Method for determining absolute coordinate and scale of object, electronic equipment and storage medium

Abstract

The invention provides a method for determining absolute coordinates and scale of an object, electronic equipment and a storage medium. The method comprises the following steps: arranging a checkerboard calibration plate with a preset specification in a target area, wherein the checkerboard calibration plate can be observed under a plurality of views shot by a camera; acquiring coordinates of all angular points of the checkerboard calibration plate in an east-north-sky coordinate system; acquiring images of all angular points through the camera, enabling the images to correspond to coordinates of an east-north-sky coordinate system, and calculating to obtain an initial pose of the camera in the east-north-sky coordinate system; according to the initial pose and the coordinate, a scale factor is calculated, and the scale factor is used for synchronizing the image size and the coordinate size of the object in the target area; performing multi-view three-dimensional reconstruction on the target area by utilizing a feature extraction and matching algorithm and combining the initial pose and the scale factor to obtain a three-dimensional point cloud of an object in the target area; and obtaining absolute coordinates and scale information of the object in the target area based on the three-dimensional point cloud.

Description

Technical Field

[0001] The present invention relates to the technical field of three-dimensional reconstruction, and in particular to a method for determining the absolute coordinates and scale of an object, an electronic device and a storage medium. Background Art

[0002] In the field of computer vision and 3D reconstruction technology, multi-view Figure 3 3D reconstruction technology is an important technical means, which collects images of the target object from multiple perspectives and uses the correlation information between images to restore the 3D structure of the object. Figure 3 3D reconstruction methods can only restore the relative scale and shape of an object, but cannot accurately obtain its absolute coordinates and scale information in the real world. This limitation greatly restricts the reconstruction results in practical applications.

[0003] In order to overcome this problem, in recent years, researchers have begun to explore the integration of other measurement techniques with multi-view Figure 3 Among them, GNSS RTK technology and total station measurement technology have attracted much attention because they can provide high-precision absolute coordinate information. However, how to combine these technologies with traditional multi-view Figure 3 How to effectively integrate three-dimensional reconstruction algorithms to achieve high-precision and high-efficiency three-dimensional reconstruction remains an urgent problem to be solved.

[0004] In view of this situation, the present invention proposes a method for multi-viewing Figure 3 This method cleverly combines GNSS RTK technology, total station measurement technology, and traditional multi-view Figure 3 The 3D reconstruction algorithm not only achieves high-precision 3D reconstruction of buildings, but also accurately determines their absolute coordinates and scale information in the northeast celestial coordinate system. This innovative method is expected to open up new horizons for the application of 3D reconstruction technology and promote the further development of computer vision and 3D reconstruction technology. Summary of the invention

[0005] The embodiments of the present disclosure aim to solve at least one of the technical problems existing in the prior art, and provide a method, electronic equipment and storage medium for determining the absolute coordinates and scale of an object. By arranging a checkerboard calibration plate of preset specifications in the target area and combining camera images, camera poses and optimization algorithms, the scale factor is accurately calculated, and ultimately three-dimensional point cloud reconstruction of objects in the target area and accurate measurement of absolute coordinates are achieved, which significantly improves the measurement accuracy of the object position and scale.

[0006] In a first aspect of the present disclosure, a method for determining the absolute coordinates and scale of an object is provided, the method comprising:

[0007] Arranging a checkerboard calibration plate of preset specifications in the target area, wherein the checkerboard calibration plate can be observed in multiple views captured by the camera;

[0008] Obtaining the coordinates of all corner points of the chessboard calibration plate in the northeast celestial coordinate system;

[0009] The camera acquires images of all corner points and corresponds them to the northeast celestial coordinate system, and calculates the initial position and posture of the camera in the northeast celestial coordinate system;

[0010] Calculating a scale factor according to the initial pose and the coordinates, wherein the scale factor is used to synchronize the image size and the coordinate size of the object in the target area;

[0011] Using a feature extraction and matching algorithm, combined with the initial pose and scale factor, a multi-view stereoscopic three-dimensional reconstruction is performed on the target area to obtain a three-dimensional point cloud of the object in the target area;

[0012] Based on the three-dimensional point cloud, the absolute coordinates and scale information of the object in the target area are obtained.

[0013] In combination with the first aspect, the length of the checkerboard calibration plate is less than 90 cm, the width is less than 70 cm, and each cell in the checkerboard calibration plate is a rectangle.

[0014] In combination with the first aspect, obtaining the coordinates of all corner points of the checkerboard calibration plate in the northeast celestial coordinate system includes:

[0015] Select three points within the preset range of the target area that can receive global satellite navigation system signals and are not collinear;

[0016] The first point is taken as the origin, the second point is taken as the first control point, and the third point is taken as the second control point, and the coordinates of the three points in the WGS84 rectangular coordinate system and the WGS84 geodetic coordinate system are determined by using the global satellite navigation system; the coordinates of the first control point and the second control point in the northeast celestial coordinate system are calculated according to the coordinates of the origin in the WGS84 rectangular coordinate system and the coordinates in the WGS84 geodetic coordinate system;

[0017] The coordinates of all corner points in the northeast celestial coordinate system are obtained according to the coordinates of the first control point and the second control point in the northeast celestial coordinate system.

[0018] In combination with the first aspect, the coordinates of the first control point and the second control point in the northeast celestial coordinate system are calculated according to the coordinates of the origin in the WGS84 rectangular coordinate system and the coordinates in the WGS84 geodetic coordinate system using the following formula:

[0019]

[0020] Among them, the coordinates of the origin in the WGS84 rectangular coordinate system are (x0, y0, z0), and the coordinates in the WGS84 geodetic coordinate system are (lon0, lat0, alt0); the coordinates of the first control point or the second control point in the WGS84 rectangular coordinate system are (x, y, z), and the coordinates in the northeast celestial coordinate system are (e, n, u).

[0021] In combination with the first aspect, the coordinates of all corner points in the northeast celestial coordinate system are obtained according to the coordinate measurement of the first control point and the second control point in the northeast celestial coordinate system, including:

[0022] Setting a total station at the first control point, setting a prism at the second control point, setting up a station for measurement, and associating the total station with the northeast celestial coordinate system;

[0023] The positions of all corner points are measured in sequence by the total station to obtain the coordinates of all corner points in the northeast celestial coordinate system. In combination with the first aspect, the calculation obtains the initial position of the camera in the northeast celestial coordinate system using the following formula:

[0024]

[0025] Among them, [e i ,n i ,u i ] T For a corner point P i The coordinates in the northeast sky coordinate system, [pu i ,pv i ] T The pixel coordinates of its projection in the image, s i is the scale factor, K is the camera intrinsic parameter matrix, and T is the camera's position in the northeast celestial coordinate system.

[0026] In combination with the first aspect, calculating the scale factor includes:

[0027] The error function is established by the following formula:

[0028]

[0029] Among them, E i is the error function, P i The predicted pixel coordinates projected in the image, U i P i The pixel coordinate observations projected in the image;

[0030] The error function is solved by least squares to obtain the scale factor, and the solution formula is as follows:

[0031]

[0032] Among them, s1, s2, …, sn is a set of scale factors.

[0033] In combination with the first aspect, performing multi-view stereoscopic 3D reconstruction on the target area to obtain a 3D point cloud of the object in the target area includes:

[0034] Acquire multiple images of the target area at an initial position of the camera;

[0035] Extract feature points from each image and match them with feature points in other images;

[0036] Obtaining a first three-dimensional point cloud of the object in the target area by triangulation according to the matched feature points;

[0037] According to the first three-dimensional point cloud, an image is corrected and matched to obtain a disparity map, and image coordinates are converted into three-dimensional coordinates according to the disparity map and camera parameters to obtain a second three-dimensional point cloud;

[0038] The second three-dimensional point cloud is subjected to Delaunay triangulation to obtain a third three-dimensional point cloud.

[0039] According to a second aspect of the present disclosure, there is provided an electronic device, comprising:

[0040] one or more processors;

[0041] A storage unit is used to store one or more programs, which, when executed by the one or more processors, enable the one or more processors to implement any of the above-mentioned methods for determining the absolute coordinates and scale of an object.

[0042] According to a third aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored, characterized in that when the computer program is executed by a processor, it can implement any of the above-mentioned methods for determining the absolute coordinates and scale of an object. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A flowchart of a method for determining the absolute coordinates and scale of an object according to an embodiment of the present disclosure;

[0044] Figure 2 for Figure 1 Schematic diagram of the process of step S102;

[0045] Figure 3 Schematic diagram of determining the coordinates of the corner points of the chessboard calibration plate for the total station;

[0046] Figure 4It is a schematic diagram of the structure of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0047] Here, exemplary embodiments are described in detail, and examples thereof are shown in the accompanying drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementations described in the following exemplary embodiments do not represent all implementations consistent with the embodiments of the present disclosure.

[0048] The terms used in the disclosed embodiments are only for the purpose of describing specific embodiments and are not intended to limit the disclosed embodiments. The singular forms of "a", "said" and "the" used in the disclosed embodiments and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0049] It should be understood that although the terms first, second, third, etc. may be used to describe various information in the disclosed embodiments, these information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of the disclosed embodiments, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0050] like Figure 1 FIG. 1 is a flow chart of a method for determining the absolute coordinates and scale of an object according to an embodiment of the present disclosure. The method comprises the following steps:

[0051] S101: arranging a checkerboard calibration plate of a preset specification in a target area, wherein the checkerboard calibration plate can be observed in multiple views captured by a camera;

[0052] S102: Obtaining coordinates of all corner points of the checkerboard calibration plate in the northeast celestial coordinate system;

[0053] S103: Acquire images of all corner points through the camera and correspond them to the coordinates of the northeast celestial coordinate system, and calculate the initial position and posture of the camera in the northeast celestial coordinate system;

[0054] S104: Calculating a scale factor according to the initial posture and the coordinates, where the scale factor is used to synchronize the image size and coordinate size of the object in the target area;

[0055] S105: Using a feature extraction and matching algorithm, combined with the initial pose and scale factor, perform multi-view stereoscopic 3D reconstruction on the target area to obtain a 3D point cloud of the object in the target area;

[0056] S106: Based on the three-dimensional point cloud, obtain the absolute coordinates and scale information of the object in the target area.

[0057] Refer to the following Figure 2-Figure 4 The method is described in detail.

[0058] The chessboard calibration plate has a length of less than 90 cm and a width of less than 70 cm, and each cell in the chessboard calibration plate is a rectangle.

[0059] Specifically, the length of the calibration plate is limited to less than 90 cm and the width is less than 70 cm. This size design is to enable the calibration plate to be used in a small or restricted space, such as a narrow corridor or a small indoor environment.

[0060] Each cell in the calibration plate is rectangular, preferably square (with a side length of 10 cm), so that the calibration plate can still provide stable corner point information under different shooting conditions.

[0061] refer to Figure 2 ,for Figure 1 Schematic diagram of the process of step S102. It includes:

[0062] S201: Select three points within a preset range of the target area that can receive global satellite navigation system signals and are not collinear;

[0063] S202: taking the first point as the origin, the second point as the first control point, and the third point as the second control point, and using the global satellite navigation system to determine the coordinates of the three points in the WGS84 rectangular coordinate system and the WGS84 geodetic coordinate system;

[0064] S203: Calculate the coordinates of the first control point and the second control point in the northeast celestial coordinate system according to the coordinates of the origin in the WGS84 rectangular coordinate system and the coordinates in the WGS84 geodetic coordinate system;

[0065] S204: Obtain coordinates of all corner points in the northeast celestial coordinate system according to the coordinates of the first control point and the second control point in the northeast celestial coordinate system.

[0066] Specifically, first, by associating the total station's measurement data with the Northeast-Sky coordinate system (a three-dimensional Cartesian coordinate system with east, north, and sky as axes), the measurement data can be accurately located in a known, standardized geographic coordinate system. This helps to accurately compare or integrate field measurement results with other surveying and mapping data or maps.

[0067] After the total station is set up at the first control point, the total station's own coordinate system can be calibrated by aligning it with the known coordinate system (the northeast sky coordinate system) so that the angles, distances and other data it measures directly correspond to the northeast sky coordinate system. This calibration ensures that subsequent measurements can accurately locate the true geographic location. Then, select three points at random from the open and unobstructed area around the target object (the spacing between the three points is not less than 10m, and the three points are not collinear), the first point as the origin, the second point as the first control point, and the third point as the second control point. These three points will be used to define the reference frame of the northeast sky coordinate system.

[0068] Then, the coordinates of the first control point and the second control point in the Northeast Sky coordinate system are calculated by using the known coordinates of the origin in the WGS84 rectangular coordinate system and the WGS84 geodetic coordinate system. This step requires converting the coordinates of the WGS84 rectangular coordinate system to the coordinates of the Northeast Sky coordinate system, which can be completed through mathematical conversion formulas, such as using the matrix transformation of the rectangular coordinate system to the Northeast Sky coordinate system.

[0069] Finally, based on the calculated northeast celestial coordinates of the two control points, the total station is used to measure the coordinates of all other corner points on the chessboard calibration plate in the northeast celestial coordinate system.

[0070] The coordinates of the first control point and the second control point in the northeast celestial coordinate system are calculated according to the coordinates of the origin in the WGS84 rectangular coordinate system and the coordinates in the WGS84 geodetic coordinate system using the following formula:

[0071]

[0072] Among them, the coordinates of the origin in the WGS84 rectangular coordinate system are (x0, y0, z0), and the coordinates in the WGS84 geodetic coordinate system are (lon0, lat0, alt0); the coordinates of the first control point or the second control point in the WGS84 rectangular coordinate system are (x, y, z), and the coordinates in the northeast celestial coordinate system are (e, n, u).

[0073] This matrix describes the rotation process from the WGS84 rectangular coordinate system to the Northeastern Celestial coordinate system. Each column of the matrix corresponds to the projection of the east, north, and celestial directions of the new coordinate system (the Northeastern Celestial coordinate system) relative to the global coordinate system (WGS84 rectangular coordinate system). Through matrix multiplication, the difference in the global coordinate system is projected into the local coordinate system.

[0074] Furthermore, the coordinates of all corner points in the northeast celestial coordinate system are obtained according to the coordinate measurement of the first control point and the second control point in the northeast celestial coordinate system.

[0075] refer to Figure 3 , a schematic diagram of the coordinates of the chessboard corner points determined by the total station

[0076] A total station is a high-precision measuring instrument, usually used to measure the distance, angle and height difference between two points. Here, the total station is set on the first control point, which has obtained the coordinates in the northeast celestial coordinate system through the above steps.

[0077] Second control point to set the prism: The prism is set at the second control point as the backsight point. The prism is used in conjunction with a total station, which can measure the precise position of the prism by emitting a laser and detecting the beam reflected back from the prism.

[0078] The process of station measurement involves aligning the total station with the Northeastern Sky coordinate system so that all data during the measurement can be associated with this coordinate system. This process ensures that the data measured by the total station can be accurately converted into coordinates in the Northeastern Sky coordinate system.

[0079] Total station calibration: When performing station measurement, it is necessary to ensure that the position of the total station at the first control point and its measured angle and orientation are consistent with the northeast celestial coordinate system.

[0080] Corner point coordinate measurement, measure the positions of the corner points in turn: place the prism at the second control point as the backsight, aim the crosshairs of the total station at each corner point on the checkerboard calibration plate in turn, and measure the positions of these corner points one by one in the corner-free mode. At each corner point, the total station will record the precise position of the prism through laser distance measurement and angle measurement.

[0081] Get the coordinates of all corner points in the Northeast Sky Coordinate System: Use the measurement data of the total station to convert the measurement results of the non-edge mode into coordinates in the Northeast Sky Coordinate System. Since the position of the total station is known and aligned with the Northeast Sky Coordinate System, the position of each corner point measured can be accurately expressed as a coordinate in the Northeast Sky Coordinate System.

[0082] Furthermore, the initial position of the camera in the northeast sky coordinate system is calculated using the following formula:

[0083]

[0084] Among them, [e i ,n i ,u i ] T For a corner point P i The initial position in the northeast sky coordinate system, [pu i ,pv i ] T The pixel coordinates of its projection in the image, s iis the scale factor, K is the camera intrinsic parameter matrix, and T is the camera's position in the northeast celestial coordinate system.

[0085] A monocular camera (with known camera intrinsic parameters K and distortion parameters) is used to capture an image containing all corner points of the chessboard, ensuring that the chessboard is clearly visible at each corner point, and the image is used as the first frame of the entire multi-view reconstruction.

[0086] Use image processing algorithms (OpenCV's findChessboardCorners function) to detect the corners of the chessboard, and match the coordinates of the corners of the chessboard in the northeast celestial coordinate system one by one.

[0087] The PnP algorithm is used (the PnP algorithm is solved by minimizing the reprojection error) to obtain the position and posture of the camera in the northeast celestial coordinate system.

[0088] Assume that the coordinates of a corner point Pi in the northeast celestial coordinate system are P i =[e i ,n i ,u i ] T , the pixel coordinate of its projection in the image is U i =[pu i ,pv i ] T ,The relationship between pixel position and corner point is determined as follows:

[0089]

[0090] The matrix form is:

[0091] s i U i =KTP i ,

[0092] Among them, s i is the scale factor, and T is the camera's position in the northeast sky coordinate system.

[0093] A least squares problem can be constructed to calculate the optimal camera pose, which minimizes:

[0094]

[0095] After substituting the coordinates of all corner points in the northeast celestial coordinate system and their projected pixel coordinates, the initial position T0 of the camera in the northeast celestial coordinate system is obtained.

[0096] Furthermore, based on the previous steps, all corner points and the obtained pose T0 are used to solve the scale factor s. i , we need to define an error function E i, we can calculate the observed value U i With the predicted value The error between:

[0097]

[0098] The goal is to find a set of scaling factors s1,s2,…,sn such that the sum of squares of all observation errors is minimized. This can be expressed as a least squares problem:

[0099]

[0100] By solving the least squares problem, the scale factor s is obtained.

[0101] In practical applications, a monocular camera is required to take multiple images from different perspectives (each image contains all the corner points of the chessboard), calculate multiple scale factors, and then take the average value as the optimal scale factor s.

[0102] Furthermore, a multi-view stereoscopic three-dimensional reconstruction is performed on the target area to obtain a three-dimensional point cloud of the object in the target area.

[0103] Use the monocular camera to continue to collect multiple images of the target building scene from different angles at the initial pose. Make sure there is enough overlap between the images for subsequent feature matching and 3D reconstruction.

[0104] Feature points are extracted from each image and matched with feature points in other images. The SIFT algorithm is used to extract representative and stable feature points from the image, and the FLANN algorithm is used to match the feature points.

[0105] Use the matched feature points to restore the sparse 3D structure of the building. Based on the initial pose and scale factor s of the monocular camera, new images are continuously added to the reconstruction process;

[0106] For the newly added images, the known coordinates of the checkerboard corner points in the northeast celestial coordinate system and the camera pose are used for feature matching, and the coordinates of the new feature points in the northeast celestial coordinate system are restored from the matched feature points using triangulation and the scale factor s. The camera pose and the position of the new feature points are optimized to minimize the reprojection error.

[0107] Based on the sparse reconstruction, the dense 3D point cloud of the building is restored. According to the camera pose obtained by sparse reconstruction, the image is corrected at the epipolar level; pixel-level matching is performed on the corrected image pair to generate a disparity map; the image coordinates are converted into 3D coordinates using the disparity map and camera parameters to generate a dense point cloud.

[0108] The generated dense point cloud is preprocessed by denoising, filtering, downsampling, etc. After preprocessing, the point cloud data is Delaunay triangulated. 18 points are selected from the point cloud data to establish an initial triangulated structure (a tetrahedron in three dimensions). The remaining points are inserted into the current triangulated structure one by one. After each point is inserted, the triangulated structure is updated to ensure that the Delaunay condition is met. Through Delaunay triangulation, the point cloud data is converted into a mesh structure composed of triangles that can approximately represent the geometric shape of the building surface.

[0109] Finally, based on the three-dimensional point cloud, the absolute coordinates and scale information of the object in the target area are obtained.

[0110] Specifically, the generated three-dimensional point cloud is processed to remove noise and abnormal points, and filtering and smoothing operations are performed.

[0111] The key feature points of the target object, such as edges, corners, etc., are identified in the processed point cloud. These feature points can usually be used to define the geometric shape of the object.

[0112] Based on the known feature point locations and point cloud data, the absolute coordinates of the object are calculated. This involves mapping the points in the point cloud into the East-West coordinate system to determine the actual location of the object.

[0113] By measuring the distance between relevant points in the point cloud, the actual size of the object can be extracted, including measuring the length, width, height, etc. of the object.

[0114] The embodiments of the present disclosure provide a method, electronic equipment and storage medium for determining the absolute coordinates and scale of an object. By arranging a checkerboard calibration plate of preset specifications in a target area and combining camera images, camera pose and optimization algorithms, the scale factor is accurately calculated, and ultimately three-dimensional point cloud reconstruction and accurate measurement of absolute coordinates of objects in the target area are achieved, thereby significantly improving the measurement accuracy of the object's position and scale.

[0115] The electronic device 400 may be a desktop computer, a notebook, a PDA, a cloud server, or other electronic device. The electronic device 400 may include, but is not limited to, a processor 401 and a memory 402. Those skilled in the art will appreciate that Figure 4 It is only an example of the electronic device 400 and does not constitute a limitation of the electronic device 400. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0116] The processor 401 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0117] The memory 402 may be an internal storage unit of the electronic device 400, for example, a hard disk or memory of the electronic device 400. The memory 402 may also be an external storage device of the electronic device 400, for example, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device 400. Further, the memory 402 may also include both an internal storage unit of the electronic device 400 and an external storage device. The memory 402 is used to store the computer program 403 and other programs and data required by the electronic device. The memory 402 may also be used to temporarily store data that has been output or is to be output.

[0118] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present disclosure. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0119] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0120] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this disclosure.

[0121] In the embodiments provided in the present disclosure, it should be understood that the disclosed / electronic devices and methods can be implemented in other ways. For example, the / electronic device embodiments described above are only schematic, for example, the division of modules or units is only a logical function division, and there may be other division methods in actual implementation, multiple units or components may be combined or may be integrated into another system, or some features may be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection of units, which may be electrical, mechanical or other forms.

[0122] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0123] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0124] If the integrated module / unit is implemented in the form of 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 present disclosure implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. The computer program may include computer program code, and the computer program code may be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or recording medium that can carry computer program code, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electric carrier signals and telecommunication signals.

[0125] The above embodiments are only used to illustrate the technical solutions of the present disclosure, rather than to limit them. Although the present disclosure has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should all be included in the protection scope of the present disclosure.

Claims

1. A method for determining the absolute coordinates and dimensions of an object, characterized in that: The method comprises: Arranging a checkerboard calibration plate of preset specifications in the target area, wherein the checkerboard calibration plate can be observed in multiple views captured by the camera; Obtaining the coordinates of all corner points of the chessboard calibration plate in the northeast celestial coordinate system; The camera acquires images of all corner points and corresponds them to the northeast celestial coordinate system, and calculates the initial position and posture of the camera in the northeast celestial coordinate system; Calculating a scale factor according to the initial pose and the coordinates, wherein the scale factor is used to synchronize the image size and the coordinate size of the object in the target area; Using a feature extraction and matching algorithm, combined with the initial pose and scale factor, a multi-view stereoscopic three-dimensional reconstruction is performed on the target area to obtain a three-dimensional point cloud of the object in the target area; Based on the three-dimensional point cloud, the absolute coordinates and scale information of the object in the target area are obtained.

2. The method according to claim 1, characterized in that The chessboard calibration plate has a length of less than 90 cm and a width of less than 70 cm, and each cell in the chessboard calibration plate is a rectangle.

3. The method according to claim 1, characterized in that The step of obtaining the coordinates of all corner points of the checkerboard calibration plate in the northeast celestial coordinate system includes: Select three points within the preset range of the target area that can receive global satellite navigation system signals and are not collinear; The first point is taken as the origin, the second point is taken as the first control point, and the third point is taken as the second control point. The coordinates of the three points in the WGS84 rectangular coordinate system and the WGS84 geodetic coordinate system are determined by using the global satellite navigation system. The coordinates of the first control point and the second control point in the northeast celestial coordinate system are calculated according to the coordinates of the origin in the WGS84 rectangular coordinate system and the coordinates in the WGS84 geodetic coordinate system; The coordinates of all corner points in the northeast celestial coordinate system are obtained according to the coordinates of the first control point and the second control point in the northeast celestial coordinate system.

4. The method according to claim 3, characterized in that The coordinates of the first control point and the second control point in the northeast celestial coordinate system are calculated according to the coordinates of the origin in the WGS84 rectangular coordinate system and the coordinates in the WGS84 geodetic coordinate system using the following formula: Among them, the coordinates of the origin in the WGS84 rectangular coordinate system are (x0, y0, z0), and the coordinates in the WGS84 geodetic coordinate system are (lon0, lat0, alt0); the coordinates of the first control point or the second control point in the WGS84 rectangular coordinate system are (x, y, z), and the coordinates in the northeast celestial coordinate system are (e, n, u).

5. The method according to claim 3, characterized in that: The coordinates of all corner points in the northeast celestial coordinate system obtained by measuring the coordinates of the first control point and the second control point in the northeast celestial coordinate system include: Setting a total station at the first control point, setting a prism at the second control point, setting up a station for measurement, and associating the total station with the northeast celestial coordinate system; The positions of all corner points are measured in sequence by the total station to obtain the coordinates of all corner points in the northeast celestial coordinate system.

6. The method according to claim 1, characterized in that The calculation obtains the initial position of the camera in the northeast sky coordinate system using the following formula: Among them, [e i ,n i ,u i ] T For a corner point P i The coordinates in the northeast sky coordinate system, [pu i ,pv i ] T The pixel coordinates of its projection in the image, s i is the scale factor, K is the camera intrinsic parameter matrix, and T is the camera's position in the northeast celestial coordinate system.

7. The method according to claim 1, characterized in that The calculation scale factor includes: The error function is established by the following formula: Among them, E i is the error function, P i The predicted pixel coordinates projected in the image, U i P i The pixel coordinate observations projected in the image; The error function is solved by least squares to obtain the scale factor, and the solution formula is as follows: Among them, s1, s2, …, sn is a set of scale factors.

8. The method according to claim 1, characterized in that The performing multi-view stereoscopic 3D reconstruction on the target area to obtain a 3D point cloud of the object in the target area comprises: Acquire multiple images of the target area at an initial position of the camera; Extract feature points from each image and match them with feature points in other images; Obtaining a first three-dimensional point cloud of the object in the target area by triangulation according to the matched feature points; According to the first three-dimensional point cloud, an image is corrected and matched to obtain a disparity map, and image coordinates are converted into three-dimensional coordinates according to the disparity map and camera parameters to obtain a second three-dimensional point cloud; The second three-dimensional point cloud is subjected to Delaunay triangulation to obtain a third three-dimensional point cloud.

9. An electronic device, characterized in that: include: one or more processors; A storage unit, used to store one or more programs, which, when executed by the one or more processors, enable the one or more processors to implement the method for determining the absolute coordinates and scale of an object according to any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, it can implement the method for determining the absolute coordinates and scale of an object according to any one of claims 1 to 8.

Images