Tunnel crack defect evaluation method and system

Abstract

The invention discloses a tunnel crack defect evaluation method, system, medium and equipment, and relates to the technical field of image recognition, and the method comprises the steps: obtaining crack image data of a to-be-evaluated tunnel, carrying out the labeling and preprocessing, and obtaining the labeled crack image data; taking the U-Net architecture as a basis, combining with a feature pyramid network, introducing an attention module, constructing a multi-scale crack defect evaluation model, obtaining crack image data of an evaluated tunnel as a data set, training and optimizing parameters of the multi-scale crack defect evaluation model, and obtaining an optimized multi-scale crack defect evaluation model; and obtaining preprocessed crack image data of the to-be-evaluated tunnel, and inputting the preprocessed crack image data into the optimized multi-scale crack defect evaluation model to obtain a crack defect evaluation result.

Description

Technical Field

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

[0002] As an important part of modern transportation infrastructure, the structural safety of tunnels is of vital importance. During the long-term operation of tunnels, due to the influence of geological conditions, environmental factors, vehicle loads and other factors, cracks and other defects may appear in the structure of tunnels. If these cracks are not detected and repaired in time, they may cause further damage to the tunnel structure and even cause safety accidents.

[0003] With the development of machine vision and image processing technology, the research on intelligent detection of tunnel cracks has been continuously expanded. The current research on automatic detection of tunnel defects mainly uses visual detection technology to collect and intelligently process tunnel defect images.

[0004] At present, the detection of tunnel cracks mainly relies on the following technologies: Visual inspection: Professionals conduct visual inspection inside the tunnel. This method is simple and easy, but inefficient and difficult to detect tiny cracks. It also poses safety risks. Ultrasonic detection: The reflection principle of ultrasonic waves is used to detect cracks inside the material, but a coupling agent is required and the operator's skills are high. The detection effect is limited for complex cracks and non-uniform materials. Infrared thermal imaging technology: Cracks are identified by detecting the temperature difference on the surface of the tunnel, but it is greatly affected by the ambient temperature and cannot detect deep cracks. Laser scanning technology: Three-dimensional data of the tunnel surface can be obtained to detect cracks, but the equipment cost is high, the data processing is complex, and the detection effect is poor for cracks covered by dirt. Acoustic emission technology: The sound wave signal generated when the crack inside the material expands is monitored, but it can only be detected when the crack is active and is not suitable for the detection of static cracks. Electromagnetic detection technology: Cracks are detected by changes in the electromagnetic field, but it is not applicable to non-conductive materials and the detection depth is limited.

[0005] The limitations of the above technologies are mainly reflected in the following aspects: Low detection efficiency: Traditional methods require a lot of manpower and time for detection, especially in long-distance tunnels. Insufficient detection accuracy: The detection ability of small cracks or deep cracks is insufficient, which is easy to cause missed detection. Complex data processing: Although some technologies can collect a large amount of data, they lack effective data processing methods and cannot quickly and accurately analyze crack information. Poor environmental adaptability: Many detection technologies are greatly affected by environmental factors, such as temperature, humidity, light, etc., which affects the accuracy of detection. Therefore, it is necessary to develop a new tunnel crack defect assessment method to improve the efficiency and accuracy of detection, reduce the impact of environmental factors, and realize automated and intelligent crack detection. Summary of the invention

[0006] In order to overcome the above-mentioned shortcomings of the prior art, the main purpose of the present invention is to provide a tunnel crack defect assessment method and system.

[0007] To achieve the above object, the present invention adopts the following technical solution, a tunnel crack defect assessment method, comprising the following steps:

[0008] Taking the U-Net architecture as the basis, a feature pyramid network is added to obtain a hybrid network structure, in which CBAM is inserted after the convolution block of the hybrid network structure, SENet is added after the bottleneck layer between the encoder and the decoder, and a Non-local module is placed after the deepest convolution block of the encoder to build a multi-scale crack defect assessment model;

[0009] Acquire the evaluated annotated crack image data as a data set, train and optimize the parameters of the multi-scale crack defect evaluation model, and obtain an optimized multi-scale crack defect evaluation model;

[0010] After preprocessing, the acquired tunnel crack image data to be evaluated is input into the optimized multi-scale crack defect evaluation model to obtain the crack defect evaluation result.

[0011] The method of obtaining the hybrid network structure comprises the following steps:

[0012] The U-Net architecture includes a downsampling path and an upsampling path;

[0013] The FPN passes through a top-down path and a bottom-up path;

[0014] After each downsampling stage of the U-Net, the top-down path of the FPN is introduced to concatenate and fuse the features of the current layer with the features of the previous layer; before each upsampling stage of the U-Net, the bottom-up path of the FPN is introduced to concatenate and add the features of the current layer with the features of the next layer to obtain a hybrid network structure.

[0015] The step of obtaining the annotated crack image data comprises the following steps:

[0016] Define the standard of tunnel cracks, select annotation tools to annotate crack image data of the tunnel to be evaluated, identify the crack location, draw a bounding box for each crack, and perform pixel-level annotation using semantic segmentation to obtain preliminary annotated crack image data;

[0017] The initially annotated crack image data is subjected to image enhancement, size adjustment, normalization and cleaning, and then data segmentation is performed to obtain the annotated crack image data.

[0018] The step of obtaining the optimized multi-scale crack defect assessment model comprises the following steps:

[0019] The evaluated annotated tunnel crack image data is obtained as a dataset and divided into a training set, a validation set, and a test set.

[0020] Select the loss function as binary cross entropy, select the optimizer as SGD, and set the hyperparameters, including the training batch size, learning rate, number of iterations, regularization parameter, dropout ratio, activation function, and architecture parameters of the multi-scale crack defect assessment model;

[0021] The validation set is used to perform model evaluation and hyperparameter adjustment on the multi-scale crack defect assessment model to obtain the optimized multi-scale crack defect assessment model.

[0022] The method of obtaining the crack defect evaluation result comprises the following steps:

[0023] Extracting the preprocessed tunnel crack image data to be evaluated by using encoder features to obtain extracted features, and enhancing the extracted features by using CBA, SENet and Non-local to obtain multi-level enhanced features;

[0024] The feature maps of the low level in the multi-level enhanced features are upsampled to a high level to obtain the sampled feature maps, and then the upsampled feature maps are concatenated with the high-level original feature maps using the side connection to obtain the concatenated features;

[0025] Apply convolution operation on the concatenated feature maps to fuse features of different scales, repeat the above fusion process for each pyramid level until the top level, and obtain multi-scale fused feature map data;

[0026] The multi-scale fusion feature mapping data is subjected to contour detection, classification and quantification to obtain the crack defect assessment results.

[0027] The process of performing contour detection, classification and quantification on the multi-scale fusion feature mapping data comprises the following steps:

[0028] The multi-scale fusion feature mapping data is used to identify possible crack areas by setting the activation function Sigmoid to obtain multiple crack areas;

[0029] Applying conditional random fields and region growing to refine the multiple crack regions to obtain multiple refined crack regions;

[0030] Perform contour extraction on multiple refined crack regions to obtain boundaries of multiple cracks;

[0031] Verifying and obtaining specific boundaries of multiple cracks through morphological operations and geometric constraints, and obtaining multiple detected crack regions; the geometric constraints include length and width ratios of the cracks;

[0032] Extract feature vectors for each detected crack region based on multi-scale fusion feature mapping, including texture, shape, and size;

[0033] Performing normalization on the feature vector to obtain a normalized feature vector;

[0034] Input the standardized feature vector into the pre-trained classification model to obtain the classification result of the crack;

[0035] The classification results are limited by non-maximum suppression merging overlap to generate crack defect assessment results.

[0036] A tunnel crack defect assessment system, comprising:

[0037] A data acquisition module, used to acquire crack image data about the tunnel to be evaluated, perform annotation and preprocessing, and obtain annotated crack image data;

[0038] An evaluation model building module is used to use the U-Net architecture as a basis, add a feature pyramid network, obtain a hybrid network structure, insert CBAM after the convolution block of the hybrid network structure, add SENet after the bottleneck layer between the encoder and the decoder, and place a Non-local module after the deepest convolution block of the encoder to build a multi-scale crack defect evaluation model; obtain the evaluated annotated crack image data as a data set, train and optimize the parameters of the multi-scale crack defect evaluation model, and obtain an optimized multi-scale crack defect evaluation model;

[0039] The evaluation and analysis module is used to pre-process the tunnel crack image data to be evaluated and then input it into the optimized multi-scale crack defect evaluation model to obtain the crack defect evaluation result.

[0040] Compared with the prior art, the beneficial effects of the present invention are as follows: by improving the U-Net architecture, the feature pyramid network is introduced to realize multi-scale feature fusion, so that the model can simultaneously capture the global semantic features and local detail features of the crack, and is particularly suitable for detecting cracks of various scales and complex forms. And through the inserted CBAM, SENet and Non-local modules, the focus is on the significant area of ​​the crack, the interference of background noise on feature extraction is suppressed, the importance between feature channels is emphasized, the sensitivity of crack detection is improved, long-distance dependencies are captured, and the model's detection ability for crack discontinuity and discontinuity is improved. The accuracy of crack detection is improved, especially under complex background and low contrast conditions. It helps the model focus on the key areas of the crack, improves the characterization ability of the features, and accurately classifies and quantifies the cracks. It can classify the detected cracks such as length, width, depth, etc. and quantify them such as defect level, providing detailed information for tunnel maintenance. The speed of crack detection is greatly improved, especially in large-scale tunnel detection projects, reducing the time and labor cost required for manual detection, and also reducing the risk of false detection and missed detection due to human error. By accurately assessing tunnel crack defects, timely maintenance can be carried out, thus ensuring the safety and reliability of the tunnel structure. The systematic approach makes the model easy to integrate and deploy, and subsequent maintenance is relatively simple.

[0041] In summary, the tunnel crack defect assessment method and technical system implemented by the above content not only improves the automation and efficiency of detection, but also improves the accuracy and safety of detection, providing strong technical support for tunnel maintenance and management. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The drawings described herein are used to provide further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute improper limitations on the present application.

[0043] Figure 1 It is a schematic diagram of the process structure of the present invention;

[0044] Figure 2 It is a schematic diagram of the process of constructing a multi-scale crack defect assessment model according to the present invention;

[0045] Figure 3 It is a schematic diagram of the process of obtaining crack image data of the present invention;

[0046] Figure 4 It is a schematic diagram of the process of optimizing the multi-scale crack defect evaluation model of the present invention;

[0047] Figure 5 It is a schematic diagram of the main process of crack defect evaluation results of the present invention;

[0048] Figure 6 It is a schematic diagram of the process framework of the crack defect evaluation result of the present invention;

[0049] Figure 7 It is a schematic diagram of the framework structure of the tunnel crack defect assessment system of the present invention;

[0050] Figure 8 It is a schematic diagram of the network structure of the multi-scale crack defect evaluation model in the present invention.

[0051] 1.CBAM module, 2.SENet module, 3.Non-local module. DETAILED DESCRIPTION

[0052] The limitations of existing tunnel crack detection technologies are mainly reflected in the following aspects: Low detection efficiency: Traditional methods require a lot of manpower and time for detection, especially in long-distance tunnels. Insufficient detection accuracy: The detection ability of small cracks or deep cracks is insufficient, which can easily lead to missed detection. Complex data processing: Although some technologies can collect a large amount of data, they lack effective data processing methods and cannot quickly and accurately analyze crack information. Poor environmental adaptability: Many detection technologies are greatly affected by environmental factors, such as temperature, humidity, light, etc., which affect the accuracy of detection. Therefore, it is necessary to develop a new tunnel crack defect assessment method to improve the efficiency and accuracy of detection, reduce the impact of environmental factors, and realize automated and intelligent crack detection.

[0053] In order to overcome the above-mentioned shortcomings of the prior art, the main purpose of the present invention is to provide a tunnel crack defect evaluation method. Figure 1-Figure 8 , including the following steps:

[0054] Acquire crack image data of a tunnel to be evaluated, perform annotation and preprocessing, and obtain annotated crack image data;

[0055] Taking the U-Net architecture as the basis, adding the feature pyramid network, obtaining a hybrid network structure, inserting CBAM after the convolution block of the hybrid network structure, adding SENet after the bottleneck layer between the encoder and the decoder, and placing a Non-local module after the deepest convolution block of the encoder, to construct a multi-scale crack defect assessment model; obtaining crack image data of the evaluated tunnel as a data set, training and optimizing the parameters of the multi-scale crack defect assessment model, and obtaining an optimized multi-scale crack defect assessment model;

[0056] The preprocessed crack image data of the tunnel to be evaluated is obtained and input into the optimized multi-scale crack defect evaluation model to obtain the crack defect evaluation result.

[0057] Among them, the multi-scale crack defect assessment model is constructed, see Figure 2 , including the following steps:

[0058] Design the U-Net architecture, such as Figure 8 As shown in the figure, the convolution layer and pooling layer of the encoder are implemented, and the upsampling layer and convolution layer of the decoder are implemented; the core of designing the U-Net architecture lies in the deep feature extraction of the encoder and the precise positioning and restoration of the decoder. The convolution layer is responsible for extracting image features, while the pooling layer is used to reduce the feature dimension and expand the receptive field. In the encoder, through the stacking of convolution layers and pooling layers layer by layer, feature abstraction from low to high layers is achieved, providing rich contextual information for subsequent defect recognition. While reducing the computational complexity, the pooling layer helps the model capture a wider distribution of crack defects. The upsampling layer of the decoder is used to restore the spatial resolution of the image, while the convolution layer is used to refine the feature map and enhance the model's ability to recognize crack details. The upsampling layer gradually restores the size of the feature map by interpolation or transposed convolution, providing support for accurate positioning of the crack position. The role of the convolution layer in the decoder is to further refine the features, strengthen the edge information of the crack defect, and improve the positioning accuracy of the model.

[0059] Taking the U-Net architecture as the basis, after adding the feature pyramid network, multiple attention modules are introduced. Specifically, CBAM is placed after the convolution block of the U-Net architecture, SENet is placed after the bottleneck layer between the encoder and the decoder, and the Non-local module is placed after the deepest convolution block of the encoder to build a multi-scale crack defect assessment model.

[0060] The introduction of attention modules in the hybrid network structure, among which, the application of CBAM module, CBAM (Convolutional Block Attention Module) is an effective attention mechanism, which enhances the model's ability to focus on key features by paying attention to the channel and spatial dimensions respectively. The channel attention mechanism evaluates the importance of different channels and assigns weights to each channel, so that the model can pay more attention to the features that contribute to crack recognition. This mechanism helps the model to accurately identify crack defects in complex backgrounds and improve the robustness of defect detection. The spatial attention mechanism focuses on the importance of different positions in the image, and accurately locates the crack position by assigning weights to each pixel position. Guided by spatial attention, the model can focus more on the crack area, reduce interference from non-crack areas, and improve the accuracy of crack detection. The introduction of the spatial attention mechanism enables the model to better adapt to the shape and position changes of cracks when processing crack defects, and improves the generalization ability of the model. And SENet (Squeeze-and-Excitation Networks) adaptively recalibrates the importance of feature channels, enhancing the model's ability to express crack features. The SE module learns the correlation between channels through global average pooling and fully connected layers, generates an attention weight for each channel, and realizes dynamic adjustment of feature channels. The introduction of this module enables the model to pay more attention to the feature channels that are important for crack identification, improving the accuracy and robustness of crack defect assessment. There is also the fusion of the Non-local module. The Non-local module uses the self-attention mechanism to model the long-distance dependency between any two positions in the image, enhancing the model's use of global contextual information. By calculating the association between each position and all other positions, the Non-local module can capture the global information of crack defects and improve the model's ability to identify cracks. The introduction of this module enables the model to take into account more distant contextual information when processing crack defects, improving the accuracy and robustness of crack detection.

[0061] Among them, see 8, the location of adding CBAM, SENet and Non-local modules in the hybrid network structure

[0062] CBAM (Convolutional Block Attention Module) is added: The CBAM module is inserted after each convolution block of the hybrid network structure. This means that after each convolution operation, channel attention and spatial attention are calculated to enhance feature representation.

[0063] Adding location of SENet (Squeeze-and-Excitation Network): SENet is added after the bottleneck layer between the encoder and decoder.

[0064] The bottleneck layer is the part of the network that connects the encoder and decoder. Usually, the spatial size of the feature map is small but the number of channels is large. Adding SENet here can effectively model the dependencies between channels and improve the ability of feature representation.

[0065] Where to add the non-local module: The non-local module is placed after the deepest convolutional block of the encoder. The deepest convolutional block of the encoder usually contains the most abstract and discriminative features. Adding the non-local module here can capture long-distance dependencies and enhance the model's ability to utilize global information.

[0066] The specific structure is shown as follows:

[0067] Input->Preprocessing->Annotation->Hybrid Network Structure->Output

[0068] See 8, where the hybrid network structure is:

[0069]

[0070]

[0071] Each convolutional block is followed by a CBAM module to enhance feature representation.

[0072] SENet is added after the bottleneck layer to model the dependencies between channels.

[0073] A Non-local module is placed after the deepest convolutional block of the encoder to capture long-distance dependencies.

[0074] This structural design enables the multi-scale crack defect assessment model to make full use of local and global information and improve the accuracy of crack defect assessment.

[0075] To obtain the annotated crack image data, refer to Figure 3 , including the following steps:

[0076] Define the standard of tunnel cracks, select annotation tools to annotate crack image data of the tunnel to be evaluated, identify the crack location, draw a bounding box for each crack, and perform pixel-level annotation using semantic segmentation to obtain preliminary annotated crack image data;

[0077] The initially annotated crack image data is subjected to image enhancement, size adjustment, normalization and cleaning, and then data segmentation is performed to obtain the annotated crack image data.

[0078] Obtain the optimized multi-scale crack defect assessment model, see Figure 4 , including the following steps:

[0079] The crack image data of the evaluated tunnel is obtained as a dataset and divided into a training set, a validation set, and a test set.

[0080] Select the loss function as binary cross entropy, select the optimizer as SGD, and set the hyperparameters, including the training batch size, learning rate, number of iterations, regularization parameter, dropout ratio, activation function, and architecture parameters of the multi-scale crack defect assessment model;

[0081] The validation set is used to perform model evaluation and hyperparameter adjustment on the multi-scale crack defect assessment model to obtain the optimized multi-scale crack defect assessment model.

[0082] To obtain the crack defect assessment results, the following steps are included:

[0083] Extracting the preprocessed tunnel crack image data to be evaluated by using encoder features to obtain extracted features, and enhancing the extracted features by using CBA, SENet and Non-local to obtain multi-level enhanced features;

[0084] The feature maps of the low level in the multi-level enhanced features are upsampled to a high level to obtain the sampled feature maps, and then the upsampled feature maps are concatenated with the high-level original feature maps using the side connection to obtain the concatenated features;

[0085] Apply convolution operation on the concatenated feature maps to fuse features of different scales, repeat the above fusion process for each pyramid level until the top level, and obtain multi-scale fused feature map data;

[0086] The multi-scale fusion feature mapping data is subjected to contour detection, classification and quantification to obtain the crack defect assessment results.

[0087] and contour detection, classification, and quantization of multi-scale fused feature maps, see Figure 6 , including the following steps:

[0088] The multi-scale fusion feature mapping data is used to identify possible crack areas by setting the activation function Sigmoid to obtain multiple crack areas;

[0089] Applying conditional random fields and region growing to refine the multiple crack regions to obtain multiple refined crack regions;

[0090] Perform contour extraction on multiple refined crack regions to obtain boundaries of multiple cracks;

[0091] Verifying and obtaining specific boundaries of multiple cracks through morphological operations and geometric constraints, and obtaining multiple detected crack regions; the geometric constraints include length and width ratios of the cracks;

[0092] Extract feature vectors for each detected crack region based on multi-scale fusion feature mapping, including texture, shape, and size;

[0093] Performing normalization on the feature vector to obtain a normalized feature vector;

[0094] Use the training data set to train the classification model constructed by the neural network.

[0095] The standardized feature vector of the detected crack is input into the trained classification model to obtain the classification result of the crack.

[0096] The classification results are subjected to non-maximum suppression to merge the overlapping crack classification results and generate crack defect assessment results.

[0097] The present invention will be further described below in conjunction with the accompanying drawings and implementation modes.

[0098] Embodiment 1:

[0099] The following is a specific implementation case to illustrate the steps of the above tunnel crack defect assessment method:

[0100] First is data acquisition and preprocessing

[0101] Step 1: Use a high-definition camera mounted on a drone to photograph a city subway tunnel and obtain a series of images of the tunnel surface.

[0102] Step 2: Define the crack marking standard, such as only cracks with a width greater than 0.5 mm will be marked.

[0103] Step 3: Use annotation tools such as LabelImg to annotate the cracks in the image, including crack location, bounding box drawing, and pixel-level semantic segmentation.

[0104] Step 4: Enhance the annotated images by rotating, flipping, scaling, resizing to a uniform size of 256x256 pixels, normalizing, scaling pixel values ​​to the range of 0-1, and cleaning to remove blurry or unclear images.

[0105] Step 5: Split the image data into 70% training set, 15% validation set and 15% test set.

[0106] 2. Construct a multi-scale crack defect assessment model

[0107] Step 1: Design a U-Net-based model, including the convolutional and pooling layers of the encoder, and the upsampling and convolutional layers of the decoder.

[0108] Step 2: Add side connections in the encoder and integrate the feature pyramid network to fuse features of different scales.

[0109] Step 3: Introduce the CBAM attention module after the convolution block of the U-Net architecture, introduce the SENet module after the bottleneck layer, and introduce the Non-local module after the deepest convolution block of the encoder.

[0110] 3. Model training and optimization

[0111] Step 1: Use the evaluated tunnel crack image dataset and perform model training according to the previous data segmentation.

[0112] Step 2: Select binary cross entropy as the loss function, SGD as the optimizer, and set hyperparameters such as batch size (32), learning rate (0.001), number of iterations (10000), etc.

[0113] Step 3: Use the validation set to evaluate the model and adjust the hyperparameters, such as the learning rate decay strategy, according to the evaluation results until the model performance reaches the best.

[0114] 4. Crack defect assessment

[0115] Step 1: Preprocess the new tunnel image to be evaluated, including resizing and normalization.

[0116] Step 2: Build an image pyramid and apply convolutional neural network to extract features at each level.

[0117] Step 3: Concatenate feature maps of different scales through upsampling and side connections.

[0118] Step 4: Apply convolution operation on the concatenated feature map to fuse the features, and repeat this process until the top layer.

[0119] Step 5: Perform contour detection, classification (crack length, width) and quantification of defect levels on the multi-scale fusion feature map.

[0120] 5. Result Output

[0121] Step 1: Extract features of the detected crack area, including texture, shape, size, etc.

[0122] Step 2: Standardize the feature vector and input it into the trained classification model to obtain the crack classification result.

[0123] Step 3: Use non-maximum suppression to merge overlapping crack classification results and generate the final crack defect assessment results.

[0124] Data acquisition module: automatically acquires tunnel images taken by drones and performs preprocessing.

[0125] Evaluation model building module: Build and train a multi-scale crack defect evaluation model.

[0126] Evaluation and analysis module: input preprocessed image data and output crack defect evaluation results.

[0127] Through the above implementation cases, this method can automatically and accurately evaluate tunnel crack defects and provide decision support for tunnel maintenance and management.

[0128] Example 2

[0129] A tunnel crack defect assessment system, see Figure 7 ,include:

[0130] An evaluation model construction module is provided, which takes the U-Net architecture as the basis, adds a feature pyramid network, obtains a hybrid network structure, inserts CBAM after the convolution block of the hybrid network structure, adds SENet after the bottleneck layer between the encoder and the decoder, and places a Non-local module after the deepest convolution block of the encoder to construct a multi-scale crack defect evaluation model; obtains the evaluated annotated crack image data as a data set, trains and optimizes the parameters of the multi-scale crack defect evaluation model, and obtains an optimized multi-scale crack defect evaluation model;

[0131] The evaluation and analysis module is used to obtain the annotated tunnel crack image data to be evaluated, and input it into the optimized multi-scale crack defect evaluation model to obtain the crack defect evaluation result.

[0132] That is, the system improves the accuracy and efficiency of crack detection by integrating advanced image processing and deep learning technologies. The following are the specific implementation steps of the system:

[0133] Data acquisition module:

[0134] Crack image acquisition: First, crack image data is collected from the tunnel. These image data need to cover different stages and types of cracks so that the system can learn and identify various crack patterns.

[0135] Image annotation and preprocessing: Annotate the collected images to identify the specific location and morphology of the cracks. In addition, perform necessary preprocessing operations such as cropping, denoising, and normalization to optimize the subsequent image analysis process.

[0136] Evaluation Model Building Modules:

[0137] Construction of hybrid network structure: A U-Net-based architecture is used in combination with a feature pyramid network to enhance the model's ability to identify cracks of different scales and complexities, and obtain a hybrid network structure. On this basis, the CBAM convolutional block attention module, SENet compression-excitation network, and Non-local module are added to enhance the model's ability to extract features and focus on key areas.

[0138] Model training: Using the labeled tunnel crack image data as the training data set, the model parameters are trained and optimized. This process involves multiple iterations, and the network parameters are continuously adjusted to minimize the prediction error, thereby obtaining more accurate crack detection performance.

[0139] Evaluation and analysis module:

[0140] Crack identification and analysis: The preprocessed tunnel crack image is input into the trained multi-scale crack defect assessment model. The model detects and identifies the presence of cracks by analyzing the features in the image.

[0141] Evaluation result output: The model outputs the type, size, shape and possible extension trend of the crack. These output results can be directly used for decision support, such as tunnel repair and reinforcement planning.

[0142] This advanced crack identification system can achieve fast and efficient crack detection, greatly improving the efficiency and accuracy of tunnel safety monitoring. This system is particularly suitable for long-term and continuous structural health monitoring, and can accurately diagnose cracks in the early stages of development, effectively preventing larger-scale structural damage.

[0143] This system, which integrates multiple deep learning technologies and image processing technologies, provides a strong technical support for the maintenance of infrastructure such as tunnels, and demonstrates the application prospects of modern engineering technology in traditional industries.

[0144] Example 3

[0145] The following is a specific example of a tunnel crack defect assessment method, showing the actual operation steps of the method and the corresponding experimental data, to verify the detection and classification effect of the multi-scale tunnel crack defect assessment model proposed in the present invention in a complex environment.

[0146] Original data: 5000 crack images from different tunnels were collected. The image resolution is 1024×1024 pixels, covering a variety of crack types, including surface cracks, through cracks, spider web cracks, etc.

[0147] Annotation Standards: Annotate the crack area using a bounding box to accurately record the shape and boundaries of the crack.

[0148] Semantic segmentation is used for pixel-level annotation (the crack area is represented by label 1, and the rest of the area is represented by label 0).

[0149] Image enhancement methods: rotation (±30°), brightness adjustment (±20%), Gaussian noise (σ=0.01). Data segmentation: training set, validation set and test set are divided in a ratio of 7:2:1.

[0150] U-Net infrastructure, embedded with Feature Pyramid Network (FPN), combined with CBAM, SENet and Non-local modules. Specific hyperparameter settings include:

[0151] Loss function: Binary Cross Entropy.

[0152] Optimizer: SGD, initial learning rate 0.01, momentum 0.9.

[0153] Batch size: 16, number of training iterations: 100.

[0154] Regularization: L2 regularization coefficient 0.0005, dropout ratio 0.5.

[0155] Training equipment: NVIDIA Tesla V100 GPU, training time is about 12 hours.

[0156] Test steps and results:

[0157] (1) Crack detection effect

[0158] The 500 crack images in the test set are input into the trained model to obtain the following detection indicators:

[0159] Detection accuracy: 96.3%.

[0160] Recall: 94.8%.

[0161] F1-Score: 95.5%.

[0162] The crack area of ​​the detection image is accurately marked, and the boundary is highly consistent with the actual crack after refinement. See the data in the figure below for details.

[0163] Image number Detection crack number Actual number of cracks Accuracy (%) Missed detection rate (%) 001 12 12 100 0 002 8 9 88.9 11.1 003 15 15 100 0

[0164] (2) Crack classification effect

[0165] The model classifies cracks into three categories based on the normalized feature vectors of crack texture, shape, and size:

[0166] Type I (shallow crack): depth less than 2 mm;

[0167] Type II (medium crack): depth 2-5mm;

[0168] Class III (deep cracks): depth greater than 5 mm.

[0169] Crack type Classification accuracy (%) Misclassification rate (%) Category I 95.8 4.2 Category II 94.7 5.3 Category III 93.2 6.8

[0170] Specific detection and classification cases:

[0171] Tunnel crack image (see table below):

[0172]

[0173] Each crack region is represented by a bounding box, and the classification results are distinguished by color (green for Class I, blue for Class II, and red for Class III).

[0174] Assessment report: Total number of cracks: 35; Category I: 20, accounting for 57.1%; Category II: 10, accounting for 28.6%; Category III: 5, accounting for 14.3%.

[0175] Crack quantification analysis: Texture mean: 0.65; Texture variance: 0.12. Shape parameters: average length 5.2cm, width 0.8cm.

[0176] After the standardized feature vector was input into the classification model, the accuracy of the quantitative analysis of cracks reached 97.4%.

[0177] It is verified through the above embodiments that the tunnel crack defect assessment method proposed in the present invention can efficiently and accurately detect and classify cracks.

[0178] It should be noted that, in the present invention, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0179] The above embodiments are merely examples of the present invention and do not limit the protection scope of the present invention. All designs that are the same or similar to the present invention fall within the protection scope of the present invention.

Claims

1. A method for evaluating tunnel crack defects, characterized in that: The following steps are involved: Taking the U-Net architecture as the basis, a feature pyramid network is added to obtain a hybrid network structure, in which CBAM is inserted after the convolution block of the hybrid network structure, SENet is added after the bottleneck layer between the encoder and the decoder, and a Non-local module is placed after the deepest convolution block of the encoder to build a multi-scale crack defect assessment model; Acquire the evaluated annotated crack image data as a data set, train and optimize the parameters of the multi-scale crack defect evaluation model, and obtain an optimized multi-scale crack defect evaluation model; After preprocessing, the acquired tunnel crack image data to be evaluated is input into the optimized multi-scale crack defect evaluation model to obtain the crack defect evaluation result.

2. The tunnel crack defect assessment method according to claim 1, characterized in that: The method of obtaining the hybrid network structure comprises the following steps: The U-Net architecture includes a downsampling path and an upsampling path; The FPN is through a top-down path and a bottom-up path; After each downsampling stage of the U-Net, the top-down path of the FPN is introduced to concatenate and fuse the features of the current layer with the features of the previous layer; before each upsampling stage of the U-Net, the bottom-up path of the FPN is introduced to concatenate and add the features of the current layer with the features of the next layer to obtain a hybrid network structure.

3. The tunnel crack defect assessment method according to claim 1, characterized in that: The step of obtaining the annotated crack image data comprises the following steps: Define the standard of tunnel cracks, select annotation tools to annotate crack image data of the tunnel to be evaluated, identify the crack location, draw a bounding box for each crack, and perform pixel-level annotation using semantic segmentation to obtain preliminary annotated crack image data; The initially annotated crack image data is subjected to image enhancement, size adjustment, normalization and cleaning, and then data segmentation is performed to obtain the annotated crack image data.

4. The tunnel crack defect assessment method according to claim 1, characterized in that: The step of obtaining the optimized multi-scale crack defect assessment model comprises the following steps: Obtain the evaluated annotated tunnel crack image data as a data set and divide it into a training set, a validation set, and a test set; Select the loss function as binary cross entropy, select the optimizer as SGD, and set the hyperparameters, including the training batch size, learning rate, number of iterations, regularization parameter, dropout ratio, activation function, and architecture parameters of the multi-scale crack defect assessment model; The validation set is used to perform model evaluation and hyperparameter adjustment on the multi-scale crack defect assessment model to obtain the optimized multi-scale crack defect assessment model.

5. The tunnel crack defect assessment method according to claim 1, characterized in that: The method of obtaining the crack defect evaluation result comprises the following steps: Extracting the preprocessed tunnel crack image data to be evaluated by using encoder features to obtain extracted features, and enhancing the extracted features by using CBA, SENet and Non-local to obtain multi-level enhanced features; The feature maps of the low level in the multi-level enhanced features are upsampled to a high level to obtain the sampled feature maps, and then the upsampled feature maps are concatenated with the high-level original feature maps using the side connection to obtain the concatenated features; Apply convolution operation on the concatenated feature map to fuse features of different scales, repeat the above fusion process for each pyramid level until the top level, and obtain multi-scale fused feature map data; The multi-scale fusion feature mapping data is subjected to contour detection, classification and quantification to obtain the crack defect assessment results.

6. The tunnel crack defect assessment method according to claim 5, characterized in that: The process of performing contour detection, classification and quantification on the multi-scale fusion feature mapping data comprises the following steps: The multi-scale fusion feature mapping data is used to identify possible crack areas by setting the activation function Sigmoid to obtain multiple crack areas; Applying conditional random fields and region growing to refine the multiple crack regions to obtain multiple refined crack regions; Perform contour extraction on multiple refined crack regions to obtain boundaries of multiple cracks; Verifying and obtaining specific boundaries of multiple cracks through morphological operations and geometric constraints, and obtaining multiple detected crack regions; the geometric constraints include length and width ratios of the cracks; Extract feature vectors for each detected crack region based on multi-scale fusion feature mapping, including texture, shape, and size; Performing normalization on the feature vector to obtain a normalized feature vector; Input the standardized feature vector into the pre-trained classification model to obtain the classification result of the crack; The classification results are limited by non-maximum suppression merging overlap to generate crack defect assessment results.

7. A tunnel crack defect assessment system, characterized in that: include: An evaluation model building module is used to use the U-Net architecture as a basis, add a feature pyramid network, obtain a hybrid network structure, insert CBAM after the convolution block of the hybrid network structure, add SENet after the bottleneck layer between the encoder and the decoder, and place a Non-local module after the deepest convolution block of the encoder to build a multi-scale crack defect evaluation model; obtain the evaluated annotated crack image data as a data set, train and optimize the parameters of the multi-scale crack defect evaluation model, and obtain an optimized multi-scale crack defect evaluation model; The evaluation and analysis module is used to pre-process the tunnel crack image data to be evaluated and then input it into the optimized multi-scale crack defect evaluation model to obtain the crack defect evaluation result.

8. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

9. A computer device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the method described in any one of claims 1 to 6 is implemented.

Images