Method and system for quickly identifying line type of structural component based on multi-order segmentation

Abstract

The invention provides a multi-order segmentation-based structural member linetype rapid identification method and system, and relates to the technical field of engineering structure intelligent detection, and the method comprises the steps: obtaining an original image of a structural member; performing coarse segmentation on the original image to generate an initial binary mask of the structural member; automatically screening out a target mask region containing a foreground prompt point through a connected domain analysis mode; calculating bounding box coordinate information of a bounding rectangle of the target mask region through a contour detection mode; extracting a corresponding target area sub-image from the original image; adopting a super-resolution reconstruction model to enhance the sub-image of the target area; performing sub-image division on the enhanced target area sub-image; fine segmentation is carried out on the sub-images, and a high-precision mask is determined; mapping the high-precision mask to an original image through coordinate mapping; and combining an edge detection algorithm to extract an outer contour line of the structural member to complete linetype identification of the structural member.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent detection of engineering structures, and in particular to a method and system for quickly identifying the linear shape of structural components based on multi-order segmentation. Background Art

[0002] The rapid linear profile recognition method for structural components based on multi-order segmentation is a new recognition method that integrates computer vision and image enhancement technology. It is mainly used to efficiently and accurately extract the linear contours of components in engineering structures from images. It can better restore the edge details of structural components in low-quality or complex background images, reduce human intervention and data dependence, and has excellent accuracy, robustness and engineering practicality. It is suitable for structural health monitoring and intelligent recognition tasks in multiple scenarios such as buildings, bridges, and tunnels.

[0003] In the fields of construction and infrastructure, the linear shape of structural components is a key geometric element that characterizes the structural spatial form, stress characteristics, and connection relationships. Its rapid and accurate identification is of great significance for ensuring structural safety, improving construction accuracy, achieving quality traceability, and conducting structural health monitoring and deformation early warning during the operation phase.

[0004] However, traditional methods for rapid identification of the linear shape of structural components usually use total station measurement points or three-dimensional laser scanning equipment. Although they are highly accurate, they have the disadvantages of expensive equipment, complex data processing, poor real-time performance, inability to cope with large-scale, high-frequency monitoring tasks, and susceptibility to environmental interference and human errors. Traditional methods introduce deep learning algorithms for rapid identification, but this algorithm is heavily dependent on large-scale, high-quality annotated data, has high training costs, and unclear boundary recognition in scenes with low image resolution and blurred details, resulting in problems such as missegmentation and boundary drift in the edge areas of structural components, affecting stability and generalization ability. Summary of the Invention

[0005] In view of the above deficiencies in the prior art, the purpose of an embodiment of the present invention is to provide a method for rapid identification of the linear shape of structural components based on multi-order segmentation, which can solve the problems that traditional methods for rapid identification of the linear shape of structural components usually use total station measuring points or three-dimensional laser scanning equipment. Although the accuracy is high, the equipment is expensive, the data processing is complex, the real-time performance is poor, and it cannot cope with large-scale, high-frequency monitoring tasks and is susceptible to environmental interference and human errors. The traditional method introduces a deep learning algorithm for rapid identification, but the algorithm is heavily dependent on large-scale, high-quality labeled data, the training cost is high, and the boundary identification is unclear in scenes with low image resolution and blurred details, resulting in problems such as missegmentation and boundary drift in the edge area of ​​the structural component, which affects the stability and generalization ability.

[0006] In a first aspect of an embodiment of the present invention, a method for rapidly identifying the line shape of a structural component based on multi-level segmentation is proposed, comprising:

[0007] S1: Obtain the original image of the structural component;

[0008] S2: using a first visual segmentation model to roughly segment the original image and generate an initial binary mask of the structural component;

[0009] S3: Based on the foreground cue points in the original image, automatically screening out a target mask area containing the foreground cue points in the initial binary mask by using a connected component analysis method;

[0010] S4: Calculating the coordinate information of the circumscribed rectangular bounding box of the target mask area by contour detection;

[0011] S5: extracting a corresponding target area sub-image from the original image according to the coordinates of the rectangular bounding box;

[0012] S6: using a super-resolution reconstruction model to enhance the sub-image of the target area;

[0013] S7: dividing the enhanced target region sub-image into sub-images to determine a plurality of sub-images;

[0014] S8: performing fine segmentation on each of the sub-images through a second visual segmentation model to determine a high-precision mask;

[0015] S9: Mapping the high-precision mask to the original image through coordinate mapping;

[0016] S10: extracting the outer contour of the structural component by combining an edge detection algorithm to complete the line type recognition of the structural component.

[0017] A second aspect of an embodiment of the present invention provides a structural component line type rapid identification system based on multi-stage segmentation, comprising: a processor and a memory;

[0018] The memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the method for rapid identification of structural component line types based on multi-level segmentation as described in the first aspect are implemented.

[0019] According to a third aspect of an embodiment of the present invention, a readable storage medium is proposed, on which a program or instruction is stored. When the program or instruction is executed by a processor, the steps of the method for rapid identification of the line type of a structural component based on multi-order segmentation as described in the first aspect are implemented.

[0020] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0021] In an embodiment of the present invention, a large visual segmentation model with support point prompts is used for coarse segmentation, candidate area screening is automatically completed, reliance on manual labeling is reduced, the level of automation is improved, and rapid positioning of the target area without training is achieved. By introducing super-resolution reconstruction, the image resolution, edge clarity and texture details are significantly improved, so that the subsequent segmentation module can still maintain high recognition accuracy when processing blurred, compressed or long-distance images, effectively breaking through the bottleneck of low-quality images, and adopting a sliding window mechanism combined with an adaptive fine segmentation scheme of local prompt points to achieve accurate recognition at the sub-image level, especially excellent performance in boundary areas. The present invention combines super-resolution image enhancement with a multi-stage refined segmentation strategy, which significantly improves the recognition accuracy and edge clarity of the contours of structural components under complex backgrounds and low-quality image conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings are only for the purpose of illustrating specific embodiments and are not to be considered as limiting the present invention. Throughout the drawings, the same reference symbols represent the same components. Obviously, the drawings described below are only some embodiments of the present invention. It is clear that those skilled in the art can derive other drawings based on these drawings without inventive effort.

[0023] Figure 1 1 is a flow chart of a method for rapid identification of structural component line types based on multi-stage segmentation provided by an embodiment of the present invention;

[0024] Figure 2 This is a schematic diagram of a process for rapid identification of structural component line shapes based on super-resolution enhancement and multi-stage refined segmentation provided by an embodiment of the present invention;

[0025] Figure 3 This is a structural schematic diagram of a system for rapidly identifying the linear shape of a structural component based on multi-stage segmentation provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the technical solutions in the embodiments of the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described are part of the embodiments of the present invention, rather than all of the embodiments. It should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work should fall within the scope of protection of the present invention.

[0027] The method for rapid identification of structural component line shapes based on multi-stage segmentation provided by the embodiment of the present invention will be described in detail below with reference to the accompanying drawings through specific embodiments and application scenarios.

[0028] Reference Manual Figure 1 , which shows a flow chart of a method for rapid identification of the line type of a structural component based on multi-stage segmentation provided by an embodiment of the present invention.

[0029] Reference Manual Figure 2 , shows a schematic diagram of the process of rapid identification of structural component line types based on super-resolution enhancement and multi-stage refined segmentation provided by an embodiment of the present invention.

[0030] like Figure 2 As shown, in this invention, the input image is first processed using support point hints and an interactive segmentation model to obtain a target outline based on the foreground point coordinates. Next, edge extraction methods are used to further extract and optimize the target boundary. Finally, structured target information is combined with refinement processing to extract the target's detailed outline. Finally, super-resolution technology and a sliding window algorithm are used to accurately repair and extract the target, ultimately generating multiple refined results and achieving accurate target recognition and extraction.

[0031] An embodiment of the present invention provides a method for quickly identifying the line shape of a structural component based on multi-level segmentation, which may include the following steps:

[0032] S1: Obtain the original image of the structural component.

[0033] Among them, structural components refer to important parts in engineering structures such as buildings, bridges, and tunnels that bear load functions or constitute the entire structure.

[0034] S2: Use the first visual segmentation model to perform coarse segmentation on the original image and generate an initial binary mask of the structural components.

[0035] Among them, the large visual segmentation model is preferably a general segmentation model that supports point prompt interaction, such as the SegmentAnything Model (SAM) or its lightweight variant, which can quickly locate the target area and generate a rough mask based on user or automatically generated point prompts. The model has strong cross-scene generalization capabilities and strong adaptability. It can complete the initial target positioning without fine-tuning specific structural components, thereby improving the automation and portability of the entire segmentation process.

[0036] It should be noted that by introducing the first visual segmentation large model, it is possible to quickly locate the target area under unsupervised or weakly supervised conditions, generate the initial mask of the structural components, and provide a stable and efficient input basis for subsequent multi-stage refined processing, effectively improving the system's automation level and cross-scene adaptability.

[0037] In a possible implementation, the first visual segmentation model is specifically a general visual segmentation model that supports point prompt interaction.

[0038] For example, general visual segmentation models that support point prompt interaction can be: SAM, RITM, FocalClick, CLIPSeg.

[0039] S3: Based on the foreground cue points in the original image, the target mask area containing the foreground cue points is automatically screened out in the initial binary mask through connected component analysis.

[0040] Foreground cues are feature points in an image that are automatically selected by the user or the model to identify the target region. These points are typically located within the target region of interest and are used to guide the model in identifying the target region's location. Connected domain analysis is an image processing technique that detects continuous pixel regions in an image and identifies "connected" regions. Specifically, it groups all adjacent regions with identical pixel values ​​into a single category.

[0041] It should be noted that by combining foreground cue points and connected domain analysis, the area containing the target can be accurately screened out, thereby avoiding missegmentation or missed segmentation, enhancing the accuracy and reliability of mask screening, and providing more accurate input for subsequent refined processing.

[0042] In a possible implementation, S3 is specifically:

[0043] Based on the judgment principle that the coordinates of foreground cue points are located inside the target mask area, the target mask area containing the foreground cue points is automatically screened out from the initial binary mask through connected component analysis.

[0044] Specifically, the determination principle of whether the foreground cue point coordinates are located inside the target mask area is as follows: if a certain "mask area" contains the foreground cue point coordinates, the area is judged to be the real target area; otherwise, the area is considered to be a mis-segmented area and should be eliminated.

[0045] In this embodiment of the present invention, the connected component analysis method specifically involves performing morphological operations on the binary mask image and then applying the eight-neighborhood or four-neighborhood connectivity rule to extract all connected regions. The region containing the coordinates of the foreground cue point is automatically selected as the target mask region, and a bounding rectangle is generated based on the boundary contour of the region for target positioning.

[0046] S4: Calculate the coordinate information of the bounding box of the target mask area through contour detection.

[0047] Among them, contour detection is an image processing method used to identify edge boundaries with the same pixel values ​​in an image, that is, to determine the "shape" or "edge" of the target area. The contour detection method is usually the findContours() function in OpenCV.

[0048] It should be noted that by extracting the boundaries of the target area through contour detection and calculating the coordinates of the circumscribed rectangular bounding box, the spatial position of the structural components can be accurately located, providing accurate reference boundaries for subsequent image cropping and area enhancement, significantly improving the positioning accuracy and processing efficiency of the overall process.

[0049] S5: Extract the corresponding target area sub-image from the original image according to the coordinates of the rectangular bounding box.

[0050] It should be noted that extracting the target area sub-image from the original image according to the bounding box coordinates can effectively focus on the area of ​​interest, reduce background interference and computational burden, and provide clear and accurately positioned input blocks for subsequent image enhancement and fine segmentation, significantly improving overall processing efficiency and recognition accuracy.

[0051] In the embodiment of the present invention, the size of the extracted sub-image of the target area may be set to be slightly larger than the circumscribed rectangular frame to avoid loss of component boundary information due to truncation and enhance robustness.

[0052] S6: Use the super-resolution reconstruction model to enhance the sub-image of the target area.

[0053] Among them, the super-resolution reconstruction model is an image enhancement technology based on deep learning, which aims to reconstruct low-resolution images into high-resolution images and restore details, edges and texture information.

[0054] It should be noted that using a super-resolution reconstruction model to enhance the sub-image of the target area can significantly improve the clarity and edge texture quality of the image, making the subsequent segmentation model more accurate in identifying component contours and detail boundaries, especially when processing blurred, compressed or long-distance collected images.

[0055] In a possible implementation, the super-resolution reconstruction model is specifically a reconstruction model built based on a deep convolutional neural network.

[0056] The reconstruction models built based on deep convolutional neural networks can be specifically: Real-ESRGAN, EDSR and RCAN. While retaining the image texture details, this model can effectively improve the image edge quality, facilitating the subsequent segmentation model to accurately judge complex boundaries.

[0057] S7: Divide the enhanced target region sub-image into sub-images to determine a plurality of sub-images.

[0058] It should be noted that by dividing the enhanced target area image into multiple sub-images, not only the modeling ability of the local area is improved, but also the recognition accuracy of edges, details and small components is effectively improved. At the same time, it is convenient to realize parallel segmentation processing at the sub-image level, thereby improving the overall computing efficiency and scalability.

[0059] In a possible implementation, S7 specifically includes:

[0060] The enhanced target region sub-image is divided into non-overlapping or optionally overlapping sub-images through a sliding window mechanism to determine a plurality of sub-images.

[0061] In this embodiment of the present invention, the window size and step size of the sliding window can be flexibly adjusted based on the size of the target area image and the segmentation requirements. A non-overlapping strategy can achieve complete regional coverage by dividing the boundary area into separate supplementary windows. In specific implementations, an overlapping sliding window strategy can also be switched to optimize segmentation consistency in the boundary transition area, improving fusion quality.

[0062] S8: Use the second visual segmentation model to perform fine segmentation on each sub-image and determine a high-precision mask.

[0063] It should be noted that by using the second visual segmentation model to refine the sub-images, the accuracy of boundary contour segmentation can be greatly improved while retaining the details of structural components. This is particularly suitable for processing areas with complex shapes or blurred edges, laying a solid foundation for high-quality contour extraction.

[0064] In a possible implementation, the second visual segmentation model is specifically a visual segmentation model guided by both the cue points and the rectangular frame.

[0065] In an embodiment of the present invention, the large visual segmentation model guided by both the cue points and the rectangular box may specifically be: a SAM model, a SAM2 model, a FastSAM model, and a SEEM model.

[0066] S9: Map the high-precision mask to the original image through coordinate mapping.

[0067] It should be noted that by mapping the high-precision mask back to the original image coordinate system, the consistency of the segmentation result and the original image is ensured, which facilitates subsequent visualization and further analysis, and improves the accuracy and practicality of the overall processing flow.

[0068] In a possible implementation, S9 specifically includes:

[0069] S901: Mapping the high-precision mask to the local coordinate system of the target region sub-image through coordinate mapping.

[0070] S902: Mapping a high-precision mask to the original image according to the coordinate position of the target area sub-image in the original image, and extracting the outer contour of the structural component in combination with an edge detection algorithm.

[0071] S10: Combined with the edge detection algorithm, the outer contour line of the structural component is extracted to complete the line type recognition of the structural component.

[0072] Among them, the edge detection algorithm is an image processing technology used to identify areas in an image where brightness or color changes significantly, that is, the edges of the image.

[0073] It should be noted that by combining edge detection algorithms to extract the outer contour lines of structural components, the boundaries and shapes of the components can be accurately identified, providing accurate basic data for subsequent structural analysis, modeling and visualization, thereby improving the accuracy and efficiency of overall recognition.

[0074] In a possible implementation, the edge detection method is specifically: Canny algorithm, Sobel algorithm or deep learning driven HED algorithm.

[0075] In an embodiment of the present invention, the edge detection method preferably uses Canny, Sobel or deep learning driven HED (Holistically-Nested Edge Detection) algorithm to detect the mask boundary and extract the coordinates of the pixel points on the boundary contour. The adjacent coordinates are connected to finally generate a line contour map of the structural component, and pseudo-color rendering can be performed to achieve visual output.

[0076] The beneficial effects brought about by the technical solution provided by the embodiment of the present invention include at least:

[0077] In an embodiment of the present invention, a large visual segmentation model with support point prompts is used for coarse segmentation, candidate area screening is automatically completed, reliance on manual labeling is reduced, the level of automation is improved, and rapid positioning of the target area without training is achieved. By introducing super-resolution reconstruction, the image resolution, edge clarity and texture details are significantly improved, so that the subsequent segmentation module can still maintain high recognition accuracy when processing blurred, compressed or long-distance images, effectively breaking through the bottleneck of low-quality images, and adopting a sliding window mechanism combined with an adaptive fine segmentation scheme of local prompt points to achieve accurate recognition at the sub-image level, especially excellent performance in boundary areas. The present invention combines super-resolution image enhancement with a multi-stage refined segmentation strategy, which significantly improves the recognition accuracy and edge clarity of the contours of structural components under complex backgrounds and low-quality image conditions.

[0078] Reference Manual Figure 3 , which shows a structural schematic diagram of a system for rapid identification of structural component line types based on multi-order segmentation provided by an embodiment of the present invention.

[0079] The embodiment of the present invention provides a structural component line type rapid identification system 20 based on multi-level segmentation, comprising: a processor 201 and a memory 202;

[0080] The memory 202 stores a program or instruction that can be run on the processor 201. When the program or instruction is executed by the processor 201, the steps of the above-mentioned method for rapid identification of structural component line types based on multi-order segmentation are implemented, and the same technical effect can be achieved. To avoid repetition, the present invention will not be repeated.

[0081] It should be understood that the processor 201 in the embodiment of the present invention may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0082] It should also be understood that the memory 202 in the embodiments of the present invention may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. The non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0083] The above embodiments can be implemented in whole or in part via software, hardware (e.g., circuits), firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When loaded or executed on a computer, the processes or functions described in accordance with the embodiments of the present invention are fully or partially performed. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired means (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server or data center that contains a collection of one or more available media. The available medium can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0084] It should be understood that in various embodiments of the present invention, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0085] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0086] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described equipment, devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0087] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interface, indirect coupling or communication connection of the device or unit, which can be electrical, mechanical or other forms.

[0088] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0089] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0090] If the functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage media include various media capable of storing program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0091] An embodiment of the present invention provides a readable storage medium including: a program or instruction is stored on the readable storage medium, and when the program or instruction is executed by a processor, the steps of the above-mentioned method for rapid identification of structural component line types based on multi-order segmentation are implemented, and the same technical effect can be achieved. To avoid repetition, the present invention will not be described in detail.

[0092] Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the embodiments of the present invention, and are not intended to limit them. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they may still modify the technical solutions described in the aforementioned embodiments, or replace some of the technical features therein with equivalents; and such modifications or replacements do not deviate from the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention. Any changes or replacements that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be covered by the scope of protection of the present invention.

Claims

1. A method for rapid identification of structural component line shapes based on multi-level segmentation, characterized in that: include: S1: Obtain the original image of the structural component; S2: using a first visual segmentation model to roughly segment the original image and generate an initial binary mask of the structural component; S3: Based on the foreground cue points in the original image, automatically screening out a target mask area containing the foreground cue points in the initial binary mask by using a connected component analysis method; S4: Calculating the coordinate information of the circumscribed rectangular bounding box of the target mask area by contour detection; S5: extracting a corresponding target area sub-image from the original image according to the coordinates of the rectangular bounding box; S6: using a super-resolution reconstruction model to enhance the sub-image of the target area; S7: dividing the enhanced target region sub-image into sub-images to determine a plurality of sub-images; S8: performing fine segmentation on each of the sub-images through a second visual segmentation model to determine a high-precision mask; S9: Mapping the high-precision mask to the original image through coordinate mapping; S10: extracting the outer contour of the structural component by combining an edge detection algorithm to complete the line type recognition of the structural component.

2. The method for rapid identification of structural component line shapes based on multi-level segmentation according to claim 1 is characterized in that: The first visual segmentation model is specifically a general visual segmentation model that supports point prompt interaction.

3. The method for rapid identification of structural component line shapes based on multi-level segmentation according to claim 1 is characterized in that: The S3 is specifically: Based on the determination principle that the coordinates of the foreground cue point are located inside the target mask area, the target mask area containing the foreground cue point is automatically screened out from the initial binary mask through the connected domain analysis method.

4. The method for rapid identification of structural component line shapes based on multi-level segmentation according to claim 1, characterized in that: The super-resolution reconstruction model is specifically a reconstruction model built based on a deep convolutional neural network.

5. The method for rapid identification of structural component line shape based on multi-level segmentation according to claim 1 is characterized in that: The S7 is specifically: The enhanced target region sub-image is divided into non-overlapping or optionally overlapping sub-images through a sliding window mechanism to determine a plurality of sub-images.

6. The method for rapid identification of structural component line shapes based on multi-level segmentation according to claim 1, characterized in that: The second visual segmentation model is specifically a visual segmentation model guided by prompt points and rectangular boxes.

7. The method for rapid identification of structural component line shape based on multi-level segmentation according to claim 1 is characterized in that: The S9 specifically includes: S901: Mapping the high-precision mask to the local coordinate system of the target area sub-image through coordinate mapping; S902: Mapping the high-precision mask to the original image according to the coordinate position of the target area sub-image in the original image, and extracting the outer contour of the structural component in combination with an edge detection algorithm.

8. The method for rapid identification of structural component line shapes based on multi-level segmentation according to claim 1, characterized in that: The edge detection method is specifically: Canny algorithm, Sobel algorithm or deep learning driven HED algorithm.

9. A fast identification system for structural component line shape based on multi-level segmentation, characterized in that: include: processor and memory; The memory stores a program or instruction that can be run on the processor, and when the program or instruction is executed by the processor, the steps of the method for rapid identification of structural component line types based on multi-order segmentation as described in any one of claims 1 to 8 are implemented.

10. A readable storage medium, characterized in that: The readable storage medium stores a program or instruction, and when the program or instruction is executed by the processor, the steps of the method for rapid identification of structural component line types based on multi-level segmentation as described in any one of claims 1 to 8 are implemented.

Images