results of the heat balance analysis and the actual observation data is verified to ensure the accuracy of the data. A spectrometer or a hyperspectral imaging device is used to collect the spectral data of the roadway fracture regions to obtain the spectral data of the fracture regions. These data include information such as the reflectivity and absorptivity at different wavelengths. The collected spectral data are analyzed, and spectral analysis methods (such as principal component analysis, spectral feature extraction) are used to extract the spectral features of the fractures. This can help identify the composition of the fracture materials, the mineral content, etc. The spectral data are registered with the fracture type region image to generate the roadway fracture spectral analysis data. These data can reveal the compositional characteristics of the fractures and possible chemical changes.

[0084] Step S4: Based on the roadway fracture heat balance data and the roadway fracture spectral analysis data, the fracture formation period is divided to generate the fracture period data; the fracture age is deduced and labeled for the fracture type region image through the fracture period data to generate the fracture age deduction data; according to the fracture age deduction data, the monitoring frequency of the roadway camera deployment data is adjusted to perform the dynamic monitoring operation of roadway fracture identification.

[0085] In the embodiments of the present invention, by fusing the roadway fracture thermal balance data and the roadway fracture spectral analysis data, these data are used to infer the formation period of the fractures. The thermal characteristics and spectral features of the fractures can reveal the time information of the formation and evolution of the fractures. The time series analysis method and the thermal spectral model are applied to identify the formation period of the fractures. According to the change patterns in the thermal balance data and the spectral data, the age or formation period of the fractures is estimated. The fractures are divided into different stages or time periods according to their formation periods to generate fracture period data. These periods can be defined based on the changes in the thermal stability of the fractures, the changes in the spectral features, etc. A fracture age deduction model is constructed, and the fracture period data is applied to the model. This can use statistical methods or machine learning models (such as regression analysis, classification models) to predict the age of the fractures. The fracture type area image is labeled according to the fracture age deduction data. The age information of the fractures is labeled into the image using an image labeling tool to generate fracture age deduction data. The fracture age deduction results are verified to ensure their accuracy and reliability. This can be done by comparing with the on-site inspection results or using the known age of the fractures as the verification basis. According to the fracture age deduction data, the monitoring requirements for fractures of different ages are analyzed. For example, newer fractures may require more frequent monitoring, while older fractures may have a lower monitoring frequency. The monitoring frequency of the roadway cameras is adjusted based on the fracture age deduction data. A monitoring frequency adjustment strategy is formulated, such as increasing the monitoring frequency for new fracture areas and reducing the monitoring frequency for old fracture areas. A dynamic monitoring operation is implemented, and the cameras are configured according to the adjusted monitoring frequency to track the changes and development of the fractures in real time.

[0086] Preferably, step S1 includes the following steps:

[0087] Step S11: Obtain roadway structure data using laser scanning;

[0088] Step S12: Divide the roadway into regions according to the roadway structure data to generate roadway structure division data; Based on the roadway structure division data, camera deployment is carried out to obtain roadway camera deployment data;

[0089] Step S13: Based on a preset time interval, roadway image acquisition is carried out according to the roadway camera deployment data to generate a roadway time-series image set; Image preprocessing is performed on the roadway time-series image set to generate a standard roadway time-series image set, where image preprocessing includes image filtering, image brightness enhancement, and image normalization;

[0090] Step S14: Analyze the roadway morphology changes of the standard roadway time-series image set to generate roadway time-series change data; Identify the surface fracture area of the standard roadway time-series image set through the roadway time-series change data to generate a roadway surface fracture area image.

[0091] In the embodiments of the present invention, by using a laser scanning device to perform high-precision measurement on the interior of the roadway, detailed roadway structure data is obtained. These data include geometric features such as the width, height, shape, and wall inclination of the roadway, as well as obstacles and surface details within the roadway. Based on the obtained roadway structure data, a reasonable regional division of the roadway is carried out. The division basis specifically includes the geometric shape of the roadway, key positions (such as bends, intersections), or the division of functional areas according to different monitoring requirements. According to the divided areas, combined with the coverage range of the camera and the monitoring target, the optimal deployment positions of the cameras in each area are determined, and roadway camera deployment data is generated. These data ensure that the cameras can comprehensively cover the key areas within the roadway and minimize the monitoring blind spots. Image acquisition is carried out at set time intervals (such as every hour, every day), the states of the roadway at different time points are recorded, and a set of roadway sequential images is generated. Noise in the sequential images is removed to maintain the clarity of the images. The image brightness is adjusted to ensure that the details of the roadway can be clearly observed under different lighting conditions. The images are standardized to eliminate the differences caused by different shooting conditions (such as lighting, angle), making the sequential images comparable, and a set of standard roadway sequential images is generated. Using image analysis techniques, the changes in the roadway morphology in the set of standard roadway sequential images are analyzed. For example, by comparing the images at different times, phenomena such as shape changes inside the roadway, ground settlement, and wall displacement are detected. The analysis results are recorded in the form of roadway sequential change data. According to the roadway sequential change data, the possible crack areas on the roadway surface are further identified. This process includes steps such as crack detection, boundary recognition, and position marking, and finally an image of the crack area on the roadway surface is generated. These images can be used for subsequent maintenance and repair work.

[0092] Preferably, step S14 includes the following steps:

[0093] Step S141: Identify feature points in the set of standard roadway sequential images to generate standard roadway sequential image feature points; use the standard roadway sequential image feature points to unify the image perspectives of the set of standard roadway sequential images to generate a set of roadway images with unified perspectives;

[0094] Step S142: Extract multi-dimensional morphological features from the set of roadway images with unified perspectives to obtain roadway multi-dimensional morphological feature data, where the multi-dimensional morphological feature extraction includes edge line extraction, surface texture extraction, and geometric contour extraction; calculate the morphological change amount of the set of roadway images with unified perspectives according to the roadway multi-dimensional morphological feature data to generate roadway sequential morphological change amount data;

[0095] Step S143: Segment the abnormal roadway change regions in the unified perspective roadway image set by using the roadway time-series morphological change amount data to generate abnormal roadway change region images; perform crack feature matching on the abnormal roadway change region images to generate crack feature matching data;

[0096] Step S144: Label the surface crack regions in the abnormal roadway change region images according to the crack feature matching data to generate roadway surface crack region images.

[0097] In the embodiment of the present invention, by using the feature point recognition algorithm to process the images in the standard roadway time-series image set, the key feature points in the images are recognized, such as the corner points, intersection points of the roadway walls, and obvious texture features on the surface. By matching the feature points of the images at different times, the shooting perspective of the images is corrected to eliminate the influence caused by the change of the camera position or angle, ensuring that all images are compared and analyzed from the same perspective to generate a unified perspective roadway image set. Identify and extract the edge lines in the roadway, such as the boundary lines between the walls, the ground, and the ceiling, to obtain the contour information of the roadway. Extract the texture features on the surface of the roadway to identify the texture and subtle changes of the material. Extract the geometric contour of the roadway, including the shapes and structural information of the walls, the ground, and the ceiling, to generate the overall contour feature data of the roadway. By comparing the morphological features at different times, calculate the morphological change amount of the roadway in the time series, such as the displacement of the walls, the degree of surface damage, etc., to generate the roadway time-series morphological change amount data. Based on the roadway time-series morphological change amount data, identify the regions with abnormal changes in the roadway. These regions may have sharp morphological changes, indicating potential structural problems or damages. Further crack feature matching is performed on the identified abnormal regions. By comparing the morphological features of the abnormal regions, identify the possible cracks to generate crack feature matching data. Use the crack feature matching data to accurately label the cracks in the abnormal change regions to generate detailed roadway surface crack region images. These images can clearly show the positions, sizes, and morphologies of the cracks, providing a basis for subsequent repair and reinforcement work.

[0098] As an example of the present invention, refer to Figure 2 shown, in this example, the step S2 includes:

[0099] Step S21: Extract the surface crack patterns from the roadway surface crack region images to obtain the surface crack pattern distribution data; perform the analysis of the pattern orientation on the surface crack pattern distribution data to generate the surface crack pattern orientation data; perform the crack trend analysis on the surface crack pattern distribution data according to the surface crack pattern orientation data to generate the surface crack texture trend data;

[0100] Step S22: performing depth map conversion based on the crack area image on the tunnel surface to generate a crack area depth map on the tunnel surface; measuring the crack width and crack depth on the crack area depth map on the tunnel surface to obtain surface crack width data and surface crack depth data;

[0101] Step S23: performing crack ductility analysis based on the surface crack width data and the surface crack depth data to generate surface crack ductility data;

[0102] Step S24: using the surface crack texture trend data and the surface crack ductility data to confirm the hidden roadway crack area of ​​the roadway surface crack area image, and obtain the hidden roadway crack area image.

[0103] In the embodiment of the present invention, the cracks in the crack area image of the roadway surface are extracted by using an image processing algorithm, and the texture features of the cracks, such as the direction, shape, spacing, etc. of the cracks, are identified to obtain the surface crack texture distribution data. The extracted crack texture is analyzed for orientation, the overall direction and inclination angle of the crack are calculated, and the surface crack texture orientation data is generated. Combined with the crack texture orientation data, the crack trend is analyzed, the direction in which the crack may expand is identified, and the surface crack texture orientation trend data is generated. Using the depth information of the image, the crack area image of the roadway surface is converted into a depth image, the three-dimensional structure of the crack is displayed, and the depth map of the crack area on the roadway surface is generated. The width and depth of the crack are measured on the depth map, the size and depth of the crack are accurately evaluated, and the surface crack width data and surface crack depth data are generated. Based on the width and depth data of the crack, the ductility of the crack is analyzed, the possibility and rate of expansion of the crack in the roadway are evaluated, and the surface crack ductility data is generated. This analysis can reveal the possible development trend of the cracks in different locations and predict their possible changes in the future. Combined with the texture trend data and ductility data of surface cracks, the potential expansion path and stress condition of the cracks are further analyzed to identify the hidden crack areas that may exist in the tunnel but have not yet appeared. These hidden crack areas are marked in the image to generate hidden tunnel crack area images for subsequent monitoring and maintenance.

[0104] Preferably, step S24 includes the following steps:

[0105] Step S241: performing crack segment fitting on the crack region image on the surface of the tunnel according to the surface crack ductility data to generate crack extension speed assessment data;

[0106] Step S242: Perform crack texture line direction vector fitting on the crack area image on the surface of the tunnel according to the surface crack texture trend data to generate crack extension direction assessment data.

[0107] Step S243: Perform implicit crack correlation analysis using crack extension speed evaluation data and crack extension direction evaluation data to generate implicit crack correlation data;

[0108] Step S244: Based on the implicit crack correlation data, perform stress field simulation on the image of the roadway surface crack area to generate an image of the roadway implicit crack area.

[0109] In the embodiment of the present invention, the cracks in the image of the roadway surface crack area are segmented by using the surface crack ductility data. First, the crack area is divided into several segments, and polynomial fitting or Bezier curve fitting is performed according to the morphological characteristics of each segment of the crack to obtain the ductility data of each segment of the crack. This fitting process can accurately capture the subtle changes of the crack. By comparing the crack fitting results at different time periods, the extension speed of the crack in each segment is calculated. The extension speed evaluation can combine time series analysis techniques to generate crack extension speed evaluation data for subsequent prediction of the crack development trend. Using the surface crack texture orientation trend data, the direction of the crack texture lines in the image of the roadway surface crack area is fitted. By analyzing the microscopic structure and direction change of the crack texture, a vector analysis method is used to fit the main direction vector of the crack texture lines. According to the fitted direction vector and combined with the crack extension speed evaluation data, the main extension direction of the crack is determined. This direction evaluation can be quantified in combination with a spatial coordinate system to generate crack extension direction evaluation data. The crack extension speed evaluation data and the crack extension direction evaluation data are comprehensively analyzed to identify potential implicit cracks. Implicit cracks refer to cracks that have not been fully revealed due to local stress concentration or material defects. Through correlation analysis, the potential connection or expansion trend between cracks is found to generate implicit crack correlation data. This data can be used to predict the future damage risk of the roadway structure. Based on the implicit crack correlation data, stress field simulation is performed on the roadway surface crack area. The stress field simulation can be carried out by finite element analysis (FEA) or other numerical simulation methods to simulate the stress distribution of the roadway under different load conditions. The stress concentration degree in the implicit crack area is focused on in the simulation to judge its possible expansion path. Through the stress field simulation results, the potential implicit crack area is marked. Combining the previous crack extension speed and direction evaluation data, the final image of the roadway implicit crack area is generated. This image can be used to formulate a roadway maintenance plan to avoid structural failure caused by further expansion of implicit cracks.

[0110] As an example of the present invention, refer to Figure 3 shown, in this example, step S3 includes:

[0111] Step S31: Integrate the images of the hidden fissure areas and the surface fissure areas of the roadway to obtain the image of the fissure type area; collect the temperature changes of the fissures in the image of the fissure type area based on the infrared thermal imaging technology to generate the image of the temperature changes of the roadway fissures.

[0112] Step S32: Calculate the adjacent temperature difference of the image of the temperature changes of the roadway fissures to obtain the temperature difference data of the roadway fissures; calculate the rate of change of the temperature difference of the temperature difference data of the roadway fissures to obtain the rate of change data of the temperature difference.

[0113] Step S33: Conduct a fissure thermal balance analysis on the image of the temperature changes of the roadway fissures through the temperature difference data and the rate of change data of the temperature difference of the roadway fissures to generate the fissure thermal balance data of the roadway fissures.

[0114] Step S34: Conduct a fissure spectrum analysis on the image of the fissure type area based on the spectral analysis technology according to the fissure thermal balance data of the roadway fissures to generate the fissure spectrum analysis data of the roadway fissures.

[0115] In the embodiments of the present invention, the images of the hidden fissure areas and the surface fissure areas of the roadway are integrated. The integration process can be achieved through image superposition, feature matching, and region fusion techniques to ensure that the hidden fissures and surface fissures are completely displayed in the same image. The finally generated fissure type region image will contain all known fissure types and positions in the roadway. Based on the infrared thermal imaging technology, the temperature change of the integrated fissure type region image is monitored. The infrared thermal imaging device can capture the temperature distribution of the fissure area in real time. By collecting the temperature data at different time points multiple times, a roadway fissure temperature change image is generated. This image will show the dynamic characteristics of the temperature change in the fissure area over time. Pixel-level analysis is performed on the roadway fissure temperature change image to calculate the temperature difference between adjacent pixels within the fissure area. By statistically analyzing these temperature differences, roadway fissure temperature difference data is obtained. The temperature difference data can reflect the thermal distribution uniformity within the fissure area, as well as potential abnormal hot spots or cold spots. Further analyze the temperature difference data to calculate the rate of change of the temperature difference within the fissure area. The rate of change of the temperature difference data can be obtained by performing differential analysis on the temperature differences at different time points, revealing the speed changes of heat conduction and heat diffusion within the fissure area, and generating the rate of change of the temperature difference data. Using the roadway fissure temperature difference data and the rate of change of the temperature difference data, a heat balance analysis is performed on the fissure temperature change image. This analysis process includes evaluating the heat conduction and heat diffusion states within the fissure area to determine whether the fissure area is in a heat balance state or there is a heat imbalance phenomenon. The analysis results can be achieved through numerical simulation or image analysis techniques to generate roadway fissure heat balance data. The heat balance data is of great significance for judging the activity degree and potential expansion risk of the fissures. Based on the roadway fissure heat balance data, further analysis is performed on the fissure type region image using spectral analysis technology. Spectral analysis can reveal the optical properties of different materials within the fissure area, such as reflectivity, absorptivity, and emissivity. By analyzing these spectral characteristics, the material composition and deterioration degree of the fissure area are judged to generate roadway fissure spectral analysis data. Using the spectral analysis data and combining with the heat balance data, the types of fissures are further classified and identified, such as thermal fissures, cold fissures, or stress fissures, etc. This process can improve the accuracy of fissure detection and provide a scientific basis for subsequent roadway maintenance and repair.

[0116] Preferably, step S34 includes the following steps:

[0117] Step S341: Based on the spectral analysis technology, Raman spectroscopy of the fissure type region image is collected according to the roadway fissure heat balance data to obtain a roadway fissure spectrogram;

[0118] Step S342: Perform fissure environment element analysis on the roadway fissure spectrogram to generate fissure environment element data; identify the chemical substance components of the fissure type region data through the fissure environment element data to generate fissure environment chemical substance data;

[0119] Step S343: Analyze the oxidation state of the fissure material in the roadway fissure spectrogram to generate fissure material oxidation state data; analyze the oxidation degree of the fissure type area data based on the fissure material oxidation state data to generate fissure oxidation degree data;

[0120] Step S344: Analyze the time-varying characteristics of the fissure spectrum of the roadway fissure spectrogram through the fissure environment chemical substance data and the fissure oxidation degree data to generate roadway fissure spectrum analysis data.

[0121] In the embodiment of the present invention, based on the spectral analysis technology, the Raman spectrum of the fissure type area image is collected by using the roadway fissure thermal equilibrium data. The Raman spectroscopy technology analyzes the frequency shift information in the scattered light by irradiating the fissure surface with a laser to identify the molecular vibration modes of the fissure material. This process can capture the spectral characteristics of different materials in the fissure area and generate a roadway fissure spectrogram. This spectrogram shows the molecular structure information of the fissure area and is the basis for subsequent analysis. Conduct a detailed environmental element analysis of the roadway fissure spectrogram. This includes identifying various elements present in the fissure area, such as metal elements, non-metal elements, and possible pollutants, through the characteristic peaks in the spectrum. The analysis process can combine the Raman spectrum database and the matching algorithm to generate fissure environment element data. Use the fissure environment element data to identify the chemical substance composition of the fissure type area data. By comparing the spectral characteristics of known chemical substances, identify the chemical substance composition in the fissure area and generate fissure environment chemical substance data. This process helps to understand the material composition of the fissure area and possible external pollution sources. Analyze the oxidation state of the fissure material in the roadway fissure spectrogram. By observing the specific oxidation characteristic peaks in the spectrogram, the oxidation state of the material in the fissure area can be determined, such as the presence of iron oxide, aluminum oxide, etc. The generated fissure material oxidation state data can reflect the aging and deterioration of the fissure material. According to the fissure material oxidation state data, analyze the oxidation degree of the fissure type area data. Use quantitative analysis methods to calculate the oxidation degree of different materials in the fissure area and generate fissure oxidation degree data. This data helps to evaluate the long-term stability of the fissure and the risk of further expansion. Combine the fissure environment chemical substance data and the fissure oxidation degree data to analyze the time-varying characteristics of the spectral features of the roadway fissure spectrogram. By comparing the spectral data of different periods, identify the change trends of the material composition and oxidation state in the fissure area and generate roadway fissure spectrum analysis data. This analysis can reveal the dynamic change characteristics of the fissure and provide an important reference for predicting the development of the fissure.

[0122] As an example of the present invention, refer to Figure 4 As shown, in this example, the step S4 includes:

[0123] Step S41: Divide the formation periods of the fissures based on the roadway fissure heat balance data and the roadway fissure spectral analysis data to generate fissure period data;

[0124] Step S42: Deduce and label the fissure ages of the fissure type area images through the fissure period data to generate fissure age deduction data;

[0125] Step S43: Compare the fissure age deduction data with the preset fissure age range. When the fissure age deduction data is less than the preset fissure age range, mark the corresponding fissure type area image as a newly formed fissure period image; when the fissure age deduction data is within the preset fissure age range, mark the corresponding fissure type area image as a stable fissure period image; when the fissure age deduction data is greater than the preset fissure age range, mark the corresponding fissure type area image as an aged fissure period image;

[0126] Step S44: Conduct discrimination on the fissure age images of the fissure type area labeled images. When it is confirmed that the fissure type area image is a newly formed fissure period image, perform high-frequency monitoring on the roadway camera deployment data. When it is confirmed that the fissure type area image is a stable fissure period image, perform medium-frequency monitoring on the roadway camera deployment data. When it is confirmed that the fissure type area image is an aged fissure period image, perform low-frequency monitoring on the roadway camera deployment data to execute the dynamic monitoring operation of roadway fissure identification.

[0127] In the embodiments of the present invention, based on the roadway fracture thermal balance data and the roadway fracture spectral analysis data, by analyzing the temperature changes and spectral characteristics during the fracture formation process, the formation characteristics of fractures at different stages are identified. Using these data, the formation periods of fractures are divided, such as the newly formed period, the stable period, and the aging period, and the corresponding fracture period data are generated. These data will serve as the basis for subsequent fracture age deduction and annotation. By deeply analyzing the fracture period data, the formation age of the fracture is deduced. The specific method includes combining the thermal balance state, spectral characteristics, and time series data of the fracture to calculate the formation time of the fracture and annotating it on the fracture type area image to generate fracture age deduction data. This data can help identify the historical development status of the fracture. Comparing the fracture age deduction data with the preset fracture age range to determine the current stage of the fracture: if the fracture age deduction data is less than the preset fracture age range, it is marked as an image of the newly formed period of the fracture. If the fracture age deduction data is within the preset fracture age range, it is marked as an image of the stable period of the fracture. If the fracture age deduction data is greater than the preset fracture age range, it is marked as an image of the aging period of the fracture. When it is confirmed that the fracture type area image is an image of the newly formed period of the fracture, high-frequency monitoring is performed on the roadway camera deployment data. This means that during the rapid development stage of the fracture, more intensive monitoring is required to capture its changes. When it is confirmed that the fracture type area image is an image of the stable period of the fracture, medium-frequency monitoring is performed on the roadway camera deployment data. Since the fracture is in a stable stage, the monitoring frequency can be appropriately reduced, but regular observation still needs to be maintained. When it is confirmed that the fracture type area image is an image of the aging period of the fracture, low-frequency monitoring is performed on the roadway camera deployment data. As the fracture enters the aging period and changes slowly, the monitoring frequency can be further reduced.

[0128] Preferably, step S42 includes the following steps:

[0129] Step S421: Extract fracture period characteristics from the fracture period data through a preset fracture period characteristic database to obtain fracture period characteristic data;

[0130] Step S422: Divide the fracture period characteristic data into a data set to generate a model training set and a model test set; use the support vector machine algorithm to train the model training set to generate a preliminary fracture age deduction model;

[0131] Step S423: Optimize and iterate the preliminary fracture age deduction model through the model test set to generate a fracture age deduction model; import the fracture type area image into the fracture age deduction model for fracture age deduction and annotation to generate a labeled image of the fracture type area.

[0132] In the embodiments of the present invention, feature extraction is performed on the fracture period data through a preset fracture period feature database. These features may include the thermal equilibrium state, spectral features, extension direction, and velocity of the fractures, etc. By extracting these feature data, valuable inputs can be provided for subsequent model training. Finally, fracture period feature data is obtained, which reflects the unique behavior patterns of fractures at different times. The fracture period feature data is divided into a model training set and a model test set. The model training set is used to build a model, while the model test set is used to verify the performance and accuracy of the model. The support vector machine (SVM) algorithm is used to train the model training set to generate a pre-model for inferring fracture age. The support vector machine is a machine learning algorithm commonly used in classification and regression analysis, especially suitable for processing complex high-dimensional data, such as fracture period feature data. The pre-model for inferring fracture age is optimized and iterated through the model test set, and the parameters and structure of the model are adjusted to improve the accuracy of its prediction. Finally, an optimized fracture age inference model is generated. The fracture type area image is imported into the optimized fracture age inference model for fracture age inference, and the results are labeled. In this way, a labeled image of the fracture type area can be automatically generated, providing accurate references for subsequent monitoring and maintenance work.

[0133] In this specification, a roadway fracture identification system based on image recognition is provided for performing the above-mentioned roadway fracture identification method based on image recognition. The roadway fracture identification system based on image recognition includes:

[0134] A surface fracture area identification module, configured to obtain roadway structure data; deploy area cameras according to the roadway structure data to obtain roadway camera deployment data; collect roadway images according to the roadway camera deployment data to generate a set of roadway time-series images; perform roadway morphology change analysis on the set of roadway time-series images to generate roadway time-series change data; identify the surface fracture area of the set of roadway time-series images through the roadway time-series change data to generate a roadway surface fracture area image;

[0135] A hidden fracture area identification module, configured to perform surface fracture trend analysis on the roadway surface fracture area image to generate surface fracture texture trend data; perform depth map conversion based on the roadway surface fracture area image to generate a roadway surface fracture area depth map; perform fracture ductility analysis on the roadway surface fracture area depth map to generate surface fracture ductility data; use the surface fracture texture trend data and the surface fracture ductility data to confirm the hidden roadway fracture area of the roadway surface fracture area image to obtain a hidden roadway fracture area image;

[0136] The fracture feature recognition module is used to integrate the images of hidden fracture regions and surface fracture regions in the roadway to obtain fracture type region images; perform fracture thermal balance analysis on the fracture type region images to generate roadway fracture thermal balance data; perform fracture spectral analysis on the fracture type region images according to the roadway fracture thermal balance data to generate roadway fracture spectral analysis data;

[0137] The monitoring frequency adjustment module is used to divide the fracture formation periods based on the roadway fracture thermal balance data and the roadway fracture spectral analysis data to generate fracture period data; deduce and label the fracture ages of the fracture type region images through the fracture period data to generate fracture age deduction data; adjust the monitoring frequency of the roadway camera deployment data according to the fracture age deduction data to perform dynamic monitoring operations for roadway fracture identification.

[0138] The beneficial effects of the present invention are as follows: By obtaining roadway structure data and deploying cameras, the structural layout of the roadway can be comprehensively understood, ensuring that data collection covers the entire roadway area and guaranteeing the comprehensiveness and accuracy of subsequent analysis. Analyzing the time-sequential image set of the roadway can monitor the changes in the roadway morphology, identify potential surface crack areas, and provide key data support for the timely discovery and treatment of cracks. Through morphological change analysis and surface crack area identification, crack areas can be effectively distinguished, laying a foundation for subsequent crack feature analysis and evaluation. Analyzing the trend of the surface crack orientation can understand the crack propagation direction and provide valuable information for further crack management and repair. Through depth map conversion and crack ductility analysis, the width and depth of cracks can be accurately measured, the ductility of cracks can be evaluated, and the impact degree of cracks on the roadway structure can be helped to be evaluated. Combining the crack orientation trend data and ductility data to confirm the hidden crack area helps to discover those cracks that may be difficult to detect, so as to carry out maintenance in advance and avoid potential risks. Integrating the hidden crack area image with the surface crack area image provides a comprehensive crack type area image, which helps to better understand the distribution and nature of cracks. Through crack thermal balance analysis, the thermal characteristics of cracks can be understood, which helps to reveal the formation mechanism of cracks and their impact on the roadway structure. Conducting spectral analysis on cracks can detect the chemical components and material properties in the cracks, provide an in-depth understanding of the crack formation causes, and provide a scientific basis for formulating repair strategies. Dividing the crack formation period according to the crack thermal balance data and spectral analysis data can determine the age of the cracks, understand the evolution process of the cracks, and provide timeliness information for crack management. Through crack age deduction and annotation, the age status of different cracks can be accurately understood, and corresponding maintenance strategies can be formulated according to the actual situation of the cracks. Adjusting the monitoring frequency of the roadway cameras according to the crack age deduction data can achieve targeted dynamic monitoring, improve the monitoring efficiency and effect, and ensure the timely discovery and treatment of new crack problems. Therefore, the present invention improves the accuracy and comprehensiveness of identification through dynamic change detection, hidden crack identification, crack classification and analysis, and crack age deduction.

[0139] Therefore, from any point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, it is intended to cover all changes falling within the meaning and scope of the equivalent elements of the application documents within the present invention.

[0140] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features invented herein.

Claims

1. A tunnel crack identification method based on image recognition, characterized in that: The following steps are involved: Step S1: Acquire tunnel structure data; perform regional camera deployment according to the tunnel structure data to obtain tunnel camera deployment data; perform tunnel image acquisition according to the tunnel camera deployment data to generate a tunnel time-series image set; perform tunnel morphology change analysis on the tunnel time-series image set to generate tunnel time-series change data; perform surface crack area recognition on the tunnel time-series image set using the tunnel time-series change data to generate a tunnel surface crack area image; Step S2: performing surface crack trend analysis on the crack area image on the tunnel surface to generate surface crack texture trend data; Performing depth map conversion based on the crack area image on the roadway surface to generate a depth map of the crack area on the roadway surface; Conduct crack ductility analysis on the depth map of crack areas on the roadway surface to generate surface crack ductility data; The surface crack texture trend data and surface crack ductility data are used to confirm the hidden crack area of ​​the roadway surface crack area image, and the hidden crack area image of the roadway is obtained; Step S3: integrating the tunnel hidden crack region image and the tunnel surface crack region image into a crack type region image to obtain a crack type region image; performing crack thermal balance analysis on the crack type region image to generate tunnel crack thermal balance data; performing crack spectrum analysis on the crack type region image according to the tunnel crack thermal balance data to generate tunnel crack spectrum analysis data; Step S4: dividing the crack formation period based on the roadway crack heat balance data and the roadway crack spectrum analysis data to generate crack period data; performing crack age deduction and labeling on the crack type area image through the crack period data to generate crack age deduction data; The monitoring frequency of the tunnel camera deployment data is adjusted according to the crack age deduction data to perform dynamic monitoring operations for tunnel crack identification.

2. The method for identifying cracks in tunnels based on image recognition according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: using laser scanning to obtain tunnel structure data; Step S12: dividing the lane into regions according to the lane structure data to generate lane structure division data; deploying cameras based on the lane structure division data to obtain lane camera deployment data; Step S13: performing lane image acquisition according to the lane camera deployment data at a preset time interval to generate a lane time series image set; performing image preprocessing on the lane time series image set to generate a standard lane time series image set, wherein the image preprocessing includes image filtering, image brightness enhancement and image standardization; Step S14: Analyze the changes in lane morphology of the standard lane time series image set to generate lane time series change data; identify surface crack areas of the standard lane time series image set using the lane time series change data to generate lane surface crack area images.

3. The method for identifying cracks in tunnels based on image recognition according to claim 2, characterized in that: Step S14 includes the following steps: Step S141: performing feature point recognition on the standard lane time series image set to generate feature points of the standard lane time series image; using the feature points of the standard lane time series image to unify the image perspective of the standard lane time series image set to generate a unified perspective lane image set; Step S142: extracting multi-dimensional morphological features from the unified perspective lane image set to obtain lane multi-dimensional morphological feature data, wherein the multi-dimensional morphological feature extraction includes edge line extraction, surface texture extraction, and geometric contour extraction; calculating the morphological variation of the unified perspective lane image set according to the lane multi-dimensional morphological feature data to generate lane time series morphological variation data; Step S143: using the lane time series morphological change data to segment the lane image set with the uniform view angle into abnormal lane change regions, and generate abnormal lane change region images; performing crack feature matching on the abnormal lane change region images, and generating crack feature matching data; Step S144: annotating the surface crack area of ​​the abnormal tunnel change area image according to the crack feature matching data to generate a tunnel surface crack area image.

4. The method for identifying cracks in tunnels based on image recognition according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: extracting surface crack textures from the crack area image on the tunnel surface to obtain surface crack texture distribution data; performing texture orientation analysis on the surface crack texture distribution data to generate surface crack texture orientation data; performing crack orientation trend analysis on the surface crack texture distribution data according to the surface crack texture orientation data to generate surface crack texture orientation trend data; Step S22: performing depth map conversion based on the crack area image on the tunnel surface to generate a crack area depth map on the tunnel surface; measuring the crack width and crack depth on the crack area depth map on the tunnel surface to obtain surface crack width data and surface crack depth data; Step S23: performing crack ductility analysis based on the surface crack width data and the surface crack depth data to generate surface crack ductility data; Step S24: using the surface crack texture trend data and the surface crack ductility data to confirm the hidden roadway crack area of ​​the roadway surface crack area image, and obtain the hidden roadway crack area image.

5. The method for identifying cracks in tunnels based on image recognition according to claim 1, characterized in that: Step S24 includes the following steps: Step S241: performing crack segment fitting on the crack region image on the surface of the tunnel according to the surface crack ductility data to generate crack extension speed assessment data; Step S242: Perform crack texture line direction vector fitting on the crack area image on the surface of the tunnel according to the surface crack texture trend data to generate crack extension direction assessment data. Step S243: Performing implicit crack association analysis based on the crack extension speed assessment data and the crack extension direction assessment data to generate implicit crack association data; Step S244: Perform stress field simulation on the crack area image on the tunnel surface based on the hidden crack association data to generate a hidden crack area image of the tunnel.

6. The method for identifying cracks in tunnels based on image recognition according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: integrating the tunnel hidden crack region image and the tunnel surface crack region image into a crack type region image to obtain a crack type region image; collecting crack temperature changes in the crack type region image based on infrared thermal imaging technology to generate a tunnel crack temperature change image; Step S32: performing adjacent temperature difference calculation on the tunnel crack temperature change image to obtain the tunnel crack temperature difference data; performing temperature difference change rate calculation on the tunnel crack temperature difference data to obtain the temperature difference change rate data; Step S33: performing crack heat balance analysis on the crack temperature change image of the tunnel using the crack temperature difference data and the temperature difference change rate data to generate crack heat balance data of the tunnel; Step S34: Based on the spectral analysis technology, crack spectrum analysis is performed on the crack type area image according to the tunnel crack thermal balance data to generate tunnel crack spectrum analysis data.

7. The method for identifying cracks in tunnels based on image recognition according to claim 6, characterized in that: Step S34 includes the following steps: Step S341: performing Raman spectrum acquisition on the crack type area image according to the roadway crack thermal balance data based on the spectrum analysis technology to obtain the roadway crack spectrum map; Step S342: performing crack environment element analysis on the crack spectrum of the roadway to generate crack environment element data; identifying chemical composition of the crack type area data through the crack environment element data to generate crack environment chemical substance data; Step S343: analyzing the oxidation state of the crack material on the crack spectrum of the roadway to generate crack material oxidation state data; analyzing the oxidation degree of the crack type area data according to the crack material oxidation state data to generate crack oxidation degree data; Step S344: Analyze the changes in crack spectrum characteristics during the time period of the roadway crack spectrum diagram using the crack environmental chemical substance data and the crack oxidation degree data to generate roadway crack spectrum analysis data.

8. The method for identifying cracks in tunnels based on image recognition according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: dividing the crack formation period based on the roadway crack heat balance data and the roadway crack spectrum analysis data to generate crack period data; Step S42: deduce and annotate the fracture age of the fracture type region image using the fracture period data to generate fracture age deduction data; Step S43: Compare the fracture age deduction data with the preset fracture age range. When the fracture age deduction data is less than the preset fracture age range, the corresponding fracture type regional image is marked as a fracture new formation period image; when the fracture age deduction data is within the preset fracture age range, the corresponding fracture type regional image is marked as a fracture stable period image; when the fracture age deduction data is greater than the preset fracture age range, the corresponding fracture type regional image is marked as a fracture aging period image; Step S44: Perform crack age image discrimination on the crack type area annotated image. When it is confirmed that the crack type area image is a crack newly formed period image, high-frequency monitoring of the alley camera deployment data is performed. When it is confirmed that the crack type area image is a crack stable period image, medium-frequency monitoring of the alley camera deployment data is performed. When it is confirmed that the crack type area image is a crack aging period image, low-frequency monitoring of the alley camera deployment data is performed to execute dynamic monitoring operations for alley crack identification.

9. The method for identifying cracks in tunnels based on image recognition according to claim 8, characterized in that: Step S42 includes the following steps: Step S421: extracting crack period features from the crack period data using a preset crack period feature database to obtain crack period feature data; Step S422: dividing the data set of the crack period characteristic data to generate a model training set and a model test set; using the support vector machine algorithm to perform model training on the model training set to generate a crack age deduction pre-model; Step S423: The fracture age deduction pre-model is optimized and iterated through the model test set to generate a fracture age deduction model; the fracture type area image is imported into the fracture age deduction model to perform fracture age deduction and annotation to generate a fracture type area annotation image.

10. A tunnel crack identification system based on image recognition, characterized in that: For executing the tunnel crack identification method based on image recognition as claimed in claim 1, the tunnel crack identification system based on image recognition comprises: The surface crack area recognition module is used to obtain the tunnel structure data; perform regional camera deployment according to the tunnel structure data to obtain the tunnel camera deployment data; perform tunnel image acquisition according to the tunnel camera deployment data to generate a tunnel time series image set; perform tunnel morphology change analysis on the tunnel time series image set to generate tunnel time series change data; perform surface crack area recognition on the tunnel time series image set through the tunnel time series change data to generate a tunnel surface crack area image; The hidden crack area identification module is used to perform surface crack trend analysis on the crack area image on the roadway surface to generate surface crack texture trend data; perform depth map conversion based on the crack area image on the roadway surface to generate a crack area depth map on the roadway surface; perform crack ductility analysis on the crack area depth map on the roadway surface to generate surface crack ductility data; use the surface crack texture trend data and surface crack ductility data to confirm the hidden roadway crack area on the crack area image on the roadway surface to obtain a hidden roadway crack area image; The crack feature recognition module is used to integrate the tunnel hidden crack area image and the tunnel surface crack area image into a crack type area image to obtain a crack type area image; perform crack thermal balance analysis on the crack type area image to generate tunnel crack thermal balance data; perform crack spectrum analysis on the crack type area image according to the tunnel crack thermal balance data to generate tunnel crack spectrum analysis data; The monitoring frequency adjustment module is used to divide the crack formation period based on the tunnel crack thermal balance data and the tunnel crack spectral analysis data to generate crack period data; to deduce and mark the crack age of the crack type area image through the crack period data to generate crack age deduction data; and to adjust the monitoring frequency of the tunnel camera deployment data according to the crack age deduction data to perform dynamic monitoring operations for tunnel crack identification.

Images