RC structure earthquake damage identification and segmentation method and device and electronic equipment

By constructing the object detection and semantic segmentation model, and using the image super-resolution algorithm to repair local damage, combined with model fusion, the problem of difficult segmentation of local damage types of RC structure earthquake damage on the overall structural scale is solved, and the RC structure is realized The long-distance identification and segmentation of earthquake damage improves the efficiency of post-seismic evaluation.

CN119027501AActive Publication Date: 2024-11-26XI'AN UNIVERSITY OF ARCHITECTURE AND TECHNOLOGY
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
CN202410992004.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-23
Publication Date
2024-11-26
Estimated Expiration
2044-07-23

AI Technical Summary

Technical Problem

In the prior art, the local damage types of RC structural earthquake damage on the overall structural scale are difficult to accurately segment, and the semantic segmentation model has high requirements for the quality of the input image, resulting in low post-seismic evaluation efficiency.

Method used

A target detection and semantic segmentation model is constructed, and local damage is repaired through a picture super-resolution algorithm, combined with object detection and semantic segmentation models to achieve long-distance identification and segmentation of seismic damage in RC structures.

Benefits of technology

It breaks through the limitations of the traditional damage segmentation model on the shooting distance of the input image, improves the efficiency of post-seismic evaluation work, and realizes the accurate identification and segmentation of seismic damage in RC structures.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119027501A_ABST
    Figure CN119027501A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of concrete structure earthquake damage identification, in particular to an RC structure earthquake damage identification and segmentation method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining an image of an earthquake damage RC structure and a component, and constructing a target detection data set and a semantic segmentation data set; constructing and training a damage positioning model and a semantic segmentation model, and performing fine adjustment on a picture super-resolution algorithm by using the target detection data set and the semantic segmentation data set; and fusing the trained damage positioning model and the trained semantic segmentation model based on a fine-tuned picture super-resolution algorithm to obtain a final damage identification and segmentation model. The method breaks through the limitation of a traditional damage segmentation model on the shooting distance of an input picture, facilitates the promotion of the practical application of an advanced computer vision algorithm in practical engineering, achieves the remote recognition and segmentation of the earthquake damage of the RC structure, and improves the efficiency of the post-earthquake evaluation work.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of earthquake damage identification of concrete structures, and in particular to a method, device, electronic device and storage medium for earthquake damage identification and segmentation of RC structures. Background Art

[0002] After an earthquake occurs, it is crucial to conduct a reasonable and accurate safety assessment of the damaged RC structure. In recent years, the rapid development of computer vision technology has provided many new paradigms for many problems in the engineering field, and has great development potential in the field of post-earthquake assessment. Computer vision-based RC structure damage location and damage segmentation can achieve non-contact rapid damage assessment, which has become an important development trend in the field of post-earthquake assessment.

[0003] At present, damage assessment methods based on computer vision can be mainly divided into damage localization (target detection) and damage segmentation (semantic segmentation). Damage localization based on target detection can locate and mark the damaged parts in the picture using rectangular boxes, and damage segmentation based on semantic segmentation can segment different damage types in the picture at the pixel level (such as concrete spalling, exposed steel bars, etc.). At present, the damage localization model can achieve damage localization at a longer distance (the input of the model can be a picture of the overall structural scale) with high accuracy. However, due to the lack of damage segmentation, such models cannot provide further guidance for more sophisticated post-earthquake assessment work. Although the semantic segmentation model can further subdivide the damage types of the structure, the input of such models is often a high-definition damage picture taken at a close distance (i.e., a picture of the component scale). When the semantic segmentation model is input with a structural scale picture, the different damage types at the local damage position on the overall structure are difficult to be accurately segmented. This is because when the local damage on the structural scale picture is magnified, the local damage picture will become very blurred, which does not meet the requirements of the existing semantic segmentation model for the input picture quality. Therefore, when using the existing semantic segmentation model to quantitatively assess structural damage, the model's limitations on input images require the evaluator to perform multiple image acquisition tasks at the component level, which greatly reduces the efficiency of post-earthquake assessment work. Summary of the invention

[0004] The present application aims to solve one of the technical problems in the related art at least to some extent.

[0005] To this end, the first purpose of this application is to propose a method for identifying and segmenting earthquake damage in RC structures to solve the problems that different damage types at local damage locations on the overall structure of existing technical means are difficult to accurately segment and do not meet the requirements of existing semantic segmentation models for input image quality.

[0006] The second object of the present application is to provide a device.

[0007] The third objective of the present application is to provide an electronic device.

[0008] A fourth objective of the present application is to provide a computer-readable storage medium.

[0009] To achieve the above-mentioned purpose, the first embodiment of the present application proposes a method for identifying and segmenting earthquake damage of RC structures, comprising:

[0010] Obtain images of earthquake-damaged RC structures and components, and construct target detection datasets and semantic segmentation datasets;

[0011] Constructing a damage localization model and a semantic segmentation model, and using the target detection data set and the semantic segmentation data set to train the damage localization model and the semantic segmentation model respectively, to obtain a trained damage localization model and a trained semantic segmentation model;

[0012] Fine-tuning the image super-resolution algorithm using the object detection dataset and the semantic segmentation dataset;

[0013] The trained damage localization model and the trained semantic segmentation model are fused based on a fine-tuned image super-resolution algorithm to obtain a final damage identification and segmentation model.

[0014] Preferably, the acquiring of images of earthquake-damaged RC structures and components and the construction of target detection datasets and semantic segmentation datasets include:

[0015] Images of earthquake-damaged RC structures and components are obtained, features are extracted from the images of the earthquake-damaged RC structures and components, and annotation processing is performed on the images, and a target detection dataset and a semantic segmentation dataset are constructed based on the feature maps after the annotation processing.

[0016] Preferably, the constructing of the damage localization model and the semantic segmentation model, using the target detection data set and the semantic segmentation data set to respectively train the damage localization model and the semantic segmentation model, and obtaining the trained damage localization model and the trained semantic segmentation model comprises:

[0017] Building a damage localization model based on the YOLO V5 network, and training the damage localization model using the target detection data set to obtain a trained damage localization model;

[0018] A semantic segmentation model is constructed using a network architecture with U-shaped jump links based on pyramid multi-scale feature fusion, Haar wavelet downsampling and attention modules, and the semantic segmentation model is trained using the semantic segmentation dataset to obtain a trained semantic segmentation model.

[0019] Preferably, it also includes:

[0020] The loss function used in training is a weighted multi-category cross entropy loss function, which is calculated as follows:

[0021]

[0022] Among them, E is the weighted cross entropy loss, α is the weight, k is the total category, α s is the scaled weight, t k is the label, y k is the predicted value.

[0023] Preferably, the fine-tuning of the image super-resolution algorithm using the object detection dataset and the semantic segmentation dataset includes:

[0024] Rescreening the object detection dataset and the semantic segmentation dataset, and aggregating the pictures that meet the preset values ​​to obtain a summary dataset;

[0025] The summarized data set is used to fine-tune the weights of the image super-resolution model StableSR to obtain a fine-tuned image super-resolution algorithm.

[0026] Preferably, constructing the target detection data set includes:

[0027] Obtain a high-definition building complex or bridge landscape picture, shrink the damaged RC component picture at the component level and paste it at a random position on the high-definition building complex or bridge landscape picture, and use a rectangular frame to mark the local damage in the picture.

[0028] Preferably, the labeling process includes: 8 types of pixels, namely background, concrete spalling, concrete cracking, concrete crushing, longitudinal reinforcement leakage, longitudinal reinforcement buckling, stirrup leakage, and concrete fragments.

[0029] To achieve the above-mentioned purpose, the second embodiment of the present application proposes a RC structure earthquake damage identification and segmentation device, comprising:

[0030] Image acquisition module, which acquires images of damaged RC structures and components and builds target detection datasets and semantic segmentation datasets;

[0031] A model construction module, constructing a damage localization model and a semantic segmentation model, using the target detection data set and the semantic segmentation data set to train the damage localization model and the semantic segmentation model respectively, to obtain a trained damage localization model and a trained semantic segmentation model;

[0032] An algorithm fine-tuning module, using the target detection dataset and the semantic segmentation dataset to fine-tune the image super-resolution algorithm;

[0033] The model fusion module fuses the trained damage localization model and the trained semantic segmentation model based on a fine-tuned image super-resolution algorithm to obtain a final damage identification and segmentation model.

[0034] To achieve the above-mentioned purpose, the third aspect of the present application provides an electronic device, including: a processor, and a memory communicatively connected to the processor;

[0035] The memory stores computer-executable instructions;

[0036] The processor executes the computer-executable instructions stored in the memory to implement any of the above methods.

[0037] To achieve the above-mentioned purpose, the fourth aspect embodiment of the present application proposes a computer-readable storage medium, including computer-executable instructions stored in the computer-readable storage medium, and the computer-executable instructions are used to implement any of the methods described above when executed by a processor.

[0038] The present application provides a method for identifying and segmenting earthquake damage in RC structures. First, the target detection algorithm is used to locate local damage on the structural scale, and then the local damage area is extracted separately. The extracted local damage image is input into the image super-resolution algorithm for repair, and then the repaired local damage image is input into the semantic segmentation model for damage segmentation. Finally, the segmentation result is re-overlaid on the corresponding position of the original image as output. It breaks through the limitation of the traditional damage segmentation model on the shooting distance of the input image, helps to promote the practical application of advanced computer vision algorithms in actual engineering, realizes the long-distance identification and segmentation of earthquake damage in RC structures, and improves the efficiency of post-earthquake assessment work.

[0039] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0041] Figure 1 A flowchart of a first specific embodiment of a method for identifying and segmenting earthquake damage of an RC structure provided by the present invention;

[0042] Figure 2 This is a schematic diagram of the semantic segmentation network model architecture;

[0043] Figure 3It is a schematic diagram of the framework of the long-distance identification and segmentation method of earthquake damage in RC structures based on image super-resolution;

[0044] Figure 4 A structural block diagram of a device for identifying and segmenting earthquake damage in an RC structure provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0045] The core of the present invention is to provide a method, device, electronic device and storage medium for identifying and segmenting earthquake damage in RC structures. By constructing a damage location model and a semantic segmentation model, long-distance identification and segmentation of earthquake damage in RC structures can be achieved, thereby improving the efficiency of post-earthquake assessment work.

[0046] In order to enable those skilled in the art to better understand the scheme of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0047] Please refer to Figure 1 , Figure 1 This is a flow chart of a first specific embodiment of a method for identifying and segmenting earthquake damage of an RC structure provided by the present invention; the specific operation steps are as follows:

[0048] Step S101: Acquire images of earthquake-damaged RC structures and components, and construct target detection datasets and semantic segmentation datasets;

[0049] Images of earthquake-damaged RC structures and components are obtained, features are extracted from the images of the earthquake-damaged RC structures and components, and annotation processing is performed on the images, and a target detection dataset and a semantic segmentation dataset are constructed based on the feature maps after the annotation processing.

[0050] The constructing of the target detection data set includes:

[0051] Obtain a high-definition building complex or bridge landscape picture, shrink the damaged RC component picture at the component level and paste it at a random position on the high-definition building complex or bridge landscape picture, and use a rectangular frame to mark the local damage in the picture.

[0052] The labeling process includes: 8 types of pixels, namely background, concrete spalling, concrete cracking, concrete crushing, longitudinal reinforcement leakage, longitudinal reinforcement buckling, stirrup leakage, and concrete fragments.

[0053] Step S102: constructing a damage localization model and a semantic segmentation model, and using the target detection dataset and the semantic segmentation dataset to train the damage localization model and the semantic segmentation model respectively, to obtain a trained damage localization model and a trained semantic segmentation model;

[0054] Building a damage localization model based on the YOLO V5 network, and training the damage localization model using the target detection data set to obtain a trained damage localization model;

[0055] A semantic segmentation model is constructed using a network architecture with U-shaped skip links based on pyramid multi-scale feature fusion, Haar wavelet downsampling and attention modules, and the semantic segmentation model is trained using the semantic segmentation dataset to obtain a trained semantic segmentation model.

[0056] The loss function used in training is a weighted multi-category cross entropy loss function, which is calculated as follows:

[0057]

[0058] Among them, E is the weighted cross entropy loss, α is the weight, k is the total category, α s is the scaled weight, t k is the label, y k is the predicted value.

[0059] Step S103: fine-tuning the image super-resolution algorithm using the target detection dataset and the semantic segmentation dataset;

[0060] Rescreening the object detection dataset and the semantic segmentation dataset, and aggregating the pictures that meet the preset values ​​to obtain a summary dataset;

[0061] The summarized data set is used to fine-tune the weights of the image super-resolution model StableSR to obtain a fine-tuned image super-resolution algorithm.

[0062] Step S104: Based on the fine-tuned image super-resolution algorithm, the trained damage localization model and the trained semantic segmentation model are fused to obtain a final damage identification and segmentation model.

[0063] This embodiment provides a method for identifying and segmenting earthquake damage in RC structures. First, the target detection algorithm is used to locate local damage on the structural scale, and then the local damage area is extracted separately. The extracted local damage image is input into the image super-resolution algorithm for repair, and then the repaired local damage image is input into the semantic segmentation model for damage segmentation. Finally, the segmentation result is re-overlaid on the corresponding position of the original image as output. It breaks through the limitation of the traditional damage segmentation model on the shooting distance of the input image, helps to promote the practical application of advanced computer vision algorithms in actual engineering, realizes the long-distance identification and segmentation of earthquake damage in RC structures, and improves the efficiency of post-earthquake assessment work.

[0064] Based on the above embodiment, this embodiment describes the RC structure earthquake damage identification and segmentation method, which is as follows:

[0065] Construct a new image dataset of damaged RC structures and components that can be used for object detection and semantic segmentation;

[0066] like Figure 2 As shown, the sources of the images used mainly include the following sources, namely, test images taken in the tests of RC beams, columns, nodes, etc. conducted by the applicant's research team in recent years, illustrations in papers in RC component test research, real damage images of RC structures in actual earthquake-stricken areas shown in earthquake damage reports, and search engines (for example, Google Image). The images in the dataset mainly include various types of RC structural components (beams, columns, nodes, walls, etc.). The images in the dataset were taken in many different environments (laboratories, environments with dim light, earthquake-stricken areas, etc.), and contain various types of complex background information and random occlusions (plant occlusions, concrete fragments, etc.). A total of 8 types of pixels are annotated in the dataset images, namely background, concrete spalling, concrete cracking, concrete crushing, longitudinal reinforcement leakage, longitudinal reinforcement buckling, stirrup leakage, and concrete fragments. The manual labeling process is based on the labelme labeling tool. After labeling, each pixel in the exported feature map has a unique category;

[0067] The specific method of making the image dataset for target detection is as follows: First, a number of high-definition building complex or bridge landscape images, mainly urban street scenes, are collected. Then, the damaged RC component images at the component level are reduced and pasted at random positions on the high-definition building complex or bridge landscape images to simulate local damage in the structural level images. Then, the local damage in the image is marked using a rectangular frame.

[0068] The manual annotation process of the image dataset used for semantic segmentation is based on the labelme annotation tool. After annotation, each pixel in the exported feature map has a unique category.

[0069] like Figure 3 As shown, the constructed target detection dataset is used to train the damage localization model based on the YOLO V5 network structure, and then a semantic segmentation model with U-shaped skip links including pyramid multi-scale feature fusion, Haar wavelet downsampling and attention module is proposed, and the proposed semantic segmentation model is trained using the constructed semantic segmentation dataset;

[0070] The learning rate scheduler uses an adaptive learning rate automatic scheduler. The core idea of ​​the adaptive learning rate automatic scheduler algorithm is to sacrifice training time and dynamically adjust the learning rate according to the change of loss during training. When the loss change is small, that is, the model tends to be stable, the learning rate is reduced for more precise adjustment; when the loss change is large, the learning rate is increased to accelerate convergence;

[0071] Use the target detection dataset and semantic segmentation dataset to fine-tune the weights of the image super-resolution algorithm StableSR;

[0072] The target detection dataset and semantic segmentation dataset were re-screened, and images with a resolution of 2K or above were summarized as high-quality image datasets. The high-quality image datasets were used to fine-tune the weights of the image super-resolution model StableSR to enhance its super-resolution accuracy in the field of damage identification and avoid excessive artifacts.

[0073] The damage localization model and the semantic segmentation model are organically integrated to form a new technical solution, which realizes the location-extraction-super-resolution-segmentation and final output of structural damage;

[0074] The embodiment of the present invention provides a method for identifying and segmenting earthquake damage in RC structures. First, the target detection algorithm is used to locate local damage on the structural scale, and then the local damage area is extracted separately. The extracted local damage image is input into the image super-resolution algorithm for repair, and then the repaired local damage image is input into the semantic segmentation model for damage segmentation. Finally, the segmentation result is re-overlaid on the corresponding position of the original image as output. It breaks through the limitation of the traditional damage segmentation model on the shooting distance of the input image, helps to promote the practical application of advanced computer vision algorithms in actual engineering, realizes the long-distance identification and segmentation of earthquake damage in RC structures, and improves the efficiency of post-earthquake assessment work.

[0075] Please refer to Figure 4 , Figure 4 A structural block diagram of a device for identifying and segmenting earthquake damage of an RC structure provided by an embodiment of the present invention; the specific device may include:

[0076] An image acquisition module 100 acquires images of earthquake-damaged RC structures and components, and constructs a target detection dataset and a semantic segmentation dataset;

[0077] A model construction module 200 constructs a damage localization model and a semantic segmentation model, and uses the target detection data set and the semantic segmentation data set to train the damage localization model and the semantic segmentation model respectively to obtain a trained damage localization model and a trained semantic segmentation model;

[0078] An algorithm fine-tuning module 300, which uses the object detection dataset and the semantic segmentation dataset to fine-tune the image super-resolution algorithm;

[0079] The model fusion module 400 fuses the trained damage localization model and the trained semantic segmentation model based on the fine-tuned image super-resolution algorithm to obtain a final damage identification and segmentation model.

[0080] An RC structure earthquake damage identification and segmentation device of the present embodiment is used to implement the aforementioned RC structure earthquake damage identification and segmentation method. Therefore, the specific implementation method of an RC structure earthquake damage identification and segmentation device can be seen in the embodiment part of the RC structure earthquake damage identification and segmentation method in the previous text. For example, the image acquisition module 100, the model construction module 200, the algorithm fine-tuning module 300, and the model fusion module 400 are respectively used to implement steps S101, S102, S103, and S104 in the aforementioned RC structure earthquake damage identification and segmentation method. Therefore, its specific implementation method can refer to the description of the corresponding various parts of the embodiment, which will not be repeated here.

[0081] In order to implement the above embodiments, the present application also proposes an electronic device, comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method provided by the above embodiments.

[0082] In order to implement the above embodiments, the present application also proposes a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the methods provided by the above embodiments.

[0083] In order to implement the above embodiments, the present application also proposes a computer program product, including a computer program, which implements the methods provided by the above embodiments when executed by a processor.

[0084] The collection, storage, use, processing, transmission, provision and disclosure of user personal information involved in this application are in compliance with relevant laws and regulations and do not violate public order and good morals.

[0085] It should be noted that personal information from users should be collected for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. In addition, such collection / sharing should be carried out after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign the agreement / authorization including authorization of relevant user information before the user uses the function. In addition, any necessary steps should be taken to protect and safeguard access to such personal information data and ensure that others who have access to personal information data comply with its privacy policy and procedures.

[0086] The present application is expected to provide an implementation scheme for users to selectively block the use or access of personal information data. That is, the present disclosure is expected to provide hardware and / or software to prevent or block access to such personal information data. Once the personal information data is no longer needed, the risk can be minimized by limiting data collection and deleting the data. In addition, when applicable, such personal information is de-identified to protect the privacy of the user.

[0087] In the description of the aforementioned embodiments, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0088] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0089] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0090] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0091] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0092] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0093] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0094] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for identifying and segmenting earthquake damage in RC structures, characterized in that: include: Obtain images of earthquake-damaged RC structures and components, and construct target detection datasets and semantic segmentation datasets; Constructing a damage localization model and a semantic segmentation model, and using the target detection data set and the semantic segmentation data set to train the damage localization model and the semantic segmentation model respectively, to obtain a trained damage localization model and a trained semantic segmentation model; Fine-tuning the image super-resolution algorithm using the object detection dataset and the semantic segmentation dataset; The trained damage localization model and the trained semantic segmentation model are fused based on a fine-tuned image super-resolution algorithm to obtain a final damage identification and segmentation model.

2. The RC structure earthquake damage identification and segmentation method according to claim 1, characterized in that: The obtaining of images of earthquake-damaged RC structures and components and the construction of target detection datasets and semantic segmentation datasets include: Images of earthquake-damaged RC structures and components are obtained, features are extracted from the images of the earthquake-damaged RC structures and components, and annotation processing is performed on the images, and a target detection dataset and a semantic segmentation dataset are constructed based on the feature maps after the annotation processing.

3. The RC structure earthquake damage identification and segmentation method according to claim 1, characterized in that: The step of constructing a damage localization model and a semantic segmentation model, and respectively training the damage localization model and the semantic segmentation model using the target detection data set and the semantic segmentation data set to obtain a trained damage localization model and a trained semantic segmentation model comprises: Building a damage localization model based on the YOLO V5 network, and training the damage localization model using the target detection data set to obtain a trained damage localization model; A semantic segmentation model is constructed using a network architecture with U-shaped skip links based on pyramid multi-scale feature fusion, Haar wavelet downsampling and attention modules, and the semantic segmentation model is trained using the semantic segmentation dataset to obtain a trained semantic segmentation model.

4. The RC structure earthquake damage identification and segmentation method according to claim 3 is characterized in that: Also includes: The loss function used in training is a weighted multi-category cross entropy loss function, which is calculated as follows: Among them, E is the weighted cross entropy loss, α is the weight, k is the total category, α s is the scaled weight, t k is the label, y k is the predicted value.

5. The RC structure earthquake damage identification and segmentation method according to claim 1, characterized in that: The fine-tuning of the image super-resolution algorithm using the target detection dataset and the semantic segmentation dataset includes: Rescreening the object detection dataset and the semantic segmentation dataset, and aggregating the pictures that meet the preset values ​​to obtain a summary dataset; The summarized data set is used to fine-tune the weights of the image super-resolution model StableSR to obtain a fine-tuned image super-resolution algorithm.

6. The RC structure earthquake damage identification and segmentation method according to claim 2, characterized in that: The constructing of the target detection data set includes: Obtain a high-definition building complex or bridge landscape picture, shrink the damaged RC component picture at the component level and paste it at a random position on the high-definition building complex or bridge landscape picture, and use a rectangular frame to mark the local damage in the picture.

7. The RC structure earthquake damage identification and segmentation method according to claim 2, characterized in that: The labeling process includes: 8 types of pixels, namely background, concrete spalling, concrete cracking, concrete crushing, longitudinal reinforcement leakage, longitudinal reinforcement buckling, stirrup leakage, and concrete fragments.

8. A device for identifying and segmenting earthquake damage of RC structures, characterized in that: include: Image acquisition module, which acquires images of damaged RC structures and components and builds target detection datasets and semantic segmentation datasets; A model construction module, constructing a damage localization model and a semantic segmentation model, using the target detection data set and the semantic segmentation data set to train the damage localization model and the semantic segmentation model respectively, to obtain a trained damage localization model and a trained semantic segmentation model; An algorithm fine-tuning module, using the target detection dataset and the semantic segmentation dataset to fine-tune the image super-resolution algorithm; The model fusion module fuses the trained damage localization model and the trained semantic segmentation model based on a fine-tuned image super-resolution algorithm to obtain a final damage identification and segmentation model.

9. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.

Citation Information

Patent Citations

  • Training method of image semantic segmentation model and server

    CN110363210A

  • Small target segmentation method and device based on target detection and super-resolution reconstruction

    CN113971763A

  • Grape leaf scab image segmentation method based on Transform

    CN115810017A

  • Method and system for monitoring construction quality of 3D printing bridge floor based on semantic segmentation

    CN116664846A

  • Bird image recognition method and system for preventing misjudgment

    CN116740758A