Wellbore port recognition and pipe network map generation method, device and computer readable storage medium

Abstract

Embodiments of the present application disclose a well wall pipe orifice recognition and pipe network diagram generation method and device and a computer readable storage medium. The method comprises: acquiring a to-be-processed equal cylindrical projection image, the to-be-processed equal cylindrical projection image being obtained by image acquisition on a manhole; detecting a pipe orifice on the to-be-processed equal cylindrical projection image to obtain a pixel coordinate of the pipe orifice in an equal cylindrical projection image coordinate system; determining a pipe orifice azimuth angle according to an X pixel coordinate of the pipe orifice in the cylindrical projection image coordinate system and a camera orientation azimuth angle; matching a connection relationship for pipe orifices of adjacent manholes according to the pipe orifice azimuth angle; and drawing a pipe network diagram between the manholes according to the connection relationship. In the foregoing manner, automatic recognition and parameter calculation of the pipe orifice can be realized according to the to-be-processed equal cylindrical projection image, manual data processing time is greatly reduced, accuracy is high, standardized operation can be realized, and the pipe network diagram can be generated in batches.

Description

Technical Field

[0001] This invention relates to the field of pipe opening spatial positioning technology, and in particular to a method, device and computer-readable storage medium for well wall pipe opening identification and pipeline network diagram generation. Background Technology

[0002] Underground pipe networks are an important component of urban infrastructure. As a key node in the pipe network, the location, direction, and size of the pipe openings in manholes are of great significance for the management, maintenance, and planning of the pipe network.

[0003] Currently, the main methods for measuring manhole openings are: manual downhole measurement, wellhead observation and recording, and ordinary camera shooting. These methods mostly rely on manual labor and cannot achieve automatic extraction of opening parameters and image generation. Summary of the Invention

[0004] The purpose of this invention is to propose a method, device, and computer-readable storage medium for wellhead identification and pipeline network map generation, aiming to solve the problems of low accuracy and low efficiency in wellhead positioning and mapping in the prior art.

[0005] To address the aforementioned technical problems, the first aspect of this application provides a method for identifying wellhead openings and generating pipeline network diagrams. The method includes: acquiring a cylindrical projection image to be processed, wherein the cylindrical projection image is obtained by image acquisition of a manhole; detecting openings on the cylindrical projection image to be processed, obtaining the pixel coordinates of the openings in the coordinate system of the cylindrical projection image; determining the azimuth angle of the openings based on the X-pixel coordinates of the openings in the coordinate system of the cylindrical projection image and the camera orientation azimuth angle; matching and connecting the openings of adjacent manholes based on the azimuth angle; and drawing a pipeline network diagram between the manholes based on the connection relationship.

[0006] To address the aforementioned technical problems, a second aspect of this application provides a device for identifying wellbore openings and generating pipeline diagrams. The device includes a processor and a memory coupled to each other. The memory stores a computer program, and the processor executes the computer program to implement the steps of the method provided in the first aspect above.

[0007] To address the aforementioned technical problems, a third aspect of this application provides a computer-readable storage medium storing program data, which, when executed by a processor, implements the steps of the method provided in the first aspect above.

[0008] The embodiments of the present invention have the following beneficial effects: Unlike existing technologies, this application detects pipe openings in the isobaric projection image to be processed, obtaining the pixel coordinates of the pipe openings in the isobaric projection image coordinate system; determines the pipe opening azimuth angle based on the X pixel coordinates of the pipe openings in the isobaric projection image coordinate system and the camera orientation azimuth angle; matches and connects the pipe openings of adjacent inspection wells based on the pipe opening azimuth angle; and draws a pipeline network diagram between the inspection wells based on the connection relationship. Through the above method, automated pipe opening identification and parameter calculation can be achieved based on the isobaric projection image to be processed, significantly reducing manual data processing time, achieving high accuracy, enabling standardized operations, and batch generation of pipeline network diagrams. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0010] in: Figure 1 This is a schematic diagram of the panoramic image coordinate system and the isocylindrical projection image coordinate system of this application; Figure 2 This is a schematic diagram of the three-dimensional coordinate system of the well body in this application; Figure 3 This is a schematic diagram of the transformation from the cylindrical projection image coordinate system to the well body three-dimensional coordinate system of this application; Figure 4 This is a schematic diagram of an embodiment of the camera acquiring images of inspection wells according to this application; Figure 5 This is a schematic diagram of an embodiment of the columnar projection image of this application; Figure 6 This is a flowchart illustrating an embodiment of the wellbore pipe opening identification and pipeline network diagram generation method of this application; Figure 7 This is a flowchart illustrating an embodiment of step S13 of this application; Figure 8 This is a flowchart illustrating an embodiment of step S14 of this application; Figure 9 This is a schematic diagram of an embodiment of the matching pipe connection relationship in this application; Figure 10 This is a comparison chart of the distortion compensation effects of this application; Figure 11 This is the pipeline for this application. Figure 1 The renderings of the embodiment; Figure 12This is a rendering of an embodiment of the 3D model of the inspection well in this application; Figure 13 This is a schematic block diagram of an embodiment of the well wall pipe opening identification and pipeline network diagram generation device of this application; Figure 14 This is a schematic block diagram illustrating the structure of an embodiment of a computer-readable storage medium according to this application. Detailed Implementation

[0011] 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.

[0012] The terms "first" and "second" in this application are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such processes, methods, products, or apparatus.

[0013] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0014] Please see Figure 1 and Figure 2 The diagram shows the three coordinate systems of this application. The following coordinate systems are established in this application: panoramic image coordinate system (azimuth, latitude), isocylindrical projection image coordinate system (pixel_x, pixel_y), and well body three-dimensional coordinate system (X,Y,Z). Figure 3 A schematic diagram of the transformation from the cylindrical projection image coordinate system to the well body three-dimensional coordinate system of this application is shown.

[0015] In this system, the X-coordinate of the isocylindrical projection image coordinate system (pixel_x, pixel_y) is obtained by longitude transformation of the panoramic image coordinate system (azimuth, latitude), and the Y-coordinate is obtained by latitude transformation of the panoramic image coordinate system (azimuth, latitude). The origin of the well body three-dimensional coordinate system (X, Y, Z) is located at the center of the bottom of the well. The Y-axis points vertically upward to represent the elevation, the X-axis points due east, the Z-axis points due north, and the well wall is located on a cylindrical surface with a radius of R.

[0016] Please refer to the following: Figure 4 and Figure 5 , Figure 4 This is a schematic diagram of an embodiment of camera-based image acquisition of inspection wells. Figure 5 This is a schematic diagram of an embodiment of an isorectangular projection image. 1 represents the manhole wall, 2 represents the manhole opening, 3 represents the manhole bottom, 4 represents the pipe opening, 5 represents the 360-degree panoramic camera, 6, 7, and 8 represent shooting positions 1, 2, and 3 respectively (depths d1, d2, and d3), and 9 represents the depth sensor. In the early data acquisition stage, this application places the 360-degree panoramic camera inside the manhole. The camera is connected to a depth sensor and an attitude sensor. Layered shooting is performed at different depth positions, with one 360-degree panoramic image captured at each depth position. Multiple pipe openings are visible in the images. The X-axis corresponds to the azimuth angle (0°, -360°), and the Y-axis corresponds to the pitch angle (+90°, -90°). The image format is isorectangular projection, and the following data is recorded simultaneously: Shooting depth: The vertical distance between the camera's current position and the wellhead is obtained through a depth sensor; Camera azimuth angle: The camera's orientation azimuth angle is obtained through an attitude sensor (such as the BNO055 nine-axis sensor); Geographic coordinates: The latitude and longitude coordinates of the inspection well are obtained through GPS / BeiDou positioning.

[0017] In addition, the total depth and radius of the inspection well are collected.

[0018] Based on the data collected above, the following embodiments are used to process the data and generate a visual pipeline network diagram.

[0019] Please see Figure 6 , Figure 6 This is a schematic flowchart illustrating an embodiment of the wellbore pipe opening identification and pipeline network diagram generation method of this application. It should be noted that if substantially the same result is obtained, this embodiment is not necessarily identical. Figure 6 The illustrated process sequence is limited. This embodiment of the wellbore pipe opening identification and pipeline network diagram generation method includes the following steps: S11: Obtain the cylindrical projection image to be processed.

[0020] This step acquires multiple cylindrical projection images to be processed, captured by a camera at different depths within different inspection wells. These cylindrical projection images are obtained through image acquisition of the inspection wells. Specifically, a panoramic image of the inner wall of the inspection well is acquired, and then the panoramic image is subjected to cylindrical equal-volume projection to obtain a cylindrical projection image of the inner wall of the inspection well. The cylindrical projection image includes information about the pipe openings exposed on the inspection well wall.

[0021] S12: Detect the pipe opening on the cylindrical projection image to be processed, and obtain the pixel coordinates of the pipe opening in the cylindrical projection image coordinate system.

[0022] Image detection technology is used to identify and detect pipe openings on isochoric projection images. Specifically, a pre-trained image detection model (e.g., the YOLOv8 object detection model) can be used to detect pipe openings in the isochoric projection image, obtaining the bounding box, segmentation mask, and confidence score for each pipe opening. For each pipe opening, at least one of the following features is extracted based on the segmentation mask: the pixel coordinates (X,Y) of the pipe opening in the isochoric projection image coordinate system, ellipse fitting parameters, the area of ​​the segmented region, the perimeter of the segmented region, the circularity of the pipe opening, and the diameter of the pipe opening. The ellipse fitting parameters are the major axis, minor axis, and rotation angle obtained by fitting an ellipse; the circularity is calculated using the formula: circularity = 4π × area / perimeter², used to evaluate the shape of the pipe opening; the pixel coordinates of the pipe opening can specifically be the pixel coordinates of the centroid of the pipe opening, i.e., the pixel coordinates of the center of the pipe opening in the isochoric projection image coordinate system.

[0023] The pipe diameter can be calculated from the average diameter based on the ellipse fitting parameters: diameter = (major axis + minor axis) / 2; the area and perimeter of the segmented region can be used to calculate the roundness; the bounding box can be used for visualization: marking the pipe position in the 3D scene and debugging image, and determining the display position of the pipe parameter label.

[0024] S13: Determine the azimuth angle of the pipe opening based on the X pixel coordinates of the pipe opening in the isocylindrical projection image coordinate system and the camera orientation azimuth angle.

[0025] The camera's azimuth angle is the angle at which the camera faces when acquiring the isochoric projection image to be processed. This angle is obtained from the camera's attitude sensor during shooting. The pixel coordinates of the pipe opening in the panoramic image coordinate system are derived from the pixel coordinates of the pipe opening in the isochoric projection image.

[0026] The azimuth of the nozzle mentioned in this application refers to the absolute azimuth of the nozzle. Please refer to [reference needed]. Figure 7 In one embodiment, the orifice azimuth angle is obtained according to the following steps: S31: Determine the relative azimuth angle of the pipe opening based on the X-pixel coordinate of the centroid of the pipe opening in the coordinate system of the isocylindrical projection image and the width of the isocylindrical projection image.

[0027] The width and height of the isobaric projection image mentioned in this application are pixel width and height, which can be pre-inputted or obtained by identifying the width and height of the isobaric projection image.

[0028] S32: Determine the absolute azimuth of the pipe opening based on the camera's facing azimuth and the relative azimuth of the pipe opening, and use the absolute azimuth of the pipe opening as the azimuth of the pipe opening.

[0029] The azimuth angle of the pipe opening is calculated using the following formula: relative_azimuth=(pixel_x / image_width)×360° absolute_azimuth=(camera_azimuth+relative_azimuth)mod 360° Where: relative_azimuth is the relative azimuth of the pipe opening, absolute_azimuth is the absolute azimuth of the pipe opening, pixel_x is the X-pixel coordinate of the centroid of the pipe opening in the coordinate system of the isochoric projection image, image_width is the width of the isochoric projection image, camera_azimuth is the azimuth of the camera when shooting, and mod 360° is to perform a 360-degree modulo operation.

[0030] It is understandable that the X=0 position of the cylindrical projection image corresponds to the camera's orientation, the increase of the X coordinate corresponds to a clockwise rotation, and the 360° modulus operation ensures that the result is within the range of [0°, 360°).

[0031] In one embodiment, the eccentricity of the ellipse can be calculated based on the ellipse fitting parameters of the pipe opening. When the eccentricity is >0.3 (the ellipse is sufficiently flat), the azimuth angle is corrected using the major axis of the ellipse to improve the azimuth angle accuracy.

[0032] S14: Based on the azimuth angle of the pipe opening, determine the pipe opening matching and connection relationship between adjacent inspection wells.

[0033] Specifically, based on the azimuth angle of each pipe opening, the extension direction of each pipe opening in multiple inspection wells can be determined, and the connection relationship between pipe openings with matching extension directions can be determined.

[0034] S15: Draw a pipeline network diagram between inspection wells based on the connection relationships.

[0035] Please refer to the following: Figure 11 and Figure 12The pipeline network map includes multiple cylindrical manhole 3D models and the connection relationships of each manhole's nozzles. The manholes are distributed according to geographical coordinates. Specifically, the pipeline network map creates cylindrical 3D models of manholes based on their total depth and radius. The manholes are drawn proportionally scaled down according to their actual geographical locations. The geographical distribution of the manholes on the network map is obtained by converting the geographical coordinates captured during camera image acquisition to a 2D plane. Connecting nozzles with known connections between different manholes is done, and information labels are added to each nozzle. These labels, displayed within a bounding box, include nozzle number, burial depth, and diameter. The labels use a billboard effect, always facing the observer. Users can intuitively determine the distribution of manholes and nozzle connections by viewing the network map. The pipeline network map is automatically generated, visually displaying the spatial distribution of nozzles. The editable and zoomable interactive interface supports interactive rotation, zooming, and editing, facilitating on-site verification and subsequent management.

[0036] Through the above methods, data acquisition relies less on manual labor. A panoramic camera can capture a complete surround view image in a single shot, eliminating the need for manual measurement of each pipe opening and professional surveyors. Ordinary operators can operate the system after simple training, making it easy to use and significantly improving accuracy. In addition, the layered shooting process can be standardized, and the measurement time for a single well can be controlled within 5-10 minutes. Furthermore, pipe openings can be automatically identified and parameters calculated, greatly reducing manual data processing time, ensuring high accuracy, and enabling standardized operations and batch generation of pipeline network maps.

[0037] Please refer to the following: Figure 8 and Figure 9 Step S14 further includes the following steps: S41: For each inspection well as the target inspection well, search for candidate wells around the target inspection well.

[0038] Specifically, candidate wells can be searched within a preset distance range of the target inspection well (the preset distance is, for example, 80-130 meters, such as 80 meters, 100 meters, 130 meters, etc.). It can be understood that there can be one or more candidate wells.

[0039] S42: Determine the geographical azimuth between the target inspection well and the candidate well.

[0040] Specifically, the geographical azimuth between the target inspection well and the candidate well can be calculated based on the geographical coordinates of the target inspection well and the candidate well acquired when the camera captures images.

[0041] S43: Based on the geographical azimuth, the azimuth of the target inspection well opening, and the azimuth of the candidate well opening, determine whether the target inspection well has an opening pointing to the candidate well, and determine whether the candidate well has an opening pointing to the target inspection well.

[0042] To determine whether the target inspection well has a pipe opening pointing towards the candidate well, specifically: calculate the difference between the geographic azimuth and the azimuth of the target inspection well's pipe opening. If the azimuth difference is less than a first preset azimuth difference threshold, then it is determined that the target inspection well has a pipe opening pointing towards the candidate well; otherwise, it is determined that the target inspection well does not have a pipe opening pointing towards the candidate well. The preset azimuth difference threshold is, for example, in the range of 20°-40°, such as 20°, 30°, 40°, etc.

[0043] The azimuth difference is determined according to the following formula: azimuth_diff=|source_azimuth-bearing_to_target| ifazimuth_diff>180:azimuth_diff=360-azimuth_diff Wherein, azimuth_diff represents the azimuth difference, source_azimuth represents the azimuth of the target inspection well nozzle, and bearing_to_target represents the geographic azimuth between the target inspection well and the candidate well.

[0044] To determine whether a candidate well has a pipe opening pointing to the target inspection well, specifically: the azimuth angle of the target inspection well's pipe opening is reversed to obtain the reversed azimuth angle of the target inspection well's pipe opening. Among the candidate wells, the pipe opening whose difference between the pipe opening azimuth angle and the reversed azimuth angle is less than a second preset azimuth angle difference threshold is considered a candidate well pointing to the target inspection well; otherwise, it is determined that there is no candidate well pointing to the target inspection well.

[0045] The reverse azimuth angle expected_reverse_azimuth is determined by the following formula: expected_reverse_azimuth=(bearing_to_target+180)mod360 S44: If there is a first pipe opening in the target inspection well pointing to the candidate well, and there is a second pipe opening in the candidate well pointing to the target inspection well, then the first pipe opening and the second pipe opening are matched and connected.

[0046] This embodiment screens candidate wells around the target manhole, quickly filtering out manholes without pipe connection relationships, reducing invalid calculations, saving computing power, and improving data processing speed. Furthermore, it matches pipe orientations based on the difference in azimuth angles, achieving automatic matching of pipe connection relationships, avoiding the inefficiency and errors of manual judgment, and improving the accuracy of pipe matching. Further, it employs a dual matching method, checking whether candidate wells point to the target manhole and whether the target manhole points to candidate wells, ensuring the pipe orientation is accurate and avoiding the lack of judgment caused by unidirectional judgment, further improving the reliability of pipe matching.

[0047] In one embodiment, if there are multiple second pipe openings in step S44, the method of the above embodiment further includes: determining the distance score between the target inspection well and each candidate well based on the geographical coordinates of the target inspection well and the candidate wells corresponding to each second pipe opening; determining the azimuth matching score between each second pipe opening and the first pipe opening based on the difference between the pipe opening azimuth and the reverse azimuth of each second pipe opening; in step S12, the pipe opening diameter is also detected, and the pipe diameter matching score between each second pipe opening and the first pipe opening is determined based on the difference between the pipe opening diameters of the first pipe opening and each second pipe opening; calculating the confidence score of the connection relationship between the first pipe opening and each second pipe opening based on at least one of the azimuth matching score, distance score, and pipe diameter matching score, and taking the second pipe opening with the highest confidence score as the final second pipe opening.

[0048] Understandably, the closer a candidate well is to the target inspection well, the higher its distance score; the smaller the difference between the azimuth and reverse azimuth of the second pipe opening, the higher its azimuth matching score; and the smaller the difference between the pipe diameter of the second pipe opening and the pipe diameter of the first pipe opening, the higher its pipe diameter matching score. Specifically, if at least two of the azimuth matching score, distance score, and pipe diameter matching score are used to calculate the confidence score, the scores are weighted and summed according to a preset weighting rule to obtain the confidence score. For example, when using the azimuth matching score, distance score, and pipe diameter matching score to calculate the confidence score, the following formula is used: confidence=azimuth_score×0.5+distance_score×0.3+diameter_score×0.2 Where confidence represents the confidence score, azimuth_score represents the azimuth matching score, distance_score represents the distance score, and diameter_score represents the pipe diameter matching score.

[0049] Optionally, the confidence score may also include a roundness score, which is weighted at 20%-30% in the confidence score calculation. Understandably, the higher the roundness, the higher the roundness score.

[0050] The method in the above embodiment further includes: converting the Y-pixel coordinates of the pipe opening in the isocylindrical projection image coordinate system to obtain the pipe opening latitude in the panoramic image coordinate system, and calculating the pipe opening burial depth based on the pipe opening latitude; after matching and connecting the first pipe opening and the second pipe opening, it further includes: determining the direction from the pipe opening with a smaller burial depth to the pipe opening with a larger burial depth as the flow direction relationship between the first pipe opening and the second pipe opening; and drawing the flow direction relationship in the pipeline network diagram.

[0051] It can be understood that the end of the pipe with a shallower burial depth is upstream, and the end of the pipe with a deeper burial depth is downstream. Specifically, when drawing the flow direction relationship in the pipeline network diagram, the directional arrows corresponding to the flow direction relationship can be marked on the line connecting the first and second pipe openings in the pipeline network diagram, or the line connecting the first and second pipe openings can be labeled with text.

[0052] The latitude of the pipe opening is calculated based on the Y-pixel coordinate of the centroid of the pipe opening in the coordinate system of the iso-cylindrical projection image and the height of the iso-cylindrical projection image, as follows: latitude_deg=(0.5-pixel_y / image_height)×180°, where pixel_y is the Y-pixel coordinate of the centroid of the pipe opening in the coordinate system of the iso-cylindrical projection image, and image_height is the height of the iso-cylindrical projection image.

[0053] It is understandable that: pixel_y=0 is located at the top of the isograil projection image, corresponding to: latitude=+90°, located directly above the panoramic image; pixel_y=image_height / 2 is located in the middle of the isograil projection image, corresponding to: latitude=0°, located in the horizontal direction of the panoramic image; pixel_y=image_height is located at the bottom of the isograil projection image, and latitude=-90° is located directly below the panoramic image.

[0054] Specifically, the burial depth of the pipe opening is calculated as follows: latitude_rad=latitude_deg×π / 180 vertical_offset=R×tan(latitude_rad) burial_depth=shooting_depth+vertical_offset Where latitude_rad is the radian value corresponding to the latitude_deg of the pipe opening, vertical_offset is the vertical offset of the pipe opening relative to the camera, shooting_depth is the depth of the camera at the time of shooting (measured from the wellhead), burial_depth is the burial depth of the pipe opening, and R is the radius of the well body, with the camera located at the center of the well during shooting. Based on the Y-pixel coordinates of the pipe opening centroid and the geometric relationship of the well body, the burial depth of the pipe opening can be accurately calculated without additional depth measurement equipment, with a calculation accuracy of ±0.1 meters.

[0055] It is understandable that when latitude > 0, the pipe opening is above the camera, vertical_offset is negative, and the burial depth decreases; when latitude < 0, the pipe opening is below the camera, vertical_offset is positive, and the burial depth increases; when latitude = 0, the pipe opening and the camera are on the same horizontal plane.

[0056] In one embodiment, the method further includes: determining the pipe opening elevation based on the difference between the total depth of the well body and the pipe opening burial depth; determining the three-dimensional spatial coordinates of the pipe opening in the three-dimensional coordinate system of the well body based on the pipe opening azimuth and the pipe opening elevation; and drawing a three-dimensional visualization image of the pipe opening on the well wall of the inspection well based on the three-dimensional spatial coordinates, the pipe opening burial depth, and the pipe opening elevation.

[0057] See also Figure 12 , Figure 12 This is a three-dimensional visualization image of the pipe opening on the manhole wall in one embodiment.

[0058] Specifically, the three-dimensional visualization image of the well body is drawn based on the total depth and radius of the well body. The pipe openings are represented by cylinders, with the direction radially outward along the well wall. Information labels can also be added to each pipe opening to display information such as pipe opening number, burial depth, and pipe opening diameter. The labels adopt the Billboard effect and are always facing the observer.

[0059] Specifically, the pipe opening elevation is the height of the pipe opening from the bottom of the well, calculated as follows: elevation = well_depth - burial_depth. Where well_depth is the total depth of the well, burial_depth is the pipe opening burial depth, and elevation is the pipe opening elevation.

[0060] Specifically, the three-dimensional spatial coordinates (wall_X, wall_Y, wall_Z) of the pipe opening in the three-dimensional coordinate system of the well body are calculated as follows: the X and Z coordinates of the pipe opening in the three-dimensional coordinate system of the well body are calculated based on the pipe opening azimuth angle, and the pipe opening elevation is used as the Y coordinate to obtain the three-dimensional spatial coordinates (wall_X, wall_Y, wall_Z) of the pipe opening in the three-dimensional coordinate system of the well body.

[0061] The X and Z coordinates of the pipe opening in the three-dimensional coordinate system of the well body are calculated based on the pipe opening azimuth angle as follows: azimuth_rad=absolute_azimuth×π / 180 wall_X = -R × sin(azimuth_rad) wall_Z = R × cos(azimuth_rad) `azimuth_rad` represents the radian value corresponding to the azimuth angle of the pipe opening. It can be understood that the correspondence between the pipe opening azimuth angle and the pipe opening's coordinates in the well's three-dimensional coordinate system is as follows (where a top view is used, the Y-axis is upward, and the X-coordinate is negative to ensure the direction of the top view aligns with north-south on the map): azimuth = 0° (due north), corresponding to: X = 0, Z = +R azimuth = 90° (due east), corresponding to: X = -R, Z = 0 azimuth = 180° (due south), corresponding to: X = 0, Z = -R azimuth = 270° (due west), corresponding to: X = +R, Z = 0.

[0062] This embodiment establishes a coordinate transformation model specifically for the special scenario of "pipe opening in well wall". It makes full use of the geometric constraint that "the pipe opening is located on the cylindrical well wall", so that the transformation from two-dimensional image pixel coordinates to three-dimensional spatial coordinates has a clear mathematical expression. The coordinate position, burial depth, elevation and azimuth of the pipe opening in the three-dimensional coordinate system of the well body are calculated through coordinate transformation, so as to realize the positioning of the pipe opening on the well wall. The calculation results are directly used for three-dimensional scene rendering without additional coordinate transformation, which facilitates the three-dimensional visualization of the inspection well.

[0063] In one embodiment, the method further includes: after detecting the pipe openings on the isobaric projection image to be processed, obtaining the confidence level of each pipe opening; transforming the Y-pixel coordinates of the pipe openings in the isobaric projection image coordinate system to obtain the pipe opening latitude in the panoramic image coordinate system, and calculating the pipe opening burial depth based on the pipe opening latitude; for the pipe openings in the isobaric projection images to be processed obtained at different depths, performing clustering processing according to the pipe opening azimuth angle and the pipe opening burial depth, and grouping the pipe openings that meet the preset azimuth angle tolerance and the preset burial depth tolerance into the same cluster; for each cluster, retaining the detection result corresponding to the pipe opening with the highest confidence level.

[0064] Because images are taken at different depths, the same pipe opening may be detected multiple times, requiring deduplication. A preset azimuth tolerance is, for example, ±15°, and a preset burial depth tolerance is, for example, ±0.5m. The pipe opening parameters corresponding to the highest confidence level (e.g., at least one of the following: bounding box, segmentation mask, confidence level, pixel coordinates of the pipe opening in the isochoric projection image coordinate system, ellipse fitting parameters, area of ​​the segmented region, perimeter of the segmented region, and circularity of the pipe opening) are retained as the detection result for that pipe opening. This embodiment identifies images taken at different depths and uses azimuth and burial depth clustering to deduplicate repeatedly identified pipe openings, avoiding duplicate detection and improving the accuracy of pipe opening identification—ensuring neither missed nor over-identified openings.

[0065] In one embodiment, after step S12, the pipe opening diameter is also obtained; after step S12, the method further includes: converting the Y-pixel coordinates of the pipe opening in the isocylindrical projection image coordinate system to obtain the pipe opening latitude in the panoramic image coordinate system; calculating the distance from the camera to the pipe opening based on the radian value corresponding to the pipe opening latitude and the well radius; determining the pipe opening angle based on the width of the isocylindrical projection image and the pipe opening diameter; and calculating the true pipe opening diameter based on the pipe opening angle and the distance from the camera to the pipe opening.

[0066] It is understood that the diameter of the pipe opening obtained by detecting the opening is the pixel diameter measured directly on the isochoric projection image. This embodiment converts the pixel-level pipe opening diameter into a real-world size. Specifically, the camera is located at the center of the well, and the pipe opening is located on the well wall. The distance from the camera to the pipe opening is determined by the ratio between the absolute value of the cosine of the well radius and the latitude of the pipe opening in radians, as shown in the following formula: distance = R / |cos(latitude_rad)|, where distance represents the distance from the camera to the pipe opening, R is the well radius, and latitude_rad represents the latitude of the pipe opening in radians. It is understood that for a horizontal pipe opening with latitude = 0°, the distance from the camera to the pipe opening is equal to the well radius R; for pipe openings that are angled upwards / downwards, the distance from the camera to the pipe opening is greater than R.

[0067] The nozzle angle represents the angle occupied by the nozzle in the field of view. The nozzle angle is determined as follows: the angle of a single pixel in the isochoric projection image is determined based on the width of the isochoric projection image; the nozzle angle is then calculated based on the angle of the single pixel and the nozzle diameter. The specific formula is as follows: angle_per_pixel=360° / image_width angle_subtended=diameter×angle_per_pixel Where image_width represents the width of the isobaric projection image, angle_per_pixel is the angle of a single pixel in the isobaric projection image, diameter represents the diameter of the pipe opening, and angle_subtended represents the angle of the pipe opening.

[0068] The true diameter of the pipe opening is determined as follows: the pipe opening angle is converted into the corresponding pipe opening angle in radians, and the true diameter is calculated using trigonometric relationships. The specific formula is as follows: angle_rad=angle_subtended×π / 180 diameter_meters=2×distance×tan(angle_rad / 2) Where angle_rad represents the radian value corresponding to the pipe opening angle, and diameter_meters represents the actual pipe opening diameter.

[0069] This embodiment converts the pixel diameter of the pipe opening into the actual size diameter, enabling non-contact, precise measurement without additional equipment. It has high accuracy, improves the three-dimensional positioning data system of the pipe opening, and provides data support for pipeline network operation and maintenance with high reliability.

[0070] In one embodiment, before determining the pipe opening angle based on the width of the iso-cylindrical projection image and the pipe opening diameter, the method further includes: calculating a stretching factor based on the pipe opening latitude; using the stretching factor to perform distortion compensation on the pipe opening diameter to obtain the distortion-compensated pipe opening diameter; and determining the pipe opening angle based on the width of the iso-cylindrical projection image and the distortion-compensated pipe opening diameter.

[0071] Please refer to the following: Figure 10 When a cylindrical projection is applied to a high-latitude region, horizontal stretching occurs, requiring compensation for the directly measured pipe diameter. Specifically, the stretch factor is calculated using trigonometric functions based on the pipe's latitude, as follows: stretch_factor = 1 / |cos(latitude_rad)|, where latitude_rad = latitude_deg × π / 180, latitude_deg is the pipe's latitude, latitude_rad is the corresponding radian value, and stretch_factor represents the stretch factor.

[0072] The distortion compensation of the pipe diameter is performed using a stretch factor, specifically by multiplying the stretch factor by the pipe diameter. The specific formula is as follows: diameter = diameter_raw / stretch_factor, where diameter_raw is the pipe diameter measured directly on the isochoric projection image, and diameter is the distortion-compensated pipe diameter.

[0073] It is understandable that at the equator (latitude=0°), stretch_factor=1, requiring no compensation; at latitude=60°, stretch_factor=2, resulting in a compensated diameter that is half the original measurement; and at latitude=80°, stretch_factor≈5.76, resulting in a compensated diameter that is approximately one-sixth of the original measurement. This embodiment uses a latitude-dependent distortion compensation algorithm to minimize the horizontal stretching effect of isocylindrical projection in high-latitude regions, significantly reducing the measurement accuracy of the pipe diameter from the original ±100% error (at 60° latitude).

[0074] In one embodiment, before step S12, the method further includes: vertically cropping and horizontally cyclically expanding the isocylindrical projection image to obtain a preprocessed image; step S12 includes: detecting the pipe opening on the preprocessed image to obtain the pixel coordinates of the pipe opening in the preprocessed image coordinate system; restoring the pixel coordinates of the pipe opening in the preprocessed image coordinate system to the isocylindrical projection image coordinate system to obtain the pixel coordinates of the pipe opening in the isocylindrical projection image coordinate system.

[0075] In one embodiment, the vertical cropping operation specifically involves setting a cropping ratio and retaining the central region of the cylindrical projection image, which occupies the cropping ratio, to obtain the cropped image. In a specific embodiment, the cropping ratio is set to 0.6, retaining 60% of the central region of the cylindrical projection image, i.e., the region of 20%-80% height of the original cylindrical projection image, and cropping the bottom 20% and top 20% of the original cylindrical projection image (i.e., the region near the pole, where there is usually no pipe opening). The effective latitude range after cropping is ±54°, avoiding the pole region where the distortion is most severe. This embodiment crops away the severely distorted region near the pole, improving the pipe opening recognition effect and accuracy.

[0076] In one embodiment, the horizontal cyclic expansion specifically involves setting an expansion ratio and cyclically expanding the left and right sides of the cropped image according to the set expansion ratio. In a specific embodiment, the expansion ratio is set to 15%. The image of the right 15% region of the original cylindrical projection image is stitched to the left side, and the image of the left 15% region of the original image is stitched to the right side, resulting in a horizontally expanded image with a width of 130% of the original image. This embodiment solves the problem of difficulty in identifying pipe openings due to their truncation at the image edge, ensuring that all pipe openings are fully presented and improving the accuracy of pipe opening recognition.

[0077] Specifically, the X-coordinate of the pipe opening in the preprocessed image coordinate system is restored to the isocylindrical projection image coordinate system in the following way: original_x = detected_x - extended_pixels. Where, when original_x < 0, original_x = original_x + original_width; when original_x >= original_width, original_x = original_x - original_width.

[0078] original_x represents the X coordinate of the pipe opening in the coordinate system of the isocylindrical projection image, detected_x represents the X pixel coordinate of the pipe opening in the coordinate system of the preprocessed image, extend_pixels represents the number of pixels horizontally extended on the left or right side of the image in the horizontal cyclic expansion operation, and original_width represents the width of the isocylindrical projection image.

[0079] The Y-coordinate of the pipe opening in the preprocessed image coordinate system is restored to the isochoric projection image coordinate system as follows: original_y = detected_y + crop_top. original_y represents the Y-coordinate of the pipe opening in the isochoric projection image coordinate system, detected_y represents the Y-pixel coordinate of the pipe opening in the preprocessed image coordinate system, and crop_top represents the top starting pixel position of the vertical crop of the isochoric projection image.

[0080] In one specific embodiment, the process of measuring and 3D modeling a single inspection well is as follows: Step 1. Equipment Preparation: Panoramic camera (or equivalent 360-degree camera) Smart devices with built-in measurement apps ESP32 Bluetooth sensor module (integrates BNO055 attitude sensor and laser rangefinder) Camera bracket / measuring rod Step 2. On-site operations (1) Assemble the equipment, fix the panoramic camera to the front end of the measuring rod, and connect the sensor module to the mobile phone via Bluetooth; (2) Create a new inspection well operation in the APP and enter the basic information of the well (number, location, etc.); (3) Slowly lower the camera into the well. The APP will automatically prompt the shooting time according to the set shooting depth (e.g., take a picture once every 1 meter); (4) When the specified depth is reached, the APP will automatically trigger the panoramic camera to take pictures and record the current depth value and azimuth angle at the same time; (5) Repeat step (4) until all depth layers have been photographed; (6) Upload images and metadata to the server for processing.

[0081] Step 3. Data Processing After receiving the data, the server performs the following processing: (1) Preprocess each panoramic image (cropping, edge expansion); (2) Using the YOLOv8 model to detect the pipe opening, the detection time is about 0.3 seconds for an image with a resolution of 5760×2880; (3) Extract features and calculate spatial coordinates for each detected pipe opening; (4) Perform deduplication and clustering on the detection results of multiple images; (5) Generate a JSON file of the recognition results and return it to the APP.

[0082] Step 4. 3D Visualization After the APP receives the recognition result: (1) Create a 3D scene using the SceneView engine; (2) Create a well body model based on the well depth and well diameter parameters; (3) Calculate the three-dimensional coordinates based on the azimuth and burial depth of each pipe opening, and create a pipe opening model; (4) Users can rotate and zoom the 3D model using gestures; (5) Supports clicking to select the pipe opening for parameter editing.

[0083] Step 5. Output measurement results Well depth: 4.2 meters Well diameter: 0.7 meters Number of pipe openings detected: 3 In one specific embodiment, the process of automatically generating a pipeline network from multiple inspection wells is as follows: Step 1. Data Preparation Assume that measurements have been completed for 10 inspection wells in a certain area, and the data for each well includes: -Geographic coordinates (longitude, latitude) -Well depth, well diameter - Pipe port list (each pipe port includes azimuth, burial depth, and pipe diameter) Step 2. Setting the plotting parameters - Search distance: 100 meters (only adjacent wells within a 100-meter radius are considered) - Search angle: 30 degrees (maximum permissible deviation between pipe azimuth and wellbore azimuth) - Confidence threshold: 70 points (matches below this score require manual verification). Step 3. Matching algorithm execution Taking the pipe opening PIPE-1 (azimuth angle 45°) of well W001 as an example: (1) Calculate the distance and azimuth of W001 to other wells: -W001 to W002: Distance 35 meters, azimuth 48° -W001 to W003: Distance 62 meters, azimuth 120° (2) Screening candidate wells: -W002 is a valid candidate if it is within a 100-meter range and the azimuth difference |45°-48°|=3°<30°. (3) Locate the reverse port in W002: The PIPE-1 azimuth of -W002 is 225°. -Desired reverse azimuth angle = (48° + 180°) = 228° -Difference |225°-228°|=3°<30°, match successful. (4) Calculate the confidence level: - Azimuth score: (1-3 / 30)×100×0.5=45 points - Distance score: (1-35 / 100)×100×0.3=19.5 points - Pipe diameter score: For pipes of the same diameter, 100 × 0.2 = 20 points. Total score: 84.5 points (5) Flow direction determination: -W001-PIPE-1 Burial depth: 2.1 meters -W002-PIPE-1 Burial depth: 2.5 meters - Flow direction: W001→W002 (upstream to downstream) Step 4. Graphing Results - Number of matching connections: 8 -High confidence level (≥85 points): 5 items -Medium confidence level (70-85 points): 2 results - Low confidence level (<70 points): 1 case (requires manual verification) For low-confidence matches, the system provides a manual confirmation interface, which can perform the following operations: highlight the connection to be confirmed on the map, display detailed parameters of the two ends of the pipe, allow the user to confirm, delete or modify the connection, and access other manually editable information.

[0084] In one specific embodiment, the process for verifying the distortion compensation accuracy for the pipe diameter is as follows: The test scenario is as follows: In a standard testing environment, a circular target of known diameter is placed: - Target diameter: 300mm - Placement location: 0.35 meters from the camera (simulating the location of the well wall) - Test locations: at different latitudes (0°, 30°, 45°, 60°) The uncompensated measurement results are shown below: The measurement results after distortion compensation are as follows: Conclusion: The distortion compensation algorithm effectively eliminates the dimensional measurement error caused by the isocylindrical projection, and the measurement accuracy after compensation is better than ±10%.

[0085] Please see Figure 13 , Figure 13 This is a schematic block diagram of an embodiment of the wellbore pipe opening identification and pipeline network diagram generation device of this application. The wellbore pipe opening identification and pipeline network diagram generation device 900 includes a processor 910 and a memory 920 coupled to each other. The memory 920 stores a computer program, and the processor 910 is used to execute the computer program to implement the wellbore pipe opening identification and pipeline network diagram generation method described in the above embodiments.

[0086] For a description of each step of the processing, please refer to the description of each step in the above embodiment of the wellbore pipe opening identification and pipeline diagram generation method of this application, and it will not be repeated here.

[0087] The memory 920 can be used to store program data and modules. The processor 910 executes various functional applications and data processing by running the program data and modules stored in the memory 920. The memory 920 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as image processing functions, data processing functions, etc.), etc.; the data storage area may store data created based on the use of the wellbore pipe identification and pipe network diagram generation device 900 (such as pixel coordinate data, pipe parameters, etc.). In addition, the memory 920 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 920 may also include a memory controller to provide the processor 910 with access to the memory 920.

[0088] See Figure 14 , Figure 14 This is a schematic block diagram of a computer-readable storage medium according to an embodiment of the present application. The computer-readable storage medium 700 stores program data 710. When the program data 710 is executed, it implements the steps of the above-described embodiments of the wellbore pipe opening identification and pipeline network diagram generation methods.

[0089] For a description of each step of the processing, please refer to the description of each step in the above embodiment of the wellbore pipe opening identification and pipeline diagram generation method of this application, and it will not be repeated here.

[0090] The computer-readable storage medium 700 can be any medium capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0091] In the various embodiments of this application, the disclosed methods, apparatus, and devices can be implemented in other ways. For example, the embodiments of the wellbore pipe opening identification and pipeline network diagram generation device described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0092] The units described as separate components may or may not be physically separate. 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 the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0093] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0094] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium.

[0095] The above description discloses only preferred embodiments of the present invention and should not be construed as limiting the scope of the present invention. Therefore, equivalent variations made in accordance with the claims of the present invention are still within the scope of the present invention.

Claims

1. A method for identifying wellbore openings and generating pipeline network diagrams, characterized in that, The method includes: Obtain the columnar projection image to be processed, which is obtained by image acquisition of the inspection well; The pipe opening is detected on the cylindrical projection image to be processed, and the pixel coordinates of the pipe opening in the coordinate system of the cylindrical projection image are obtained. The azimuth angle of the pipe opening is determined based on the X pixel coordinates of the pipe opening in the isocylindrical projection image coordinate system and the camera orientation azimuth angle. Based on the azimuth angle of the pipe opening, the pipe opening matching connection relationship between adjacent inspection wells is determined; Draw a pipeline network diagram between the inspection wells based on the connection relationship.

2. The method according to claim 1, characterized in that, The step of matching and connecting pipe openings in adjacent inspection wells based on the pipe opening azimuth angle includes: Each of the aforementioned inspection wells is designated as a target inspection well, and candidate wells are searched around the target inspection well. Determine the geographical azimuth between the target inspection well and the candidate well; Based on the geographical azimuth, the azimuth of the target inspection well opening, and the azimuth of the candidate well opening, determine whether the target inspection well has an opening pointing to the candidate well, and determine whether the candidate well has an opening pointing to the target inspection well. If there is a first pipe opening in the target inspection well that points to the candidate well, and there is a second pipe opening in the candidate well that points to the target inspection well, then the first pipe opening and the second pipe opening are matched and connected.

3. The method according to claim 2, characterized in that, After detecting the pipe opening on the cylindrical projection image to be processed, the pipe opening diameter is also obtained; If the second port comprises multiple ports, the method further includes: Based on the geographical coordinates of the target inspection well and the candidate wells corresponding to each second pipe opening, the distance scores of the target inspection well and each candidate well are determined respectively. Based on the difference between the azimuth angle of each second pipe opening and the reverse azimuth angle, the azimuth angle matching score between each second pipe opening and the first pipe opening is determined respectively. Based on the difference in diameter between the first pipe opening and each of the second pipe openings, the pipe diameter matching score between each second pipe opening and the first pipe opening is determined. The confidence score of the connection relationship between the first pipe port and each of the second pipe ports is calculated based on at least one of the azimuth matching score, distance score, and pipe diameter matching score. The second pipe port with the highest confidence score is selected as the final second pipe port.

4. The method according to claim 2, characterized in that, Also includes: The pipe opening is transformed in the Y-pixel coordinate system of the isocylindrical projection image to obtain the pipe opening latitude in the panoramic image coordinate system, and the pipe opening burial depth is calculated based on the pipe opening latitude. After establishing the matching connection between the first and second pipe ports, the method further includes: The direction from the pipe with the smaller burial depth to the pipe with the larger burial depth is determined as the flow direction relationship between the first pipe opening and the second pipe opening. The flow direction relationship is drawn in the pipeline network diagram.

5. The method according to claim 4, characterized in that, The method further includes: determining the pipe opening elevation based on the difference between the total depth of the well body and the burial depth of the pipe opening; The three-dimensional spatial coordinates of the pipe opening in the well body's three-dimensional coordinate system are determined based on the pipe opening azimuth angle and the pipe opening elevation. Based on the three-dimensional spatial coordinates, the pipe opening burial depth, and the pipe opening elevation, a three-dimensional visualization image of the pipe opening on the manhole wall is drawn.

6. The method according to claim 1, characterized in that, After detecting the pipe openings on the columnar projection image to be processed, the confidence level of each pipe opening is also obtained. The method further includes: converting the Y-pixel coordinates of the pipe opening in the iso-cylindrical projection image coordinate system to obtain the pipe opening latitude in the panoramic image coordinate system, and calculating the pipe opening burial depth based on the pipe opening latitude; for pipe openings in the iso-cylindrical projection images to be processed obtained at different depths, performing clustering processing according to the pipe opening azimuth and the pipe opening burial depth, and grouping pipe openings that meet the preset azimuth tolerance and preset burial depth tolerance into the same cluster; For each cluster, retain the detection result corresponding to the pipe opening with the highest confidence level.

7. The method according to claim 1, characterized in that, The step of determining the azimuth angle of the pipe opening based on the X-pixel coordinates of the pipe opening in the isocylindrical projection image coordinate system and the camera orientation azimuth angle includes: The relative azimuth angle of the pipe opening is determined based on the X-pixel coordinate of the centroid of the pipe opening in the coordinate system of the isocylindrical projection image and the width of the isocylindrical projection image. The absolute azimuth angle of the pipe opening is determined based on the azimuth angle of the camera orientation and the relative azimuth angle of the pipe opening, and the absolute azimuth angle of the pipe opening is used as the azimuth angle of the pipe opening.

8. The method according to claim 1, characterized in that, After detecting the pipe opening on the cylindrical projection image to be processed, the pipe opening diameter is also obtained; The method further includes: The Y-pixel coordinates of the pipe opening in the isocylindrical projection image coordinate system are transformed to obtain the pipe opening latitude in the panoramic image coordinate system. The distance from the camera to the pipe opening is calculated based on the radian value corresponding to the pipe opening latitude and the well radius. The pipe opening angle is determined based on the width of the iso-cylindrical projection image and the pipe opening diameter; The true diameter of the pipe opening is calculated based on the pipe opening angle and the distance from the camera to the pipe opening.

9. The method according to claim 8, characterized in that, Before determining the pipe opening angle based on the width of the isocytic projection image and the pipe opening diameter, the method further includes: Calculate the stretch factor based on the latitude of the pipe opening; The pipe diameter is distorted by using a stretching factor to compensate for the distortion, resulting in the distorted pipe diameter. The step of determining the pipe opening angle based on the width of the isocytic projection image and the pipe opening diameter includes: The pipe opening angle is determined based on the width of the cylindrical projection image and the pipe opening diameter after distortion compensation.

10. The method according to claim 1, characterized in that, Before detecting the tube opening on the columnar projection image to be processed, the process includes: The vertically cropped and horizontally cyclically expanded cylindrical projection images are used to obtain preprocessed images. The step of detecting the pipe opening on the isochoric projection image to be processed, and obtaining the pixel coordinates of the pipe opening in the coordinate system of the isochoric projection image, includes: The pipe opening is detected on the preprocessed image to obtain the pixel coordinates of the pipe opening in the coordinate system of the preprocessed image; The pixel coordinates of the pipe opening in the preprocessed image coordinate system are restored to the isocylindrical projection image coordinate system to obtain the pixel coordinates of the pipe opening in the isocylindrical projection image coordinate system.

11. A device for identifying wellhead pipe openings and generating pipeline network diagrams, characterized in that, The wellbore opening identification and pipeline network diagram generation device includes a processor and a memory coupled to each other; the memory stores a computer program, and the processor is used to execute the computer program to implement the steps of the method as described in any one of claims 1-10.

12. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores program data that, when executed by a processor, implements the steps of the method as described in any one of claims 1-10.

Images