Concrete road crack identification method and system

Abstract

The invention discloses a concrete road crack identification method and system. The method comprises the following steps: constructing a concrete road crack identification model based on improved DeepLabv3 +; inputting the concrete road crack data set into the concrete road crack recognition model, optimizing model parameters of the concrete road crack recognition model based on a composite loss function combining edge enhancement and geometric adaptability, and training to generate a weight of the concrete road crack recognition model, obtaining a target crack identification model; and inputting a real-time concrete road crack image into the target crack recognition model, outputting by the target crack recognition model to obtain a preliminary recognition result, and optimizing the preliminary recognition result through a false detection elimination and leak detection repair algorithm to obtain a final recognition result. The false detection rate and the omission rate are obviously reduced, and the accuracy and the integrity of a final recognition result are ensured.

Description

Technical Field

[0001] The present invention belongs to the technical field of computer vision and road maintenance, and in particular relates to a method and system for identifying cracks in a concrete road. Background Art

[0002] Road cracks are one of the most common diseases in transportation infrastructure such as highways and urban roads. Their formation is mainly caused by the combined effects of multiple factors such as traffic load, environmental impact and construction quality. The appearance of cracks not only affects the service life and driving comfort of the road, but also increases driving safety hazards and further leads to early road damage. Therefore, timely detection and maintenance of road cracks are of great significance to ensure traffic safety and extend the life of the road.

[0003] Traditional road crack detection relies on manual observation and measurement. Workers identify cracks with their naked eyes and use tools to measure them. This method is low-cost but inefficient, easily affected by worker fatigue and subjective factors, and difficult to cover large areas of roads. Cracks are accurately measured using equipment such as crack width meters and laser scanners. This method is highly accurate, but the equipment is expensive and cannot efficiently complete large-scale detection tasks.

[0004] With the development of computer vision and artificial intelligence technology, automated road crack detection technology based on image processing has gradually become a research hotspot. These technologies mainly capture road images and use algorithms to automatically identify cracks, with the advantages of high efficiency, accuracy and low cost. In recent years, deep learning technologies such as convolutional neural networks (CNN) have been widely used in the field of crack detection. For example, networks such as U-Net and DeepLab can complete pixel-level segmentation of cracks in an end-to-end manner, greatly improving detection accuracy and robustness. Since cracks have various forms, they may appear as linear, mesh, block or other complex forms. The detection algorithm needs to have strong generalization capabilities for different crack types. In addition, the road environment is complex, and crack detection may be interfered by shadows, oil stains, lighting changes, road surface texture, etc., resulting in reduced detection accuracy. Summary of the invention

[0005] The present invention provides a concrete road crack identification method and system, which are used to solve the technical problems in the prior art of low detection accuracy and insufficient adaptability to the diversity of crack morphologies due to significant interference from complex backgrounds.

[0006] In a first aspect, the present invention provides a method for identifying cracks in a concrete road, comprising: A concrete road crack recognition model based on improved DeepLabv3+ is constructed, wherein the concrete road crack recognition model includes an encoder and a decoder directly connected to the encoder; the encoder includes a deep convolutional network layer and an improved dilated spatial pyramid pooling module; the decoder includes a bilinear upsampling module, a 1×1 convolution module, and a 3×3 convolution module; Acquire a concrete road crack image, and annotate and preprocess the concrete road crack image to obtain a concrete road crack data set; The concrete road crack data set is input into the concrete road crack recognition model, model parameters of the concrete road crack recognition model are optimized based on a composite loss function combining edge enhancement and geometric adaptability, weights of the concrete road crack recognition model are generated through training, and a target crack recognition model is obtained; The real-time concrete road crack image is input into the target crack recognition model, the target crack recognition model outputs a preliminary recognition result, and the preliminary recognition result is optimized by a false detection elimination and missed detection repair algorithm to obtain a final recognition result.

[0007] In a second aspect, the present invention provides a concrete road crack identification system, comprising: A construction module configured to construct a concrete road crack recognition model based on improved DeepLabv3+, wherein the concrete road crack recognition model includes an encoder and a decoder directly connected to the encoder; the encoder includes a deep convolutional network layer and an improved dilated spatial pyramid pooling module; the decoder includes a bilinear upsampling module, a 1×1 convolution module, and a 3×3 convolution module; An acquisition module is configured to acquire a concrete road crack image, and annotate and preprocess the concrete road crack image to obtain a concrete road crack data set; an optimization module, configured to input the concrete road crack data set into the concrete road crack recognition model, optimize the model parameters of the concrete road crack recognition model based on a composite loss function combining edge enhancement and geometric adaptability, train and generate weights of the concrete road crack recognition model, and obtain a target crack recognition model; The recognition module is configured to input the real-time concrete road crack image into the target crack recognition model, the target crack recognition model outputs a preliminary recognition result, and optimizes the preliminary recognition result through a false detection elimination and missed detection repair algorithm to obtain a final recognition result.

[0008] In a third aspect, an electronic device is provided, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the steps of the concrete road crack identification method of any embodiment of the present invention.

[0009] In a fourth aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor is caused to execute the steps of the concrete road crack identification method of any embodiment of the present invention.

[0010] The concrete road crack recognition method and system of the present application improves the encoder and decoder structure of the DeepLabv3+ model and introduces an improved void space pyramid pooling module, which significantly enhances the model's ability to extract multi-scale features and improves the accuracy of crack detection, especially in complex background and fine crack detection. The composite loss function combining edge enhancement and geometric adaptability is adopted to effectively improve the model's perception of crack edges. At the same time, the constraints of crack geometric characteristics are considered to enhance the adaptability to the diversity of crack morphology, so that the model can work stably in different scenarios and conditions. The feature fusion and channel adjustment strategies of the decoder are improved to simplify the calculation process, and combined with the lightweight processing strategy, the model reasoning speed is greatly improved, which can meet the real-time requirements of road crack recognition tasks. The preliminary detection results are further optimized through the false detection elimination and missed detection repair algorithms, and the false detection rate and missed detection rate are significantly reduced to ensure the accuracy and completeness of the final recognition results. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0012] Figure 1 A flowchart of a method for identifying cracks in a concrete road provided by an embodiment of the present invention; Figure 2 A structural block diagram of a concrete road crack identification system provided by an embodiment of the present invention; Figure 3 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0013] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0014] See also Figure 1 , which shows a flow chart of a concrete road crack identification method of the present application.

[0015] like Figure 1 As shown, the concrete road crack identification method specifically includes the following steps: Step S101, constructing a concrete road crack recognition model based on improved DeepLabv3+ (a semantic segmentation model based on deep learning), wherein the concrete road crack recognition model includes an encoder and a decoder directly connected to the encoder; the encoder includes a deep convolutional network layer and an improved dilated spatial pyramid pooling module; the decoder includes a bilinear upsampling module, a 1×1 convolution module, and a 3×3 convolution module.

[0016] In this step, the improved atrous spatial pyramid pooling module includes: A dynamic multi-branch feature extraction module, which includes a 1×1 convolution module, a 3×3 dilated convolution module with dilation rates of 6, 12, and 18, a global average pooling module, and a dynamic asymmetric dilated convolution module. The dynamic asymmetric dilated convolution module adaptively adjusts the dilation rate in the horizontal direction according to the directional characteristics of the crack distribution in the input feature map by introducing a dynamic receptive field adjustment factor. and the vertical expansion rate , the expression is: , , In the formula, is the basic expansion rate in the horizontal direction, , are adjustment coefficients, The input feature map The variance in the horizontal direction, is the basic expansion rate in the vertical direction, The input feature map Variance in the vertical direction; The input features of the 3×3 convolution module with a dilation rate of 6 consist of the deep features and the output features of the 1×1 convolution module; The input features of the 3×3 convolutional module with a dilation rate of 12 are composed of the deep features and the output features of the convolutional module with a dilation rate of 6; The input features of the 3×3 convolutional module with a dilation rate of 18 are composed of the deep features and the output features of the convolutional module with a dilation rate of 12; The crack shape sensitive attention module combines directional gradients and edge information to weight the output features of the 3×3 dilated convolution module with dilation rates of 6, 12, and 18, the global average pooling module, and the dynamic asymmetric dilated convolution module. The attention weight calculation formula of the crack shape sensitive attention module is: , In the formula, is the channel weight, is the Sigmoid function, , are the gradients of the feature map F in the horizontal and vertical directions, respectively. is a weight matrix used to fuse gradient features with original features.

[0017] The output features of the 1×1 convolution module, the dynamic asymmetric dilated convolution module, and the crack shape sensitive attention module are merged through a feature fusion operation to obtain fused features; The fused features are channel-adjusted through another 1×1 convolution module to generate the output deep features of the improved atrous spatial pyramid pooling module.

[0018] In this embodiment, the crack shape-sensitive attention module combines channel attention and spatial attention mechanisms to enhance the features of the long and thin strip characteristics and directional distribution characteristics of the cracks. First, in the channel attention part, the input feature map is subjected to global average pooling and global maximum pooling to generate a global descriptor, thereby capturing global statistical information in the channel dimension. Next, the descriptor is nonlinearly mapped through two layers of 1×1 convolution and ReLU activation function, and the channel weight is generated using the Sigmoid function, which is finally applied to the input feature map to strengthen key channel features and suppress irrelevant information. Subsequently, the enhanced feature map further captures the directional and spatial multi-scale characteristics of the cracks through dynamic asymmetric dilated convolution and multi-scale asymmetric convolution, and dynamically adjusts the receptive field to adapt to the shape and length of the crack.

[0019] In the spatial attention part, the spatial attention weights are generated using the horizontal and vertical gradient information and edge features of the feature map. The gradient and edge information are fused through 1×1 convolution, and the weight value is normalized using the Sigmoid function to generate a significant enhanced spatial feature expression. Finally, the feature map after channel enhancement and spatial enhancement is weighted point by point, and the output contains both directional and edge characteristics, and strengthens the crack feature expression of the key area significance, which significantly improves the detection and classification capabilities of cracks.

[0020] In the improved concrete crack road recognition model of DeepLabv3+, the deep convolutional network layer is set to the lightweight model MobileNetv2, and the shallow features output are mainly used to capture the edge information and local texture details of the cracks. These features are generated by the first few layers of the network's Bottleneck modules, with the resolution gradually decreasing and the number of channels gradually increasing, as follows: First, the size of the first shallow feature is 1 / 4H × 1 / 4W, and the number of channels is 24. It comes from the initial convolution layer (Conv1) and the first Bottleneck module of MobileNetV2. After the image passes through Conv1 (3×3 standard convolution, step size of 2, downsampling), the resolution of the feature map is reduced to 1 / 2 of the original image, and the number of channels is 16; then the shallow feature is extracted through the first Bottleneck module (expansion factor is 1), the resolution is further reduced to 1 / 4, and the number of channels is increased to 24. This feature mainly captures the basic edge information and local details of the crack, retaining a high spatial resolution.

[0021] Secondly, the size of the second shallow feature is 1 / 8H × 1 / 8W, the number of channels is 32, and it comes from the second Bottleneck module of the MobileNetV2 backbone network. After passing through the first Bottleneck module, the feature map enters the second Bottleneck module (with an expansion factor of 6). After depthwise separable convolution and feature transformation, the resolution is further reduced to 1 / 8, and the number of channels is increased to 32. This feature introduces more semantic information based on edge and texture information, and can capture more details of the crack area.

[0022] Finally, the size of the third shallow feature is 1 / 16H × 1 / 16W, and the number of channels is 64, which comes from the third Bottleneck module of the MobileNetV2 backbone network. After the feature map passes through multiple Bottleneck modules, the resolution is reduced to 1 / 16, and the number of channels is further increased to 64. This feature gradually contains the mesoscale structural information of the crack, providing support for the subsequent deep feature fusion.

[0023] After entering the decoder, these features need to undergo the following operations: first, adjust the number of channels through a 1×1 convolution module to ensure channel consistency of features of different scales; then use instance normalization to standardize the features to eliminate the differences in feature distribution caused by different batches of data; finally, use the ReLU activation function to enhance the nonlinear representation capability of the features.

[0024] The decoder part receives the shallow features and deep features output by the encoder. The shallow feature information is processed into feature maps of the same size through bilinear upsampling and then merged. The channel is compressed through a 1×1 convolution module to generate a first feature map. The deep feature information is extracted through an improved dilated space pyramid pooling module, and then a second feature map is obtained through bilinear upsampling. After the first feature map is fused with the second feature map, features are extracted through a 3×3 convolution module, and the channel is adjusted through a 1×1 convolution module to finally complete the classification prediction. The prediction result is restored to the same size as the input image using a bilinear upsampling module to obtain a preliminary prediction result.

[0025] Step S102, obtaining a concrete road crack image, and annotating and preprocessing the concrete road crack image to obtain a concrete road crack dataset.

[0026] In this step, the collected concrete road crack images are enhanced, the contrast of the crack area is enhanced by histogram equalization, gamma correction or contrast adjustment, and the corresponding segmentation label map is added; the enhanced images and labels are integrated into an image dataset, and the image dataset is divided into a training set and a test set.

[0027] Step S103: input the concrete road crack data set into the concrete road crack recognition model, optimize the model parameters of the concrete road crack recognition model based on a composite loss function combining edge enhancement and geometric adaptability, train and generate the weights of the concrete road crack recognition model, and obtain a target crack recognition model.

[0028] In this step, the preprocessed crack data set is input into the crack recognition model, the predicted output of the model is calculated through forward propagation, and the composite loss function combining edge enhancement and geometric adaptability is calculated based on the true label and the predicted output. The composite loss function is composed of cross entropy loss and edge perception loss, where cross entropy loss is used to optimize pixel-level classification accuracy, and edge perception loss is used to enhance the model's ability to capture crack edge details. At the same time, in order to adapt to the geometric characteristics of the crack, the composite loss function dynamically adjusts the weight distribution during the calculation process, making the model more accurate in identifying the crack trunk and edge area. Finally, the model parameters are optimized through back propagation and gradient update, and the training is iterated until convergence to generate the final weights of the target crack recognition model.

[0029] The composite loss function includes the basic segmentation loss sub-function, the edge enhancement loss sub-function and the geometric adaptability loss sub-function; The expression of the composite loss function is: , In the formula, is the basic segmentation loss sub-function, , are all balance weight parameters, is the edge enhancement loss sub-function, is the geometric adaptability loss sub-function.

[0030] The composite loss function is adjusted by , and The value of can achieve an adaptive balance between different loss terms to improve the accuracy and robustness of crack detection.

[0031] It should be noted that the expression of the basic segmentation loss subfunction is: , In the formula, For the The true label of each pixel, For the The predicted value of each pixel, is the total number of pixels; The expression of the edge enhancement loss subfunction is: , In the formula, is the dynamic weight based on edge pixels; The expression of the geometric adaptability loss subfunction is: , , In the formula, is the geometric weight, is a parameter that controls the weight of geometric features. is a nonlinear function of crack width, For the The pixel location of the crack area.

[0032] Step S104, inputting the real-time concrete road crack image into the target crack recognition model, the target crack recognition model outputs a preliminary recognition result, and optimizes the preliminary recognition result through a false detection elimination and missed detection repair algorithm to obtain a final recognition result.

[0033] In this step, three shallow feature information of different scales and one deep feature information of the real-time concrete road crack image are extracted according to the deep convolutional network layer, and the deep convolutional network layer is a lightweight network structure; the shallow feature information of three different scales is processed into feature maps of the same size by the bilinear upsampling module and then merged, and the channel is compressed by the 1×1 convolution module to generate a first feature map; the improved void space pyramid pooling module processes the deep feature information through multi-scale dilated convolution, and upsamples it through the bilinear upsampling module to obtain a second feature map; the first feature map and the second feature map are fused, and after fusion, the features are extracted by the 3×3 convolution module, and the channel is adjusted by the 1×1 convolution module, and the prediction result is restored to the same size as the real-time concrete road crack image by the bilinear upsampling module to obtain a preliminary prediction result.

[0034] Furthermore, the initially identified crack areas are extracted Multidimensional geometric features ,in, , , as well as , is the area, is the circumference, The coordinates in the binary image are The pixel value of the pixel, 1 represents cracks, 0 represents background, For Region The borders of , The crack area The horizontal and vertical coordinates of a pixel point on the boundary, , The crack area on the border with The horizontal and vertical coordinates of another adjacent pixel point, is the shape factor, is the eccentricity of the circumscribed ellipse, is the major axis of the circumscribed ellipse, is the minor axis of the circumscribed ellipse; Calculate the normalized score of each feature and combine it with the weighted coefficient to get the comprehensive score, which is expressed as: , In the formula, is the comprehensive score, is the number of features, For Region The value of the i-th feature of is the weight of the feature, is the standard deviation of feature i, is the mean of feature i; like , then remove the false detection area, is the threshold of the comprehensive score; Missed detection repair based on optimized tensor decomposition, constructing sparse adjacency tensors , the expression is: , In the formula, is the Euclidean distance between two points, is the angle between two points, represents the adjacency relationship between the i-th and j-th crack connected regions, , The crack area and The centroid coordinates of is the distance threshold, is the angle threshold, is the length of the first dimension of T, indicating the number of rows of the tensor, is the second dimension length of T, indicating the number of columns of the tensor, represents the field of real numbers; The tensor Decomposed into a low-rank form through non-negative tensor decomposition, the expression is: , In the formula, is the rank of the decomposition, is the kth factor vector used to describe the characteristics of the tensor in the first dimension, is the outer product operation of the tensor, is the kth factor vector used to describe the characteristics of the tensor in the second dimension, is the kth factor vector used to describe the characteristics of the tensor in the third dimension; Define an objective function to restore the connected area by optimizing the sparsity and smoothness constraints. The expression of the objective function is: , In the formula, and are the constraint weight coefficients for sparsity and smoothness, respectively. is the L2 norm, used to constrain smoothness, is the Frobenius norm, is the L1 norm, used to constrain sparsity, for The gradient of , , is the factor vector in tensor decomposition, corresponding to the three dimensions of tensor T respectively.

[0035] The reconstructed tensor obtained by optimization Represents possible crack connection areas and reconstructs the tensor The expression is: , In the formula, To represent the vector The i-th element of To represent the vector The jth element of ; Will Mapping back to the image space, generating the connected crack image, the expression is: , In the formula, It is a line connection operation between two points; Crack image after fusion of false detections and removal and reconstruction areas , output the final detection result, the expression is: , In the formula, The final fused crack image.

[0036] In summary, the method of the present application, by improving the encoder and decoder structure of the DeepLabv3+ model and introducing an improved dilated space pyramid pooling module, significantly enhances the model's ability to extract multi-scale features and improves the accuracy of crack detection, especially in complex backgrounds and fine crack detection. The composite loss function that combines edge enhancement and geometric adaptability can effectively improve the model's perception of crack edges, while considering the constraints of crack geometric characteristics, enhancing the adaptability to the diversity of crack morphology, so that the model can work stably in different scenarios and conditions. The feature fusion and channel adjustment strategies of the decoder are improved to simplify the calculation process, and combined with the lightweight processing strategy, the model reasoning speed is greatly improved, which can meet the real-time requirements of road crack recognition tasks. The preliminary detection results are further optimized through the false detection elimination and missed detection repair algorithms, significantly reducing the false detection rate and missed detection rate, and ensuring the accuracy and completeness of the final recognition results.

[0037] In a specific embodiment, the simulation experiment is implemented under PYTORCH, and NVIDIA(R) Tesla(R) V100 GPU is used for training and testing in the experiment. 100 rounds (epochs) are carried out on the constructed concrete road crack data set, the first epoch≤50 is the freezing stage, batch_size is 8; the latter epoch>50 is the thawing stage, batch_size (batch size) is 4, the image size is uniformly scaled to 512×512 during training, SGD (stochastic gradient descent) is used as the optimizer, the initial learning rate is 7e-3, the learning rate decrease method is step (equal interval adjustment), the momentum is 0.9, and the weight_decay (weight decay) is set to 1e-4.

[0038] The superior performance of the method of the present invention is verified by comparing with the original DeepLabv3+ model and three other representative semantic segmentation models. The three algorithms are PSPNet, HRNet and U-Net. In order to evaluate the performance of the model in road crack detection, the evaluation indicators used are: average pixel accuracy (MPA), average intersection over union (MIoU), accuracy, precision and F1 score, as well as inference time for comparing model complexity. The experimental results on the data set of this embodiment are shown in Table 1.

[0039] Table 1: Comparison of experimental results of self-built datasets , From the results of semantic segmentation indicators given in Table 1, it can be seen that the method of the present application has the shortest reasoning time in the process of concrete road crack recognition, and MPA, MIoU, Accuracy, Precision and F1-score are better than the other four models, indicating that the method of the present application not only has significant advantages in recognition accuracy and robustness, but also has high efficiency, and can meet the dual requirements of real-time and accuracy in actual road crack detection.

[0040] See also Figure 2 , which shows a structural block diagram of a concrete road crack identification system of the present application.

[0041] like Figure 2 As shown, the concrete road crack identification system 200 includes a construction module 210 , an acquisition module 220 , an optimization module 230 and an identification module 240 .

[0042] Among them, the construction module 210 is configured to construct a concrete road crack recognition model based on the improved DeepLabv3+, and the concrete road crack recognition model includes an encoder and a decoder directly connected to the encoder; the encoder includes a deep convolutional network layer and an improved void space pyramid pooling module; the decoder includes a bilinear upsampling module, a 1×1 convolution module and a 3×3 convolution module; the acquisition module 220 is configured to acquire a concrete road crack image, and annotate and preprocess the concrete road crack image to obtain a concrete road crack data set; the optimization module 230 is configured to input the concrete road crack data set into the concrete road crack recognition model, optimize the model parameters of the concrete road crack recognition model based on a composite loss function combining edge enhancement and geometric adaptability, train and generate the weights of the concrete road crack recognition model, and obtain a target crack recognition model; the recognition module 240 is configured to input the real-time concrete road crack image into the target crack recognition model, the target crack recognition model outputs a preliminary recognition result, and optimizes the preliminary recognition result through a false detection elimination and missed detection repair algorithm to obtain a final recognition result.

[0043] It should be understood that Figure 2 Modules and references documented in Figure 1 Therefore, the operations and features described above for the method and the corresponding technical effects are also applicable to Figure 2 The modules in it will not be described in detail here.

[0044] In some other embodiments, the present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor is caused to execute the concrete road crack identification method in any of the above method embodiments; As an implementation mode, the computer-readable storage medium of the present invention stores computer-executable instructions, and the computer-executable instructions are configured as follows: A concrete road crack recognition model based on improved DeepLabv3+ is constructed, wherein the concrete road crack recognition model includes an encoder and a decoder directly connected to the encoder; the encoder includes a deep convolutional network layer and an improved dilated spatial pyramid pooling module; the decoder includes a bilinear upsampling module, a 1×1 convolution module, and a 3×3 convolution module; Acquire a concrete road crack image, and annotate and preprocess the concrete road crack image to obtain a concrete road crack data set; The concrete road crack data set is input into the concrete road crack recognition model, model parameters of the concrete road crack recognition model are optimized based on a composite loss function combining edge enhancement and geometric adaptability, weights of the concrete road crack recognition model are generated through training, and a target crack recognition model is obtained; The real-time concrete road crack image is input into the target crack recognition model, the target crack recognition model outputs a preliminary recognition result, and the preliminary recognition result is optimized by a false detection elimination and missed detection repair algorithm to obtain a final recognition result.

[0045] The computer-readable storage medium may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required by at least one function; the data storage area may store data created according to the use of the concrete road crack identification system, etc. In addition, the computer-readable storage medium may include a high-speed random access memory, and may also include a memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the computer-readable storage medium may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the concrete road crack identification system via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0046] Figure 3 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Figure 3As shown, the device includes: a processor 310 and a memory 320. The electronic device may also include: an input device 330 and an output device 340. The processor 310, the memory 320, the input device 330 and the output device 340 may be connected via a bus or other means. Figure 3 In the example, the bus connection is used. The memory 320 is the computer-readable storage medium mentioned above. The processor 310 executes various functional applications and data processing of the server by running the non-volatile software programs, instructions and modules stored in the memory 320, that is, the concrete road crack identification method of the above method embodiment is realized. The input device 330 can receive input digital or character information, and generate key signal input related to user settings and function control of the concrete road crack identification system. The output device 340 may include display devices such as display screens.

[0047] The electronic device can execute the method provided by the embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not described in detail in this embodiment, please refer to the method provided by the embodiment of the present invention.

[0048] As an implementation mode, the electronic device is applied to a concrete road crack identification system and is used for a client, and includes: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can: A concrete road crack recognition model based on improved DeepLabv3+ is constructed, wherein the concrete road crack recognition model includes an encoder and a decoder directly connected to the encoder; the encoder includes a deep convolutional network layer and an improved dilated spatial pyramid pooling module; the decoder includes a bilinear upsampling module, a 1×1 convolution module, and a 3×3 convolution module; Acquire a concrete road crack image, and annotate and preprocess the concrete road crack image to obtain a concrete road crack data set; The concrete road crack data set is input into the concrete road crack recognition model, model parameters of the concrete road crack recognition model are optimized based on a composite loss function combining edge enhancement and geometric adaptability, weights of the concrete road crack recognition model are generated through training, and a target crack recognition model is obtained; The real-time concrete road crack image is input into the target crack recognition model, the target crack recognition model outputs a preliminary recognition result, and the preliminary recognition result is optimized by a false detection elimination and missed detection repair algorithm to obtain a final recognition result.

[0049] Through the description of the above implementation modes, those skilled in the art can clearly understand that each implementation mode can be implemented by means of software plus a necessary general hardware platform, or of course by hardware. Based on such an understanding, the above technical solution can essentially or in other words be embodied in the form of a software product that contributes to the prior art. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods of each embodiment or some parts of the embodiment.

[0050] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for identifying cracks in a concrete road, characterized in that: include: A concrete road crack recognition model based on improved DeepLabv3+ is constructed, wherein the concrete road crack recognition model includes an encoder and a decoder directly connected to the encoder; the encoder includes a deep convolutional network layer and an improved dilated spatial pyramid pooling module; the decoder includes a bilinear upsampling module, a 1×1 convolution module, and a 3×3 convolution module; Acquire a concrete road crack image, and annotate and preprocess the concrete road crack image to obtain a concrete road crack data set; The concrete road crack data set is input into the concrete road crack recognition model, model parameters of the concrete road crack recognition model are optimized based on a composite loss function combining edge enhancement and geometric adaptability, weights of the concrete road crack recognition model are generated through training, and a target crack recognition model is obtained; The real-time concrete road crack image is input into the target crack recognition model, the target crack recognition model outputs a preliminary recognition result, and the preliminary recognition result is optimized by a false detection elimination and missed detection repair algorithm to obtain a final recognition result.

2. A method for identifying cracks in a concrete road according to claim 1, characterized in that: The real-time concrete road crack image is input into the target crack recognition model, and the target crack recognition model outputs a preliminary recognition result, which includes: Extracting shallow feature information of three different scales and one deep feature information of the real-time concrete road crack image according to the deep convolutional network layer, wherein the deep convolutional network layer is a lightweight network structure; The shallow feature information of three different scales is processed into feature maps of the same size by the bilinear upsampling module and then merged, and the channel is compressed by the 1×1 convolution module to generate a first feature map; The improved atrous spatial pyramid pooling module processes deep feature information through multi-scale dilated convolution, and upsamples through a bilinear upsampling module to obtain a second feature map; The first feature map is fused with the second feature map, and after fusion, the features are extracted by the 3×3 convolution module, and the channels are adjusted by the 1×1 convolution module. The prediction results are restored to the same size as the real-time concrete road crack image using a bilinear upsampling module to obtain a preliminary prediction result.

3. A method for identifying cracks in a concrete road according to claim 1, characterized in that: The composite loss function includes a basic segmentation loss sub-function, an edge enhancement loss sub-function and a geometric adaptability loss sub-function; The expression of the composite loss function is: ， In the formula, is the basic segmentation loss sub-function, , are all balance weight parameters, is the edge enhancement loss sub-function, is the geometric adaptability loss sub-function.

4. A method for identifying cracks in a concrete road according to claim 3, characterized in that: The expression of the basic segmentation loss subfunction is: ， In the formula, For the The true label of each pixel, For the The predicted value of each pixel, is the total number of pixels; The expression of the edge enhancement loss subfunction is: ， In the formula, is the dynamic weight based on edge pixels; The expression of the geometric adaptability loss subfunction is: ， ， In the formula, is the geometric weight, is a parameter that controls the weight of geometric features. is a nonlinear function of crack width, For the The pixel position of the crack area.

5. A method for identifying cracks in a concrete road according to claim 1, characterized in that: The improved hole space pyramid pooling module includes: A dynamic multi-branch feature extraction module, which includes a 1×1 convolution module, a 3×3 dilated convolution module with dilation rates of 6, 12, and 18, a global average pooling module, and a dynamic asymmetric dilated convolution module. The dynamic asymmetric dilated convolution module adaptively adjusts the dilation rate in the horizontal direction according to the directional characteristics of the crack distribution in the input feature map by introducing a dynamic receptive field adjustment factor. and the vertical expansion rate , the expression is: ， ， In the formula, is the basic expansion rate in the horizontal direction, , are adjustment coefficients, The input feature map The variance in the horizontal direction, is the basic expansion rate in the vertical direction, The input feature map Variance in the vertical direction; The input features of the 3×3 convolution module with a dilation rate of 6 consist of the deep features and the output features of the 1×1 convolution module; The input features of the 3×3 convolutional module with a dilation rate of 12 are composed of the deep features and the output features of the convolutional module with a dilation rate of 6; The input features of the 3×3 convolutional module with a dilation rate of 18 are composed of the deep features and the output features of the convolutional module with a dilation rate of 12; The crack shape sensitive attention module combines directional gradients and edge information to weight the output features of the 3×3 dilated convolution module with dilation rates of 6, 12, and 18, the global average pooling module, and the dynamic asymmetric dilated convolution module. The attention weight calculation formula of the crack shape sensitive attention module is: ， In the formula, is the channel weight, is the Sigmoid function, , are the gradients of the feature map F in the horizontal and vertical directions, respectively. is a weight matrix used to fuse gradient features with original features.

6. A method for identifying cracks in a concrete road according to claim 1, characterized in that: The optimization of the preliminary recognition result by using the false detection elimination and missed detection repair algorithm to obtain the final recognition result includes: Extract the initially identified crack area Multidimensional geometric features ,in, , , as well as , is the area, is the circumference, The coordinates in the binary image are The pixel value of the pixel, 1 represents cracks, 0 represents background, For Region The borders of , The crack area The horizontal and vertical coordinates of a pixel point on the boundary, , The crack area on the border with The horizontal and vertical coordinates of another adjacent pixel point, is the shape factor, is the eccentricity of the circumscribed ellipse, is the major axis of the circumscribed ellipse, is the minor axis of the circumscribed ellipse; Calculate the normalized score of each feature and combine it with the weighted coefficient to get the comprehensive score, which is expressed as: ， In the formula, is the comprehensive score, is the number of features, For Region The value of the i-th feature of is the weight of the feature, is the standard deviation of feature i, is the mean of feature i; like , then remove the false detection area, is the threshold of the comprehensive score; Missed detection repair based on optimized tensor decomposition, constructing sparse adjacency tensors , the expression is: ， In the formula, is the Euclidean distance between two points, is the angle between two points, represents the adjacency relationship between the i-th and j-th crack connected regions, , The crack area and The centroid coordinates of is the distance threshold, is the angle threshold, is the length of the first dimension of T, indicating the number of rows of the tensor, is the second dimension length of T, indicating the number of columns of the tensor, represents the field of real numbers; The tensor Decomposed into a low-rank form through non-negative tensor decomposition, the expression is: ， In the formula, is the rank of the decomposition, is the kth factor vector used to describe the characteristics of the tensor in the first dimension, is the outer product operation of the tensor, is the kth factor vector used to describe the characteristics of the tensor in the second dimension, is the kth factor vector used to describe the characteristics of the tensor in the third dimension; Define an objective function to restore the connected area by optimizing the sparsity and smoothness constraints. The expression of the objective function is: ， In the formula, and are the constraint weight coefficients for sparsity and smoothness, respectively. is the L2 norm, used to constrain smoothness, is the Frobenius norm, is the L1 norm, used to constrain sparsity, for The gradient of , , is the factor vector in tensor decomposition, corresponding to the three dimensions of tensor T; The reconstructed tensor obtained by optimization Represents possible crack connection areas and reconstructs the tensor The expression is: ， In the formula, To represent the vector The i-th element of To represent the vector The jth element of ; Will Mapping back to the image space, generating the connected crack image, the expression is: ， In the formula, It is a line connection operation between two points; Crack image after fusion of false detections and removal and reconstruction areas , output the final detection result, the expression is: ， In the formula, The final fused crack image.

7. A concrete road crack identification system, characterized in that: include: A construction module configured to construct a concrete road crack recognition model based on improved DeepLabv3+, wherein the concrete road crack recognition model includes an encoder and a decoder directly connected to the encoder; the encoder includes a deep convolutional network layer and an improved dilated spatial pyramid pooling module; the decoder includes a bilinear upsampling module, a 1×1 convolution module, and a 3×3 convolution module; An acquisition module is configured to acquire a concrete road crack image, and annotate and preprocess the concrete road crack image to obtain a concrete road crack data set; an optimization module, configured to input the concrete road crack data set into the concrete road crack recognition model, optimize the model parameters of the concrete road crack recognition model based on a composite loss function combining edge enhancement and geometric adaptability, train and generate weights of the concrete road crack recognition model, and obtain a target crack recognition model; The recognition module is configured to input the real-time concrete road crack image into the target crack recognition model, the target crack recognition model outputs a preliminary recognition result, and optimizes the preliminary recognition result through a false detection elimination and missed detection repair algorithm to obtain a final recognition result.

8. An electronic device, characterized in that: include: At least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images