Image recognition-based underground pipe network construction drawing generation and verification method and system

Abstract

This invention discloses a method and system for generating and verifying underground pipeline network construction drawings based on image recognition. This invention relates to the field of construction drawing verification and analysis technology, solving the technical problem of insufficient and inefficient detection of pipeline network element integrity and spatial conflicts during the verification process. By comparing the extracted pipeline network element data with the original design data element by element, verifying from dimensions such as element type, quantity, and attributes, this invention can quickly and accurately determine whether the construction drawings are complete and promptly identify missing or erroneous elements. Utilizing the minimum bounding box and three-dimensional projection overlap judgment algorithm, it can efficiently detect spatial conflicts between pipeline network elements, improving the efficiency and accuracy of conflict detection. By classifying overlapping elements according to the elastic modulus of the element materials, and conducting targeted analysis on both rigid and non-rigid overlapping elements, it can not only determine whether design conflicts exist but also provide a more scientific basis for design optimization.

Description

Technical Field

[0001] This invention relates to the field of construction drawing verification and analysis technology, specifically to a method and system for generating and verifying underground pipeline network construction drawings based on image recognition. Background Technology

[0002] In urban infrastructure construction, underground pipeline systems are complex and extensive, encompassing various types of pipelines such as water supply and drainage, gas, electricity, and communications.

[0003] Traditional underground pipeline construction drawing design and verification mainly rely on manual drawing and review, which is inefficient and prone to errors. With the development of computer technology, some designs use CAD software for two-dimensional drawing, which improves drawing efficiency. However, in the drawing verification stage, manual checking against design specifications and original data is still required, making it difficult to discover complex spatial conflict issues.

[0004] In recent years, although image recognition and 3D modeling technologies have begun to be applied in the engineering field, existing technologies still have limitations in the generation and verification of underground pipeline network construction drawings. For example, image recognition accuracy is insufficient, making it difficult to accurately extract pipeline network element features; the 3D modeling process is complex, and there is a lack of effective means to automatically generate construction drawings; during the verification process, the detection of pipeline network element integrity and spatial conflicts is not comprehensive or efficient enough, failing to meet the high-precision and high-efficiency requirements of modern urban underground pipeline network construction. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides a method and system for generating and verifying underground pipeline network construction drawings based on image recognition, which solves the problem that the detection of pipeline network element integrity and spatial conflicts is not comprehensive and efficient during the verification process.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a method for generating and verifying underground pipeline network construction drawings based on image recognition, which specifically includes the following steps:

[0007] Image data of the underground pipeline area is collected and preprocessed to obtain preprocessed images. At the same time, image features are extracted and a three-dimensional model is built to generate construction drawings.

[0008] The construction drawings are verified and analyzed. The pipeline network elements in the construction drawings are compared with the original data. If the two are the same, a conflict verification analysis signal is generated. If the two are different, the different elements are obtained and missing information is generated.

[0009] The conflict check analysis signal is processed, each pipeline element is labeled and its corresponding adjacent elements are determined in order. Then, the minimum bounding box algorithm is used to determine the overlap between the pipeline element and its adjacent elements, and normal design information or overlap analysis signal is generated.

[0010] The acquired overlap analysis signal is analyzed to identify adjacent elements that overlap and classify them into hard overlap elements and non-hard overlap elements according to their design properties. The hard overlap elements are analyzed to calculate their corresponding overlap distance and compare it with the preset distance value to generate conflict design information or influence analysis signal, and overlap level information is generated based on the overlap distance.

[0011] Analyze non-hard overlapping elements to determine their impact on pipeline network elements and generate normal or conflict design information.

[0012] As a further aspect of the present invention, the specific method for generating construction drawings is as follows:

[0013] Using drones equipped with high-definition cameras to collect image data of underground pipe network areas, and performing noise reduction, grayscale conversion, and binarization preprocessing operations to obtain preprocessed images, image recognition algorithms are used to extract image features, and combined with geographic information system technology, a three-dimensional model of the underground pipe network is constructed, and construction drawings are automatically generated according to the drawing specifications and requirements of construction drawings.

[0014] As a further aspect of the present invention, the specific method for verifying and analyzing the construction drawings is as follows:

[0015] Obtain all pipeline elements in the construction drawings and compare them with the original data. If the pipeline elements are the same as the original data, it means that the construction drawings are complete and a conflict check analysis signal is generated. Conversely, if the pipeline elements are different from the original data, it means that the construction drawings are incomplete and an incomplete analysis signal is generated.

[0016] For incomplete signal analysis, the corresponding incomplete elements are obtained based on the original data, and omission information is generated using these elements as a standard.

[0017] As a further aspect of the present invention, the specific method for processing the collision check analysis signal is as follows:

[0018] Retrieve all network elements and label them as i, where i = 1, 2, ..., j, and j represents the type of network element. Then, according to the labeling order of network element i, retrieve the adjacent elements whose distance is less than a threshold and label them as i. a And a = 1, 2, ..., b, where b represents the type of adjacent elements;

[0019] Next, taking network element i as the target element, and establishing its corresponding minimum bounding box, denoted as the target bounding box, a three-dimensional coordinate system is established with the center point of the bounding box as the origin. The maximum vertex coordinates max(x) of the target bounding box are then obtained. i y i , z i ) and minimum vertex coordinates min(x) i yi , z i Similarly, construct the smallest bounding box corresponding to adjacent elements and denote it as the bounding box to be analyzed. At the same time, obtain the maximum vertex coordinates and the minimum vertex coordinates min(x) of the bounding box to be analyzed. ia y ia , z ia ), and perform analysis based on the established minimum rectangular bounding box.

[0020] As a further aspect of the present invention, the specific method for performing the analysis based on the established minimum rectangular bounding box is as follows:

[0021] According to the adjacent element index i a The relationship between the projections on the x, y, and z axes and the projection of the target bounding box is analyzed sequentially, and the specific relationships are as follows:

[0022] x-axis projection overlap: min i x≤max ia .x and max i x≥min ia .x;

[0023] y-axis projection overlap: min i .y≤ma ia .y and max i .y≥min ia .y;

[0024] z-axis projection overlap: min i .z≤ma ia .z and max i .z≥min ia .z;

[0025] If any set of projections on the x, y, and z axes does not overlap, it indicates that there is no overlap between them, and normal design information is generated. Conversely, if the projections on the x, y, and z axes all overlap, it indicates that there is an overlap between them, and an overlap analysis signal is generated.

[0026] As a further aspect of the present invention, the specific method for analyzing the acquired overlap analysis signal is as follows:

[0027] Obtain adjacent elements that overlap with the target element and denote them as elements to be analyzed. At the same time, analyze the design properties of the elements to be analyzed and classify them into hard overlapping elements and non-hard overlapping elements according to the design properties. Specifically, elements with an elastic modulus E greater than 5 GPa are classified as hard elements, and elements with an elastic modulus E less than 5 GPa are classified as non-hard elements. Analyze the hard overlapping elements and non-hard overlapping elements obtained by classification separately.

[0028] As a further aspect of the present invention, the specific method for separately analyzing the hard overlapping elements and non-hard overlapping elements obtained from the classification is as follows:

[0029] The obtained hard overlapping elements are analyzed. The maximum straight-line distance between the overlapping parts of the two elements is taken and compared with the preset distance value. If the overlapping distance is greater than the preset distance value, conflict design information is generated. If the overlapping distance is less than the preset distance, an impact analysis signal is generated.

[0030] Next, the generated impact analysis signal is analyzed, the overlap level is determined based on the obtained overlap distance, and overlap level information is generated.

[0031] The obtained non-hard overlapping elements are analyzed to determine whether their design affects the target element. If it does not affect the target element, normal design information is generated; otherwise, if it does affect the target element, conflict design information is generated.

[0032] The underground pipeline network construction drawing generation and verification system based on image recognition includes: an image data acquisition module, a data verification and analysis module, a pipeline network construction conflict analysis module, an adaptive processing module, and a verification information output module.

[0033] The image data acquisition module is used to acquire image data of the underground pipe network area, preprocess the data to obtain preprocessed images, extract image features, build a three-dimensional model, generate construction drawings, and transmit them to the data verification and analysis module.

[0034] The data verification and analysis module is used to verify and analyze the acquired construction drawings, compare the pipeline network elements in the construction drawings with the original data. If the two are the same, a conflict verification and analysis signal is generated and transmitted to the pipeline construction conflict analysis module. If the two are different, the different elements are acquired, omission information is generated and transmitted to the verification information output module.

[0035] The pipeline construction conflict analysis module is used to process the acquired conflict verification analysis signal, label each pipeline element and determine the corresponding adjacent elements in order, then use the minimum bounding box algorithm to determine the overlap between the pipeline element and its adjacent elements, generate normal design information or overlap analysis signal, and transmit the overlap analysis signal to the adaptive processing module.

[0036] The adaptive processing module is used to analyze the acquired overlap analysis signal, identify adjacent elements that overlap, and classify them into hard overlap elements and non-hard overlap elements according to their design properties. The hard overlap elements are analyzed, their corresponding overlap distances are calculated and compared with preset distance values, conflict design information or influence analysis signals are generated, and overlap level information is generated based on the overlap distance and transmitted to the verification information output module.

[0037] Analyze non-hard overlapping elements to determine their impact on pipeline elements, generate normal design information or conflict design information, and transmit them to the verification information output module.

[0038] The verification information output module is used to display the acquired omission information, overlap level information, normal design information, and conflict design information to the corresponding management personnel.

[0039] This invention provides a method and system for generating and verifying underground pipeline network construction drawings based on image recognition. Compared with existing technologies, it has the following advantages:

[0040] This invention collects image data using drones and mobile devices, and employs noise reduction, grayscale conversion, and binarization preprocessing techniques, combined with the Canny algorithm and OCR technology, to more accurately extract pipeline network image features and text annotation information. This provides a reliable data foundation for subsequent modeling and design. Based on the extracted image feature information, a three-dimensional model is constructed using GIS technology, and plan views, elevation views, and section views are automatically generated according to construction drawing specifications, improving the efficiency of construction drawing generation and reducing errors in manual drawing.

[0041] This invention compares the extracted pipeline element data with the original design data element by element, verifying them from dimensions such as element type, quantity, and attributes. This allows for a quick and accurate determination of the completeness of construction drawings and timely detection of missing or erroneous elements. Utilizing the minimum bounding box and 3D projection overlap judgment algorithm, it can efficiently detect spatial conflicts between pipeline elements, improving the efficiency and accuracy of conflict detection. By classifying overlapping elements according to the elastic modulus of the element materials, it conducts targeted analysis on both rigid and non-rigid overlapping elements. This not only determines whether design conflicts exist but also identifies the conflict level and degree of impact, providing a more scientific basis for design optimization. Attached Figure Description

[0042] Figure 1 This is a diagram illustrating the steps and methods of the present invention;

[0043] Figure 2 This is a system block diagram of the present invention. Detailed Implementation

[0044] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0045] Example 1: Please refer to Figure 1This application provides a method for generating and verifying underground pipeline network construction drawings based on image recognition. The method specifically includes the following steps:

[0046] Step 1: Utilize drones equipped with high-definition cameras or handheld mobile devices to collect image data of the underground pipeline network area. Simultaneously, pipeline image information can be obtained from existing electronic documents such as CAD drawings. Preprocessing operations are performed on the acquired image data to obtain preprocessed images. These preprocessing operations include noise reduction, grayscale conversion, and binarization to improve image quality and facilitate subsequent feature extraction. For example, noise reduction removes random noise from the image, grayscale conversion converts the color image to a grayscale image, and binarization further converts the grayscale image into a black and white image, highlighting key information such as pipeline lines. Simultaneously, image recognition algorithms are used to extract image features from the preprocessed image. Edge detection algorithms (such as the Canny algorithm) extract geometric features such as pipeline lines and nodes, identifying information such as pipeline direction, diameter, and connection method. Meanwhile, optical character recognition (OCR) technology is used to extract textual annotation information from images, such as pipe diameter, material, elevation, and slope. Based on the extracted image feature information and combined with geographic information system (GIS) technology, a three-dimensional model of the underground pipe network is constructed. Professional three-dimensional modeling software or specific three-dimensional modeling algorithms can be used to convert two-dimensional pipe network information into a three-dimensional model. Based on the three-dimensional model, construction drawings, including plan views, elevation views, and section views, are automatically generated in accordance with the drawing specifications and requirements of construction drawings.

[0047] Step 2: Verify and analyze the obtained construction drawings. Use computer vision algorithms (such as YOLO and Faster R-CNN) to extract features from the construction drawings, identify the location, shape, and labeling information of pipeline network elements such as pipelines, valves, and inspection wells, and extract text labels in the drawings through optical character recognition technology, including parameters such as pipe diameter, material, and coordinates. Convert the identified pipeline network elements into structured data, such as storing the type, location, and attributes of each element in JSON format.

[0048] The extracted pipeline element data is compared element by element with the original design data (such as design database, survey report), and the verification is performed according to the following verification rules:

[0049] Element type verification: Check whether the drawings contain all the pipe network element types required by the design.

[0050] Element quantity verification: Compare the quantity of the same type of element in the drawing with that in the original data to see if they are consistent.

[0051] Element attribute validation: Check whether the attribute parameters (such as pipe diameter, material) of each element match the original data;

[0052] If all pipeline elements are exactly the same as the original data, the construction drawings are determined to be complete, a conflict check analysis signal is generated, and the next conflict detection process is initiated. If any inconsistency exists (missing elements, attribute errors, etc.), the construction drawings are determined to be incomplete, and an incomplete analysis signal is generated.

[0053] By comparing and analyzing, missing or incorrect pipeline elements in the construction drawings are identified. Based on the original data, a detailed omission information report is generated, including the type, location, and attribute requirements of the missing elements. The missing or incorrect locations are marked on the drawings and highlighted in red to facilitate quick location and modification by designers.

[0054] Step 3: Obtain the generated conflict check analysis signal and analyze it. Obtain all pipeline elements and label them as i, where i = 1, 2, ..., j, and j represents the type of pipeline element. Then, obtain the adjacent elements corresponding to pipeline element i in the order of their labels. Here, adjacent elements are defined as pipeline elements whose straight-line distance is less than a preset value. Simultaneously, label the obtained adjacent elements as i. a And a = 1, 2, ..., b, where b represents the type of adjacent elements;

[0055] Next, taking network element i as the target element, we construct its corresponding minimum bounding box, denoted as the target bounding box. Here, the bounding box represents the entire target element. Simultaneously, we establish a three-dimensional coordinate axis with the center point of the target bounding box as the origin, and obtain the maximum and minimum vertices of the target bounding box, along with their corresponding three-dimensional coordinates, denoted as max(x). i y i , z i ) and min(x i y i , z i Similarly, construct the smallest bounding box corresponding to adjacent elements and denote it as the bounding box to be analyzed. At the same time, obtain the maximum and minimum vertex coordinates max(x) of the bounding box to be analyzed. ia y ia , z ia ) and min(x ia y ia , z ia );

[0056] According to the adjacent element index i a The relationship between the projections on the x, y, and z axes and the target bounding box projection is analyzed sequentially, and the overlap between the two is determined based on the size relationship of the projections. The specific determination method is as follows:

[0057] x-axis projection overlap: min i x≤max ia.x and max i x≥min ia .x;

[0058] y-axis projection overlap: min i .y≤ma ia .y and max i .y≥min ia .y;

[0059] z-axis projection overlap: min i .z≤ma ia .z and max i .z≥min ia .z;

[0060] If any set of projections on the x, y, and z axes does not overlap, it indicates that there is no overlap between them, and normal design information is generated. Conversely, if the projections on the x, y, and z axes all overlap, it indicates that there is an overlap between them, and an overlap analysis signal is generated.

[0061] After receiving the collision check analysis signal, all pipeline network elements (pipelines, valves, manholes, etc.) are extracted from the construction drawings using image recognition or structured data parsing technology. They are then classified into j categories according to type and sequentially labeled i=1, 2, ..., j (for example, i=1 represents category 1 pipelines, i=2 represents valves). A distance threshold D is set (e.g., D=2m for municipal pipelines by default). The straight-line distance between elements is calculated using the Euclidean distance formula, and adjacent elements with a distance less than D from element i are selected and labeled ia (a=1, 2, ..., b, where b is the number of adjacent elements).

[0062] Generate a minimum axial bounding box (AABB) for element i, denoted as the target bounding box, whose minimum vertex coordinates are min. i (x i y i , z i The maximum vertex coordinate is max. i (x i y i , z i ), and with the center point O of the bounding box i Establish a local three-dimensional coordinate system with the origin.

[0063] For each adjacent element i a Repeat the above steps to generate the bounding box to be analyzed, and obtain its minimum / maximum vertex coordinates min(x). ia y ia , z ia ) and max(x ia y ia , z ia).

[0064] Single-axis projection judgment: for each adjacent element i a Check whether its projections on the x, y, and z axes overlap with the target bounding box projection:

[0065] x-axis overlap condition: min i x≤max ia .x and max i x≥min ia .x;

[0066] y-axis overlap condition: min i .y≤max ia .y and max i .y≥min ia .y;

[0067] z-axis overlap condition: min i .z≤max ia .z and max i .z≥min ia .z;

[0068] If all three coordinate axis projections satisfy the overlap condition, then it is determined that there is a spatial conflict between element i and ia, and an overlap analysis signal is generated.

[0069] If the projections of any coordinate axis do not overlap, then there is no conflict, and normal design information is generated.

[0070] Suppose an underground pipeline project includes the following elements:

[0071] Sewage pipeline (element i=1): pipe diameter DN300, burial depth 2m, length 10m, coordinates (100, 100, -2);

[0072] Gas pipeline (adjacent element i1): pipe diameter DN150, burial depth 1.5m, horizontal distance from sewage pipeline 1.8m (less than the preset value D=2m), coordinates (101, 100, -1.5).

[0073] Sewage pipeline (target element i=1):

[0074] Target bounding box: minimum vertex min i (95, 98.5, -2.15), maximum vertex max i (105, 101.5, -1.85);

[0075] The center point coordinates are O1(100, 100, -2).

[0076] Gas pipeline (adjacent element i1):

[0077] The bounding box to be analyzed has the following values: minimum vertex min i1 (100.25, 99.25, -1.65) and maximum vertex max i1 (101.75, 100.75, -1.35).

[0078] x-axis projection:

[0079] min i x = 95 ≤ max1.x = 101.75 and max i x = 105 ≥ mini1.x = 100.25, satisfying the overlap condition;

[0080] y-axis projection:

[0081] min i .y=98.5≤maxi1.y=100.75 and max i .y=101.5≥mini1.y=99.25, satisfying the overlap condition;

[0082] z-axis projection:

[0083] min i .z=-2.15≤maxi1.z=-1.35 and max i z = -1.85 ≥ mini1.z = -1.65, satisfying the overlap condition.

[0084] Since the x, y, and z axis projections all overlap, the system determines that there is a spatial conflict between the sewage pipeline and the gas pipeline, and generates an overlap analysis signal.

[0085] Step 4: Process the generated overlap analysis signal to obtain adjacent elements that overlap with the target element, and record them as elements to be analyzed. At the same time, analyze the design properties of the elements to be analyzed, where the design properties represent the hardness or softness of the corresponding element material. Specifically, they are distinguished by the elastic modulus E. Elements with an elastic modulus E greater than 5 GPa are classified as hard elements, and elements with an elastic modulus E less than 5 GPa are classified as non-hard elements. Based on the design properties, hard overlapping elements and non-hard overlapping elements are obtained. For example, valves and inspection wells are hard overlapping elements, while pipelines are non-hard overlapping elements. Then, the hard overlapping elements and non-hard overlapping elements obtained by classification are analyzed separately.

[0086] The obtained hard overlapping elements are analyzed, and the overlap distance between the hard overlapping elements and the target elements is calculated. The overlap distance is represented as the maximum straight-line distance between the two overlapping parts. The obtained overlap distance is compared with the corresponding preset distance value. The specific value of the preset distance value is set according to the actual situation of the corresponding hard overlapping elements and the target elements. If the overlap distance is greater than the preset distance value, it indicates that there is a design conflict in the current hard overlapping elements, and conflict design information is generated. If the overlap distance is less than the preset distance, it indicates that the current hard overlapping elements can be designed normally, and an impact analysis signal is generated.

[0087] Next, the generated impact analysis signal is analyzed, and the overlap level is determined based on the obtained overlap distance. The overlap level is divided into three levels: Level 1, Level 2, and Level 3. The overlap distance gradually increases from Level 1 to Level 3, and overlap level information is generated simultaneously.

[0088] The obtained non-hard overlapping elements are analyzed to determine whether their design affects the target element. If it does not affect the target element, normal design information is generated; otherwise, if it does affect the target element, conflict design information is generated.

[0089] Example 2: Please refer to Figure 2 This application provides an image recognition-based system for generating and verifying underground pipeline network construction drawings. The system includes: an image data acquisition module, a data verification and analysis module, a pipeline network construction conflict analysis module, an adaptive processing module, and a verification information output module. Furthermore, it integrates... Figure 2 It can be seen that the above functional modules are connected electrically in one direction.

[0090] The image data acquisition module is used to acquire image data of the underground pipe network area, perform preprocessing to obtain preprocessed images, extract image features and build a three-dimensional model, generate construction drawings, and transmit them to the data verification and analysis module. The specific processing method is the same as the processing process in step one of embodiment one.

[0091] The data verification and analysis module is used to verify and analyze the acquired construction drawings, compare the pipeline network elements in the construction drawings with the original data, and if the two are the same, generate a conflict verification and analysis signal and transmit it to the pipeline construction conflict analysis module. If the two are different, acquire the different elements, generate omission information and transmit it to the verification information output module. The specific processing method is the same as the processing process in step two of embodiment one.

[0092] The pipeline construction conflict analysis module is used to process the acquired conflict verification analysis signal, label each pipeline element and determine the corresponding adjacent elements in order, then use the minimum bounding box algorithm to determine the overlap between the pipeline element and its adjacent elements, generate normal design information or overlap analysis signal, and transmit the overlap analysis signal to the adaptive processing module. The specific processing method is the same as the processing process in step three of embodiment one.

[0093] The adaptive processing module is used to analyze the acquired overlap analysis signal, identify adjacent elements that overlap, and classify them into hard overlap elements and non-hard overlap elements according to their design properties. The hard overlap elements are analyzed, their corresponding overlap distances are calculated and compared with preset distance values, conflict design information or influence analysis signals are generated, and overlap level information is generated based on the overlap distance and transmitted to the verification information output module.

[0094] Non-hard overlapping elements are analyzed to determine their impact on pipeline elements, generating normal design information or conflict design information, and transmitting it to the verification information output module. The specific processing method is the same as the processing process in step four of embodiment one.

[0095] The verification information output module is used to display the acquired omission information, overlap level information, normal design information, and conflict design information to the corresponding management personnel.

[0096] The data in the above formulas are all calculated using numerical values, without substituting the units of the parameters. In addition, the contents not described in detail in this specification are all prior art known to those skilled in the art.

[0097] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. A method for generating and verifying underground pipeline network construction drawings based on image recognition, characterized in that, The method specifically includes the following steps: Image data of the underground pipeline area is collected and preprocessed to obtain preprocessed images. At the same time, image features are extracted and a three-dimensional model is built to generate construction drawings. The construction drawings are verified and analyzed. The pipeline network elements in the construction drawings are compared with the original data. If the two are the same, a conflict verification analysis signal is generated. If the two are different, the different elements are obtained and missing information is generated. The conflict check analysis signal is processed, each pipeline element is labeled and its corresponding adjacent elements are determined in sequence. Then, the minimum bounding box algorithm is used to determine the overlap between the pipeline element and its adjacent elements, and normal design information or overlap analysis signal is generated. Retrieve all network elements and label them as i, where i = 1, 2, ..., j, and j represents the type of network element. Then, according to the labeling order of network element i, retrieve the adjacent elements whose distance is less than a threshold and label them as i. a And a = 1, 2, ..., b, where b represents the type of adjacent elements; Next, taking network element i as the target element, and establishing its corresponding minimum bounding box, denoted as the target bounding box, a three-dimensional coordinate system is established with the center point of the bounding box as the origin. The maximum vertex coordinates max(x) of the target bounding box are then obtained. i y i , z i ) and minimum vertex coordinates min(x) i y i , z i Similarly, construct the smallest bounding box corresponding to adjacent elements and denote it as the bounding box to be analyzed. At the same time, obtain the maximum vertex coordinates and the minimum vertex coordinates min(x) of the bounding box to be analyzed. ia y ia , z ia ), and perform analysis based on the established minimum rectangular bounding box; The acquired overlap analysis signal is analyzed to identify adjacent elements that overlap and classify them into hard overlap elements and non-hard overlap elements according to their design properties. The hard overlap elements are analyzed to calculate their corresponding overlap distance and compare it with the preset distance value to generate conflict design information or influence analysis signal, and overlap level information is generated based on the overlap distance. Analyze non-hard overlapping elements to determine their impact on pipeline network elements and generate normal or conflict design information.

2. The method for generating and verifying underground pipeline network construction drawings based on image recognition according to claim 1, characterized in that, The specific method for generating construction drawings is as follows: Using drones equipped with high-definition cameras to collect image data of underground pipe network areas, and performing noise reduction, grayscale conversion, and binarization preprocessing operations to obtain preprocessed images, image recognition algorithms are used to extract image features, and combined with geographic information system technology, a three-dimensional model of the underground pipe network is constructed, and construction drawings are automatically generated according to the drawing specifications and requirements of construction drawings.

3. The method for generating and verifying underground pipeline network construction drawings based on image recognition according to claim 1, characterized in that, The specific method for verifying and analyzing the construction drawings is as follows: Obtain all pipeline elements in the construction drawings and compare them with the original data. If the pipeline elements are the same as the original data, it means that the construction drawings are complete and a conflict check analysis signal is generated. Conversely, if the pipeline elements are different from the original data, it means that the construction drawings are incomplete and an incomplete analysis signal is generated. For incomplete signal analysis, the corresponding incomplete elements are obtained based on the original data, and omission information is generated using these elements as a standard.

4. The method for generating and verifying underground pipeline network construction drawings based on image recognition according to claim 1, characterized in that, The specific method for performing the analysis based on the established minimum rectangular bounding box is as follows: According to the adjacent element index i a The relationship between the projections on the x, y, and z axes and the projection of the target bounding box is analyzed sequentially, and the specific relationships are as follows: x-axis projection overlap: min i x≤max ia .x and max i x≥min ia .x; y-axis projection overlap: min i .y≤max ia .y and max i .y≥min ia .y; z-axis projection overlap: min i .z≤max ia .z and max i .z≥min ia .z; If any set of projections on the x, y, and z axes does not overlap, it indicates that there is no overlap between them, and normal design information is generated. Conversely, if the projections on the x, y, and z axes all overlap, it indicates that there is an overlap between them, and an overlap analysis signal is generated.

5. The method for generating and verifying underground pipeline network construction drawings based on image recognition according to claim 4, characterized in that, The specific method for analyzing the acquired overlap analysis signal is as follows: Obtain adjacent elements that overlap with the target element and denote them as elements to be analyzed. At the same time, analyze the design properties of the elements to be analyzed and classify them into hard overlapping elements and non-hard overlapping elements according to the design properties. Specifically, elements with an elastic modulus E greater than 5 GPa are classified as hard elements, and elements with an elastic modulus E less than 5 GPa are classified as non-hard elements. Analyze the hard overlapping elements and non-hard overlapping elements obtained by classification separately.

6. The method for generating and verifying underground pipeline network construction drawings based on image recognition according to claim 5, characterized in that, The specific method for analyzing the hard overlapping elements and non-hard overlapping elements obtained from the classification separately is as follows: The obtained hard overlapping elements are analyzed. The maximum straight-line distance between the overlapping parts of the two elements is taken and compared with the preset distance value. If the overlapping distance is greater than the preset distance value, conflict design information is generated. If the overlapping distance is less than the preset distance, an impact analysis signal is generated. Next, the generated impact analysis signal is analyzed, the overlap level is determined based on the obtained overlap distance, and overlap level information is generated simultaneously. The obtained non-hard overlapping elements are analyzed to determine whether their design affects the target element. If it does not affect the target element, normal design information is generated; otherwise, if it does affect the target element, conflict design information is generated.

7. An image recognition-based system for generating and verifying underground pipeline network construction drawings, used to execute the method for generating and verifying underground pipeline network construction drawings according to any one of claims 1-6, characterized in that, include: Image data acquisition module, data verification and analysis module, pipeline construction conflict analysis module, adaptive processing module, and verification information output module; The image data acquisition module is used to acquire image data of the underground pipe network area, preprocess the data to obtain preprocessed images, extract image features, build a three-dimensional model, generate construction drawings, and transmit them to the data verification and analysis module. The data verification and analysis module is used to verify and analyze the acquired construction drawings, compare the pipeline network elements in the construction drawings with the original data. If the two are the same, a conflict verification and analysis signal is generated and transmitted to the pipeline construction conflict analysis module. If the two are different, the different elements are acquired, omission information is generated and transmitted to the verification information output module. The pipeline construction conflict analysis module processes the acquired conflict verification analysis signals, labels each pipeline element and determines its corresponding adjacent elements in sequence, then uses the minimum bounding box algorithm to determine the overlap between the pipeline element and its adjacent elements, generating normal design information or overlap analysis signals. The specific processing method is as follows: Retrieve all network elements and label them as i, where i = 1, 2, ..., j, and j represents the type of network element. Then, according to the labeling order of network element i, retrieve the adjacent elements whose distance is less than a threshold and label them as i. a And a = 1, 2, ..., b, where b represents the type of adjacent elements; Next, taking network element i as the target element, and establishing its corresponding minimum bounding box, denoted as the target bounding box, a three-dimensional coordinate system is established with the center point of the bounding box as the origin. The maximum vertex coordinates max(x) of the target bounding box are then obtained. i y i , z i ) and minimum vertex coordinates min(x) i y i , z i Similarly, construct the smallest bounding box corresponding to adjacent elements and denote it as the bounding box to be analyzed. At the same time, obtain the maximum vertex coordinates and the minimum vertex coordinates min(x) of the bounding box to be analyzed. ia y ia , z ia ), and perform analysis based on the established minimum rectangular bounding box; The overlap analysis signal is then transmitted to the adaptive processing module. The adaptive processing module is used to analyze the acquired overlap analysis signal, identify adjacent elements that overlap, and classify them into hard overlap elements and non-hard overlap elements according to their design properties. The hard overlap elements are analyzed, their corresponding overlap distances are calculated and compared with preset distance values, conflict design information or influence analysis signals are generated, and overlap level information is generated based on the overlap distance and transmitted to the verification information output module. Analyze non-hard overlapping elements to determine their impact on pipeline elements, generate normal design information or conflict design information, and transmit them to the verification information output module. The verification information output module is used to display the acquired omission information, overlap level information, normal design information, and conflict design information to the corresponding management personnel.

Images