CN114841965B - Steel structure deformation detection method and device, computer equipment and storage medium - Google Patents
Steel structure deformation detection method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN114841965B CN114841965B CN202210491706.7A CN202210491706A CN114841965B CN 114841965 B CN114841965 B CN 114841965B CN 202210491706 A CN202210491706 A CN 202210491706A CN 114841965 B CN114841965 B CN 114841965B
- Authority
- CN
- China
- Prior art keywords
- data
- steel structure
- dimensional
- point cloud
- dimensional point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B21/00—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant
- G01B21/32—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant for measuring the deformation in a solid
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
- G06T7/337—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods involving reference images or patches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/66—Analysis of geometric attributes of image moments or centre of gravity
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20016—Hierarchical, coarse-to-fine, multiscale or multiresolution image processing; Pyramid transform
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20112—Image segmentation details
- G06T2207/20164—Salient point detection; Corner detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30136—Metal
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The method comprises the steps of extracting two-dimensional contour data of a steel structure according to three-dimensional point cloud data, performing rough registration on the two-dimensional contour data and a preset steel structure contour template to obtain first measurement data, performing fine registration on the first measurement data according to an iterative closest point algorithm to obtain second measurement quantity, calculating the minimum distance error from the second measurement data to the steel structure contour template to determine the deformation quantity of the steel structure, wherein on one hand, the two-dimensional contour data is favorable for reducing unnecessary interference data, reducing the calculation quantity of deformation of the steel structure, and on the other hand, performing rough registration and fine registration on the two-dimensional contour data of the steel structure, namely, a double registration mode is favorable for improving the accuracy of the steel structure variable, and further realizing comprehensive, accurate and rapid steel structure deformation analysis effect.
Description
Technical Field
The application relates to the technical field of engineering structure deformation detection, in particular to a steel structure deformation detection method, a device, computer equipment and a storage medium.
Background
The steel structure is widely applied to large-scale construction sites due to the excellent performances of large strength, large span, good shaping, high temperature resistance and the like. However, the steel structure is affected by external environment after assembly forming, namely, the steel structure is subjected to changes of surrounding loads, such as wind, temperature and other weather changes, so that internal stress of the steel structure can change, and the steel structure is locally unevenly deformed. The deformation of the steel structure is a common problem in the engineering and industrial fields, and has adverse effects on the normal construction of the engineering and the normal operation of the industry. If the deformation of the steel structure exceeds the alarm value, the safety accident is possibly caused, thereby threatening the safety of people. Therefore, it is necessary to detect deformation of the steel structure in time, analyze the safety state of the steel structure, and predict the subsequent deformation tendency.
Aiming at deformation detection of a steel structure, the traditional detection means mainly adopts a total station measurement mode, namely three-dimensional coordinates of space feature points are acquired one by one for a deformation region of the steel structure, and geometric relations between the feature points of the deformation region and space reference surfaces and lines are analyzed according to point position coordinate values, so that deformation values are calculated. The detection means has low field operation efficiency and large calculation amount, and the deformation value of the space discrete point is difficult to comprehensively and accurately reflect the space integral deformation condition of the steel structure.
Aiming at the problem that the processing and the whole deformation analysis of the steel structure point cloud data are difficult to comprehensively, accurately and efficiently realized in the prior art, no effective solution is proposed at present.
Disclosure of Invention
The embodiment of the application aims to provide a steel structure deformation detection method for solving the problems of low efficiency and low accuracy of current steel structure deformation measurement.
In order to solve the above technical problems, an embodiment of the present application provides a method for detecting deformation of a steel structure, including the following steps:
acquiring three-dimensional point cloud data of a steel structure;
extracting two-dimensional contour data of the steel structure according to the three-dimensional point cloud data;
coarse registration is carried out on the two-dimensional profile data and a preset steel structure profile template so as to obtain first measurement data;
carrying out fine registration on the first measurement data according to an iterative closest point algorithm to obtain a second measurement quantity;
and calculating the minimum distance error from the second measurement data to the steel structure profile template to determine the deformation quantity of the steel structure.
In some embodiments, extracting two-dimensional profile data of the steel structure from the three-dimensional point cloud data comprises:
determining the extending direction of the steel structure according to the three-dimensional point cloud data of the steel structure;
determining bounding box data of the steel structure from the three-dimensional point cloud data of the steel structure;
And extracting two-dimensional profile data of the steel structure from the bounding box data according to the extending direction.
In some embodiments, determining the direction of extension of the steel structure from the three-dimensional point cloud data of the steel structure comprises:
determining centroid data of the three-dimensional point cloud data from the three-dimensional point cloud data of the steel structure;
constructing a covariance matrix according to the three-dimensional point cloud data and the centroid data;
and determining the extending direction of the steel structure according to the covariance matrix.
In some embodiments, extracting two-dimensional profile data of the steel structure from bounding box data according to the extension direction includes:
determining a cross section corresponding to the bounding box data according to the extending direction and the centroid data;
according to the distance from the bounding box data to the cross section, the bounding box data corresponding to the distance meeting the preset distance interval is taken as the cross section data;
the cross-sectional data is projected onto the cross-section to obtain two-dimensional profile data.
In some embodiments, the steel structure profile template includes a plurality of second corner points and a plurality of second triangles constructed according to the second corner points, and performing coarse registration on the two-dimensional profile data and a preset steel structure profile template to obtain first measurement data includes:
acquiring a first corner point of two-dimensional contour data;
Constructing a plurality of first triangles corresponding to the first corner points;
matching calculation is carried out on the first triangle and the second triangle so as to obtain a rotation matrix and a translation vector;
the rotation matrix and the translation vector are converted to obtain first measurement data.
In some implementations, acquiring the first corner of the two-dimensional profile data includes:
acquiring a plurality of adjacent points of the two-dimensional contour data;
connecting a plurality of adjacent points with the two-dimensional contour data to obtain a plurality of edges;
acquiring an included angle formed between every two sides from a plurality of sides, wherein the included angle comprises an angle value;
and taking the two-dimensional profile data corresponding to the included angle which accords with the preset angle value as a first corner point.
In some embodiments, matching the first triangle and the second triangle to obtain the rotation matrix and the translation vector comprises:
obtaining a plurality of similar triangles matched with the first triangle from the second triangle;
calculating an initial rotation matrix and an initial translation vector of coincidence of corresponding points between every two similar triangles;
acquiring a plurality of registration errors according to the initial rotation matrix and the initial translation vector;
and determining the minimum registration error from the plurality of registration errors, and taking an initial rotation matrix and an initial translation vector corresponding to the minimum registration error as a final rotation matrix and a translation vector.
In order to solve the above technical problem, the embodiment of the application provides a steel structure deformation detection device, and the steel structure deformation detection device includes:
the acquisition module is used for acquiring three-dimensional point cloud data of the steel structure;
the extraction module is used for extracting the two-dimensional profile data of the steel structure according to the three-dimensional point cloud data;
the coarse registration module is used for performing coarse registration on the two-dimensional profile data and a preset steel structure profile template to obtain first measurement data;
the fine registration module is used for carrying out fine registration on the first measurement data according to an iterative closest point algorithm so as to obtain a second measurement quantity;
and the calculation module is used for calculating the minimum distance error from the second measurement data to the steel structure profile template so as to determine the deformation quantity of the steel structure.
In some embodiments, the extraction module comprises:
the extending direction determining unit is used for determining the extending direction of the steel structure according to the three-dimensional point cloud data of the steel structure;
the bounding box unit is used for determining bounding box data of the steel structure from the three-dimensional point cloud data of the steel structure;
and the extraction unit is used for extracting the two-dimensional profile data of the steel structure from the bounding box data according to the extending direction.
In some embodiments, the extension direction determining unit includes:
the mass center subunit is used for determining mass center data of the three-dimensional point cloud data from the three-dimensional point cloud data of the steel structure;
the matrix subunit is used for constructing a covariance matrix according to the three-dimensional point cloud data and the centroid data;
and the extension direction subunit is used for determining the extension direction of the steel structure according to the covariance matrix.
In some embodiments, the extraction unit comprises:
a cross section subunit, configured to determine a cross section corresponding to the bounding box data according to the extension direction and the centroid data;
the section data subunit is used for taking bounding box data corresponding to the distance which accords with the preset distance interval as section data according to the distance from the bounding box data to the cross section;
and a projection subunit for projecting the section data onto the cross section to obtain two-dimensional profile data.
In some embodiments, the steel structure contour template includes a plurality of second corner points and a plurality of second triangles constructed according to the second corner points, and the coarse registration module includes:
the angular point acquisition unit is used for acquiring a first angular point of the two-dimensional contour data;
the construction unit is used for constructing a plurality of first triangles corresponding to the first corner points;
The matching calculation unit is used for carrying out matching calculation on the first triangle and the second triangle so as to obtain a rotation matrix and a translation vector;
and the conversion unit is used for converting the rotation matrix and the translation vector to obtain first measurement data.
In some embodiments, the corner acquisition unit comprises:
a neighboring point acquisition subunit, configured to acquire a plurality of neighboring points of the two-dimensional contour data;
the edge connection subunit is used for connecting a plurality of adjacent points with the two-dimensional profile data to obtain a plurality of edges;
an included angle obtaining subunit, configured to obtain, from a plurality of edges, an included angle formed between each two edges, where the included angle includes an angle value;
the angular point obtaining subunit is configured to use two-dimensional contour data corresponding to an included angle that meets a preset angle value as a first angular point.
In some embodiments, the matching calculation unit includes:
a similar subunit, configured to obtain, from the second triangle, a plurality of similar triangles that match the first triangle;
the gesture calculation subunit is used for calculating an initial rotation matrix and an initial translation vector of coincidence of corresponding points between every two similar triangles;
the registration error acquisition subunit is used for acquiring a plurality of registration errors according to the initial rotation matrix and the initial translation vector;
And the gesture determining subunit is used for determining the minimum registration error from the plurality of registration errors, and taking an initial rotation matrix and an initial translation vector corresponding to the minimum registration error as final rotation matrices and translation vectors.
In order to solve the above technical problems, an embodiment of the present application further provides a computer device, including a memory and a processor, where the memory stores a computer program, and the processor implements the steps of the steel structure deformation detection method when executing the computer program.
In order to solve the above technical problem, the embodiments of the present application further provide a computer readable storage medium, where a computer program is stored, where the computer program when executed by a processor implements the steps of the steel structure deformation detection method described above.
Compared with the prior art, the embodiment of the application has the following main beneficial effects:
the three-dimensional point cloud data are obtained, two-dimensional contour data of the steel structure are extracted according to the three-dimensional point cloud data, coarse registration is conducted on the two-dimensional contour data and a preset steel structure contour template to obtain first measurement data, fine registration is conducted on the first measurement data according to an iterative closest point algorithm to obtain second measurement quantity, minimum distance errors from the second measurement data to the steel structure contour template are calculated to determine deformation quantity of the steel structure, on one hand, the three-dimensional point cloud data improve efficiency and accuracy of steel structure surface data acquisition, meanwhile, the two-dimensional contour data are extracted from the three-dimensional point cloud data to be beneficial to reducing unnecessary interference data, calculation amount of steel structure deformation is reduced, registration and calculation efficiency are improved, on the other hand, coarse registration and fine registration are conducted on the two-dimensional contour data of the steel structure, namely, a double registration mode is beneficial to improving accuracy of steel structure variables, and further comprehensive, accurate and rapid steel structure deformation analysis effects are achieved.
Drawings
For a clearer description of the solution in the present application, a brief description will be given below of the drawings that are needed in the description of the embodiments of the present application, it being obvious that the drawings in the following description are some embodiments of the present application, and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art.
FIG. 1 is an exemplary system architecture diagram in which the present application may be applied;
fig. 2 is a schematic flow chart of a method for detecting deformation of a steel structure according to an embodiment of the present application;
FIG. 3-a is a three-dimensional point cloud data schematic of a steel structure according to an embodiment of the present application;
fig. 3-b is a schematic diagram of a two-dimensional contour extraction and corner detection result of a steel structure according to an embodiment of the present application;
FIG. 4 is a schematic view of a steel structure profile template according to an embodiment of the present application;
FIG. 5 is a schematic diagram of a result of coarse registration of three-dimensional point cloud data based on template contour matching and a design template in an embodiment of the present application;
FIG. 6 is a schematic diagram of a three-dimensional point cloud data and a design template fine registration result according to an embodiment of the present application;
FIG. 7 is a schematic view of an embodiment of a steel structure deformation detection device provided herein;
FIG. 8 is a schematic diagram of one embodiment of a computer device provided herein.
Description of the embodiments
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used in the description of the applications herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having" and any variations thereof in the description and claims of the present application and in the description of the figures above are intended to cover non-exclusive inclusions. The terms first, second and the like in the description and in the claims or in the above-described figures, are used for distinguishing between different objects and not necessarily for describing a sequential or chronological order.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the present application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
In order to better understand the technical solutions of the present application, the following description will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings.
As shown in fig. 1, a system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium to provide communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
The user may interact with the server 105 via the network 104 using the terminal devices 101, 102, 103 to receive or send messages or the like. Various communication client applications, such as a web browser application, a shopping class application, a search class application, an instant messaging tool, a mailbox client, social platform software, etc., may be installed on the terminal devices 101, 102, 103.
The terminal devices 101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablet computers, electronic book readers, MP3 players (Moving Picture Experts Group Audio Layer III, dynamic video expert compression standard audio plane 3), MP4 (Moving Picture Experts Group Audio Layer IV, dynamic video expert compression standard audio plane 4) players, laptop and desktop computers, and the like.
The server 105 may be a server providing various services, such as a background server providing support for pages displayed on the terminal devices 101, 102, 103.
It should be noted that, the method for detecting the deformation of the steel structure provided in the embodiments of the present application is generally executed by a server/terminal device, and accordingly, the device for detecting the deformation of the steel structure is generally disposed in the server/terminal device.
It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
In this embodiment of the present application, as shown in fig. 2, fig. 2 is a schematic flow chart of a method for detecting deformation of a steel structure provided in this embodiment of the present application, and a specific implementation of the method for detecting deformation of a steel structure includes:
s201: and acquiring three-dimensional point cloud data of the steel structure.
The three-dimensional point cloud data is a massive point set expressing target space distribution and target surface characteristics under the same space reference system, and the obtained point set is after the space coordinates of each sampling point of the object surface are obtained.
The three-dimensional point cloud data includes a three-dimensional image of the steel structure that expresses data of three dimensions in space, such as length, width, and depth. The acquisition of three-dimensional point cloud data is mainly divided into two types according to a measurement principle, wherein one type is obtained according to a laser measurement principle, and the three-dimensional point cloud data comprises three-dimensional coordinates (X, Y, Z) and laser reflection Intensity (Intensity), and the Intensity information is related to the surface material, roughness and incident angle direction of a target, the emission energy of an instrument and the laser wavelength; the other is obtained according to the principles of photogrammetry, including three-dimensional coordinates (X, Y, Z) and color information (RGB). In the embodiment of the application, a depth camera is adopted to acquire three-dimensional point cloud data of a steel structure.
As shown in fig. 3-a, fig. 3-a is a three-dimensional point cloud data schematic diagram of a steel structure according to an embodiment of the present application.
S202: and extracting two-dimensional contour data of the steel structure according to the three-dimensional point cloud data.
Further, two-dimensional data of the steel structure contour are extracted from the three-dimensional point cloud data, namely, each two-dimensional data represents coordinate information of two-dimensional contour points, namely, the two-dimensional contour data, compared with the method for directly adopting the three-dimensional point cloud data to conduct registration calculation to measure the steel structure, the two-dimensional contour data reduces interference of other irrelevant data for calculating deformation data of the steel structure, and meanwhile, the two-dimensional data volume is far smaller than that of the three-dimensional point cloud data, so that measurement efficiency of the steel structure is improved.
In some embodiments, extracting two-dimensional profile data of a steel structure from three-dimensional point cloud data specifically includes the steps of:
determining the extending direction of the steel structure according to the three-dimensional point cloud data of the steel structure;
determining bounding box data of the steel structure from the three-dimensional point cloud data of the steel structure;
and extracting two-dimensional profile data of the steel structure from the bounding box data according to the extending direction.
Specifically, in order to measure the deformation condition inside the steel structure, it is necessary to determine the internal structural condition of the steel structure, that is, to determine the extending direction of the steel structure, and thus to determine bounding box data around the extending direction.
In some embodiments, determining the direction of extension of the steel structure from the three-dimensional point cloud data of the steel structure comprises:
determining centroid data of the three-dimensional point cloud data from the three-dimensional point cloud data of the steel structure;
constructing a covariance matrix according to the three-dimensional point cloud data and the centroid data;
and determining the extending direction of the steel structure according to the covariance matrix.
The extension direction of the steel structure can be determined, for example, specifically according to the equations (1) and (2).
Further, the centroid data of the three-dimensional point cloud data is determined from the three-dimensional point cloud number of the steel structure as shown in formula (1):
formula (1)
Wherein, the liquid crystal display device comprises a liquid crystal display device,as centroid, centroid data can be expressed as +.>，/>Respectively expressed as three-dimensional coordinates of the centroid on the spatial coordinate system, ">Is three-dimensional point cloud data->The number of three-dimensional space points in>Is any three-dimensional point cloud data.
Further, constructing a covariance matrix according to the three-dimensional point cloud data and the centroid data is shown in formula (2):
formula (2)
Wherein, the liquid crystal display device comprises a liquid crystal display device,for covariance matrix, the covariance matrix includes three eigenvalues corresponding to each eigenvector,/-for>Is a vector outer product symbol.
Further, the eigenvector corresponding to the largest eigenvalue of the covariance matrix is the direction of the straight line which is formed by fitting the three-dimensional point cloud data of the steel structure, namely the extending direction is obtained by fitting. Thus, from the covariance matrix Obtaining a feature vector corresponding to the maximum feature value, and taking the feature vector as the extending direction of the three-dimensional data of the steel structure, wherein the extending direction can be expressed as +.>Wherein->Expressed as three-dimensional coordinates of the extension direction in a spatial coordinate system, i.e., an x-coordinate, a y-coordinate and a z-coordinate, respectively.
In the embodiment of the application, the covariance matrix is constructed by combining the centroid data of the three-dimensional point cloud data of the steel structure and according to the three-dimensional point cloud data and the centroid data, so that the extending direction of the steel structure is determined, and basic data support is provided for the follow-up comprehensive, accurate and efficient realization of the processing and the whole deformation analysis of the three-dimensional point cloud data of the steel structure.
In some embodiments, extracting two-dimensional profile data of the steel structure from bounding box data according to the extension direction includes:
determining a cross section corresponding to the bounding box data according to the extending direction and the centroid data;
according to the distance from the bounding box data to the cross section, the bounding box data corresponding to the distance meeting the preset distance interval is taken as the cross section data;
the cross-sectional data is projected onto the cross-section to obtain two-dimensional profile data.
Specifically, the bounding box algorithm is an algorithm for solving the optimal bounding space of the discrete point set, and the basic idea is to approximately replace a complex geometric object with a geometric body (called a bounding box) with a slightly larger volume and simple characteristics, so that the bounding box algorithm can be used for determining bounding box data of a steel structure from three-dimensional point cloud data, namely, the bounding box data is part of three-dimensional point cloud data of the steel structure, and the bounding box algorithm can be, but is not limited to, an AABB bounding box, a bounding sphere, a direction bounding box OBB, a fixed direction convex hull FDH and the like.
Further, perpendicular to the extending direction of the steel structure, intercepting the two-dimensional profile data of the steel structure at the middle part of the bounding box data of the steel structure, wherein the specific implementation can be obtained according to the formula (3) and the formula (6):
determining the cross section corresponding to bounding box data according to the extension direction and centroid data can be obtained according to formula (3):
formula (3)
Wherein the extending direction is，/>Centroid dataI.e. formula (3) is an expression of cross section, according to bounding box data +.>And the expression of the known cross section, the individual bounding box data +.>Distance from cross section is->Wherein->The number of points in the bounding box is represented, and the specific number is influenced by the sparseness of the point cloud acquired by the sensor.
Further, all distances are recordedPoints falling within a predetermined distance interval, e.g. set to [0,0.015 ]]The bounding box data which is about to fall within the preset distance interval is taken as cross section data, and the cross section data is projected to the cross section to obtain two-dimensional profile data +.>And obtaining the two-dimensional contour points. Wherein (1)>Point cloud data representing a two-dimensional contour, +.>The number of data points on the representation cross section, the specific number being affected by the sparseness of the point cloud acquired by the sensor.
Fig. 3-b are schematic diagrams illustrating two-dimensional contour extraction and corner detection results of a steel structure according to an embodiment of the present application. The bounding box data of the whole bounding steel structure is determined from the three-dimensional point cloud data, and then the bounding box data in the extending direction is calculated and projected to screen the two-dimensional outline data of the steel structure, so that the interference of other three-dimensional point cloud data irrelevant to the calculation of the deformation data of the steel structure is reduced, and meanwhile, the two-dimensional data quantity is far less than the three-dimensional point cloud data, so that the measurement efficiency of the steel structure is improved.
S203: and performing coarse registration on the two-dimensional profile data and a preset steel structure profile template to obtain first measurement data.
The first measurement data are two-dimensional contour data obtained through rough registration calculation.
As shown in fig. 4, fig. 4 is a schematic view of a steel structure profile template according to an embodiment of the present application. The preset steel structure profile template is standard structure reference data of a theoretical model profile, whether the actual steel structure is deformed or not can be determined by comparing the standard structure reference data with the actual steel structure data, the preset steel structure profile template can be regarded as an ideal model, and the standard structure reference data can be generated by modeling software.
Specifically, coarse registration is performed on the two-dimensional profile data and a preset steel structure profile template, so as to obtain first measurement data, wherein the first measurement data comprises:
Acquiring a first corner point of two-dimensional contour data;
constructing a plurality of first triangles corresponding to the first corner points;
matching calculation is carried out on the first triangle and the second triangle so as to obtain a rotation matrix and a translation vector;
the rotation matrix and the translation vector are converted to obtain first measurement data.
In some implementations, acquiring the first corner of the two-dimensional profile data includes:
acquiring a plurality of adjacent points of the two-dimensional contour data;
connecting a plurality of adjacent points with the two-dimensional contour data to obtain a plurality of edges;
acquiring an included angle formed between every two sides from a plurality of sides, wherein the included angle comprises an angle value;
and taking the two-dimensional profile data corresponding to the included angle which accords with the preset angle value as a first corner point.
Specifically, a KNN (K-Nearest Neighbor) algorithm is used to find two-dimensional contour points in the two-dimensional contour dataThe adjacent points will be->The adjacent points are respectively connected with the two-dimensional contour points to obtain +.>And (5) a strip edge. Calculating the angle value corresponding to the included angle formed by any two sides to obtain +.>And an angle value. The preset angle value can be set at 90 degrees, if the angle value corresponding to the included angle is distributed near 90 degrees, the two-dimensional contour point corresponding to the included angle at the moment is taken as the angular point, namely the first angular point, and if the angle value is mostly distributed in the range of 180 degrees or near 0 degrees, the two-dimensional contour point corresponding to the included angle at the moment is not the angular point. As shown in fig. 4, fig. 4 is a schematic diagram of two-dimensional contour extraction and corner detection results of a steel structure according to an embodiment of the present application.
The first corner point of the two-dimensional profile data not only reserves important characteristics of the shape of the steel structure, but also can effectively reduce the data volume of the calculation deformation of the steel structure, effectively improve the calculation speed, be favorable for the reliable matching of the follow-up profile template of the steel structure, and enable the real-time processing to be possible.
Further, a plurality of first angles can be obtained in the above manner, and the plurality of first angles can be taken as a two-dimensional cross-section angle point set and can be expressed as. In the two-dimensional section angle point set H, 3 first angle points are arbitrarily selected to form a first triangle, and finally the +.>A first triangle.
Further, the steel structure contour template comprises a plurality of second angular points of the standard steel structure contour and a plurality of second triangles constructed according to the second angular points, and the mode of acquiring the second angular points and the second triangles is the same as the mode of acquiring the first angular points and the first triangles, namely the plurality of second angular points can be used as a theoretical model contour angular point setIn, and likewise in the set of theoretical model contour corner points +.>Optionally three second corner points as a second triangle, finally obtaining +.>The specific procedure of the second triangle is not described here again.
In some embodiments, matching the first triangle and the second triangle to obtain the rotation matrix and the translation vector comprises:
obtaining a plurality of similar triangles matched with the first triangle from the second triangle;
calculating an initial rotation matrix and an initial translation vector of coincidence of corresponding points between every two similar triangles;
acquiring a plurality of registration errors according to the initial rotation matrix and the initial translation vector;
and determining the minimum registration error from the plurality of registration errors, and taking an initial rotation matrix and an initial translation vector corresponding to the minimum registration error as a final rotation matrix and a translation vector.
In particular, toEach of the first triangles is in +.>Finding the most similar in the second trianglesI.e. similar triangles, wherein the number of similar triangles may be set according to the actual measurement, 3 similar triangles are obtained in the embodiment of the present application. The acquisition mode of the similar triangle comprises the following steps:
the three side length values of each first triangle are recorded and arranged in order from small to large, namely: for the firstA first triangle with side length value of +. >Wherein->Similarly, three side length values of each second triangle are recorded, and the side length values of the second triangles are respectively +.>Calculating any first triangle +.>And a second triangle->Difference value->,/>The smaller the first triangle and the second triangle are, the more similar the first triangle and the second triangle are; according to->For ordering from->Each triangle of the first triangles is +.>The most similar 3 second triangles are found among the second triangles.
Further, calculating the initial rotation matrix and the initial translation vector for the coincidence of the corresponding points between every two similar triangles includes:
according to the corresponding relation of the side lengths of the 3 most similar second triangles, the corresponding relation of the vertexes of the second triangles, namely the three vertexes of the first triangle, can be determinedThree vertices corresponding to the second triangle respectively +.>The method comprises the steps of carrying out a first treatment on the surface of the Calculating covariance matrix->Wherein->,The method comprises the steps of carrying out a first treatment on the surface of the For covariance matrix->SVD (Singular Value Decomposition ) decomposition to obtain +>Wherein U and V represent two mutually orthogonal matrices and S represents a pair of angular matrices; the initial rotation matrix +.>Initial translation vector。
Further, a registration error is calculated according to equation (4):
Formula (4)
And finding an initial rotation matrix and an initial translation vector corresponding to the minimum error in all registration errors, namely a final rotation matrix and a final translation vector.
Further, based on the obtained rotation matrix and translation vector, coarse registration of the two-dimensional profile data of the steel structure and the profile template of the steel structure is realized, so as to transform the two-dimensional profile data into first measurement data, and the first measurement data can be obtained according to a formula (5):
Q=formula (5)
Wherein, the liquid crystal display device comprises a liquid crystal display device,representing the final rotation matrix, P representing the actual two-dimensional profile data, +.>And representing the final translation vector, wherein Q is represented as first measurement data, namely a new data set obtained after the actual two-dimensional profile data is transformed, and the Q is basically consistent with the posture of the steel structure profile template.
As shown in fig. 5, fig. 5 is a schematic diagram of a result of rough registration of three-dimensional point cloud data based on template contour matching and a design template according to an embodiment of the present application.
S204: and carrying out fine registration on the first measurement data according to an iterative closest point algorithm to obtain a second measurement quantity.
Further, the iterative closest point algorithm is ICP (Iterative Closest Poin) algorithm, and the fine registration of the first measurement data of the steel structure and the steel structure contour template is realized by utilizing the iterative closest point ICP algorithm, which specifically comprises the following steps: discretizing the steel structure profile template to obtain a point set The method comprises the steps of carrying out a first treatment on the surface of the For each point in the first measurement data Q +.>By means of KNN (K-Nearest neighbor)bor, K-neighbor) algorithm in point set +.>Find the nearest point, namely +.>Corresponding points of (2); calculating a rigid body transformation matrix which minimizes the average distance of the corresponding point pairs; based on the rigid transformation matrix, spatially transforming the first measurement data Q to obtain a new point set +.>The method comprises the steps of carrying out a first treatment on the surface of the Iterating the process of finding the corresponding points, calculating the rigid transformation matrix and transforming the actual measurement point sets until the average distance between the corresponding points of the two point sets is less than the threshold value +.>Until the final transformed actual measurement point set is +.>I.e. the second measurement data.
Specifically, calculating the rigid body transformation matrix includes: based on point setCorresponding relation with the points in the point set Q, calculating covariance matrix +.>Wherein->For each point in the first measurement data Q, and (2)>Is a point setThe nearest point found in (a) i.e. the corresponding point of each point in the first measurement data Q, +.>,,/>Is the number of corresponding pairs of points; also for covariance matrix->SVD decomposition is carried out to obtainWherein U ' and V ' represent two mutually orthogonal matrices and S ' represents a pair of angular matrices; the method comprises the steps of carrying out a first treatment on the surface of the Rigid body transformation matrix minimizing the average distance between point set Q and point set S, including minimum rotation matrix +. >Minimum translation vector ∈>。
Further, based on the above obtained rigid transformation, the first measurement data Q is subjected to rigid transformation to obtain a new point setI.e. second measurement data, wherein +.>。
Fig. 6 is a schematic diagram of three-dimensional point cloud data and a fine registration result of a design template according to an embodiment of the present application, as shown in fig. 6.
S205: and calculating the minimum distance error from the second measurement data to the steel structure profile template to determine the deformation quantity of the steel structure.
Calculating the minimum distance error from the second measurement data to the steel structure profile template, namely the deformation of the actual steel structure, comprising: for the purpose ofNumber of profiles per two-dimensional profileAnd calculating the minimum distance from the point to the steel structure profile template, namely the deformation quantity of the actual steel structure.
The three-dimensional point cloud data are obtained, two-dimensional contour data of the steel structure are extracted according to the three-dimensional point cloud data, coarse registration is conducted on the two-dimensional contour data and a preset steel structure contour template to obtain first measurement data, fine registration is conducted on the first measurement data according to an iterative closest point algorithm to obtain second measurement quantity, minimum distance errors from the second measurement data to the steel structure contour template are calculated to determine deformation quantity of the steel structure, on one hand, the three-dimensional point cloud data improve efficiency and accuracy of steel structure surface data acquisition, meanwhile, the two-dimensional contour data are extracted from the three-dimensional point cloud data to be beneficial to reducing unnecessary interference data, calculation amount of steel structure deformation is reduced, registration and calculation efficiency are improved, on the other hand, coarse registration and fine registration are conducted on the two-dimensional contour data of the steel structure, namely, a double registration mode is beneficial to improving accuracy of steel structure variables, and further comprehensive, accurate and rapid steel structure deformation analysis effects are achieved.
Those skilled in the art will appreciate that implementing all or part of the above-described methods in accordance with the embodiments may be accomplished by way of a computer program stored in a computer-readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. The storage medium may be a nonvolatile storage medium such as a magnetic disk, an optical disk, a Read-Only Memory (ROM), or a random access Memory (Random Access Memory, RAM).
It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.
With further reference to fig. 7, as an implementation of the method shown in fig. 2, the present application provides an embodiment of a steel structure deformation detection apparatus, where the embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 2, and the apparatus may be specifically applied to various electronic devices.
As shown in fig. 7, a schematic structural diagram of an embodiment of a steel structure deformation detection device provided in the present application, where the steel structure deformation detection device further includes: an acquisition module 71, an extraction module 72, a coarse registration module 73, a fine registration module 74, and a calculation module 75. Wherein, the liquid crystal display device comprises a liquid crystal display device,
an acquisition module 71, configured to acquire three-dimensional point cloud data of a steel structure;
an extracting module 72, configured to extract two-dimensional profile data of the steel structure according to the three-dimensional point cloud data;
a coarse registration module 73, configured to perform coarse registration on the two-dimensional profile data and a preset steel structure profile template, so as to obtain first measurement data;
a fine registration module 74, configured to perform fine registration on the first measurement data according to an iterative closest point algorithm to obtain a second measurement quantity;
a calculation module 75 for calculating a minimum distance error of the second measurement data to the steel structure profile template to determine a deformation amount of the steel structure.
In some embodiments, the extraction module 72 includes:
the extending direction determining unit is used for determining the extending direction of the steel structure according to the three-dimensional point cloud data of the steel structure;
the bounding box unit is used for determining bounding box data of the steel structure from the three-dimensional point cloud data of the steel structure;
and the extraction unit is used for extracting the two-dimensional profile data of the steel structure from the bounding box data according to the extending direction.
In some embodiments, the extension direction determining unit includes:
the mass center subunit is used for determining mass center data of the three-dimensional point cloud data from the three-dimensional point cloud data of the steel structure;
the matrix subunit is used for constructing a covariance matrix according to the three-dimensional point cloud data and the centroid data;
and the extension direction subunit is used for determining the extension direction of the steel structure according to the covariance matrix.
In some embodiments, the extraction unit comprises:
a cross section subunit, configured to determine a cross section corresponding to the bounding box data according to the extension direction and the centroid data;
the section data subunit is used for taking bounding box data corresponding to the distance which accords with the preset distance interval as section data according to the distance from the bounding box data to the cross section;
and a projection subunit for projecting the section data onto the cross section to obtain two-dimensional profile data.
In some embodiments, the steel structure outline template includes a plurality of second corner points and a plurality of second triangles constructed according to the second corner points, and the coarse registration module 73 includes:
the angular point acquisition unit is used for acquiring a first angular point of the two-dimensional contour data;
the construction unit is used for constructing a plurality of first triangles corresponding to the first corner points;
the matching calculation unit is used for carrying out matching calculation on the first triangle and the second triangle so as to obtain a rotation matrix and a translation vector;
and the conversion unit is used for converting the rotation matrix and the translation vector to obtain first measurement data.
In some embodiments, the corner acquisition unit comprises:
a neighboring point acquisition subunit, configured to acquire a plurality of neighboring points of the two-dimensional contour data;
the edge connection subunit is used for connecting a plurality of adjacent points with the two-dimensional profile data to obtain a plurality of edges;
an included angle obtaining subunit, configured to obtain, from a plurality of edges, an included angle formed between each two edges, where the included angle includes an angle value;
the angular point obtaining subunit is configured to use two-dimensional contour data corresponding to an included angle that meets a preset angle value as a first angular point.
In some embodiments, the matching calculation unit includes:
A similar subunit, configured to obtain, from the second triangle, a plurality of similar triangles that match the first triangle;
the gesture calculation subunit is used for calculating an initial rotation matrix and an initial translation vector of coincidence of corresponding points between every two similar triangles;
the registration error acquisition subunit is used for acquiring a plurality of registration errors according to the initial rotation matrix and the initial translation vector;
and the gesture determining subunit is used for determining the minimum registration error from the plurality of registration errors, and taking an initial rotation matrix and an initial translation vector corresponding to the minimum registration error as final rotation matrices and translation vectors.
The specific manner in which the respective modules perform the operations in the steel structure deformation detecting apparatus of the above embodiment has been described in detail in the embodiments related to the method, and will not be described in detail here.
In order to solve the technical problems, the embodiment of the application also provides computer equipment. Referring specifically to fig. 8, fig. 8 is a basic structural block diagram of a computer device according to the present embodiment.
The computer device 8 comprises a memory 81, a processor 82, a network interface 83 communicatively connected to each other via a system bus. It should be noted that only computer device 8 having components 81-83 is shown in the figures, but it should be understood that not all of the illustrated components are required to be implemented and that more or fewer components may be implemented instead. It will be appreciated by those skilled in the art that the computer device herein is a device capable of automatically performing numerical calculations and/or information processing in accordance with predetermined or stored instructions, the hardware of which includes, but is not limited to, microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASICs), programmable gate arrays (fields-Programmable Gate Array, FPGAs), digital processors (Digital Signal Processor, DSPs), embedded devices, etc.
The computer equipment can be a desktop computer, a notebook computer, a palm computer, a cloud server and other computing equipment. The computer equipment can perform man-machine interaction with a user through a keyboard, a mouse, a remote controller, a touch pad or voice control equipment and the like.
The memory 81 includes at least one type of readable storage medium including flash memory, hard disk, multimedia card, card type memory (e.g., SD or D steel structure deformation detection memory, etc.), random Access Memory (RAM), static Random Access Memory (SRAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), programmable Read Only Memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the storage 81 may be an internal storage unit of the computer device 8, such as a hard disk or a memory of the computer device 8. In other embodiments, the memory 81 may also be an external storage device of the computer device 8, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash Card (Flash Card) or the like, which are provided on the computer device 8. Of course, the memory 81 may also comprise both an internal memory unit of the computer device 8 and an external memory device. In this embodiment, the memory 81 is generally used to store an operating system and various application software installed on the computer device 8, such as program codes of a steel structure deformation detection method. Further, the memory 81 may be used to temporarily store various types of data that have been output or are to be output.
The processor 82 may be a central processing unit (Central Processing Unit, CPU), controller, microcontroller, microprocessor, or other data processing chip in some embodiments. The processor 82 is typically used to control the overall operation of the computer device 8. In this embodiment, the processor 82 is configured to execute a program code stored in the memory 81 or process data, such as a program code for executing the steel structure deformation detection method.
The network interface 83 may comprise a wireless network interface or a wired network interface, which network interface 83 is typically used to establish a communication connection between the computer device 8 and other electronic devices.
The present application also provides another embodiment, namely, a computer-readable storage medium storing a steel structure deformation detection program executable by at least one processor to cause the at least one processor to perform the steps of the steel structure deformation detection method as described above.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk), comprising several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to perform the method described in the embodiments of the present application.
It is apparent that the embodiments described above are only some embodiments of the present application, but not all embodiments, the preferred embodiments of the present application are given in the drawings, but not limiting the patent scope of the present application. This application may be embodied in many different forms, but rather, embodiments are provided in order to provide a more thorough understanding of the present disclosure. Although the present application has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described in the foregoing, or equivalents may be substituted for elements thereof. All equivalent structures made by the specification and the drawings of the application are directly or indirectly applied to other related technical fields, and are also in the protection scope of the application.
Claims (7)
1. A method for detecting deformation of a steel structure, the method comprising:
acquiring three-dimensional point cloud data of a steel structure;
extracting two-dimensional contour data of the steel structure according to the three-dimensional point cloud data;
coarse registration is carried out on the two-dimensional profile data and a preset steel structure profile template so as to obtain first measurement data;
According to an iterative closest point algorithm, performing fine registration on the first measurement data to obtain a second measurement quantity;
calculating a minimum distance error from the second measurement data to the steel structure profile template to determine a deformation amount of the steel structure;
the extracting the two-dimensional profile data of the steel structure according to the three-dimensional point cloud data comprises the following steps:
determining the extending direction of the steel structure according to the three-dimensional point cloud data of the steel structure;
determining bounding box data of the steel structure from the three-dimensional point cloud data of the steel structure;
extracting two-dimensional profile data of the steel structure from the bounding box data according to the extending direction;
wherein, the determining the extending direction of the steel structure according to the three-dimensional point cloud data of the steel structure comprises:
determining centroid data of the three-dimensional point cloud data from the three-dimensional point cloud data of the steel structure;
constructing a covariance matrix according to the three-dimensional point cloud data and the centroid data;
determining the extending direction of the steel structure according to the covariance matrix;
wherein the extracting the two-dimensional profile data of the steel structure from the bounding box data according to the extending direction includes:
Determining a cross section corresponding to the bounding box data according to the extending direction and the centroid data;
according to the distance from the bounding box data to the cross section, bounding box data corresponding to the distance conforming to a preset distance interval are used as cross section data;
the cross-sectional data is projected onto the cross-section to obtain two-dimensional profile data.
2. The method of claim 1, wherein the steel structure profile template includes a plurality of second corner points and a plurality of second triangles constructed according to the second corner points, and the performing coarse registration on the two-dimensional profile data and a preset steel structure profile template to obtain the first measurement data includes:
acquiring a first corner point of the two-dimensional contour data;
constructing a plurality of first triangles corresponding to the first corner points;
performing matching calculation on the first triangle and the second triangle to obtain a rotation matrix and a translation vector;
and converting the rotation matrix and the translation vector to obtain first measurement data.
3. The method of claim 2, wherein the acquiring the first angle point of the two-dimensional profile data comprises:
Acquiring a plurality of adjacent points of the two-dimensional contour data;
connecting the plurality of adjacent points with the two-dimensional profile data to obtain a plurality of edges;
acquiring an included angle formed between every two sides from the plurality of sides, wherein the included angle comprises an angle value;
and taking the two-dimensional profile data corresponding to the included angle which accords with the preset angle value as a first corner point.
4. The method of claim 2, wherein said matching the first triangle and the second triangle to obtain a rotation matrix and a translation vector comprises:
obtaining a plurality of similar triangles matched with the first triangle from the second triangle;
calculating an initial rotation matrix and an initial translation vector of coincidence of corresponding points between every two similar triangles;
acquiring a plurality of registration errors according to the initial rotation matrix and the initial translation vector;
and determining the minimum registration error from the plurality of registration errors, and taking an initial rotation matrix and an initial translation vector corresponding to the minimum registration error as a final rotation matrix and a translation vector.
5. The utility model provides a steel construction deformation detection device which characterized in that, steel construction deformation detection device includes:
The acquisition module is used for acquiring three-dimensional point cloud data of the steel structure;
the extraction module is used for extracting the two-dimensional profile data of the steel structure according to the three-dimensional point cloud data;
the extracting the two-dimensional profile data of the steel structure according to the three-dimensional point cloud data comprises the following steps:
determining the extending direction of the steel structure according to the three-dimensional point cloud data of the steel structure;
determining bounding box data of the steel structure from the three-dimensional point cloud data of the steel structure;
extracting two-dimensional profile data of the steel structure from the bounding box data according to the extending direction;
wherein, the determining the extending direction of the steel structure according to the three-dimensional point cloud data of the steel structure comprises:
determining centroid data of the three-dimensional point cloud data from the three-dimensional point cloud data of the steel structure;
constructing a covariance matrix according to the three-dimensional point cloud data and the centroid data;
determining the extending direction of the steel structure according to the covariance matrix;
wherein the extracting the two-dimensional profile data of the steel structure from the bounding box data according to the extending direction includes:
determining a cross section corresponding to the bounding box data according to the extending direction and the centroid data;
According to the distance from the bounding box data to the cross section, bounding box data corresponding to the distance conforming to a preset distance interval are used as cross section data;
projecting the cross-sectional data to the cross-section to obtain two-dimensional profile data;
the coarse registration module is used for performing coarse registration on the two-dimensional profile data and a preset steel structure profile template to obtain first measurement data;
the fine registration module is used for carrying out fine registration on the first measurement data according to an iterative closest point algorithm so as to obtain a second measurement quantity;
and the calculation module is used for calculating the minimum distance error from the second measurement data to the steel structure profile template so as to determine the deformation quantity of the steel structure.
6. A computer device comprising a memory and a processor, the memory having stored therein a computer program, the processor, when executing the computer program, implementing the steps of the steel structure deformation detection method of any one of claims 1 to 4.
7. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when executed by a processor, implements the steps of the steel structure deformation detection method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210491706.7A CN114841965B (en) | 2022-04-30 | 2022-04-30 | Steel structure deformation detection method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210491706.7A CN114841965B (en) | 2022-04-30 | 2022-04-30 | Steel structure deformation detection method and device, computer equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114841965A CN114841965A (en) | 2022-08-02 |
| CN114841965B true CN114841965B (en) | 2023-08-01 |
Family
ID=82567011
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210491706.7A Active CN114841965B (en) | 2022-04-30 | 2022-04-30 | Steel structure deformation detection method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114841965B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114596525A (en) * | 2022-03-03 | 2022-06-07 | 合肥工业大学 | Dynamic bridge form identification method based on computer vision |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102564347A (en) * | 2011-12-30 | 2012-07-11 | 中国科学院上海光学精密机械研究所 | Object three-dimensional outline measuring device and method based on Dammann grating |
| CN105852971A (en) * | 2016-05-04 | 2016-08-17 | 苏州点合医疗科技有限公司 | Registration navigation method based on skeleton three-dimensional point cloud |
| CN106600690A (en) * | 2016-12-30 | 2017-04-26 | 厦门理工学院 | Complex building three-dimensional modeling method based on point cloud data |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106022210A (en) * | 2016-05-04 | 2016-10-12 | 成都指码科技有限公司 | Vein profile three-dimensional point cloud matching identity identifying method and device |
| CN111598823B (en) * | 2020-05-19 | 2023-07-25 | 北京数字绿土科技股份有限公司 | Multisource mobile measurement point cloud data space-ground integration method and storage medium |
| CN112669359B (en) * | 2021-01-14 | 2023-05-26 | 武汉理工大学 | Three-dimensional point cloud registration method, device, equipment and storage medium |
| CN112902874B (en) * | 2021-01-19 | 2022-09-27 | 中国汽车工程研究院股份有限公司 | Image acquisition device and method, image processing method and device and image processing system |
| CN114332212B (en) * | 2022-03-11 | 2022-06-07 | 中国铁路设计集团有限公司 | Track superelevation and front-back height detection method based on vehicle-mounted mobile laser point cloud |
-
2022
- 2022-04-30 CN CN202210491706.7A patent/CN114841965B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102564347A (en) * | 2011-12-30 | 2012-07-11 | 中国科学院上海光学精密机械研究所 | Object three-dimensional outline measuring device and method based on Dammann grating |
| CN105852971A (en) * | 2016-05-04 | 2016-08-17 | 苏州点合医疗科技有限公司 | Registration navigation method based on skeleton three-dimensional point cloud |
| CN106600690A (en) * | 2016-12-30 | 2017-04-26 | 厦门理工学院 | Complex building three-dimensional modeling method based on point cloud data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114841965A (en) | 2022-08-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108764048B (en) | Face key point detection method and device | |
| CN111508021B (en) | Pose determining method and device, storage medium and electronic equipment | |
| Bai et al. | Polyline approach for approximating Hausdorff distance between planar free-form curves | |
| EP3937077B1 (en) | Lane marking detecting method, apparatus, electronic device, storage medium, and vehicle | |
| CN111459269B (en) | Augmented reality display method, system and computer readable storage medium | |
| CN110599582B (en) | Rapid algorithm of rectangular object bounding box | |
| CN114841965B (en) | Steel structure deformation detection method and device, computer equipment and storage medium | |
| CN112990010A (en) | Point cloud data processing method and device, computer equipment and storage medium | |
| CN114863060A (en) | Point cloud-based three-dimensional model reconstruction method, device, equipment and storage medium | |
| CN112683169A (en) | Object size measuring method, device, equipment and storage medium | |
| CN115457492A (en) | Target detection method and device, computer equipment and storage medium | |
| JP2014106725A (en) | Point group analyzer, point group analysis method and point group analysis program | |
| CN112733641A (en) | Object size measuring method, device, equipment and storage medium | |
| US10740962B2 (en) | Method and apparatus for uncertainty modeling of point cloud | |
| CN116844124A (en) | Three-dimensional object detection frame labeling method, three-dimensional object detection frame labeling device, electronic equipment and storage medium | |
| CN114266876A (en) | Positioning method, visual map generation method and device | |
| Huang et al. | Circle detection and fitting using laser range finder for positioning system | |
| CN117392735B (en) | Face data processing method, device, computer equipment and storage medium | |
| Lomov et al. | Dynamic programming for curved reflection symmetry detection in segmented images | |
| CN115655128A (en) | Steel structure deformation positioning method and device, computer equipment and storage medium | |
| CN116109685B (en) | Part point cloud registration method, device, equipment and medium | |
| CN117314917B (en) | Bridge crack detection method and device, computer equipment and storage medium | |
| CN117272489B (en) | Monitoring method, system and equipment for calculating deformation safety of building curtain wall | |
| CN116883764B (en) | Battery system fault identification method and device | |
| Zhang et al. | 3D vision measurement for small devices based on consumer sensors |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |