Method for Measuring Pier Surface and Hole Positions Based on UAV Close-Range Photogrammetry

Abstract

The present invention relates to a method for measuring the surface and hole positions of bridge piers based on UAV close-range photogrammetry, belonging to the technical field of engineering surveying. The method includes: performing three-dimensional reconstruction based on aerial images and aerial triangulation results to obtain a target model of the bridge pier to be measured; the aerial images are obtained by using a UAV to collect images of the bridge pier to be measured; the aerial triangulation results are determined based on the aerial images; identifying hole positions in the target model based on a preset local window to determine reference points; and determining the hole position information and surface information of the bridge pier to be measured based on the relative positions of the reference points within the preset local window. The method for measuring the surface and hole positions of bridge piers based on UAV close-range photogrammetry provided by the present invention avoids problems such as repeated climbing of personnel and rework of prefabricated components, and provides higher measurement accuracy, data density, and operation efficiency. It can be used as a way to obtain information about bridge pier prefabricated components and be promoted in bridge construction.

Description

Technical Field

[0001] The present invention relates to the technical field of engineering surveying, and particularly to a method for measuring the surface and hole positions of bridge piers based on unmanned aerial vehicle (UAV) close-range photogrammetry. Background Art

[0002] With the development of information technology, some digital and automated means have gradually emerged in the field of engineering construction. However, the current identification solutions for the surface shape of bridge piers and the deviation of prefabricated hole positions are still relatively backward. Prefabricated components such as hanging brackets can only be uniformly manufactured according to the design specifications first. When it is found that they do not match during on-site manual installation, feedback and rework are then carried out, resulting in rework and low efficiency.

[0003] To achieve prior identification of the pier surface and hole positions, methods such as total station measurement, lidar scanning, and photogrammetry can be used. Among them, the total station measurement method can only obtain a small number of discrete points. At the same time, due to the depression of the hole positions, the depth information cannot be correctly obtained, and the efficiency is low; the scanning height of the stationary lidar is limited, and it cannot measure the higher parts of the bridge pier; the airborne radar is also restricted by the scanning angle and registration accuracy, and the hole position identification based on point clouds is more difficult than that based on images; the traditional oblique photogrammetry method has a relatively long shooting distance and is mainly used for the reconstruction of three-dimensional models of large survey areas with medium and low resolutions or the collection of medium and small scale topographic maps. Its typical resolution is 3 - 5 cm, which is difficult to meet the requirements for precise measurement of the surface and hole positions of bridge piers.

[0004] The close-range photogrammetry method can effectively avoid the above restrictions such as data density and accuracy, and obtain a three-dimensional model with high resolution and high relative accuracy. However, due to its texture characteristics, the model is not smooth near the hole positions, so it is difficult to directly extract accurate hole position coordinates from the model. In addition, this method is also easily affected by factors such as uneven illumination. Summary of the Invention

[0005] In view of this, it is necessary to provide a method for measuring the surface and hole positions of bridge piers based on UAV close-range photogrammetry to solve the problem of low accuracy and efficiency of existing measurement methods.

[0006] To solve the above problems, the present invention provides a method for measuring the surface and hole positions of bridge piers based on UAV close-range photogrammetry, including:

[0007] Performing three-dimensional reconstruction based on aerial images and aerial triangulation results to obtain a target model of the bridge pier to be measured; the aerial images are obtained by using a UAV to collect images of the bridge pier to be measured; the aerial triangulation results are determined based on the aerial images;

[0008] Identifying the hole positions in the target model based on a preset local window to determine reference points;

[0009] Determine the hole position information and surface information of the pier to be measured based on the relative position of the reference point within the preset local window.

[0010] In one possible implementation, the method for identifying the hole positions in the target model based on the preset local window and determining the reference point includes:

[0011] Identify the hole positions in the preset local window based on the target detection method;

[0012] Determine the reference point based on the coordinates of the center of the hole position in the preset local window.

[0013] In one possible implementation, the method for determining the hole position information and surface information of the pier to be measured based on the relative position of the reference point within the preset local window includes:

[0014] Calibrate the relative position in the target model to obtain the calibrated position of the reference point:

[0015] Extract the three-dimensional coordinates of the reference point in the coordinate system corresponding to the target model based on the calibrated position;

[0016] Determine the hole position information based on the three-dimensional coordinates of the reference point in the coordinate system corresponding to the target model; the hole position information includes the three-dimensional coordinates of the center of the hole position in the coordinate system corresponding to the target model;

[0017] Fit the three-dimensional coordinates of the reference point in the coordinate system corresponding to the target model to obtain the surface information.

[0018] In one possible implementation, the method for determining the hole position information based on the three-dimensional coordinates of the reference point in the coordinate system corresponding to the target model includes:

[0019] Based on the three-dimensional coordinates of the reference point in the coordinate system corresponding to the target model, use the least squares distance weighted interpolation method or surface fitting method to optimally estimate the coordinates of the center of the hole position, and determine the hole position information.

[0020] In one possible implementation, after determining the hole position information and surface information of the pier to be measured based on the relative position of the reference point within the preset local window, it further includes:

[0021] Register the three-dimensional coordinates of the center of the hole position in the coordinate system corresponding to the target model with the coordinates of the center of the prefabricated hole position in the preset scheme to determine the relative relationship between the coordinate system corresponding to the target model and the coordinate system corresponding to the preset scheme;

[0022] Based on the relative relationship, a difference between the prefabricated hole position and the hole position is determined.

[0023] In a possible implementation, before performing three-dimensional reconstruction based on the aerial image and the aerial triangulation result to obtain the target model of the bridge pier to be measured, the method further includes:

[0024] Based on the shape and position distribution of the bridge pier to be measured, a preset route of the UAV is determined; the preset routes include: a full-area controlled oblique photography route, a complete column-surrounding photography route, and a high-density photography route close to key parts;

[0025] The aerial image is acquired by collecting images of the bridge pier to be measured according to the preset route using a drone.

[0026] In a possible implementation, before performing three-dimensional reconstruction based on the aerial image and the aerial triangulation result to obtain the target model of the bridge pier to be measured, the method further includes:

[0027] Preprocessing the aerial image to obtain POS information;

[0028] Perform aerial triangulation based on the aerial image and the POS information to obtain the aerial triangulation result.

[0029] The present invention also provides a device for measuring bridge pier surfaces and hole positions based on drone close-up photogrammetry, comprising:

[0030] The reconstruction module is used to perform 3D reconstruction based on aerial images and aerial triangulation results to obtain the target model of the bridge pier to be measured;

[0031] An identification module, configured to identify the hole positions in the target model based on a preset local window and determine a reference point;

[0032] A determination module is used to determine the hole position information and surface information of the pier to be measured based on the relative position of the reference point within the preset local window.

[0033] On the other hand, the present invention also provides an electronic device, comprising a memory and a processor, wherein:

[0034] The memory is used to store programs;

[0035] The processor is coupled to the memory and is used to execute the program stored in the memory to implement the bridge pier surface and hole position measurement method based on drone close-up photogrammetry as described in any of the above implementations.

[0036] On the other hand, the present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the bridge pier surface and hole position measurement method based on drone close-up photogrammetry described in any of the above-mentioned implementation methods.

[0037] The beneficial effects of the present invention are as follows: the bridge pier surface and hole position measurement method provided by the present invention based on drone close-up photogrammetry can obtain all-round and multi-angle aerial images of the bridge pier by using the drone to perform image acquisition on the bridge pier to be measured, and obtain aerial triangulation results based on the aerial images, so as to obtain the target model of the bridge pier to be measured, and identify the hole position according to the preset local window to determine multiple reference points near the hole position, so as to obtain the hole position information and surface information of the bridge pier to be measured according to the relative position of the reference point in the preset local window. Combining the flexibility of the drone and the precision of photogrammetry, it can realize fast and accurate measurement of the bridge pier surface and hole position, which not only improves the measurement efficiency, but also reduces the risk and cost of manual measurement. Compared with traditional manual measurement methods or other measurement methods, it avoids problems such as repeated climbing by personnel and rework of prefabricated parts, provides higher measurement accuracy, data density and operation efficiency, and can be used as a method for obtaining information of bridge pier prefabricated parts and promoted in bridge construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0039] Figure 1 This is a flow chart of one embodiment of a method for measuring bridge pier surfaces and hole positions based on UAV close-up photogrammetry provided by the present invention;

[0040] Figure 2 This is a second method flow chart of an embodiment of the method for measuring bridge pier surface and hole position based on UAV close-up photogrammetry provided by the present invention;

[0041] Figure 3 A schematic diagram of a preset route provided by the present invention;

[0042] Figure 4 The overall texture map of the top of the bridge pier provided by the present invention;

[0043] Figure 5 The overall structural diagram of the top of the bridge pier provided by the present invention;

[0044] Figure 6The partial texture map of the top of the pier provided by the present invention;

[0045] Figure 7 The partial structure diagram of the top of the pier provided by the present invention;

[0046] Figure 8 The schematic diagram of the observation window and reference points provided by the present invention;

[0047] Figure 9 The structural schematic diagram of an embodiment of the pier surface and hole position measuring device based on UAV close-range photogrammetry provided by the present invention;

[0048] Figure 10 The structural schematic diagram of an embodiment of the electronic device provided by the present invention. Specific embodiments

[0049] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present invention.

[0050] In the description of the embodiments of the present invention, unless otherwise specified, the meaning of "plurality" is two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships, for example: A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone.

[0051] The descriptions such as "first" and "second" involved in the embodiments of the present invention are only for descriptive purposes, and cannot be understood as indicating or implying their relative importance or implicitly indicating the quantity of the indicated technical features. Therefore, the technical features defined with "first" and "second" can explicitly or implicitly include at least one such feature.

[0052] Figure 1 One of the method flowcharts of an embodiment of the pier surface and hole position measuring method based on UAV close-range photogrammetry provided by the present invention, as Figure 1 shown, the pier surface and hole position measuring method based on UAV close-range photogrammetry includes:

[0053] S101. Perform three-dimensional reconstruction based on the aerial image and the aerial triangulation result to obtain the target model of the pier to be measured; the aerial image is obtained by the UAV collecting images of the pier to be measured; the aerial triangulation result is determined based on the aerial image;

[0054] S102. Identify the hole positions in the target model based on a preset local window, and determine the reference points;

[0055] S103. Determine the hole position information and surface information of the pier to be measured based on the relative positions of the reference points within the preset local window.

[0056] In S101, perform 3D reconstruction based on the aerial image and aerial triangulation results to obtain the target model of the pier to be measured.

[0057] A drone can be used to collect images of the pier to be measured. The flight path and altitude of the drone can be pre-planned to ensure that all-round and multi-angle images of the pier can be captured.

[0058] Perform aerial triangulation based on the collected aerial image, which involves matching the feature points in the image. By calculating the 3D coordinates of these feature points, an accurate three-dimensional model of the pier to be measured, that is, the target model, can be constructed.

[0059] In S102, identify the hole positions in the target model based on a preset local window, and determine the reference points.

[0060] In the target model, in order to accurately identify the hole positions, a preset local window can be set. The size and position of the preset local window can be determined according to the actual situation of the pier and the distribution characteristics of the hole positions. Then, use the preset local window to identify the holes in the target model. For example, an image detection method based on deep learning can be used for hole position identification. After identifying the hole positions, several reference points can be automatically searched near the hole positions.

[0061] In S103, determine the hole position information and surface information of the pier to be measured based on the relative positions of the reference points within the preset local window.

[0062] Record the relative positions of all reference points in the preset local window, and calibrate the positions in the 3D model to obtain the calibrated positions of the reference points. Then, extract the 3D coordinates of the reference points in the corresponding coordinate system of the 3D model, so as to determine the 3D coordinates of the hole center in the corresponding coordinate system of the target model, that is, obtain the hole position information, and fit the 3D coordinates of the reference points in the corresponding coordinate system of the target model to obtain the shape information, that is, obtain the surface information.

[0063] Compared with the prior art, the embodiment of the present invention provides a method for measuring the surface and hole position of a pier based on close-up photogrammetry using a drone. By using a drone to collect images of the pier to be measured, all-round and multi-angle aerial images of the pier can be obtained, and aerial triangulation is performed based on the aerial images to obtain aerial triangulation results, so that a target model of the pier to be measured can be obtained, and the hole position can be identified according to a preset local window to determine multiple reference points near the hole position, so that the hole position information and surface information of the pier to be measured can be obtained according to the relative positions of the reference points within the preset local window. Combining the flexibility of the drone and the precision of photogrammetry, rapid and accurate measurement of the pier surface and hole position can be achieved, which not only improves the measurement efficiency, but also reduces the risk and cost of manual measurement. Compared with traditional manual measurement methods or other measurement methods, it avoids problems such as repeated climbing by personnel and rework of prefabricated parts, provides higher measurement accuracy, data density and operation efficiency, and can be used as a method for obtaining information on pier prefabricated parts and promoted in bridge construction.

[0064] In some embodiments of the present invention, before performing three-dimensional reconstruction based on the aerial image and the aerial triangulation results to obtain the target model of the bridge pier to be measured, the method further includes:

[0065] Based on the shape and position distribution of the bridge pier to be measured, a preset route of the UAV is determined; the preset routes include: a full-area controlled oblique photography route, a complete column-surrounding photography route, and a high-density photography route close to key parts;

[0066] The aerial image is acquired by collecting images of the bridge pier to be measured according to the preset route using a drone.

[0067] According to the shape and location distribution of the bridge piers to be measured, preset drone routes with multiple levels and shooting densities are planned.

[0068] For example, based on the shape and location distribution of the bridge piers, the following three levels of preset routes can be designed:

[0069] (1) Control the oblique photography route in the entire area.

[0070] Based on camera parameters and pier heights, oblique photogrammetry routes were laid out with a minimum 80% overlap in the heading direction and a minimum 70% overlap in the lateral direction. This ensured full coverage of the surrounding terrain, ensuring the integrity and continuity of the model for the entire survey area. Due to the varying heights of the piers, the resolution requirements for oblique routes were lower; a ground resolution of 3-5 cm was generally sufficient.

[0071] (2) Complete cylindrical photography route.

[0072] Design a surrounding flight path according to the specific shape of each column to achieve full coverage of the shooting angle for the plane orientation of the column and full coverage of the shooting range for the surface and bottom ground of the column, so as to ensure the integrity of each column model. The surrounding flight path has a higher requirement for resolution. The ground resolution should usually be below 1 cm, and it can also be adjusted when the column is relatively high.

[0073] (3) High-density photography flight path for key parts.

[0074] For the areas of interest on the column surface, such as near the prefabricated hole positions and column number markings, etc., use close-range photography to conduct high-density shooting to ensure the fineness of the key areas of the model. The close-range photography is usually within 10 m from the column. Only focus on whether the shooting of the area of interest is fine and whether the coverage is sufficient, without considering issues such as ground connection, etc. This step has the highest requirement for resolution, but the shooting content may not include the ground. Therefore, the resolution relative to the column surface is concerned, which should usually be within 2 mm and at most not exceed 3 mm.

[0075] Control the drone to reach the designated position according to the preset flight path, perform the designated actions, and obtain aerial images with multiple levels and resolutions.

[0076] The method for measuring the surface and hole positions of bridge piers based on drone close-range photogrammetry provided by the embodiments of the present invention determines the preset flight path of the drone according to the shape and position distribution of the bridge piers to be measured. Through the above flight path design, it can not only achieve data coverage of the entire measurement area and all columns, but also obtain sufficient high-resolution images, thus ensuring the balance between model integrity and fineness. In addition, when arranging the flight path, the column height, shape, and the resolution of the used camera should be fully considered to ensure that the overlap degree of the captured images is sufficient and there is no missing shooting angle.

[0077] In some embodiments of the present invention, before performing three-dimensional reconstruction based on the aerial images and the results of aerial triangulation to obtain the target model of the bridge piers to be measured, it further includes:

[0078] Preprocess the aerial images to obtain POS information;

[0079] Perform aerial triangulation based on the aerial images and the POS information to obtain the results of aerial triangulation.

[0080] The preprocessing may include airborne positioning and orientation data processing and image optical consistency processing. After obtaining the aerial images, perform airborne positioning and orientation data processing to obtain POS information. POS information refers to the shooting position and attitude information of each image.

[0081] And perform image optical consistency processing on the aerial images, including the following steps:

[0082] (1)Adjust the exposure value of the image to reduce the brightness difference between the backlight area and the bright area;

[0083] (2)Unify the color styles among images to reduce the differences in color temperature, white balance, and each channel component;

[0084] (3)Adjust the contrast and geometric distortion degree of the image to correctly highlight the features of the photographed object.

[0085] Through the above adjustment methods, the image content can be made correct and the style unified, so as to avoid structural misidentification or texture misalignment during modeling, and ensure the measurable attributes and visual effects of the model. The photos can be pre-classified first and then processed in batches.

[0086] Perform aerial triangulation based on the adjusted original image and POS data, adjust the image control network, and obtain the optimal pose state of each image and the optimal estimation of the camera parameters.

[0087] Thus, three-dimensional reconstruction is carried out according to aerial triangulation and the original aerial images to obtain a high-precision model of the pier to be measured.

[0088] In some embodiments of the present invention, the identification of hole positions in the target model based on a preset local window and determining reference points includes:

[0089] Identifying hole positions in the preset local window based on an object detection method;

[0090] Determining the reference points based on the coordinates of the center of the hole positions in the preset local window.

[0091] An appropriate observation window, that is, a preset local window, can be selected near each group of hole positions in the target model. Hole position information is identified within the window and several reference points are automatically generated.

[0092] Exemplarily, the selection methods for the preset local window and reference points are as follows:

[0093] (1)The observation line of sight should be in the vertical plane and approximately perpendicular to the local surface of the column to reduce the influence of the perspective effect of objects being larger when closer and smaller when farther away;

[0094] (2)The hole positions in the model should be symmetrically distributed up and down about the center of the window, and the connecting line of the upper and lower boundaries should not exceed 2 / 3 of the height of the window to ensure the stability of point position identification;

[0095] (3)Select an object detection method based on deep learning such as the YOLO series or the RCNN series to identify hole positions in the window and extract the coordinates of the center of the hole positions in the two-dimensional window;

[0096] (4) Automatically search for several reference points near the hole positions according to the recognition results. The reference points should be located in the relatively flat areas around the hole positions on the column facade, evenly distributed and with a high density. There should be at least 8 points around each hole position, and at least 5 points on the line connecting every two hole positions. Record the relative positions of all the points in the two-dimensional window and calibrate them in the three-dimensional model.

[0097] In some embodiments of the present invention, determining the hole position information and surface information of the pier to be measured based on the relative positions of the reference points in the preset local window includes:

[0098] Calibrate the relative positions in the target model to obtain the calibrated positions of the reference points:

[0099] Based on the calibrated positions, extract the three-dimensional coordinates of the reference points in the coordinate system corresponding to the target model;

[0100] Based on the three-dimensional coordinates of the reference points in the coordinate system corresponding to the target model, determine the hole position information; the hole position information includes the three-dimensional coordinates of the hole center in the coordinate system corresponding to the target model;

[0101] Fit the three-dimensional coordinates of the reference points in the coordinate system corresponding to the target model to obtain the surface information.

[0102] In some embodiments of the present invention, determining the hole position information based on the three-dimensional coordinates of the reference points in the coordinate system corresponding to the target model includes:

[0103] Based on the three-dimensional coordinates of the reference points in the coordinate system corresponding to the target model, use the least squares-based distance weighted interpolation method or surface fitting method to optimally estimate the coordinates of the hole center and determine the hole position information.

[0104] Extract the three-dimensional coordinates of the reference points based on the model data corresponding to the two-dimensional window image for calculating the coordinates of the hole center position and extracting the surface information of the column. [[ID=2,5]]

[0105] Based on the calibrated positions of the reference points obtained in the previous steps, extract the three-dimensional coordinates of all points in the independent coordinate system of the model. Combining the position relationship in the two-dimensional window, use methods such as least squares-based distance weighted interpolation or surface fitting to optimally estimate the coordinates of the hole center and obtain the three-dimensional coordinates of the hole center in the coordinate system corresponding to the target model.

[0106] The reason for this is that there are often protrusions or depressions at the hole positions in the model, making it difficult to directly collect the correct coordinates at the hole center. While the surrounding reference points are relatively flat, which can be used to represent the shape of the column surface and also for fitting and calculating the coordinates of the hole center.

[0107] In some embodiments of the present invention, after determining the hole position information and surface information of the pier to be measured based on the relative position of the reference point within the preset local window, the following steps are further included:

[0108] Register the three-dimensional coordinates of the hole center in the coordinate system corresponding to the target model with the prefabricated hole center coordinates in the preset scheme to determine the relative relationship between the coordinate system corresponding to the target model and the coordinate system corresponding to the preset scheme;

[0109] Based on the relative relationship, determine the difference between the prefabricated hole position and the hole position.

[0110] Register the measured point positions in the model coordinate system with the prefabricated hole center coordinates in the preset scheme to obtain the relative relationship between the two coordinate frames, namely the relative relationship between the coordinate system corresponding to the target model and the coordinate system corresponding to the preset scheme.

[0111] According to the hole center position coordinates obtained in the previous steps, find the corresponding hole position coordinates in the pier construction design drawing. The scale parameters of these two coordinate systems are the same, but there are relative rotation and translation. Therefore, establish a mathematical model of rotation + translation for the two coordinate systems. Based on the two sets of homologous coordinate sequences collected, perform parameter estimation based on the least squares principle to achieve the alignment of the two coordinate frames, which is convenient for calculating the hole position deviation. Certain constraint conditions or robust models can be added during the estimation to avoid the influence of hole positions with large deviations from the design position on the registration result.

[0112] Based on the registered coordinate frames, count the difference between the actual position and the design position of each prefabricated hole and determine whether the deviation value exceeds the limit.

[0113] Thus, provide prefabrication suggestions according to the deviation value, provide column shape information based on the key point coordinates on the column surface, provide hole position distribution information based on the hole position deviation statistical results, and provide design suggestions for prefabricated parts based on the above information.

[0114] Exemplarily, the following prefabrication suggestions can be provided:

[0115] (1) Based on the point position measurement and coordinate registration in the previous steps, the three-dimensional coordinates of each prefabricated hole position on the column in the coordinate system of the preset scheme and its deviation value relative to the design position can be obtained;

[0116] (2) By fitting the reference point coordinates in the region of interest, the surface shape information of this region can be obtained;

[0117] (3) Based on the hole position deviation and column surface shape, provide the reference manufacturing dimensions and shapes of prefabricated parts such as hanging bars.

[0118] The pier surface and hole position measurement method based on UAV close-range photogrammetry provided by the embodiments of the present invention proposes a method for measuring the column surface shape and hole position deviation based on an independent column coordinate system. Since it focuses on relative positions and relative shapes, it is possible to measure millimeter-level relative information on a high-precision model without relying on external control points or target points for absolute coordinate correction.

[0119] Compared with traditional manual measurement methods or other measurement methods, the pier surface and hole position measurement method based on UAV close-range photogrammetry provided by the embodiments of the present invention avoids problems such as repeated climbing of personnel and rework of prefabricated components, and provides higher measurement accuracy, data density, and operation efficiency. It can be used as a way to obtain pier prefabrication information and be promoted in bridge construction.

[0120] The embodiments of the present invention are based on UAV close-range photogrammetry technology and image recognition technology. The following will describe in detail the pier surface and hole position measurement method based on UAV close-range photogrammetry provided by the present invention in combination with specific scenarios. Figure 2 This is the second flowchart of the method for an embodiment of the pier surface and hole position measurement method based on UAV close-range photogrammetry provided by the present invention. As Figure 2 shown, it shows a typical implementation process, which specifically includes the following steps:

[0121] Step 1, flight route planning: According to the shape and position distribution of the pier to be measured, plan 3 levels of preset UAV flight routes. Figure 3 This is a schematic diagram of the preset flight route provided by the present invention. As Figure 3 shown, from top to bottom are the oblique flight route, the circumferential flight route, and the close-range flight route, and their design principles have been introduced in the invention content.

[0122] In the embodiments of the present invention: the column height is about 10m;

[0123] The relative flight height of the oblique flight route is 100m, and the ground resolution is about 1.3cm;

[0124] The relative flight height of the circumferential flight route is 30m, and the ground resolution is about 3.8mm;

[0125] The distance of the close-range flight route from the pier surface is about 5 - 10m, and the corresponding resolution on the pier surface is 0.6 - 1.2mm;

[0126] All of the above meet the requirements for image resolution.

[0127] Step 2, implementation of flight tasks.

[0128] Control the UAV to reach the designated position for shooting according to the above preset flight path. To ensure the image quality, the optimal choice is a cloudy day with sufficient light to avoid weak texture in the shadow area. Secondly, it is the time around noon on a sunny day to reduce the area of the shadow area caused by the solar altitude angle.

[0129] Step 3. Data preprocessing.

[0130] Step 3.1. According to the airborne positioning and attitude data, obtain the POS information corresponding to each image based on RTK or PPK technology.

[0131] Step 3.2. Check and adjust the brightness, contrast, hue, etc. of the UAV images to make the target clear, the gloss uniform, weaken the color difference between photos, and highlight the target features.

[0132] Step 4. Aerotriangulation.

[0133] Establish a unified block for multiple continuous column regions in the embodiment. Combine the POS information and camera parameters, perform aerotriangulation on all the original images in the block, and use the bundle adjustment method for regional network adjustment to obtain the optimal pose state of each image and the optimal estimation of the camera parameters.

[0134] Step 5. Modeling.

[0135] Perform high-precision 3D reconstruction on the designated area in the block. Since the image density is large, the memory occupation of unified modeling is too large, and modeling can be performed by partitioning or by column, and the model quality is checked. Figures 4 to 7 Shows a high-precision 3D model of the top of a pier in the embodiment, where Figure 4 is the overall texture map of the top of the pier provided by the present invention, Figure 5 is the overall structure map of the top of the pier provided by the present invention, Figure 4 and 5 correspond to the same area. Figure 6 is the partial texture map of the top of the pier provided by the present invention, Figure 7 is the partial structure map of the top of the pier provided by the present invention, Figure 6 and 7 correspond to the same area.

[0136] There are many types of aerotriangulation and modeling software on the market, such as DJI Terra, ContextCapture, Reconstruction Master, Metashape, etc. As long as the model effect is normal, they can all be used. Reconstruction Master is selected in the embodiment, which can automatically complete the image optical consistency adjustment in step 3.2 and simplify the process.

[0137] Step 6. Selection of local window and reference points.

[0138] Select an appropriate observation window near each group of hole positions in the model. Call the deep learning algorithm within the window to identify the hole position information, and automatically generate several reference points around it.

[0139] In the embodiment, the YOLOv8 model is selected, and a total of 3 loss functions in 2 parts are mainly used for the target detection task:

[0140] 1. Regression loss.

[0141] (1) Distribution Focal Loss (DFL), calculates the offsets of the center point of the anchor point to the upper left corner and the lower right corner.

[0142]

[0143] Among them, 、 are the predicted values and adjacent predicted values output by the network, 、 、 are the actual values, integral values and adjacent integral values of the label. The specific conversion process is: y = the distance of the center from a certain side / the current downsampling factor.

[0144] (2) IoU Loss localization loss, using CIoU loss, only calculates the localization loss of positive samples, and is a metric to measure the overlap degree between the predicted bounding box and the true bounding box.

[0145]

[0146]

[0147]

[0148] In the formula, and respectively represent the prediction and the actual situation, 、 and respectively represent the center, width and height of the corresponding bounding box, is the diagonal distance of the bounding box, is the Euclidean distance between the center coordinates of the two boxes, is the original Intersection over Union (IoU).

[0149] 2. Classification loss.

[0150] (1) The classification loss uses Binary CrossEntropy Loss (BCE loss), and only calculates the classification loss of positive samples;

[0151]

[0152] Wherein, is the number of samples, is the true label of the th sample, and is the probability that the

[0153] Figure 8 th sample predicted by the model is a positive class. The BCE Loss can measure the gap between the probability distribution predicted by the model and the actual observed labels. Figure 8 As shown, the model structures near all reference points have been checked and confirmed to be flat.

[0154] Step 7: Measurement of the target point position.

[0155] Based on the model data corresponding to the two-dimensional window image, the three-dimensional coordinates of the reference points are extracted, and then the coordinates of the hole center position are estimated by methods such as distance weighted interpolation or surface fitting. Repeat this process until all the hole positions on each cylinder are measured.

[0156] A distance interpolation method used in the embodiment is:

[0157]

[0158] Wherein, etc. represent a set of hole center coordinates interpolated from a pair of reference points, is the weight assigned to it, which can be weighted according to the distance. The coordinates of a hole position are calculated from at least 4 pairs of reference points in different directions.

[0159] The estimation criterion for the registration parameters is:

[0160]

[0161] The parameter calculation steps include:

[0162] (1) Calculate the centroids of the two sets of point clouds and , and translate them to the centroid coordinate system;

[0163] (2) Calculate the covariance matrix:

[0164]

[0165] (3) Perform SVD decomposition on the matrix to obtain and :

[0166]

[0167] (4) Estimate the rotation matrix:

[0168]

[0169] (5) Estimate the translation:

[0170]

[0171] If there are large deviations in the hole positions during implementation, an outlier rejection strategy can be adopted to eliminate gross errors.

[0172] Step 9: Statistical analysis of point position deviation: Based on the registration results of the coordinate frame, the coordinates of each prefabricated hole collected are converted into the design coordinate system to obtain the difference from the design coordinates, and it is determined whether the deviation value exceeds the limit. The determination method needs to be formulated in combination with actual requirements. The determination criterion in the embodiment is 1 cm.

[0173] Step 10: Provide prefabrication suggestions: Based on the statistical results of the hole position deviation, suggestions for fabricating prefabricated parts such as hanging brackets can be provided. For the hole positions with deviation values exceeding the limit, the true shape between two hole positions can be provided in combination with the reference points on the column surface.

[0174] The present invention combines the technologies of UAV close-range photogrammetry, computer vision 3D reconstruction, and image recognition based on deep learning, and proposes a method for measuring the surface shape and prefabricated hole positions of bridge piers. Its direct purpose is to optimize the fabrication and installation process of bridge pier prefabricated parts, avoid repeated climbing caused by manual trial and error, and improve construction efficiency. At the same time, high-precision and high-density data of the bridge pier surface shape can be provided for the quality inspection of bridge pier construction, etc.

[0175] In order to better implement the method for measuring the surface and hole positions of bridge piers based on UAV close-range photogrammetry in the embodiments of the present invention, on the basis of the method for measuring the surface and hole positions of bridge piers based on UAV close-range photogrammetry, the embodiments of the present invention also provide a device for measuring the surface and hole positions of bridge piers based on UAV close-range photogrammetry. Figure 9 For a structural schematic diagram of an embodiment of the device for measuring the surface and hole positions of bridge piers based on UAV close-range photogrammetry provided by the present invention, as Figure 9 shown, the device 900 for measuring the surface and hole positions of bridge piers based on UAV close-range photogrammetry includes:

[0176] A reconstruction module 910, configured to perform 3D reconstruction based on aerial images and aerial triangulation results to obtain a target model of the bridge pier to be measured;

[0177] An identification module 920, configured to identify the hole positions in the target model based on a preset local window and determine reference points;

[0178] A determination module 930, configured to determine the hole position information and surface information of the pier to be measured based on the relative positions of the reference points within the preset local window.

[0179] The pier surface and hole position measuring device 900 based on UAV close-range photogrammetry provided in the above embodiments can implement the technical solutions described in the embodiments of the pier surface and hole position measuring method based on UAV close-range photogrammetry. The specific implementation principles of the above modules or units can be referred to the corresponding content in the embodiments of the pier surface and hole position measuring method based on UAV close-range photogrammetry, which will not be elaborated here.

[0180] As Figure 10 shown, the present invention also correspondingly provides an electronic device 1000. The electronic device 1000 includes a processor 1001, a memory 1002, and a display 1003. Figure 10 Only some components of the electronic device 1000 are shown, but it should be understood that it is not required to implement all the shown components, and more or fewer components can be alternatively implemented.

[0181] In some embodiments, the processor 1001 may be a central processing unit (CPU), a microprocessor, or other data processing chips, configured to run the program code stored in the memory 1002 or process data, such as the pier surface and hole position measuring method based on UAV close-range photogrammetry in the present invention.

[0182] In some embodiments, the processor 1001 may be a single server or a server group. The server group may be centralized or distributed. In some embodiments, the processor 1001 may be local or remote. In some embodiments, the processor 1001 may be implemented on a cloud platform. In some embodiments, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a distributed cloud, an internal cloud, a multi-cloud, etc., or any combination of the above.

[0183] In some embodiments, the memory 1002 may be an internal storage unit of the electronic device 1000, such as the hard disk or memory of the electronic device 1000. In some other embodiments, the memory 1002 may also be an external storage device of the electronic device 1000, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the electronic device 1000.

[0184] Furthermore, the memory 1002 may include both the internal storage unit of the electronic device 1000 and external storage devices. The memory 1002 is used to store the application software installed in the electronic device 1000 and various types of data.

[0185] In some embodiments, the display 1003 may be an LED display, a liquid crystal display, a touch liquid crystal display, an organic light-emitting diode (OLED) touch screen, etc. The display 1003 is used to display the information in the electronic device 1000 and to display a visual user interface. The components 1001 - 1003 of the electronic device 1000 communicate with each other through the system bus.

[0186] In one embodiment, when the processor 1001 executes the pier surface and hole position measurement program based on UAV close-range photogrammetry in the memory 1002, the following steps can be achieved:

[0187] Perform three-dimensional reconstruction based on the aerial image and the aerial triangulation result to obtain the target model of the pier to be measured; the aerial image is obtained by the UAV collecting images of the pier to be measured; the aerial triangulation result is determined based on the aerial image;

[0188] Identify the hole positions in the target model based on a preset local window to determine the reference points;

[0189] Determine the hole position information and surface information of the pier to be measured based on the relative positions of the reference points within the preset local window.

[0190] It should be understood that when the processor 1001 executes the pier surface and hole position measurement program based on UAV close-range photogrammetry in the memory 1002, in addition to the above functions, other functions can also be achieved. For details, refer to the description of the corresponding method embodiments above.

[0191] Furthermore, the embodiments of the present invention do not specifically limit the type of the mentioned electronic device 1000. The electronic device 1000 may be a mobile phone, a tablet computer, a personal digital assistant (PDA), a wearable device, a laptop computer, or other portable electronic devices. Exemplary embodiments of the portable electronic device include, but are not limited to, portable electronic devices equipped with IOS, android, microsoft, or other operating systems. The above-mentioned portable electronic devices may also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (such as a touch panel). It should also be understood that in some other embodiments of the present invention, the electronic device 1000 may not be a portable electronic device, but a desktop computer with a touch-sensitive surface (such as a touch panel).

[0192] Correspondingly, the embodiments of the present invention also provide a computer-readable storage medium. The computer-readable storage medium is used to store computer-readable programs or instructions. When the programs or instructions are executed by a processor, the steps or functions in the method for measuring the surface and hole positions of a bridge pier based on close-range photogrammetry by an unmanned aerial vehicle provided in the above method embodiments can be implemented.

[0193] Those skilled in the art can understand that all or part of the processes of implementing the above method embodiments can be completed by instructing relevant hardware (such as a processor, a controller, etc.) through a computer program. The computer program can be stored in a computer-readable storage medium. Among them, the computer-readable storage medium is a magnetic disk, an optical disk, a read-only memory, or a random access memory, etc.

[0194] The method for measuring the surface and hole positions of a bridge pier based on close-range photogrammetry by an unmanned aerial vehicle provided by the present invention has been introduced in detail above. Specific examples are used in this article to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those skilled in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A method for measuring bridge pier surface and hole position based on UAV close-up photogrammetry, characterized in that: include: Performing three-dimensional reconstruction based on aerial images and aerial triangulation results to obtain a target model of the bridge pier to be measured; the aerial images are obtained by capturing images of the bridge pier to be measured by a drone; and the aerial triangulation results are determined based on the aerial images; Identify the hole positions in the target model based on a preset local window and determine reference points; the reference points are located in a flat area around the hole positions, and at least 8 reference points are distributed for each hole position; Determining hole position information and surface information of the bridge pier to be measured based on the relative position of the reference point within the preset local window; The determining of the hole position information and surface information of the pier to be measured based on the relative position of the reference point within the preset local window includes: The relative position is calibrated on the target model to obtain the calibrated position of the reference point: Based on the calibrated position, extracting the three-dimensional coordinates of the reference point in the coordinate system corresponding to the target model; Determine the hole position information based on the three-dimensional coordinates of the reference point in the coordinate system corresponding to the target model; the hole position information includes the three-dimensional coordinates of the hole position center in the coordinate system corresponding to the target model; The three-dimensional coordinates of the reference point in the corresponding coordinate system of the target model are fitted to obtain the surface information.

2. The method for measuring bridge pier surface and hole position based on UAV close-up photogrammetry according to claim 1 is characterized in that: The identifying the hole positions in the target model based on the preset local window and determining the reference points includes: Identifying the hole position in the preset local window based on a target detection method; The reference point is determined based on the coordinates of the center of the hole position in the preset local window.

3. The method for measuring bridge pier surface and hole position based on UAV close-up photogrammetry according to claim 1 is characterized in that: The determining of the hole position information based on the three-dimensional coordinates of the reference point in the coordinate system corresponding to the target model includes: Based on the three-dimensional coordinates of the reference point in the corresponding coordinate system of the target model, the coordinates of the hole center are optimally estimated using a distance weighted interpolation method based on least squares or a surface fitting method to determine the hole information.

4. The method for measuring bridge pier surface and hole position based on UAV close-up photogrammetry according to claim 1 is characterized in that: After determining the hole position information and surface information of the bridge pier to be measured based on the relative position of the reference point within the preset local window, the method further includes: Aligning the three-dimensional coordinates of the hole center in the target model's corresponding coordinate system with the prefabricated hole center coordinates in the preset solution, and determining the relative relationship between the target model's corresponding coordinate system and the preset solution's corresponding coordinate system; Based on the relative relationship, a difference between the prefabricated hole position and the hole position is determined.

5. The method for measuring bridge pier surface and hole position based on UAV close-up photogrammetry according to claim 1 is characterized in that: Before performing three-dimensional reconstruction based on the aerial image and the aerial triangulation results to obtain the target model of the bridge pier to be measured, the method further includes: Based on the shape and position distribution of the bridge pier to be measured, a preset route of the UAV is determined; the preset routes include: a full-area controlled oblique photography route, a complete column-surrounding photography route, and a high-density photography route close to key parts; The aerial image is acquired by collecting images of the bridge pier to be measured according to the preset route using a drone.

6. The method for measuring bridge pier surface and hole position based on UAV close-up photogrammetry according to claim 1 is characterized in that: Before performing three-dimensional reconstruction based on the aerial image and the aerial triangulation results to obtain the target model of the bridge pier to be measured, the method further includes: Preprocessing the aerial image to obtain POS information; Perform aerial triangulation based on the aerial image and the POS information to obtain the aerial triangulation result.

7. A device for measuring bridge pier surface and hole position based on drone close-up photogrammetry, characterized in that: include: The reconstruction module is used to perform 3D reconstruction based on aerial images and aerial triangulation results to obtain the target model of the bridge pier to be measured; An identification module is used to identify the hole positions in the target model based on a preset local window and determine reference points; the reference points are located in a flat area around the hole positions, and at least 8 reference points are distributed for each hole position; a determination module, configured to determine hole position information and surface information of the pier to be measured based on the relative position of the reference point within the preset local window; The determining of the hole position information and surface information of the pier to be measured based on the relative position of the reference point within the preset local window includes: The relative position is calibrated on the target model to obtain the calibrated position of the reference point: Based on the calibrated position, extracting the three-dimensional coordinates of the reference point in the coordinate system corresponding to the target model; Determine the hole position information based on the three-dimensional coordinates of the reference point in the coordinate system corresponding to the target model; the hole position information includes the three-dimensional coordinates of the hole position center in the coordinate system corresponding to the target model; The three-dimensional coordinates of the reference point in the corresponding coordinate system of the target model are fitted to obtain the surface information.

8. An electronic device, characterized in that: comprising a memory and a processor, wherein, The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the bridge pier surface and hole position measurement method based on drone close-up photogrammetry as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for measuring bridge pier surfaces and hole positions based on drone close-up photogrammetry as described in any one of claims 1 to 6 is implemented.

Images