Automatic calibration method and equipment for installation posture of curtain wall glass

Abstract

The invention relates to the technical field of attitude estimation, in particular to an automatic attitude calibration method and device for curtain wall glass installation, and the method comprises the steps: obtaining the initial pose information of a curtain wall glass calibration plate and a curtain wall frame calibration plate; the relative poses of the curtain wall glass calibration plate and the curtain wall frame calibration plate are obtained, and installation pre-adjustment is carried out; according to the pose expression conditions of the calibration feature points corresponding to the curtain wall glass calibration plate and the curtain wall frame calibration plate after the coordinate origin is adjusted, the installation angles of the calibration feature points are adjusted, and installation pose data of a first calibration point are obtained; according to the relative position relationship of the calibration feature points corresponding to the curtain wall glass calibration plate and the curtain wall frame calibration plate, obtaining the installation pose data of the second calibration point; and according to the installation pose data, carrying out staged calibration on the installed and pre-adjusted curtain wall glass to obtain a pose calibration result of curtain wall glass installation. According to the method, the problem of coordinate unification among different objects is fully considered, and a relatively good calibration effect is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of attitude estimation, and in particular to an automatic attitude calibration method and device for curtain wall glass installation. Background Art

[0002] As modern buildings develop towards high-rise and curved surfaces, curtain wall glass, as a key component of the building's external protective structure, has a direct impact on the quality of the building's appearance and structural safety performance due to its installation accuracy. Traditional curtain wall installation mostly relies on manual measurement and positioning, which has problems such as low efficiency, accumulation of repeated calibration errors, and high risks of high-altitude operations. Especially in the installation of special-shaped curtain walls and large-size unit panels, manual calibration is difficult to meet the millimeter-level posture matching requirements, resulting in stress concentration and sealing failure between the glass panel and the curtain wall frame.

[0003] In the existing technology, the laser total station can achieve three-dimensional coordinate positioning with prism reflection, but it is difficult to adapt to dynamic construction scenes due to the size of the equipment and the ability to track multiple targets. The posture estimation system based on inertial navigation is easily disturbed by mechanical vibration and has cumulative error defects. Some studies have tried to introduce machine vision technology, such as achieving relative posture solution through feature point matching, but feature loss is prone to occur on the surface of weakly textured curtain walls. However, it is impossible to consider the unification of multiple coordinate systems between camera-glass-installation frame, resulting in poor results of posture automation calibration methods. Summary of the invention

[0004] In order to solve the technical problem that the prior art cannot take into account the unification of multiple coordinate systems between camera, glass and installation frame, resulting in poor effect of the automatic posture calibration method, the purpose of the present invention is to provide a curtain wall glass installation posture automatic calibration method and device, the technical solution adopted is as follows:

[0005] In a first aspect, the present invention provides a method for automatic calibration of the posture of curtain wall glass installation, comprising:

[0006] Acquire initial position information of the curtain wall glass calibration plate and the curtain wall frame calibration plate, wherein the initial position information includes a rotation dimension and a translation dimension;

[0007] Performing a matrix transformation operation according to the initial posture information to obtain the relative posture of the curtain wall glass calibration plate and the curtain wall frame calibration plate; and using the relative posture to pre-adjust the curtain wall glass for installation;

[0008] According to the posture performance of the calibration feature points corresponding to the curtain wall glass calibration plate and the curtain wall frame calibration plate after adjusting the coordinate origin, adjusting the installation angle of the calibration feature points to obtain the installation posture data of the first calibration point;

[0009] Obtain the installation pose data of the second calibration point according to the relative position relationship of the calibration feature points corresponding to the curtain wall glass calibration plate and the curtain wall frame calibration plate;

[0010] Perform phased calibration on the curtain wall glass after pre-adjusting the installation according to the installation pose data to obtain the pose calibration result of the curtain wall glass installation.

[0011] Preferably, the obtaining of the initial pose information of the curtain wall glass calibration plate and the curtain wall frame calibration plate specifically includes:

[0012] Obtain the two-dimensional image of the curtain wall glass calibration plate and the two-dimensional image of the curtain wall frame calibration plate;

[0013] For any two-dimensional image, based on the pixel coordinates of different pixel points on the two-dimensional image and the spatial coordinates of the corresponding pixels in the three-dimensional space, set the coordinate origin of the calibration plate three-dimensional space as the centroid of the calibration plate, and use the PnP algorithm to obtain the first rotation matrix and the first translation matrix of the pixel coordinate system of the two-dimensional image relative to the corresponding calibration plate space coordinate system. The initial pose information includes the first rotation matrix and the first translation matrix.

[0014] Preferably, the obtaining of the relative pose between the curtain wall glass calibration plate and the curtain wall frame calibration plate by performing matrix transformation operations according to the initial pose information specifically includes:

[0015] Based on the initial pose information of the curtain wall glass calibration plate, determine the homogeneous coordinate matrix of the first relative pose from the curtain wall glass calibration plate to the image acquisition device;

[0016] Perform matrix inverse transformation based on the initial pose information of the curtain wall frame calibration plate to determine the homogeneous coordinate matrix of the second relative pose from the image acquisition device to the curtain wall frame calibration plate;

[0017] Based on the product of the homogeneous coordinate matrices between the first relative pose and the second relative pose, determine the homogeneous coordinate matrix of the global relative pose between the curtain wall glass calibration plate and the curtain wall frame calibration plate;

[0018] Based on the homogeneous coordinate matrix of the global relative pose, determine the relative pose between the curtain wall glass calibration plate and the curtain wall frame calibration plate.

[0019] Preferably, the adjusting of the installation angle of the calibration feature points according to the pose performance of the calibration feature points corresponding to the curtain wall glass calibration plate and the curtain wall frame calibration plate after adjusting the coordinate origin to obtain the installation pose data of the first calibration point specifically includes:

[0020] Obtain any set of corresponding corner points of the curtain wall glass calibration plate and the curtain wall frame calibration plate, and respectively denote them as the first calibration feature point and the second calibration feature point; the first calibration points shown include the first calibration feature point of the curtain wall glass calibration plate and the second calibration feature point of the curtain wall frame calibration plate;

[0021] Set the coordinate origin of the three-dimensional space of the curtain wall glass calibration plate as the first calibration feature point, and set the coordinate origin of the three-dimensional space of the curtain wall frame calibration plate as the second calibration feature point, and respectively obtain the first feature pose of the first calibration feature point and the second feature pose of the second calibration feature point;

[0022] Perform matrix transformation operations according to the first feature pose and the second feature pose to obtain the relative pose between the first calibration feature point and the second calibration feature point;

[0023] According to the difference between the actual measured size of the curtain wall glass and the actual measured size of the curtain wall frame, combined with the preset safety distance, obtain the second translation matrix of the first calibration feature point; according to the space coordinate system of the curtain wall glass calibration plate and the preset rotation angle, obtain the second rotation matrix of the first calibration feature point;

[0024] Under the relative pose between the first calibration feature point and the second calibration feature point, sequentially rotate according to the second rotation matrix and translate according to the second translation matrix to obtain the installation pose data of the first calibration point.

[0025] Preferably, the obtaining of the second translation matrix of the first calibration feature point according to the difference between the actual measured size of the curtain wall glass and the actual measured size of the curtain wall frame, combined with the preset safety distance, specifically includes:

[0026] The actual measured size of the curtain wall glass obtained includes the actual length of each side of the curtain wall glass, and the actual measured size of the curtain wall frame obtained includes the actual length of each side of the curtain wall frame;

[0027] Based on the difference in the actual length of the corresponding sides between the curtain wall glass and the curtain wall frame, determine the unilateral installation redundancy distance of each side of the curtain wall glass, and take the average value of the unilateral installation redundancy distances of all sides of the curtain wall glass as the balanced redundancy distance;

[0028] Move the curtain wall glass calibration plate in the negative direction by the balanced redundancy distance to obtain the second translation matrix of the first calibration feature point.

[0029] Preferably, the obtaining of the second rotation matrix of the first calibration feature point according to the space coordinate system of the curtain wall glass calibration plate and the preset rotation angle, specifically includes:

[0030] Set the angle of rotating the curtain wall glass calibration plate along the x-axis to a preset rotation angle to obtain the x-axis rotation matrix; set the angle of rotating the curtain wall glass calibration plate in the reverse direction along the y-axis to a preset rotation angle to obtain the y-axis rotation matrix; take the product of the x-axis rotation matrix and the y-axis rotation matrix as the second rotation matrix of the first calibration feature point.

[0031] Preferably, the obtaining the installation pose data of the second calibration point according to the relative position relationship between the calibration feature points corresponding to the curtain wall glass calibration plate and the curtain wall frame calibration plate specifically includes:

[0032] Obtain any corner point collinear with the first calibration feature point of the curtain wall glass calibration plate as the third calibration feature point, and take the corner point on the curtain wall frame calibration plate corresponding to and matching the third calibration feature point as the fourth calibration feature point; the second calibration point includes the third calibration feature point and the fourth calibration feature point;

[0033] Use the PnP algorithm to perform coordinate transformation on the third calibration feature point to obtain the current spatial coordinates of the third calibration feature point in the spatial coordinate system of the curtain wall frame calibration plate; obtain the target spatial coordinates of the fourth calibration feature point in the spatial coordinate system of the curtain wall frame calibration plate;

[0034] Based on the current spatial coordinates and the coordinates of the first calibration feature point, determine the current spatial vector of the first calibration feature point pointing to the third calibration feature point in the current pose; based on the target spatial coordinates and the coordinates of the first feature point, determine the target spatial vector of the first calibration feature point pointing to the fourth calibration feature point in the current pose;

[0035] Obtain the third rotation matrix of the third calibration feature point according to the current spatial vector and the target spatial vector, and the installation pose data of the second calibration point includes the third rotation matrix.

[0036] Preferably, the obtaining the third rotation matrix of the third calibration feature point according to the current spatial vector and the target spatial vector specifically includes:

[0037] Under the condition of satisfying the constraint R B ·v1 = v2, solve the third rotation matrix R B of the third calibration feature point, where v1 is the current spatial vector and v2 is the target spatial vector.

[0038] Preferably, the obtaining the attitude calibration result of the curtain wall glass installation by performing stage calibration on the curtain wall glass after installation pre-adjustment according to the installation pose data specifically includes:

[0039] Perform the first-stage calibration operation on the curtain wall glass after installation pre-adjustment based on the installation pose data of the first calibration point;

[0040] Perform the second-stage calibration operation on the curtain wall glass after the first-stage calibration based on the installation pose data of the second calibration point;

[0041] Obtain the relative pose in the third stage of the current curtain wall glass calibration plate and the curtain wall frame calibration plate, and use the relative pose in the third stage to perform final adjustment on the curtain wall glass to obtain the pose calibration result of the curtain wall glass installation.

[0042] In a second aspect, the present invention provides an automatic pose calibration device for curtain wall glass installation, including a memory, a processor, and a computer program stored on the memory and running on the processor. When the computer program is executed by the processor, it implements the steps of an automatic pose calibration method for curtain wall glass installation.

[0043] The embodiments of the present invention have at least the following beneficial effects:

[0044] The present invention first obtains the initial pose information corresponding to the curtain wall glass calibration plate and the curtain wall frame calibration plate respectively, which includes the rotation dimension and the translation dimension, providing a data basis for subsequent feature analysis. By analyzing the relative pose information between the two through the initial pose information, the relative pose between the curtain wall glass calibration plate and the curtain wall frame calibration plate is obtained; three-dimensional space pose alignment is achieved, the problem of multi-coordinate system unification is solved, and then pre-adjustment of the curtain wall glass installation is realized for the unified relative pose. Then, a phased calibration operation is performed on the corresponding calibration feature points on the curtain wall glass and the curtain wall frame. On the one hand, the coordinate origin needs to be adjusted, the degree of translation required is analyzed by analyzing the pose performance of the corresponding calibration feature points, and the degree of rotation required is analyzed by adjusting the installation angle, and the installation pose data of the first calibration point is determined, which also represents the installation process of the first stage. On the other hand, the relative position relationship of the corresponding calibration feature points needs to be analyzed, and the degree of rotation required for the calibration feature points is analyzed to determine the installation pose data of the second calibration point, which also represents the installation process of the second stage. Finally, phased calibration realizes the automatic pose calibration operation of curtain wall glass installation. The present invention fully considers the problem of coordinate unification between different objects, and performs phased calibration, gradually iterating and optimizing, ensuring better calibration effects. Description of the Drawings

[0045] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0046] Figure 1 It is a step flow chart of an automatic pose calibration method for curtain wall glass installation provided by the present invention;

[0047] Figure 2 It is the flowchart of the first sub-step of an automatic attitude calibration method for curtain wall glass installation provided by the present invention;

[0048] Figure 3 It is the flowchart of the second sub-step of an automatic attitude calibration method for curtain wall glass installation provided by the present invention;

[0049] Figure 4 It is the schematic diagram of the installation result in the first stage provided by the present invention;

[0050] Figure 5 It is the flowchart of the third sub-step of an automatic attitude calibration method for curtain wall glass installation provided by the present invention;

[0051] Figure 6 It is the schematic diagram of the installation result in the second stage provided by the present invention;

[0052] Figure 7 It is the structural schematic diagram of an automatic attitude calibration device for curtain wall glass installation provided by the present invention;

[0053] Figure 8 It is the structural schematic diagram of a computer device provided by the present invention. Specific Embodiments

[0054] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific embodiments, structures, features, and effects of the SMS encryption method and system based on 5G technology proposed according to the present invention.

[0055] Before introducing the specific solutions provided by the embodiments of the present application, some terms used in the present application are explained for the convenience of those skilled in the art to understand, and are not used to limit the present application.

[0056] (1) PnP algorithm: The purpose is to solve the method of 2D-3D point pair motion, and it solves the problem of estimating the pose of the camera in the reference coordinate system based on the two-dimensional pixel coordinates of the feature points in the image and their corresponding three-dimensional space coordinates. Intuitively, when the camera observes an object in space, given the three-dimensional space coordinates of n points on the observed object (relative to a specified coordinate system O) and their two-dimensional projection positions, how to estimate the pose of the camera (i.e., the attitude of the camera in the coordinate system O) is exactly what PNP needs to solve, that is, to solve the relative relationship between the camera and the reference coordinate system using the known correspondence between the three-dimensional structure and the image. The above-mentioned attitude or pose includes position and direction, that is, a 6-degree-of-freedom state, which is the rotation matrix and translation vector to be solved, and the two are collectively referred to as the external parameters of the camera.

[0057] (2) Curtain wall: It is the external wall enclosure of a building, hung like a curtain, so it is also called a suspended wall. A curtain wall usually consists of a support skeleton made of metal materials, a fixing structure, and curtain wall glass. Since a curtain wall is composed of multiple units, that is, multiple pieces of curtain wall glass, and the curtain wall glass is installed piece by piece during installation. Curtain wall installation equipment belongs to well-known technology and can control the rotation of the curtain wall glass, that is, the angle inclination and translation operations.

[0058] (3) Calibration plate: It is an important tool used in the fields of machine vision, image measurement, photogrammetry, 3D reconstruction, etc. It is usually a flat plate with a fixed-spacing pattern array. By taking pictures of the calibration plate with a camera and combining with a calibration algorithm, a geometric model of camera imaging can be established.

[0059] In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0060] Among them, in the description of the embodiments of the present invention, unless otherwise specified, " / " means "or". For example, A / B can mean A or B. The "and / or" in the text is only a description of the association relationship between associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of the present invention, "multiple" means two or more than two.

[0061] Hereinafter, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as implying or suggesting relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features.

[0062] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0063] The following specifically describes the specific solutions of a method and device for automatically calibrating the posture of curtain wall glass provided by the present invention with reference to the accompanying drawings.

[0064] Please refer to Figure 1 , which shows a flowchart of the steps of a method for automatically calibrating the posture of curtain wall glass provided by an embodiment of the present invention. The method includes the following steps:

[0065] Step S100, obtaining the initial pose information of the curtain wall glass calibration plate and the curtain wall frame calibration plate, where the initial pose information includes the rotation dimension and the translation dimension.

[0066] Fix the curtain wall glass to be installed with a clamping device, and then lift the curtain wall glass through the rotating shaft and telescopic rod of the clamping device and move it to a preset position. Among them, the clamping device refers to the clamping device on the curtain wall installation equipment for realizing the automatic calibration and installation operation of the curtain wall glass, which is a well-known technology and will not be introduced in detail here.

[0067] For the curtain wall glass to be installed, stick a calibration board B1 flat on the side facing the image acquisition device; place a calibration board B2 on the keel of the curtain wall installation wall. Among them, the image acquisition device refers to the image acquisition device on the curtain wall installation equipment, which is used to collect the image information of the curtain wall glass and the curtain wall frame.

[0068] Furthermore, the curtain wall glass can be roughly calibrated through machine vision technology and two calibration boards to obtain the preliminary pose of the curtain wall glass. Specifically, the collected image information includes the two-dimensional image of the curtain wall glass calibration board and the two-dimensional image of the curtain wall frame calibration board.

[0069] For any two-dimensional image, based on the pixel coordinates of different pixel points on the two-dimensional image and the spatial coordinates of the corresponding pixels in the three-dimensional space, set the coordinate origin of the calibration board in the three-dimensional space as the centroid of the calibration board, and use the PnP algorithm to obtain the first rotation matrix and the first translation matrix of the pixel coordinate system of the two-dimensional image relative to the spatial coordinate system of the corresponding calibration board. The initial pose information includes the first rotation matrix and the first translation matrix.

[0070] Taking the curtain wall glass calibration board B1 as an example, set the centroid of the curtain wall glass calibration board B1 as the coordinate origin, and at the same time use the corner detection technology to detect the two-dimensional image respectively, and obtain the spatial coordinates of three non-collinear corners on the curtain wall glass calibration board B1 in the three-dimensional space. By using the PnP algorithm with the spatial coordinates of these three corners and the corresponding pixel coordinates in the two-dimensional image of the curtain wall glass calibration board B1, obtain the initial pose information [R1, t1] of the image acquisition device relative to the curtain wall glass calibration board B1. Among them, R1 represents the first rotation matrix of the pixel coordinate system of the image acquisition device relative to the spatial coordinate system of the curtain wall glass calibration board B1, with a size of 3*3, and t1 represents the first translation matrix of the pixel coordinate system of the image acquisition device relative to the spatial coordinate system of the curtain wall glass calibration board B1, with a size of 3*1.

[0071] The initial pose information [R2, t2] of the curtain wall frame calibration board B2 can be obtained in the same way, where R2 represents the first rotation matrix of the pixel coordinate system of the image acquisition device relative to the spatial coordinate system of the curtain wall frame calibration board B2, with a size of 3*3, and t2 represents the first translation matrix of the pixel coordinate system of the image acquisition device relative to the spatial coordinate system of the curtain wall frame calibration board B2, with a size of 3*1. It can be understood that when obtaining the initial pose information [R2, t2] of the curtain wall frame calibration board B2, the centroid of the curtain wall frame calibration board B2 is set as the origin of the coordinate system.

[0072] Step S200, perform matrix transformation operations according to the initial pose information to obtain the relative pose between the curtain wall glass calibration board and the curtain wall frame calibration board; use the relative pose to perform pre-adjustment of the installation of the curtain wall glass.

[0073] It can be understood that the initial pose information characterizes the relative pose performance of the image acquisition device relative to each calibration board. In order to achieve pose alignment in three-dimensional space, the image acquisition device can be used as a transfer point to analyze the relative pose performance between the curtain wall glass calibration board B1 and the curtain wall frame calibration board B2.

[0074] Furthermore, in order to achieve the alignment operation of the overall posture of the curtain wall glass and the overall posture of the curtain wall frame, and to limit the movement of the curtain wall glass to a safe installation distance, a safe distance can be moved based on the relative pose performance information between the curtain wall glass calibration board and the curtain wall frame calibration board to ensure the alignment of the overall postures between the curtain wall glass and the curtain wall frame and maintain a safe installation distance.

[0075] Finally, the relative pose between the curtain wall glass calibration board and the curtain wall frame calibration board can be used to perform pre-adjustment of the installation of the curtain wall glass. Taking a three-axis device as an example, the rotation matrix of the relative pose is decomposed into motion parameters of three axes, namely Euler angles, and the three-axis device is controlled to adjust the angle according to the Euler angles; the translation vector of the relative pose is corresponding to the displacement of the robotic arm for position adjustment. The control adjustment process is a well-known technology and will not be introduced in detail here.

[0076] Step S300, according to the pose performance of the calibration feature points corresponding to the curtain wall glass calibration board and the curtain wall frame calibration board after adjusting the coordinate origin, adjust the installation angle of the calibration feature points to obtain the installation pose data of the first calibration point.

[0077] After pre - adjustment, the present invention conducts phased calibration. Through iterative optimization by step - by - step installation, the error is gradually reduced. In the first stage, calibration operations are performed on any fixed feature point. After adjusting the coordinate origin to the calibration feature point, the rotational pose performance between the corresponding and matched feature points of the curtain wall glass calibration plate and the curtain wall frame calibration plate is analyzed to adjust the installation angle, and the difference in dimensions between the curtain wall glass calibration plate and the curtain wall frame calibration plate is analyzed to adjust the translation distance, thereby determining the pose information corresponding to the calibration operation of a fixed feature point.

[0078] As can be seen from step S100, the corner detection technology can be used to separately detect and obtain the corners of the curtain wall glass calibration plate and the corners of the curtain wall frame calibration plate. By using the corner matching operation, the corresponding matching relationship between the corners of the two can be obtained. This is a well - known technology and will not be introduced in detail here.

[0079] Based on this, any set of corresponding and matched corners of the curtain wall glass calibration plate and the curtain wall frame calibration plate are respectively denoted as the first calibration feature point and the second calibration feature point; the first calibration point includes the first calibration feature point of the curtain wall glass calibration plate and the second calibration feature point of the curtain wall frame calibration plate.

[0080] Furthermore, adjust the coordinate origin. Set the coordinate origin of the three - dimensional space of the curtain wall glass calibration plate as the first calibration feature point, and set the coordinate origin of the three - dimensional space of the curtain wall frame calibration plate as the second calibration feature point. Respectively obtain the first feature pose of the first calibration feature point and the second feature pose of the second calibration feature point. The method for obtaining the pose is the same as the method for obtaining the initial pose information in step S100.

[0081] Based on the first feature pose and the second feature pose, analyze the relative pose performance between the first calibration specific point and the second calibration feature point, and then, on this basis, adjust the pose performance. That is, when calibrating the pose of the first calibration point, in order to prevent the overall position deviation of the curtain wall glass, first, the pose is rotationally adjusted. The rotation matrix of this adjustment operation is called the avoidance matrix. Adjust the pose of the curtain wall glass through the avoidance matrix to install the first calibration feature point first.

[0082] At the same time, it can prevent collision problems during the installation of the first calibration feature point of the curtain wall glass. Considering the difference balance situation between the actual measured dimensions of the curtain wall glass and the curtain wall frame, determine the translation adjustment matrix of the pose. Based on the rotation dimension and the translation dimension, the corresponding pose information between the first calibration feature point of the curtain wall glass calibration plate and the second calibration feature point of the curtain wall frame calibration plate can be obtained, that is, the installation pose data of the first calibration point. The installation pose data of the first calibration point represents the pose information performance required for adjusting the pose of a feature point on the curtain wall glass calibration plate to reach the target position after pose adjustment.

[0083] Step S400: Obtain the installation pose data of the second calibration point according to the relative position relationship of the calibration feature points corresponding to the curtain wall glass calibration board and the curtain wall frame calibration board.

[0084] After the pose calibration in the first stage is achieved, the pose calibration operation in the second stage is carried out. Mainly considering the rotation and displacement conditions that another corner point on the curtain wall glass calibration board needs to move to the target position, at this time, in order to avoid damaging the pose calibration result in the first stage, it is necessary to fix the position of the first calibration point and carry out the pose calibration process of the second calibration point.

[0085] Specifically, obtain any corner point collinear with the first calibration feature point of the curtain wall glass calibration board as the third calibration feature point. As Figure 4 shown, for example, take the corner point at the lower right corner of the square curtain wall glass as the third calibration feature point. Take the corner point on the curtain wall frame calibration board corresponding to and matching the third calibration feature point as the fourth calibration feature point; the second calibration point includes the third calibration feature point and the fourth calibration feature point.

[0086] Then, use the PnP algorithm to perform coordinate transformation on the third calibration feature point to obtain the current spatial coordinates of the third calibration feature point in the spatial coordinate system of the curtain wall frame calibration board; obtain the target spatial coordinates of the fourth calibration feature in the spatial coordinate system of the curtain wall frame calibration board.

[0087] It can be understood that the coordinate system corresponding to the spatial coordinates of the third calibration feature point is the spatial coordinate system of the curtain wall glass calibration board, and the target point that the third calibration feature point needs to move to is the fourth calibration feature point. The coordinate system corresponding to the spatial coordinates of the fourth calibration feature point is the spatial coordinate system of the curtain wall frame calibration board. In order to achieve coordinate unification, it is necessary to use the relative pose situation between the curtain wall glass and the curtain wall frame at this time, and combine the PnP algorithm to perform coordinate transformation on the third calibration feature point to convert the spatial coordinates of the third calibration feature point from the spatial coordinate system of the curtain wall glass calibration board to the spatial coordinate system of the curtain wall frame calibration board.

[0088] Furthermore, since the position of the first calibration feature point needs to be fixed, then the rotation situation that the third calibration feature point in the current second stage needs to be adjusted can be determined by comparing the relative position between the current actual position information and the first calibration feature point, and the relative position between the position information of the target point and the first calibration feature point, and obtain the installation pose data of the final third calibration feature point, that is, the installation pose data of the second calibration point.

[0089] Step S500: Perform staged calibration on the curtain wall glass after installation pre-adjustment according to the installation pose data to obtain the pose calibration result of the curtain wall glass installation.

[0090] The first-stage calibration operation of the curtain wall glass after installation pre-adjustment based on the installation pose data of the first calibration point has been described in the subsequent embodiments and will not be elaborated here. The second-stage calibration operation of the curtain wall glass after the first-stage calibration based on the installation pose data of the second calibration point; has been described in the subsequent embodiments and will not be elaborated here. Obtain the relative pose of the third stage between the current curtain wall glass calibration plate and the curtain wall frame calibration plate, and use the relative pose of the third stage to perform final adjustment on the curtain wall glass to obtain the pose calibration result of the curtain wall glass installation.

[0091] It can be understood that after the calibration operations of the first stage and the second stage are completed, it is necessary to re-obtain the relative pose between the curtain wall glass calibration plate and the curtain wall frame calibration plate, denoted as the relative pose of the third stage. The method for obtaining the relative pose has been described in detail in the above steps and will not be elaborated here.

[0092] It should be noted that at this time, the positions of the first calibration point and the second calibration point are fixed. Therefore, the coordinate origin corresponding to obtaining the relative pose is still at the position of the first calibration point. As Figure 6 shown, the position of one side of the curtain wall glass is fixed. Therefore, there is no need to perform the translation adjustment operation of the translation matrix. Only the angle of the curtain wall glass needs to be adjusted for step-by-step installation. That is, the translation matrix t included in the relative pose of the third stage C =[0,0,0] T . After the position of the curtain wall glass reaches the installation position, subsequent operations such as fixing, sealing, and caulking the curtain wall glass are performed to complete the installation of the curtain wall glass.

[0093] So far, it can be understood that the main implementation process of the phased calibration in this embodiment includes: first, align the centroids of the curtain wall glass and the curtain wall frame, and perform the pre-adjustment operation of the pose calibration; then, adjust the coordinate origin, align a characteristic corner point of the curtain wall glass and the curtain wall frame, and perform the first-stage calibration operation of the pose calibration; further, under the condition that the characteristic corner point adjusted in the first stage is fixed, perform the second-stage calibration operation of the pose calibration to realize the installation operation of one side of the curtain wall glass. Finally, perform the overall rotation adjustment on the curtain wall glass to realize all the pose calibration operations of the curtain wall glass and complete the installation operation of the curtain wall glass.

[0094] In summary, calibration plates are respectively provided on the curtain wall glass and the curtain wall frame of the present invention. By combining the image acquisition device with the PnP algorithm, the relative pose between the two is obtained, solving the problem of unified multi-coordinate systems and ensuring the consistency of the pose calculation reference. The relative pose between the curtain wall glass and the curtain wall frame is deduced through matrix transformation (homogeneous coordinate matrix) to achieve three-dimensional spatial pose alignment. Calibration is carried out in stages (the first calibration point → the second calibration point → overall pose adjustment), and the error is gradually reduced through iterative optimization of the installation distance level by level. Through the collaborative calibration of the PnP algorithm and the double calibration plates, millimeter-level pose matching is achieved, solving the problem of error accumulation in traditional manual calibration. Through the calibration of the calibration plate coordinate system, manual intervention is reduced, the complexity of the calibration process is reduced, and the installation efficiency is improved. It is compatible with machine vision, deep learning models and industrial control modules, and supports feature recognition of the surface of curtain walls with weak texture.

[0095] In some embodiments, the above step S200 can be implemented by Figure 2 the sub-steps shown as follows:

[0096] Step S201, based on the initial pose information of the curtain wall glass calibration plate, determine the homogeneous coordinate matrix of the first relative pose from the curtain wall glass calibration plate to the image acquisition device.

[0097] Specifically, the homogeneous coordinate matrix T of the first relative pose of the image acquisition device relative to the curtain wall glass calibration plate B1 B1→C can be expressed as where C represents the image acquisition device. The homogeneous coordinate matrix is a mathematical expression that unifies spatial transformation, which enables complex spatial transformations to be multiplied in a chain, for example: camera → calibration plate → curtain wall center, or curtain wall glass → image acquisition device → curtain wall frame. Based on this, the image acquisition device can be used as a transfer point to obtain the relative pose representation of the curtain wall glass relative to the curtain wall frame.

[0098] Step S202, based on the initial pose information of the curtain wall frame calibration plate, perform matrix inverse transformation to determine the homogeneous coordinate matrix of the second relative pose from the image acquisition device to the curtain wall frame calibration plate.

[0099] Specifically, the homogeneous coordinate matrix T of the relative pose of the image acquisition device relative to the curtain wall frame calibration plate B2 B2→C can be expressed as Using the inverse transformation operation of the matrix, the homogeneous coordinate matrix T of the relative pose B2→C , is converted into the homogeneous coordinate matrix of the second relative pose of the curtain wall frame calibration plate B2 relative to the image acquisition device C, which can be expressed as represents the transpose matrix of matrix R2.

[0100] Step S203: Determine the homogeneous coordinate matrix of the global relative pose between the curtain wall glass calibration plate and the curtain wall frame calibration plate based on the product of the homogeneous coordinate matrices between the first relative pose and the second relative pose.

[0101] Specifically, taking the image acquisition device C as the transfer point, multiply in a chain to obtain the homogeneous coordinate matrix of the global relative pose between the curtain wall glass calibration plate B1 and the curtain wall frame calibration plate B2, which can be expressed as:

[0102]

[0103] where, T B1→B2 is the homogeneous coordinate matrix of the global relative pose between the curtain wall glass calibration plate B1 and the curtain wall frame calibration plate B2, T B1→C is the homogeneous coordinate matrix of the first relative pose of the image acquisition device C relative to the curtain wall glass calibration plate B1, and T C→B2 is the homogeneous coordinate matrix of the second relative pose of the curtain wall frame calibration plate B2 relative to the image acquisition device C.

[0104] Step S204: Determine the relative pose between the curtain wall glass calibration plate and the curtain wall frame calibration plate based on the homogeneous coordinate matrix of the global relative pose.

[0105] Specifically, from the homogeneous coordinate matrix it can be known that the relative pose between the curtain wall glass calibration plate and the curtain wall frame calibration plate can be expressed as where, R3 represents the corresponding rotation matrix between the curtain wall glass calibration plate and the curtain wall frame calibration plate, and t3 represents the corresponding translation matrix between the curtain wall glass calibration plate and the curtain wall frame calibration plate.

[0106] It should be further noted that in this embodiment, the set safe installation distance is 10 cm. Therefore, on the basis of the relative pose of the curtain wall glass and the curtain wall frame, a safe translation distance can be added. Based on this, the translation matrix corresponding to the relative pose between the curtain wall glass calibration plate and the curtain wall frame calibration plate can be updated, expressed as t3 ′ = t3 + [0, 0, -d0] T , where d0 represents the preset safe distance. Therefore, the updated relative pose between the curtain wall glass calibration plate and the curtain wall frame calibration plate can be expressed as [R3, t3 ′ .

[0107] In some embodiments, the above step S300 can be implemented through the Figure 3 sub-steps shown as follows:

[0108] Step S301: Perform matrix transformation operations according to the first feature pose and the second feature pose to obtain the relative pose between the first calibration feature point and the second calibration feature point.

[0109] The first feature pose represents the pose information of the image acquisition device relative to the first calibration feature point of the curtain wall glass calibration plate after the transformation of the coordinate origin, and the second feature pose represents the pose information of the image acquisition device relative to the second calibration feature point of the curtain wall frame calibration plate after the transformation of the coordinate origin. According to the same method as in step S200, taking the image acquisition device as the transfer point, the relative pose between the first calibration feature point and the second calibration feature point can be obtained as [R p1 , t p1 , where R p1 is the rotation matrix corresponding to the relative pose, and t p1 is the translation matrix corresponding to the relative pose, and p1 represents the first calibration point.

[0110] Based on this, the relative pose between the first calibration feature point and the second calibration feature point represents the relative pose between the curtain wall glass and the curtain wall frame after adjusting the origin to the first calibration feature point and the second calibration feature point in the spatial coordinate systems corresponding to the curtain wall glass and the curtain wall frame.

[0111] Step S302: According to the difference between the actual measured size of the curtain wall glass and the actual measured size of the curtain wall frame, combined with the preset safety distance, obtain the second translation matrix of the first calibration feature point.

[0112] The first step is to obtain the actual measured size of the curtain wall glass, including the actual length of each side of the curtain wall glass, and obtain the actual measured size of the curtain wall frame, including the actual length of each side of the curtain wall frame.

[0113] In this embodiment, a square curtain wall glass is taken as an example for illustration, and directly obtain the actual length of each side of the square curtain wall glass and the actual length of each side of the curtain wall frame.

[0114] The second step is to determine the unilateral installation redundancy distance of each side of the curtain wall glass based on the difference in the actual lengths of the corresponding sides between the curtain wall glass and the curtain wall frame, and take the average value of the unilateral installation redundancy distances of all sides of the curtain wall glass as the balanced redundancy distance.

[0115] Specifically, the side between the corner points where the curtain wall glass and the curtain wall frame have a matching relationship is called the corresponding side between the curtain wall glass and the curtain wall frame. Considering that there may be an error length when installing the curtain wall glass, it can be averaged to both the left and right sides. Therefore, is used as the unilateral installation redundancy distance of a certain side of the curtain wall glass, and l B1,i represents the actual length of the i-th side of the curtain wall glass, and l B2,i represents the actual length of the i-th side of the curtain wall frame.

[0116] As a specific example, the balanced redundancy distance can be expressed by the formula: Where d1 represents the balanced redundancy distance, and n represents the total number of corresponding sides of the curtain wall glass and the curtain wall frame. represents the unilateral installation redundancy distance of the i-th corresponding side of the curtain wall glass and the curtain wall frame.

[0117] In the third step, move the curtain wall glass calibration plate in the negative direction by the balanced redundancy distance to obtain the second translation matrix of the first calibration feature point.

[0118] The second translation matrix t4 of the first calibration feature point can be expressed as t4 = [-d1, -d1, 0] T , and the second translation matrix represents the reverse translation in the X-axis or Y-axis direction to compensate for the dimensional deviation between the curtain wall glass and the curtain wall frame. The second translation matrix reflects that by synthesizing the dimensional differences of multiple sides, an error gap is left for centered installation.

[0119] In some embodiments, after moving the curtain wall glass calibration plate in the negative direction by the balanced redundancy distance, move a preset safety distance to obtain the second translation matrix t ′ 4, t ′ 4 = t4 + [-d1, -d1, d0] T , where d0 is the preset safety distance and d1 is the balanced redundancy distance, which can avoid errors to a certain extent.

[0120] Step S303: Obtain the second rotation matrix of the first calibration feature point according to the spatial coordinate system of the curtain wall glass calibration plate and the preset rotation angle.

[0121] Set an avoidance angle to prevent collision problems during the installation of the first calibration feature point of the curtain wall glass. In this embodiment, the value of the avoidance angle is θ = 10°. Further, set the angle of rotating the curtain wall glass calibration plate along the x-axis to the preset rotation angle to obtain the x-axis rotation matrix; set the angle of rotating the curtain wall glass calibration plate in the reverse direction along the y-axis to the preset rotation angle to obtain the y-axis rotation matrix; take the product of the x-axis rotation matrix and the y-axis rotation matrix as the second rotation matrix of the first calibration feature point.

[0122] Among them, the x-axis rotation matrix can be expressed as The y-axis rotation matrix can be expressed as The second rotation matrix of the first calibration feature point can be expressed as R4 = R x ·R y . The curtain wall glass calibration plate rotates clockwise by θ around the x-axis and rotates in the reverse direction by θ around the y-axis, achieving the purpose of tilting downward and adjusting inward. By adjusting the tilting direction of the curtain wall glass, the situation of collision during installation is avoided.

[0123] Step S304, under the relative pose of the first calibration feature point and the second calibration feature point, perform rotations successively according to the second rotation matrix and translations according to the second translation matrix to obtain the installation pose data of the first calibration point.

[0124] Specifically, in the case of the relative pose representation information of the first calibration feature point and the second calibration feature point, through operations such as the cascading order of rotations and the alignment of translation coordinate systems, comprehensively considering the degrees of rotation and translation that the first calibration feature point finally needs, the installation pose data corresponding to the first calibration feature point is obtained, that is, the installation pose data of the first calibration point.

[0125] The installation pose data corresponding to the first calibration feature point also includes a rotation matrix and a translation matrix, where the rotation matrix R5 = R4·R p1 , and the translation matrix t5 = R4·t p1 + t4. The installation pose data corresponding to the first calibration feature point is [R5, t5] = [R4·R p1 , R4·t p1 + t4], where t4 is the second translation matrix of the first calibration feature point, R4 is the second rotation matrix of the first calibration feature point, R p1 is the rotation matrix corresponding to the relative pose, and t p1 is the translation matrix corresponding to the relative pose, and p1 represents the first calibration point.

[0126] After obtaining the installation pose data of the first calibration point, the first-stage controlled installation process of the curtain wall glass can be carried out through the installation pose data. The installation process has been described in step 200 and will not be elaborated here. The schematic diagram of the top view of the installation result is as Figure 4 shown, and it can be seen that the characteristic corner points in the upper right corner have achieved alignment installation operations.

[0127] In some embodiments, step S400 can be implemented by the Figure 5 sub-steps shown as follows:

[0128] Step S401, use the PnP algorithm to perform coordinate transformation on the third calibration feature point to obtain the current spatial coordinates of the third calibration feature point in the spatial coordinate system of the curtain wall frame calibration plate; obtain the target spatial coordinates of the fourth calibration feature point in the spatial coordinate system of the curtain wall frame calibration plate.

[0129] Before coordinate transformation, that is, at this time, the control adjustment operation in the first stage has been executed, and the complete installation process of the first calibration point has been achieved. It is also necessary to obtain the relative pose [R0, t0] between the curtain wall glass and the curtain wall frame at this time, where R0 is the rotation matrix and t0 is the translation matrix. The specific acquisition method is the same as that in step S200. It should be understood that it is necessary to re-acquire the relative pose information of the image acquisition device relative to the curtain wall glass calibration plate and the relative pose information of the image acquisition device relative to the curtain wall frame calibration plate, and then use the image acquisition device as a transfer point to obtain the relative pose [R0, t0] of the curtain wall glass relative to the curtain wall frame. And it should be noted that the coordinate origin should still be set at the position of the first calibration point.

[0130] Obtain the spatial coordinates of the third calibration feature point in the spatial coordinate system of the curtain wall glass calibration plate, and perform coordinate transformation using the relative pose [R0, t0] between the current glass calibration plate and the curtain wall frame calibration plate to obtain the coordinates of the third calibration feature point in the spatial coordinate system of the curtain wall frame calibration plate, denoted as the current spatial coordinates.

[0131] As a specific example, the process of coordinate transformation can be expressed as P B ′ 0 = R0 · P B0 + t0, P B ′ 0 represents the current spatial coordinates of the third calibration feature point, and P B0 represents the spatial coordinates of the third calibration feature point in the spatial coordinate system of the curtain wall glass calibration plate.

[0132] Furthermore, the target spatial coordinates of the fourth calibration feature point in the spatial coordinate system of the curtain wall frame calibration plate can be directly obtained in the spatial coordinate system of the curtain wall frame calibration plate, and the target spatial coordinates also represent the target point that the third calibration feature point needs to reach for installation adjustment.

[0133] Step S402: Based on the current spatial coordinates and the coordinates of the first calibration feature point, determine the current spatial vector from the first calibration feature point to the third calibration feature point in the current pose; based on the target spatial coordinates and the coordinates of the first feature point, determine the target spatial vector from the first calibration feature point to the fourth calibration feature point in the current pose.

[0134] Specifically, after the adjustment of the first calibration point in the first stage, the position of the first calibration point remains fixed. Ignoring minor installation errors, it is approximately considered that the two calibration feature points of the first calibration point coincide, that is, the first calibration feature point and the second calibration feature point on the curtain wall glass calibration plate coincide after pose calibration adjustment. Therefore, the first calibration point does not distinguish between the current position and the coordinate position, and both are the coordinate origin.

[0135] Then, the current spatial vector v1 in the current pose can be expressed as v1 = P B ′ 0 - P A , P B ′ 0 represents the current spatial coordinates of the third calibration feature point, and P A represents the current coordinates of the first calibration feature point, which is also the coordinate origin. The target spatial vector v2 in the current pose can be expressed as v2 = P B ′ 1 - P A , P B ′ 1 represents the target spatial coordinates of the fourth calibration feature point in the spatial coordinate system of the curtain wall frame calibration plate.

[0136] It can be understood that the modulus of the current spatial vector v1 can be calculated through the current spatial coordinates of the third calibration feature point and the coordinates of the first calibration feature point, and the direction of the current spatial vector v1 is the direction from the first calibration feature point to the third calibration feature point. The modulus of the target spatial vector v2 can be calculated through the target spatial coordinates corresponding to the fourth calibration feature point and the coordinates of the first calibration feature point, and the direction of the target spatial vector v2 is the direction from the first calibration feature point to the fourth calibration feature point.

[0137] Step S403, obtain the third rotation matrix of the third calibration feature point according to the current spatial vector and the target spatial vector, and the installation pose data of the second calibration point includes the third rotation matrix.

[0138] Set the third rotation matrix as R B , when the third rotation matrix, the current spatial vector, and the target spatial vector satisfy a certain relationship, the corresponding third rotation matrix R can be solved B , specifically, under the constraint condition R B ·v1 = v2, use the SVD decomposition algorithm to solve the third rotation matrix R of the third calibration feature point B , v1 is the current spatial vector, and v2 is the target spatial vector.

[0139] Among them, the simple steps of SVD decomposition can be described as follows. First, calculate the covariance matrix Perform singular value decomposition on the covariance matrix H to obtain the third rotation matrix as R B = V·U T , both V and U are orthogonal matrices of singular value decomposition, which is a well-known technology and will not be introduced in detail here.

[0140] Finally, it should be noted that since the position of the first calibration point is fixed, no translation operation is required, and only rotation is needed. Therefore, the translation matrix corresponding to the installation pose data of the second calibration point is t B =[0, 0, 0] T , and the rotation matrix corresponding to the installation pose data of the second calibration point is the third rotation matrix.

[0141] So far, the second-stage control installation process of the curtain wall glass can be carried out through the installation pose data of the second calibration point. The installation process has been described in step 200 and will not be elaborated here. The schematic diagram of the side view of the installation result is as Figure 7 shown, and it can be seen that the two characteristic corner points belonging to the same side have achieved the alignment installation operation.

[0142] The present invention provides an automatic attitude calibration device for curtain wall glass installation, including a memory, a processor, and a computer program stored on the memory and running on the processor. When the computer program is executed by the processor, it implements the steps of an automatic attitude calibration method for curtain wall glass installation. As Figure 7 shown, the automatic attitude calibration device for curtain wall glass installation includes:

[0143] A data acquisition module, configured to acquire the initial pose information of the curtain wall glass calibration board and the curtain wall frame calibration board, where the initial pose information includes a rotation dimension and a translation dimension;

[0144] An installation pre-adjustment module, configured to perform matrix transformation operations according to the initial pose information to obtain the relative pose of the curtain wall glass calibration board and the curtain wall frame calibration board; and perform installation pre-adjustment on the curtain wall glass by using the relative pose;

[0145] A first-stage analysis module, configured to adjust the installation angle of the calibration feature points according to the pose performance of the calibration feature points corresponding to the curtain wall glass calibration board and the curtain wall frame calibration board after adjusting the coordinate origin, and obtain the installation pose data of the first calibration point;

[0146] A second-stage analysis module, configured to obtain the installation pose data of the second calibration point according to the relative position relationship of the calibration feature points corresponding to the curtain wall glass calibration board and the curtain wall frame calibration board;

[0147] A final attitude calibration module, configured to perform staged calibration on the curtain wall glass after installation pre-adjustment according to the installation pose data, and obtain the attitude calibration result of the curtain wall glass installation.

[0148] The embodiment of the present application also provides a computer device. Please refer to Figure 8, which shows a schematic structural diagram of a computer device provided by an embodiment of the present invention. The computer device includes a memory 801, a processor 802, and a computer program 803 stored in the memory 801 and running on the processor 802. When the processor 802 executes the computer program 803, the computer device can execute an automatic attitude calibration method for curtain wall glass installation introduced above.

[0149] An embodiment of the present application also provides a computer program product. When the computer program product runs on a computer device, the computer device can execute an automatic attitude calibration method for curtain wall glass installation introduced above.

[0150] An embodiment of the present application also provides a computer-readable storage medium. Computer program code is stored in the computer-readable storage medium. When the computer program code runs on a computer device, the computer device can execute an automatic attitude calibration method for curtain wall glass installation introduced above.

[0151] In the embodiments provided in the present application, it should be understood that the provided computer device, computer program product, and computer-readable storage medium are all used to execute the corresponding methods provided above. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the methods provided above, and will not be elaborated here.

[0152] The above embodiments are only used to illustrate the technical solutions of the present application, and are not intended to limit them. Although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features. These modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for automatic calibration of the posture of curtain wall glass installation, characterized in that: The method comprises the following steps: obtaining initial position information of a curtain wall glass calibration plate and a curtain wall frame calibration plate, wherein the initial position information comprises a rotation dimension and a translation dimension; Performing a matrix transformation operation according to the initial posture information to obtain the relative posture of the curtain wall glass calibration plate and the curtain wall frame calibration plate; and using the relative posture to pre-adjust the curtain wall glass for installation; According to the posture performance of the calibration feature points corresponding to the curtain wall glass calibration plate and the curtain wall frame calibration plate after adjusting the coordinate origin, adjusting the installation angle of the calibration feature points to obtain the installation posture data of the first calibration point; According to the relative position relationship of the calibration feature points corresponding to the curtain wall glass calibration plate and the curtain wall frame calibration plate, the installation posture data of the second calibration point is obtained; The curtain wall glass after installation pre-adjustment is calibrated in stages according to the installation posture data to obtain the posture calibration results of the curtain wall glass installation.

2. The method for automatic calibration of the installation posture of curtain wall glass according to claim 1, characterized in that: The obtaining of the initial position information of the curtain wall glass calibration plate and the curtain wall frame calibration plate specifically includes: Obtain a two-dimensional image of a curtain wall glass calibration plate and a two-dimensional image of a curtain wall frame calibration plate; For any two-dimensional image, based on the pixel coordinates of different pixel points on the two-dimensional image and the spatial coordinates of the corresponding pixels in the three-dimensional space, the coordinate origin of the three-dimensional space of the calibration plate is set to the center of mass of the calibration plate, and the PnP algorithm is used to obtain the first rotation matrix and the first translation matrix of the pixel coordinate system of the two-dimensional image relative to the corresponding calibration plate space coordinate system. The initial pose information includes the first rotation matrix and the first translation matrix.

3. The method for automatic calibration of the installation posture of curtain wall glass according to claim 1, characterized in that: The performing of a matrix transformation operation according to the initial posture information to obtain the relative posture of the curtain wall glass calibration plate and the curtain wall frame calibration plate specifically includes: Based on the initial posture information of the curtain wall glass calibration plate, determine the homogeneous coordinate matrix of the first relative posture of the curtain wall glass calibration plate to the image acquisition device; Performing inverse matrix transformation based on the initial posture information of the curtain wall frame calibration plate to determine a homogeneous coordinate matrix of a second relative posture from the image acquisition device to the curtain wall frame calibration plate; Determine a homogeneous coordinate matrix of a global relative pose between a curtain wall glass calibration plate and a curtain wall frame calibration plate based on the product of the homogeneous coordinate matrices between the first relative pose and the second relative pose; Based on the homogeneous coordinate matrix of the global relative pose, the relative pose of the curtain wall glass calibration plate and the curtain wall frame calibration plate is determined.

4. The method for automatic calibration of the installation posture of curtain wall glass according to claim 2, characterized in that: According to the posture performance of the calibration feature points corresponding to the curtain wall glass calibration plate and the curtain wall frame calibration plate after adjusting the coordinate origin, adjusting the installation angle of the calibration feature points to obtain the installation posture data of the first calibration point specifically includes: Obtain any set of corner points that correspond to and match the curtain wall glass calibration plate and the curtain wall frame calibration plate, and record them as the first calibration feature point and the second calibration feature point respectively; the first calibration point shown includes the first calibration feature point of the curtain wall glass calibration plate and the second calibration feature point of the curtain wall frame calibration plate; The coordinate origin of the three-dimensional space of the curtain wall glass calibration plate is set as the first calibration feature point, and the coordinate origin of the three-dimensional space of the curtain wall frame calibration plate is set as the second calibration feature point, and the first feature pose of the first calibration feature point and the second feature pose of the second calibration feature point are respectively obtained; Perform a matrix transformation operation according to the first feature pose and the second feature pose to obtain a relative pose of the first calibrated feature point and the second calibrated feature point; According to the difference between the actual measured size of the curtain wall glass and the actual measured size of the curtain wall frame, combined with the preset safety distance, the second translation matrix of the first calibration feature point is obtained; according to the spatial coordinate system of the curtain wall glass calibration plate and the preset rotation angle, the second rotation matrix of the first calibration feature point is obtained; Under the relative posture of the first calibration feature point and the second calibration feature point, the first calibration point is rotated according to the second rotation matrix and translated according to the second translation matrix to obtain the installation posture data of the first calibration point.

5. The method for automatic calibration of the installation posture of curtain wall glass according to claim 4, characterized in that: The method of obtaining the second translation matrix of the first calibration feature point according to the difference between the actual measured size of the curtain wall glass and the actual measured size of the curtain wall frame in combination with a preset safety distance specifically includes: Obtaining the actual measurement size of the curtain wall glass includes the actual length of each side of the curtain wall glass, and obtaining the actual measurement size of the curtain wall frame includes the actual length of each side of the curtain wall frame; Based on the difference in actual lengths of the corresponding sides between the curtain wall glass and the curtain wall frame, the single-sided installation redundant distance of each side of the curtain wall glass is determined, and the average of the single-sided installation redundant distances of all sides of the curtain wall glass is taken as the balanced redundant distance; the curtain wall glass calibration plate is moved in the negative direction to obtain the second translation matrix of the first calibration feature point.

6. The method for automatic calibration of the installation posture of curtain wall glass according to claim 4, characterized in that: The step of obtaining the second rotation matrix of the first calibration feature point according to the spatial coordinate system of the curtain wall glass calibration plate and the preset rotation angle specifically includes: The angle at which the curtain wall glass calibration plate is rotated along the x-axis is set to the preset rotation angle to obtain the x-axis rotation matrix; the angle at which the curtain wall glass calibration plate is rotated in the opposite direction along the y-axis is set to the preset rotation angle to obtain the y-axis rotation matrix; the product of the x-axis rotation matrix and the y-axis rotation matrix is ​​used as the second rotation matrix of the first calibration feature point.

7. The method for automatic calibration of the installation posture of curtain wall glass according to claim 4, characterized in that: The step of obtaining the installation posture data of the second calibration point according to the relative position relationship of the calibration feature points corresponding to the curtain wall glass calibration plate and the curtain wall frame calibration plate specifically includes: Obtain any corner point that is collinear with the first calibration feature point of the curtain wall glass calibration plate as the third calibration feature point, and use the corner point on the curtain wall frame calibration plate that matches the third calibration feature point as the fourth calibration feature point; the second calibration point includes the third calibration feature point and the fourth calibration feature point; The third calibration feature point is transformed by using the PnP algorithm to obtain the current spatial coordinates of the third calibration feature point in the spatial coordinate system of the curtain wall frame calibration plate; the target spatial coordinates of the fourth calibration feature point in the spatial coordinate system of the curtain wall frame calibration plate are obtained; Based on the current spatial coordinates and the coordinates of the first calibrated feature point, determine a current spatial vector pointing from the first calibrated feature point to the third calibrated feature point in the current position and posture; based on the target spatial coordinates and the coordinates of the first feature point, determine a target spatial vector pointing from the first calibrated feature point to the fourth calibrated feature point in the current position and posture; A third rotation matrix of the third calibration feature point is acquired according to the current space vector and the target space vector, and the installation posture data of the second calibration point includes the third rotation matrix.

8. The method for automatic calibration of the installation posture of curtain wall glass according to claim 7, characterized in that: The step of obtaining a third rotation matrix of the third calibration feature point according to the current space vector and the target space vector specifically includes: B When v1=v2, solve the third rotation matrix R of the third calibration feature point B , v1 is the current space vector, v2 is the target space vector.

9. The method for automatic calibration of the installation posture of curtain wall glass according to claim 1, characterized in that: The step of calibrating the pre-adjusted curtain wall glass in stages according to the installation posture data to obtain the posture calibration result of the curtain wall glass installation specifically includes: Based on the installation posture data of the first calibration point, the first stage calibration operation is performed on the curtain wall glass after pre-adjustment of the installation; based on the installation posture data of the second calibration point, the second stage calibration operation is performed on the curtain wall glass after the first stage calibration; the third stage relative posture of the current curtain wall glass calibration plate and the curtain wall frame calibration plate is obtained, and the curtain wall glass is finally adjusted using the third stage relative posture to obtain the posture calibration result of the curtain wall glass installation.

10. An automatic calibration device for the installation of curtain wall glass, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the computer program is executed by a processor, the steps of the method for automatic calibration of the posture of curtain wall glass installation as described in any one of claims 1 to 9 are implemented.

Images