Binocular Structured Light Detection Method, System, Device and Medium for Deformation of Building Components

Abstract

The present invention discloses a binocular structured light detection method, system, device and medium for the deformation of building components. The method includes: encoding the structured light information required for the deformation detection of the area to be detected of the building component and transmitting the encoded structured light information, performing three-dimensional reconstruction on the acquired input image based on the encoded structured light information to obtain a three-dimensional point cloud data sequence; sequentially performing feature point matching on the pre-data and post-data of the three-dimensional point cloud data sequence to obtain a displacement field; calculating a strain field based on the displacement field; and performing visualization processing on the displacement field and the strain field to obtain a displacement field vector diagram and a strain field vector diagram. The present invention uses a non-contact binocular structured light detection method, without the need for contact detection of the surface of the building component. Through three-dimensional reconstruction, feature point matching, calculation of the displacement field and the strain field, and visualization processing, a displacement field vector diagram and a strain field vector diagram are obtained, reducing the computational complexity and improving the deformation detection efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of deformation detection of building components, and particularly relates to a binocular structured light detection method, system, device and medium for deformation of building components. Background Art

[0002] When building components are subjected to external forces or temperature loads, etc., deformations such as tension, compression, shear, torsion and bending will occur. The occurrence of deformations in building components will not only affect the normal use of building components or the structures where the building components are located, causing a sense of insecurity in the users' psychology, but when the deformations develop to a certain extent, they will affect the safety of building components or the structures where the building components are located. Therefore, in order to ensure the normal and safe use of building components, it is very necessary to detect their deformations.

[0003] Currently, the deformation detection of building components mainly adopts the following two methods: one is the contact detection method using devices such as displacement gauges and resistance strain gauges, and the other is the non-contact detection method based on two-dimensional digital image correlation method (Two-dimensional Digital Image Correlation, 2D-DIC) or three-dimensional digital image correlation method (Three-dimensional Digital Image Correlation, 3D-DIC). However, both of these methods have their own limitations: the contact detection method using devices such as displacement gauges and resistance strain gauges requires the arrangement of multiple measuring points. Nevertheless, discrete point arrangement still cannot capture the complete deformation information of building components; secondly, when the object undergoes large deformations, contact devices such as resistance strain gauges will fall off. 2D-DIC uses a monocular camera for data acquisition and can only be used for in-plane deformation detection of the surface of planar objects, with certain limitations; 3D-DIC uses a binocular camera for data acquisition. Although it can perform in-plane and out-of-plane deformation detection of the object to be measured, its stereo matching depends on the feature information of the surface of the object to be measured. To achieve high matching accuracy, its computational complexity is high and the amount of calculation is large; in addition, for the detection methods based on 2D-DIC and 3D-DIC, their measurement accuracy is strongly related to the performance of hardware in the system such as cameras and lenses. Therefore, this type of detection method cannot meet the increasingly complex deformation detection requirements of building components. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to overcome the defects of high computational complexity and large amount of calculation in the existing methods for detecting the deformation of building components, and to provide a binocular structured light detection method, system, device and medium for the deformation of building components.

[0005] The present invention solves the above technical problem through the following technical solutions:

[0006] In the first aspect of the present invention, a binocular structured light detection method for the deformation of building components is provided. The binocular structured light detection method includes:

[0007] Encoding the structured light information required for the deformation detection of the area to be detected of the building component, and transmitting the encoded structured light information;

[0008] Collecting an input image of the area to be detected of the building component;

[0009] Performing three-dimensional reconstruction on the input image based on the encoded structured light information to obtain a three-dimensional point cloud data sequence of the deformation process of the area to be detected of the building component;

[0010] Performing feature point matching on the pre-order data and the post-order data of the three-dimensional point cloud data sequence in sequence to obtain a displacement field of the deformation process of the area to be detected of the building component;

[0011] Calculating a strain field of the deformation process of the area to be detected of the building component based on the displacement field;

[0012] Performing visualization processing on the displacement field and the strain field to obtain a displacement field vector diagram and a strain field vector diagram.

[0013] Preferably, before the step of collecting an input image of the area to be detected of the building component, the binocular structured light detection method further includes:

[0014] Adjusting the angle and the baseline distance between the first camera and the second camera to obtain an adjusted angle and an adjusted baseline distance;

[0015] The step of performing three-dimensional reconstruction on the input image based on the encoded structured light information to obtain a three-dimensional point cloud data sequence of the deformation process of the area to be detected of the building component includes:

[0016] Performing three-dimensional reconstruction on the input image based on the encoded structured light information, the adjusted angle, and the adjusted baseline distance to obtain a three-dimensional point cloud data sequence of the deformation process of the area to be detected of the building component.

[0017] Preferably, before the step of performing visualization processing on the displacement field and the strain field to obtain a displacement field vector diagram and a strain field vector diagram, the binocular structured light detection method further includes:

[0018] Storing and transmitting the displacement field and the strain field.

[0019] Preferably, the step of collecting an input image of the area to be detected of the building component includes:

[0020] Set the brightness of the structured light projector, the exposure times of the first camera and the second camera, and the time interval for sending the trigger signal;

[0021] Send the trigger signal to the structured light projector or the first camera or the second camera according to the time interval for sending the trigger signal;

[0022] Control the structured light projector to project the encoded structured light information onto the area to be detected of the building component according to the trigger signal, and control the first camera and the second camera to respectively collect the input images of the area to be detected of the building component;

[0023] and / or,

[0024] The step of performing feature point matching on the pre-order data and the post-order data of the three-dimensional point cloud data sequence in sequence to obtain the displacement field of the deformation process of the area to be detected of the building component includes:

[0025] Project the three-dimensional point cloud data sequence into a two-dimensional grayscale image sequence;

[0026] Divide the region of interest of the pre-order images in the two-dimensional grayscale image sequence;

[0027] Construct a set of interest points of the pre-order images based on the region of interest of the pre-order images;

[0028] Construct a set of candidate points of the post-order images corresponding to each interest point in the set of interest points of the pre-order images;

[0029] Perform feature point matching on the set of interest points of the pre-order images and the set of candidate points of the post-order images to obtain the displacement field of the deformation process of the area to be detected of the building component.

[0030] The second aspect of the present invention provides a binocular structured light detection system for building component deformation, and the binocular structured light detection system includes an image acquisition module, a three-dimensional reconstruction module, a feature point matching module, a calculation module and a visualization module;

[0031] The image acquisition module is used to encode the structured light information required for deformation detection of the area to be detected of the building component, and transmit the encoded structured light information;

[0032] The image acquisition module is used to collect the input images of the area to be detected of the building component;

[0033] The three-dimensional reconstruction module is used to perform three-dimensional reconstruction on the input images based on the encoded structured light information to obtain a three-dimensional point cloud data sequence of the deformation process of the area to be detected of the building component;

[0034] The feature point matching module is used to perform feature point matching on the pre-order data and post-order data of the 3D point cloud data sequence in turn to obtain the displacement field of the deformation process of the area to be detected of the building component;

[0035] The calculation module is used to calculate the strain field of the deformation process of the area to be detected of the building component based on the displacement field;

[0036] The visualization module is used to perform visualization processing on the displacement field and the strain field to obtain a displacement field vector diagram and a strain field vector diagram.

[0037] Preferably, the image acquisition module includes a first camera, a second camera, a device support device, and a core processor;

[0038] The core processor is used to adjust the angle between the first camera and the second camera and the baseline distance through the device support device to obtain the adjusted angle and the adjusted baseline distance;

[0039] The 3D reconstruction module is used to perform 3D reconstruction on the input image based on the encoded structured light information, the adjusted angle, and the adjusted baseline distance to obtain the 3D point cloud data sequence of the deformation process of the area to be detected of the building component.

[0040] Preferably, the binocular structured light detection system further includes a data dump module;

[0041] The data dump module is used to store and transmit the displacement field and the strain field.

[0042] Preferably, the image acquisition module further includes a structured light projector and an external trigger;

[0043] The core processor is used to set the brightness of the structured light projector, the exposure times of the first camera and the second camera, and the time interval for sending trigger signals;

[0044] The core processor is used to send the trigger signal to the structured light projector or the first camera or the second camera through the external trigger according to the time interval for sending trigger signals;

[0045] The core processor is used to control the structured light projector to project the encoded structured light information onto the area to be detected of the building component according to the trigger signal, and control the first camera and the second camera to respectively collect the input images of the area to be detected of the building component;

[0046] and / or,

[0047] The feature point matching module includes a projection unit, a partitioning unit, a first construction unit, a second construction unit, and a feature point matching unit;

[0048] The projection unit is configured to project the three-dimensional point cloud data sequence into a two-dimensional grayscale image sequence;

[0049] The partitioning unit is configured to partition the region of interest of the previous image in the two-dimensional grayscale image sequence;

[0050] The first construction unit is configured to construct a set of interest points of the previous image based on the region of interest of the previous image;

[0051] The second construction unit is configured to construct a set of candidate points of the subsequent image corresponding to each interest point in the set of interest points of the previous image;

[0052] The feature point matching unit is configured to perform feature point matching on the set of interest points of the previous image and the set of candidate points of the subsequent image to obtain a displacement field of the deformation process of the region to be detected of the building component.

[0053] A third aspect of the present invention provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the binocular structured light detection method for building component deformation as described in the first aspect is implemented.

[0054] A fourth aspect of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the binocular structured light detection method for building component deformation as described in the first aspect is implemented.

[0055] The positive and progressive effects of the present invention are as follows:

[0056] Through the non-contact binocular structured light detection method, the present invention does not require contact detection on the surface of the building component. By performing three-dimensional reconstruction on the input images, a three-dimensional point cloud data sequence of the deformation process of the region to be detected of the building component is obtained. Feature point matching is performed on the three-dimensional point cloud data sequence to obtain a displacement field, and a strain field is calculated through the displacement field. Furthermore, visualization processing is performed on the displacement field and the strain field to obtain a displacement field vector diagram and a strain field vector diagram, reducing the computational complexity and improving the deformation detection efficiency. Description of the Drawings

[0057] Figure 1 It is the first flow chart of the binocular structured light detection method for building component deformation in Embodiment 1 of the present invention.

[0058] Figure 2 It is the second flow chart of the binocular structured light detection method for building component deformation in Embodiment 1 of the present invention.

[0059] Figure 3 This is the third flowchart of the binocular structured light detection method for the deformation of building components in Embodiment 1 of the present invention.

[0060] Figure 4 This is the flowchart of step 102 of the binocular structured light detection method for the deformation of building components in Embodiment 1 of the present invention.

[0061] Figure 5 This is the flowchart of step 104 of the binocular structured light detection method for the deformation of building components in Embodiment 1 of the present invention.

[0062] Figure 6 This is the structural schematic diagram of the binocular structured light detection system for the deformation of building components in Embodiment 2 of the present invention.

[0063] Figure 7(a) is the first structural schematic diagram of the image acquisition module of the binocular structured light detection system for the deformation of building components in Embodiment 2 of the present invention.

[0064] Figure 7(b) is the second structural schematic diagram of the image acquisition module of the binocular structured light detection system for the deformation of building components in Embodiment 2 of the present invention.

[0065] Figure 8 This is the structural schematic diagram of the electronic device in Embodiment 3 of the present invention. Detailed implementation manners

[0066] The present invention will be further described below by way of embodiments, but the present invention is not limited to the scope of the described embodiments.

[0067] Embodiment 1

[0068] This embodiment provides a binocular structured light detection method for the deformation of building components. As Figure 1 shown, the binocular structured light detection method includes:

[0069] Step 101: Encode the structured light information required for the deformation detection of the area to be detected of the building component, and transmit the encoded structured light information;

[0070] In this embodiment, the structured light information required for the deformation detection of the area to be detected of the building component is encoded, and the encoded structured light information is burned into the structured light projector.

[0071] It should be noted that there are various methods for encoding structured light information. For example, the methods for encoding structured light information include, but are not limited to, the encoding method of combining Gray code and phase shift code based on time encoding, the DeBruijn encoding method based on space encoding, and the gray direct encoding method based on direct encoding, etc.

[0072] Step 102: Collect the input image of the area to be detected of the building component;

[0073] In this embodiment, speckles are prepared in the area to be detected on the surface of the building component, and the speckles are included in the input image. By recording the entire deformation process of the building component, the dynamic measurement of the deformation of the building component is realized. The so-called dynamic measurement means that when the area to be detected on the building component undergoes changes such as translation, stretching, and rotation, two cameras are required to record the speckles on the surface of the building component during the entire change process.

[0074] It should be noted that there are two methods for preparing speckles: one is to use the natural features of the area to be detected as speckles, and the other is to generate speckles by artificially spraying black and white paint.

[0075] Step 103: Perform three-dimensional reconstruction on the input image based on the encoded structured light information to obtain a sequence of three-dimensional point cloud data of the deformation process of the area to be detected on the building component;

[0076] In this embodiment, each point in the sequence of three-dimensional point cloud data includes three-dimensional coordinate information and grayscale information or three-dimensional coordinate information and color information.

[0077] It should be noted that the sequence of three-dimensional point cloud data refers to a multi-frame sequence of three-dimensional point cloud data sorted by time, which is obtained by performing three-dimensional reconstruction on the input images of the area to be detected on the building component in the order of acquisition time.

[0078] Step 104: Perform feature point matching on the pre-order data and post-order data of the sequence of three-dimensional point cloud data in turn to obtain the displacement field of the deformation process of the area to be detected on the building component;

[0079] In this embodiment, step 104 includes:

[0080] Step 104': Perform feature point matching on the pre-order data and post-order data of the sequence of three-dimensional point cloud data based on the three-dimensional coordinate information and grayscale information or three-dimensional coordinate information and color information in turn to obtain the displacement field of the deformation process of the area to be detected on the building component.

[0081] In this embodiment, feature point matching is performed on the pre-order data and post-order data of the sequence of three-dimensional point cloud data based on correlation analysis in turn to obtain the displacement field of the deformation process of the area to be detected on the building component.

[0082] It should be noted that the pre-order data and post-order data are two relative concepts. In the sequence of three-dimensional point cloud data, sorted by time, the pre-order data is the three-dimensional point cloud data before the post-order data, and the post-order data is the three-dimensional point cloud data after the pre-order data.

[0083] In addition, multiple groups of pre-sequence data and post-sequence data can be selected, and feature point matching is performed on each group of pre-sequence data and post-sequence data in chronological order to obtain a displacement field sequence sorted by time, so as to realize the tracking of the continuous deformation process of the area to be detected of the building component.

[0084] Step 105: Calculate the strain field of the deformation process of the area to be detected of the building component based on the displacement field;

[0085] In this embodiment, the strain field of the deformation process of the area to be detected of the building component is calculated based on the displacement field by using the geometric equation.

[0086] Step 106: Perform visualization processing on the displacement field and the strain field to obtain a displacement field vector diagram and a strain field vector diagram.

[0087] In this embodiment, the displacement field and the strain field are visualized as a displacement field vector diagram and a strain field vector diagram and displayed.

[0088] In an implementable solution, as Figure 2 shown, before step 102, the binocular structured light detection method further includes:

[0089] Step 101-1: Adjust the angle and baseline distance between the first camera and the second camera to obtain the adjusted angle and the adjusted baseline distance;

[0090] In this embodiment, the first camera and the second camera can be a left camera and a right camera;

[0091] It should be noted that the physical properties of the two cameras are the same, and both are used to collect optical two-dimensional images of the building component.

[0092] In this embodiment, the left camera is fixedly connected to the left rotating base, and a left sliding motor is arranged at the bottom of the left rotating base. The left rotating motor controls the left camera to rotate at an angle in the plane to realize the automatic adjustment of the angle between the main optical axes of the two cameras, and the left sliding motor automatically adjusts the left rotating base to move linearly on the support rod to realize the automatic adjustment of the baseline distance between the two cameras; similarly, the right camera is fixedly connected to the right rotating base, and a right sliding motor is arranged at the bottom of the right rotating base. The right rotating motor controls the right camera to rotate at an angle in the plane to realize the automatic adjustment of the angle between the main optical axes of the two cameras, and the right sliding motor automatically adjusts the right rotating base to move linearly on the support rod to realize the automatic adjustment of the baseline distance between the two cameras.

[0093] In this embodiment, two parameters, namely the size of the building component and the working distance of the detection system, are obtained, and two other parameters, namely the angle between the principal optical axes of the two cameras and the baseline distance between the two cameras, are calculated. The angle between the principal optical axes of the two cameras and the baseline distance between the two cameras are automatically adjusted by controlling the rotating motor and the sliding motor, so that the highest deformation detection accuracy can be achieved within the effective field of view of the detection system for the building component.

[0094] In this embodiment, when adjusting the angle between the principal optical axes of the first camera and the second camera and the baseline distance between the two cameras, it should be noted that the angle between the principal optical axes of the two cameras can generally be adjusted within the range of 15° to 60°, or can be adjusted within other ranges according to the actual situation, and the baseline distance is adjusted according to the actual situation, and no specific limitation is made here.

[0095] Step 103 includes:

[0096] Step 103': Based on the encoded structured light information, the adjusted angle, and the adjusted baseline distance, perform three-dimensional reconstruction on the input image to obtain a three-dimensional point cloud data sequence of the deformation process of the area to be detected of the building component.

[0097] In an implementable solution, as Figure 3 shown, before step 106, this binocular structured light detection method further includes:

[0098] Step 106-1: Store and transmit the displacement field and the strain field.

[0099] In this embodiment, the displacement field and the strain field are stored in the local data storage device, and at the same time, according to the received data dump command, the displacement field and the strain field are transmitted.

[0100] In an implementable solution, as Figure 4 shown, step 102 includes:

[0101] Step 1021: Set the brightness of the structured light projector, the exposure times of the first camera and the second camera, and the time interval for sending the trigger signal;

[0102] In the specific implementation process, first manually adjust the focal length of the structured light projector and the image distances and apertures of the first camera and the second camera; specifically, turn the focal length adjustment lever on the structured light projector to adjust the focal length of the structured light projector so that the structured light image is clearly presented in the area to be detected of the building component; by rotating the focus adjustment ring and the aperture adjustment ring, adjust the image distances and apertures of the two cameras to make the imaging clearer.

[0103] In this embodiment, the brightness of the structured light projector, the exposure times of the two cameras, and the time interval for sending the trigger signal are set; the brightness of the structured light projector and the exposure times of the two cameras are set according to the ambient illumination, and the time interval of the trigger signal is set according to the deformation rate of the building component.

[0104] Step 1022: Send a trigger signal to the structured light projector, the first camera, or the second camera at the time interval for sending the trigger signal.

[0105] In this embodiment, when starting to collect input images, a trigger signal is sent once every set time interval until the input image collection stops; the specific method for the central processing unit (such as a microprocessing unit) to trigger the structured light projector and the two cameras is as follows: send a trigger signal to the structured light projector, and the trigger signal is transmitted to the two cameras through an external trigger to synchronously trigger the two cameras; the specific method for the central processing unit to trigger the structured light projector and the two cameras can also be: send a trigger signal to the left camera, and the trigger signal is transmitted to the structured light projector and the right camera through an external trigger to synchronously trigger the structured light projector and the right camera; the specific method for the central processing unit to trigger the structured light projector and the two cameras can also be: send a trigger signal to the right camera, and the trigger signal is transmitted to the structured light projector and the left camera through an external trigger to synchronously trigger the structured light projector and the left camera.

[0106] Step 1023: Control the structured light projector to project the encoded structured light information to the area to be detected of the building component according to the trigger signal, and control the first camera and the second camera to respectively collect the input images of the area to be detected of the building component.

[0107] In this embodiment, every time a trigger signal is received, the structured light projector projects the encoded structured light information to the area to be detected of the building component, and at the same time, the left and right cameras respectively collect the input images.

[0108] This embodiment is based on the optical measurement principle and adopts a non-contact three-dimensional deformation field detection method, without the need for contact detection on the surface of the building component; at the same time, this embodiment actively encodes the structured light information required for the deformation detection of the area to be detected of the building component and transmits the encoded structured light information. The three-dimensional reconstruction of the deformation process of the building component does not depend on the surface feature information of the area to be detected, but is based on the encoded structured light information, reducing the computational complexity and improving the deformation detection efficiency; further, the effective field of view range is changed by adjusting the included angle of the principal optical axes of the two cameras and the baseline distance between the two cameras; under the condition of uniform ambient light, the brightness of the structured light projector and the exposure times of the two cameras can be reasonably set to simply achieve a high-precision description of the deformation degree of the building component, with simple operation and control and good application prospects.

[0109] In an implementable solution, as Figure 5 shown, step 104 includes:

[0110] Step 1041: Project the three-dimensional point cloud data sequence into a two-dimensional grayscale image sequence;

[0111] In this embodiment, combining the internal and external parameters of two cameras and a structured light projector, the three-dimensional point cloud data sequence in the world coordinate system is projected into a two-dimensional grayscale image sequence. Specifically, along the line of sight of the left camera or the right camera, all the three-dimensional point cloud data sorted by time in the three-dimensional point cloud data sequence are sequentially projected onto the imaging plane of the left camera or the right camera, and it is dimension-reduced into two-dimensional grayscale image data, thereby constituting a two-dimensional grayscale image sequence. The calculation formula is formula (1):

[0112]

[0113] where Z c represents the Z-axis coordinate value in the coordinate system of the left camera or the right camera; (x, y) represents the coordinates in the pixel coordinate system of the left camera or the right camera; I represents the internal parameter matrix of the left camera or the right camera; R represents the rotation matrix between the world coordinate system and the pixel coordinate system of the left camera or the right camera; T represents the translation matrix between the world coordinate system and the pixel coordinate system of the left camera or the right camera; (X w , Y w , Z w ) represents the coordinates in the world coordinate system.

[0114] It should be noted that the grayscale value of each pixel point (x, y) in the two-dimensional grayscale image is the value after grayscale processing of the grayscale information or color information of the three-dimensional point (X w , Y w , Z w ).

[0115] Step 1042: Divide the region of interest of the previous image in the two-dimensional grayscale image sequence;

[0116] It should be noted that the previous image and the subsequent image are two relative concepts. In the two-dimensional grayscale image sequence, sorted by time, the previous image is the two-dimensional grayscale image before the subsequent image, and the subsequent image is the two-dimensional grayscale image after the previous image.

[0117] Step 1043: Construct a set of interest points of the previous image based on the region of interest of the previous image;

[0118] In this embodiment, in the region of interest defined in each pre-image in the two-dimensional grayscale image sequence, an interest point set of the pre-image is constructed, that is: an initial starting point P0 is selected in the region of interest, a suitable search step length L is set, and the search is carried out according to the step length L to construct the interest point set of the pre-image, and a reference region is constructed with each interest point P(x0, y0) in the interest point set as the center. The reference region contains (2m + 1) × (2m + 1) (m ∈ N) reference points, and the coordinates of each reference point Q(x, y) in the reference region can be expressed by formula (2):

[0119]

[0120] Step 1044: Construct a candidate point set of the post-image corresponding to each interest point in the interest point set of the pre-image;

[0121] In this embodiment, a candidate point set of the post-image is constructed based on each interest point in the interest point set of the pre-image, that is: for each point P(x0, y0) in the interest point set, a candidate point set on the post-image is constructed. The candidate point set contains n (n ∈ N) candidate points, and the coordinates of each candidate point P * (x0 * , y0 * ) can be expressed by formula (3):

[0122]

[0123] With each candidate point P * (x0 * , y0 * ) in the candidate point set as the center, a target region is constructed. The target region contains (2m + 1) × (2n + 1) (m ∈ N) target points, and the coordinates of each target point Q * (x * , y * ) can be expressed by formula (4):

[0124]

[0125] Step 1045: Perform feature point matching on the interest point set of the pre-image and the candidate point set of the post-image to obtain the displacement field of the deformation process of the region to be detected of the building component.

[0126] In this embodiment, each interest point in the interest point set of the pre-image is matched with its candidate point set on the post-image based on the gray value, that is: the sum of squared differences of zero-mean normalized cross-correlation (C ZNSSD ) can be selected as one of the correlation indexes, or other correlation indexes can be selected. For the reference region of the interest point P(x0, y0) and each candidate point P * (x0* , y0 * Calculate the correlation for the target area of (), set the threshold C0 for the correlation index. When C ZNSSD reaches the minimum value and this value is less than the set threshold C0, then the candidate point P * (x0 * , y0 * ) is taken as the corresponding point of the point of interest P(x0, y0). The specific calculation formula of C ZNSSD is as shown in formula (5):

[0127]

[0128] For each point of interest P(x0, y0) in the set of points of interest and its corresponding point P * (x0 * , y0 * ), map them to three dimensions to obtain the feature point M(x, y, z) and its corresponding point M * (x * , y * , z * ) and form a set of feature point pairs.

[0129] In particular, the meanings of the symbols in formulas (2), (3), (4), and (5) are explained as follows: Δx, Δy: The distances between the reference point Q and the point of interest P in the x - direction and y - direction, which can be adjusted according to the set number of reference points (2m + 1)×(2m + 1) (m ∈ N); u, v: The distances that the candidate point P * moves in the x - direction and y - direction compared to the point of interest P, which can be adjusted according to the set number of candidate points n (n ∈ N); Ω: The set of reference points Q in the reference area; F(x, y): The gray - scale value of the reference point Q(x, y) in the reference area; G * (x * , y * ): The gray - scale value of the target point Q * (x * , y * ) in the target area; The average gray - scale value of the reference point Q(x, y) in the reference area; The target point Q in the target area * (x * , y * )'s average gray - scale value.

[0130] In this embodiment, for each feature point pair M(x, y, z) and M * (x * , y * , z *) Calculate the displacement value of the feature point M(x, y, z) using the following formula (6):

[0131]

[0132] It should be noted that the displacement values of each feature point in the feature point pair set constitute a displacement field.

[0133] Step 105: Calculate the strain field of the deformation process of the area to be detected of the building component based on the displacement field; specifically:

[0134] Calculate the normal strain of the feature point M(x, y, z) based on the geometric equation using formula (7):

[0135]

[0136] Calculate the shear strain of the feature point M(x, y, z) based on the geometric equation using formula (8):

[0137]

[0138] Specifically, the symbolic meanings of formulas (6), (7), and (8) are explained as follows: X(x, y, z), Y(x, y, z), Z(x, y, z): the x, y, z coordinates of the feature point M(x, y, z); X(x*, y*, z*), Y(x*, y*, z*), Z(x*, y*, z*): the x, y, z coordinates of the feature point M * (x * , y * , z * ); U, V, W: the displacements of the feature point M(x, y, z) in the x, y, z directions; ε x , ε y , ε z : the normal strains of the feature point M(x, y, z) in the x, y, z directions; γ xy , γ yz , γ zx : the shear strains of the feature point M(x, y, z) in the x-y direction, y-z direction, and z-x direction.

[0139] It should be noted that the normal strains and shear strains of each feature point in the feature point pair set constitute a strain field.

[0140] In this embodiment, through the non-contact binocular structured light detection method, there is no need to perform contact detection on the surface of building components. By performing three-dimensional reconstruction on the input image, a three-dimensional point cloud data sequence of the deformation process of the area to be detected of the building component is obtained. Feature point matching is performed on the three-dimensional point cloud data sequence to obtain a displacement field, and a strain field is calculated through the displacement field. Furthermore, visualization processing is performed on the displacement field and the strain field to obtain a displacement field vector diagram and a strain field vector diagram, reducing the computational complexity and improving the deformation detection efficiency.

[0141] Embodiment 2

[0142] This embodiment provides a binocular structured light detection system for the deformation of building components, as Figure 6 shown. The binocular structured light detection system includes an image acquisition module 21, a three-dimensional reconstruction module 22, a feature point matching module 23, a calculation module 24, and a visualization module 25;

[0143] The image acquisition module 21 is used to encode the structured light information required for the deformation detection of the area to be detected of the building component and transmit the encoded structured light information;

[0144] In this embodiment, the structured light information required for the deformation detection of the area to be measured of the building component is encoded, and the encoded structured light information is burned into the structured light projector.

[0145] It should be noted that there are various methods for encoding structured light information. For example, the methods for encoding structured light information include, but are not limited to, the encoding method of combining Gray code with phase shift code based on time encoding, the DeBruijn encoding method based on spatial encoding, and the gray direct encoding method based on direct encoding, etc.

[0146] In this embodiment, the encoded structured light information is projected onto the area to be detected of the building component through the structured light projector in the image acquisition module;

[0147] The image acquisition module 21 is used to acquire the input image of the area to be detected of the building component;

[0148] In this embodiment, speckles are prepared in the area to be detected on the surface of the building component, and the speckles are included in the input image. By recording the entire deformation process of the building component, dynamic measurement of the deformation of the building component can be achieved. The so-called dynamic measurement means that when the area to be detected of the building component undergoes changes such as translation, stretching, and rotation, two cameras are required to record the speckles on the surface of the building component during the entire change process.

[0149] It should be noted that there are two methods for preparing speckles: one is to use the natural features of the area to be detected as speckles, and the other is to generate speckles by manually spraying black and white paint.

[0150] The 3D reconstruction module 22 is used to perform 3D reconstruction on the input image based on the encoded structured light information to obtain a sequence of 3D point cloud data of the deformation process of the area to be detected of the building component;

[0151] In this embodiment, each point in the sequence of 3D point cloud data includes 3D coordinate information and grayscale information or 3D coordinate information and color information.

[0152] It should be noted that the sequence of 3D point cloud data refers to a sequence of multiple frames of 3D point cloud data sorted by time obtained by performing 3D reconstruction on the input images of the area to be detected of the building component in the order of acquisition time.

[0153] The feature point matching module 23 is used to perform feature point matching on the previous data and the subsequent data of the sequence of 3D point cloud data in turn to obtain the displacement field of the deformation process of the area to be detected of the building component;

[0154] In this embodiment, the feature point matching module 23 is used to perform feature point matching on the previous data and the subsequent data of the sequence of 3D point cloud data based on the 3D coordinate information and grayscale information or 3D coordinate information and color information in turn to obtain the displacement field of the deformation process of the area to be detected of the building component.

[0155] In this embodiment, based on the correlation analysis, feature point matching is performed on the previous data and the subsequent data of the sequence of 3D point cloud data in turn to obtain the displacement field of the deformation process of the area to be detected of the building component.

[0156] It should be noted that the previous data and the subsequent data are two relative concepts. In the sequence of 3D point cloud data, sorted by time, the previous data is the 3D point cloud data before the subsequent data, and the subsequent data is the 3D point cloud data after the previous data.

[0157] In addition, multiple groups of previous data and subsequent data can be selected, and feature point matching is performed on each group of previous data and subsequent data in the order of time to obtain a sequence of displacement fields sorted by time, so as to realize the tracking of the continuous deformation process of the area to be detected of the building component.

[0158] The calculation module 24 is used to calculate the strain field of the deformation process of the area to be detected of the building component based on the displacement field;

[0159] In this embodiment, based on the displacement field, the strain field of the deformation process of the area to be detected of the building component is calculated using the geometric equation.

[0160] The visualization module 25 is used to perform visualization processing on the displacement field and the strain field to obtain a displacement field vector diagram and a strain field vector diagram.

[0161] In this embodiment, the displacement field and the strain field are visualized as a displacement field vector diagram and a strain field vector diagram and displayed.

[0162] In an implementable solution, as shown in FIG. 7(a), the image acquisition module 21 includes a first camera 121, a second camera 122, a device support device 140, and a core processor 150;

[0163] The core processor 150 is used to adjust the included angle and the baseline distance between the first camera 121 and the second camera 122 through the device support device 140 to obtain the adjusted included angle and the adjusted baseline distance;

[0164] In this embodiment, the core processor can be a PC or other devices, and no specific limitation is made here.

[0165] In this embodiment, the first camera 121 and the second camera 122 can be a left camera 121 and a right camera 122;

[0166] It should be noted that the physical properties of the two cameras are the same, and both are used to collect optical two-dimensional images of building components.

[0167] In this embodiment, the left camera is fixedly connected to the left rotating base, and a left sliding motor is arranged at the bottom of the left rotating base. The left rotating motor controls the left camera to rotate at an angle in a plane to realize the automatic adjustment of the included angle between the main optical axes of the two cameras. The left sliding motor automatically adjusts the left rotating base to move linearly on the support rod to realize the automatic adjustment of the baseline distance between the two cameras; Similarly, the right camera is fixedly connected to the right rotating base, and a right sliding motor is arranged at the bottom of the right rotating base. The right rotating motor controls the right camera to rotate at an angle in a plane to realize the automatic adjustment of the included angle between the main optical axes of the two cameras. The right sliding motor automatically adjusts the right rotating base to move linearly on the support rod to realize the automatic adjustment of the baseline distance between the two cameras.

[0168] In this embodiment, two parameters, namely the size of the building component and the working distance of the detection system, are obtained, and two parameters, namely the included angle between the main optical axes of the two cameras and the baseline distance between the two cameras, are calculated. The included angle between the main optical axes of the two cameras and the baseline distance between the two cameras are automatically adjusted by controlling the rotating motor and the sliding motor, so that the highest deformation detection accuracy can be achieved within the effective field of view of the detection system for the building component.

[0169] In this embodiment, when adjusting the included angle between the main optical axes of the first camera and the second camera and the baseline distance between the two cameras, it should be noted that the included angle between the main optical axes of the two cameras can usually be adjusted within the range of 15° to 60°, or can be adjusted within other ranges according to the actual situation. The baseline distance is adjusted according to the actual situation, and no specific limitation is made here.

[0170] The 3D reconstruction module 22 is used to perform 3D reconstruction on the input image based on the encoded structured light information, the adjusted included angle, and the adjusted baseline distance, so as to obtain a sequence of 3D point cloud data of the deformation process of the area to be detected of the building component.

[0171] In an implementable solution, as Figure 6 shown, the binocular structured light detection system further includes a data dump module 26;

[0172] The data dump module 26 is used to store and transmit the displacement field and the strain field.

[0173] In this embodiment, the displacement field and the strain field are stored in a local data storage device, and at the same time, according to the received data dump command, the displacement field and the strain field are transmitted.

[0174] In an implementable solution, as Figure 7(a)-7(b) shown, the image acquisition module 21 further includes a structured light projector 110 and an external trigger 130;

[0175] The core processor 150 is used to set the brightness of the structured light projector 110, the exposure times of the first camera 121 and the second camera 122, and the time interval for sending trigger signals;

[0176] In the specific implementation process, first manually adjust the focal length of the structured light projector 110 and the image distances and apertures of the first camera 121 and the second camera 122; specifically, turn the focal length adjustment lever on the structured light projector to adjust the focal length of the structured light projector so that the structured light image clearly appears in the area to be detected of the building component; by rotating the focus adjustment ring and the aperture adjustment ring, adjust the image distances and apertures of the two cameras to make the imaging clearer.

[0177] In this embodiment, set the brightness of the structured light projector, the exposure times of the two cameras, and the time interval for sending trigger signals; the brightness of the structured light projector and the exposure times of the two cameras are set according to the ambient illumination, and the time interval of the trigger signal is set according to the deformation rate of the building component.

[0178] The core processor 150 is used to send trigger signals to the structured light projector 110 or the first camera 121 or the second camera 1221 through the external trigger 130 at the time interval of sending trigger signals;

[0179] In this embodiment, when starting the input image acquisition, a trigger signal is sent at every set time interval until the input image acquisition stops. The specific methods for the central processing unit (such as a microprocessing unit) to trigger the structured light projector and the two cameras are as follows: sending a trigger signal to the structured light projector, and the trigger signal is transmitted to the two cameras through an external trigger to synchronously trigger the two cameras; the specific method for the central processing unit to trigger the structured light projector and the two cameras can also be: sending a trigger signal to the left camera, and the trigger signal is transmitted to the structured light projector and the right camera through an external trigger to synchronously trigger the structured light projector and the right camera; the specific method for the central processing unit to trigger the structured light projector and the two cameras can also be: sending a trigger signal to the right camera, and the trigger signal is transmitted to the structured light projector and the left camera through an external trigger to synchronously trigger the structured light projector and the left camera.

[0180] The central processing unit 150 is configured to control the structured light projector 110 to project encoded structured light information to the area to be detected of the building component according to the trigger signal, and control the first camera 121 and the second camera 122 to respectively acquire input images of the area to be detected of the building component.

[0181] In this embodiment, every time a trigger signal is received, the structured light projector projects encoded structured light information to the area to be detected of the building component, and at the same time, the left and right cameras respectively acquire input images.

[0182] In the specific implementation process, as shown in FIG. 7(b), the image acquisition module 21 includes a support base 144. Two support rods 143 are installed on the support base 144. The two support rods 143 pass through two camera rotating bases 141 and the fixed base 142 of the structured light projector 110. The two camera rotating bases 141 are respectively located on the left and right sides of the fixed base 142 of the structured light projector 110. The left camera 121 and the right camera 122 are respectively installed on the two camera rotating bases 141. Each of the two camera rotating bases 141 is equipped with a rotating motor and a sliding motor. The rotating motor enables the two cameras to automatically rotate parallel to the two camera rotating bases. The sliding motor enables the two camera rotating bases to automatically slide on the two support rods. The structured light projector 110 is installed on the base 142. The fixed base 142 of the structured light projector 110 is equipped with a sliding motor, enabling the fixed base 142 of the structured light projector 110 to automatically slide on the two support rods 143. The core processor 150 sends a trigger signal to the structured light projector 110, the left camera 121 or the right camera 122 through the external trigger 130. The core processor 150 transmits the encoded structured light information to the structured light projector 110 through the data transmission line 160. The left camera 121 and the right camera 122 transmit image signals to the core processor 150 through the data transmission line 160. The core processor 150 controls the rotating motor and the sliding motor to automatically adjust the included angle of the main optical axes of the left camera 121 and the right camera 122 and the baseline distance between the left camera 121 and the right camera 122.

[0183] This embodiment is based on the optical measurement principle and adopts a non-contact three-dimensional deformation field detection method, without the need for contact detection of the surface of building components. At the same time, this embodiment actively encodes the structured light information required for the deformation detection of the area to be detected of the building component and transmits the encoded structured light information. The three-dimensional reconstruction of the deformation process of the building component does not depend on the surface feature information of the area to be detected, but is based on the encoded structured light information, reducing the computational complexity and improving the deformation detection efficiency. Further, by adjusting the included angle of the main optical axes of the two cameras and the baseline distance between the two cameras, the effective field of view range is changed. Under the condition of uniform ambient light, the deformation degree of the building component can be simply and accurately described by reasonably setting the brightness of the structured light projector and the exposure time of the two cameras. The operation and control are simple, and it has good application prospects.

[0184] In an implementable solution, as Figure 6 shown, the feature point matching module 23 includes a projection unit 231, a division unit 232, a first construction unit 233, a second construction unit 234, and a feature point matching unit 235;

[0185] The projection unit 231 is used to project the three-dimensional point cloud data sequence into a two-dimensional grayscale image sequence;

[0186] In this embodiment, by combining the internal and external parameters of two cameras and a structured light projector, a sequence of three-dimensional point cloud data in the world coordinate system is projected into a sequence of two-dimensional grayscale images. Specifically, all the three-dimensional point cloud data sorted by time in the sequence of three-dimensional point cloud data are projected onto the imaging plane of the left camera or the right camera along the line of sight of the left camera or the right camera, and are reduced to two-dimensional grayscale image data, thereby constituting a sequence of two-dimensional grayscale images. The calculation formula is formula (1) in Embodiment 1;

[0187] The partitioning unit 232 is configured to partition the region of interest of the previous images in the sequence of two-dimensional grayscale images;

[0188] It should be noted that the previous image and the subsequent image are two relative concepts. In the sequence of two-dimensional grayscale images, sorted by time, the previous image is a two-dimensional grayscale image that comes before the subsequent image, and the subsequent image is a two-dimensional grayscale image that comes after the previous image.

[0189] The first construction unit 233 is configured to construct a set of interest points of the previous image based on the region of interest of the previous image;

[0190] In this embodiment, a set of interest points of the previous image is constructed in the region of interest delimited by each previous image in the sequence of two-dimensional grayscale images, that is: in the region of interest, an initial starting point P0 is selected, a suitable search step length L is set, and search is performed according to the step length L to construct a set of interest points of the previous image, and a reference region is constructed with each interest point P(x0, y0) in the set of interest points as the center. The reference region contains (2m + 1)×(2m + 1) (m ∈ N) reference points, and the coordinates of each reference point Q(x, y) in the reference region can be expressed by formula (2) in Embodiment 1:

[0191] The second construction unit 234 is configured to construct a set of candidate points of the subsequent image corresponding to each interest point in the set of interest points of the previous image;

[0192] In this embodiment, a set of candidate points of the subsequent image is constructed for each interest point in the set of interest points of the previous image, that is: for each point P(x0, y0) in the set of interest points, a set of candidate points of the subsequent image is constructed, and the set of candidate points contains n (n ∈ N) candidate points. The coordinates of each candidate point P * (x0 * ,y0 * ) can be expressed by formula (3) in Embodiment 1;

[0193] For each candidate point P in the set of candidate points * (x0 * ,y0 *)Construct a target area centered on it. The target area contains (2m + 1) × (2m + 1) (m ∈ N) target points. Each target point Q in the target area * (x * ,y * ) coordinates can be expressed by formula (4) of Embodiment 1.

[0194] The feature point matching unit 235 is used to perform feature point matching on the pre-image interest point set and the post-image candidate point set to obtain the displacement field of the deformation process of the building component to be detected area.

[0195] In this embodiment, each interest point in the pre-image interest point set is matched with its candidate point set in the post-image based on the gray value, that is: the sum of squared differences of zero-mean normalized cross-correlation (C ZNSSD ) can be selected as one of the correlation metrics, or other correlation metrics can be selected. The reference area of the interest point P(x0, y0) and each candidate point P in its candidate point set * (x0 * ,y0 * ) target area for correlation calculation, set the threshold C0 of the correlation metric. When C ZNSSD takes the minimum value and this value is less than the set threshold C0, then the candidate point P * (x0 * ,y0 * ) is used as the corresponding point of the interest point P(x0, y0). The specific calculation formula of C ZNSSD is as shown in formula (5) of Embodiment 1;

[0196] Map each interest point P(x0, y0) in the interest point set and its corresponding point P * (x0 * ,y0 * ) to three dimensions to obtain the feature point M(x, y, z) and its corresponding point M * (x * ,y * ,z * ) and form a set of feature point pairs.

[0197] Specifically, the symbolic meanings of formulas (2), (3), (4), and (5) are explained as follows: Δx, Δy: the distances between the reference point Q and the interest point P in the x-direction and y-direction, which can be adjusted according to the set number of reference points (2m + 1) × (2m + 1) (m ∈ N); u, v: the distances that the candidate point P * moves in the x-direction and y-direction compared to the interest point P, which can be adjusted according to the set number of candidate points n (n ∈ N); Ω: the set of reference points Q in the reference area; F(x, y): the gray value of the reference point Q(x, y) in the reference area; G * (x* , y * ): The target point Q in the target area * (x * , y * )'s grayscale value; The average grayscale value of the reference point Q(x, y) in the reference area; The target point Q in the target area * (x * , y * )'s average grayscale value.

[0198] In this embodiment, for each feature point pair M(x, y, z) and M in the obtained set of feature point pairs according to the above * (x * , y * , z * ), the displacement value of the feature point M(x, y, z) is calculated using formula (6) of Embodiment 1; it should be noted that the displacement values of each feature point in the set of feature point pairs constitute a displacement field.

[0199] The calculation module 24 is used to calculate the strain field of the deformation process of the area to be detected of the building component based on the displacement field. Specifically, the normal strain of the feature point M(x, y, z) is calculated using formula (7) of Embodiment 1 based on the geometric equation; and the shear strain of the feature point M(x, y, z) is calculated using formula (8) of Embodiment 1 based on the geometric equation;

[0200] Specifically, the symbolic meanings of formulas (6), (7), and (8) are explained as follows: X(x, y, z), Y(x, y, z), Z(x, y, z): the x, y, z coordinates of the feature point M(x, y, z); X(x*, y*, z*), Y(x*, y*, z*), Z(x*, y*, z*): the feature point M * (x * , y * , z * )'s x, y, z coordinates; U, V, W: the displacements of the feature point M(x, y, z) in the x, y, z directions; ε x , ε y , ε z : the normal strains of the feature point M(x, y, z) in the x, y, z directions; γ xy , γ yz , γ zx : the shear strains of the feature point M(x, y, z) in the x-y direction, y-z direction, and z-x direction.

[0201] It should be noted that the normal strains and shear strains of each feature point in the set of feature point pairs constitute a strain field.

[0202] In this embodiment, through a non-contact binocular structured light detection method, there is no need to perform contact detection on the surface of building components. By performing 3D reconstruction on the input image, a 3D point cloud data sequence of the deformation process of the area to be detected of the building components is obtained. Feature point matching is performed on the 3D point cloud data sequence to obtain a displacement field, and a strain field is calculated through the displacement field. Furthermore, visualization processing is performed on the displacement field and the strain field to obtain a displacement field vector diagram and a strain field vector diagram, reducing the computational complexity and improving the deformation detection efficiency.

[0203] Embodiment 3

[0204] Figure 8 FIG. is a schematic structural diagram of an electronic device provided in Embodiment 3 of the present invention. The electronic device includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the binocular structured light detection method for the deformation of building components in Embodiment 1. Figure 8 The electronic device 30 shown is merely an example and should not impose any limitation on the functions and usage scope of the embodiments of the present invention.

[0205] As Figure 8 shown, the electronic device 30 may be presented in the form of a general-purpose computing device, for example, it may be a server device. The components of the electronic device 30 may include but are not limited to: at least one of the above-mentioned processors 31, at least one of the above-mentioned memories 32, and a bus 33 connecting different system components (including the memory 32 and the processor 31).

[0206] The bus 33 includes a data bus, an address bus, and a control bus.

[0207] The memory 32 may include volatile memory, such as a random access memory (RAM) 321 and / or a cache memory 322, and may further include a read-only memory (ROM) 323.

[0208] The memory 32 may further include a program / utilities 325 having a set (at least one) of program modules 324. Such program modules 324 include but are not limited to: an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include the implementation of a network environment.

[0209] The processor 31 executes various functional applications and data processing by running the computer program stored in the memory 32, such as the binocular structured light detection method for the deformation of building components in Embodiment 1 of the present invention.

[0210] The electronic device 30 can also communicate with one or more external devices 34 (such as a keyboard, a pointing device, etc.). Such communication can be carried out through the input / output (I / O) interface 35. Moreover, the model generation device 30 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN) and / or a public network, such as the Internet) through the network adapter 36. As Figure 8 shown, the network adapter 36 communicates with other modules of the model generation device 30 through the bus 33. It should be understood that although not shown in the figure, other hardware and / or software modules can be used in combination with the model generation device 30, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (redundant array of independent disks) systems, tape drives, and data backup storage systems, etc.

[0211] In addition, the electronic device can also be implemented in the form of an electronic chip, on which there are memory, processor-related electronic components, and an operating program stored on the memory and executable on the processor.

[0212] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present invention, the features and functions of two or more of the above-described units / modules can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided and embodied by multiple units / modules.

[0213] Embodiment 4

[0214] This embodiment provides a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements the binocular structured light detection method for the deformation of building components in Embodiment 1.

[0215] Among them, the more specific forms that the readable storage medium can adopt can include but are not limited to: portable disks, hard disks, random access memories, read-only memories, erasable programmable read-only memories, optical storage devices, magnetic storage devices, or any suitable combination of the above.

[0216] In a possible implementation manner, the present invention can also be implemented in the form of a program product, which includes program code, and when the program product runs on a terminal device, the program code is used to make the terminal device execute the binocular structured light detection method for the deformation of building components in Embodiment 1.

[0217] Among them, the program code for implementing the present invention can be written in any combination of one or more programming languages, and the program code can be executed entirely on the user device, partially on the user device, executed as an independent software package, partially on the user device and partially on a remote device, or entirely on a remote device.

[0218] Although the specific embodiments of the present invention have been described above, those skilled in the art should understand that this is only an example, and the protection scope of the present invention is defined by the appended claims. Without departing from the principles and essence of the present invention, those skilled in the art can make various changes or modifications to these embodiments, but these changes and modifications all fall within the protection scope of the present invention.

Claims

1. A binocular structured light detection method for the deformation of building components, characterized in that The binocular structured light detection method includes: Encoding the structured light information required for the deformation detection of the area to be detected of the building component, and transmitting the encoded structured light information; Collecting the input image of the area to be detected of the building component; Performing three-dimensional reconstruction on the input image based on the encoded structured light information to obtain a three-dimensional point cloud data sequence of the deformation process of the area to be detected of the building component; Performing feature point matching on the pre-order data and the post-order data of the three-dimensional point cloud data sequence in sequence to obtain the displacement field of the deformation process of the area to be detected of the building component; Calculating the strain field of the deformation process of the area to be detected of the building component based on the displacement field; Performing visualization processing on the displacement field and the strain field to obtain a displacement field vector diagram and a strain field vector diagram; The step of collecting the input image of the area to be detected of the building component includes: Setting the brightness of the structured light projector, the exposure times of the first camera and the second camera, and the time interval for sending the trigger signal; Sending the trigger signal to the structured light projector or the first camera or the second camera according to the time interval for sending the trigger signal; Controlling the structured light projector to project the encoded structured light information onto the area to be detected of the building component according to the trigger signal, and controlling the first camera and the second camera to respectively collect the input image of the area to be detected of the building component; And / or The step of performing feature point matching on the pre-order data and the post-order data of the three-dimensional point cloud data sequence in sequence to obtain the displacement field of the deformation process of the area to be detected of the building component includes: Projecting the three-dimensional point cloud data sequence into a two-dimensional grayscale image sequence; Dividing the region of interest of the pre-order image in the two-dimensional grayscale image sequence; Constructing a pre-order image interest point set based on the region of interest of the pre-order image; Constructing a post-order image candidate point set corresponding to each interest point in the pre-order image interest point set; Performing feature point matching on the pre-order image interest point set and the post-order image candidate point set to obtain the displacement field of the deformation process of the area to be detected of the building component.

2. The binocular structured light detection method for the deformation of building components according to claim 1, characterized in that, Before the step of collecting the input image of the area to be detected of the building component, the binocular structured light detection method further includes: Adjusting the angle between the first camera and the second camera and the baseline distance to obtain the adjusted angle and the adjusted baseline distance; The step of performing three-dimensional reconstruction on the input image based on the encoded structured light information to obtain a three-dimensional point cloud data sequence of the deformation process of the area to be detected of the building component includes: Performing three-dimensional reconstruction on the input image based on the encoded structured light information, the adjusted angle, and the adjusted baseline distance to obtain a three-dimensional point cloud data sequence of the deformation process of the area to be detected of the building component.

3. The binocular structured light detection method for the deformation of building components according to claim 1, characterized in that, Before the step of performing visualization processing on the displacement field and the strain field to obtain a displacement field vector diagram and a strain field vector diagram, the binocular structured light detection method further includes: Storing and transmitting the displacement field and the strain field.

4. A binocular structured light detection system for the deformation of building components, characterized in that, The binocular structured light detection system includes an image acquisition module, a three-dimensional reconstruction module, a feature point matching module, a calculation module, and a visualization module; The image acquisition module is used to encode the structured light information required for deformation detection of the area to be detected of the building component, and transmit the encoded structured light information; The image acquisition module is used to acquire the input image of the area to be detected of the building component; The three-dimensional reconstruction module is used to perform three-dimensional reconstruction on the input image based on the encoded structured light information to obtain a three-dimensional point cloud data sequence of the deformation process of the area to be detected of the building component; The feature point matching module is used to perform feature point matching on the pre-order data and the post-order data of the three-dimensional point cloud data sequence in sequence to obtain the displacement field of the deformation process of the area to be detected of the building component; The calculation module is used to calculate the strain field of the deformation process of the area to be detected of the building component based on the displacement field; The visualization module is used to perform visualization processing on the displacement field and the strain field to obtain a displacement field vector diagram and a strain field vector diagram; The image acquisition module further includes a structured light projector and an external trigger; The core processor is used to set the brightness of the structured light projector, the exposure times of the first camera and the second camera, and the time interval for sending the trigger signal; The core processor is used to send the trigger signal to the structured light projector, the first camera, or the second camera through the external trigger according to the time interval for sending the trigger signal; The core processor is used to control the structured light projector to project the encoded structured light information onto the area to be detected of the building component according to the trigger signal, and control the first camera and the second camera to respectively acquire the input image of the area to be detected of the building component; and / or, The feature point matching module includes a projection unit, a division unit, a first construction unit, a second construction unit, and a feature point matching unit; The projection unit is used to project the three-dimensional point cloud data sequence into a two-dimensional grayscale image sequence; The division unit is used to divide the region of interest of the pre-order image in the two-dimensional grayscale image sequence; The first construction unit is used to construct a pre-order image interest point set based on the region of interest of the pre-order image; The second construction unit is used to construct a post-order image candidate point set corresponding to each interest point in the pre-order image interest point set; The feature point matching unit is used to perform feature point matching on the pre-order image interest point set and the post-order image candidate point set to obtain the displacement field of the deformation process of the area to be detected of the building component.

5. The binocular structured light detection system for the deformation of building components according to claim 4, characterized in that The image acquisition module includes a first camera, a second camera, a device support device, and a core processor; The core processor is used to adjust the angle between the first camera and the second camera and the baseline distance through the device support device to obtain the adjusted angle and the adjusted baseline distance; The three-dimensional reconstruction module is configured to perform three-dimensional reconstruction on the input image based on the encoded structured light information, the adjusted included angle, and the adjusted baseline distance, so as to obtain a sequence of three-dimensional point cloud data of the deformation process of the area to be detected of the building component.

6. The binocular structured light detection system for the deformation of building components according to claim 4, characterized in that, The binocular structured light detection system further includes a data dump module; The data dump module is configured to store and transmit the displacement field and the strain field.

7. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the binocular structured light detection method for the deformation of the building component according to any one of claims 1-3.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the binocular structured light detection method for the deformation of the building component according to any one of claims 1-3.

Images