A method, device, equipment and storage medium for identifying periodic repeating structure

By acquiring point cloud data of the structure, segmenting and constructing 3D models of substructures, projecting and calculating similarity, the problem of the inability to quickly and accurately identify periodic repeating structures in existing technologies is solved, achieving efficient structure identification and cost reduction.

CN114694135BActive Publication Date: 2024-11-29CHINA RAILWAY CONSTR HEAVY IND
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202210318400.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-03-29
Publication Date
2024-11-29
Estimated Expiration
2042-03-29

AI Technical Summary

Technical Problem

Existing technologies cannot quickly and accurately identify whether a structure is a periodic repeating structure, leading to increased design and production costs.

Method used

By acquiring point cloud data of the structure, extracting the structural outline and segmenting it into sub-structural outlines, constructing 3D models of the sub-structures, projecting them onto multiple projection planes, calculating the similarity between the 3D models of the sub-structures, and determining whether they reach the threshold proportion.

Benefits of technology

It enables rapid and accurate identification of repetitive structures, improving operational efficiency and reducing design and production costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114694135B_ABST
    Figure CN114694135B_ABST
Patent Text Reader

Abstract

The present application discloses a method, device, equipment and storage medium for identifying a periodic repetitive structure, the method comprising: obtaining point cloud data of a structure to be identified; extracting a structural outline according to the point cloud data, and dividing the structural outline into a plurality of substructure outlines; constructing a substructure three-dimensional model corresponding to each substructure outline; establishing a plurality of projection planes, and projecting the substructure three-dimensional model onto each projection plane respectively; calculating the similarity between each substructure three-dimensional model; judging whether the structure to be identified is a periodic repetitive structure according to the proportion of the similarity between each substructure three-dimensional model reaching a threshold. This fully takes into account the characteristics of the structure, has a small amount of data processing, a fast calculation speed, and can effectively and accurately identify periodic repetitive structures, thereby guiding design and production, effectively improving operating efficiency, reducing costs, and avoiding repeated design.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of automated production technology, and in particular to a method, device, equipment and storage medium for identifying a periodic repeating structure. Background Art

[0002] In the process of structural production, the successful application of structural automated manufacturing workstations has greatly improved the automation level of structural welding. A large number of periodic repetitive structures are produced or applied in the manufacturing workstation. For example, in the construction of large ships, there are many box-type structures, some of which are expected to be repeated periodically in the manufacturing process without any errors or defects. However, since the sizes of the box-type structures are not exactly the same, it is currently impossible to quickly and accurately identify whether each box-type structure is a periodic repetitive structure, which has a great impact on the subsequent guidance of design and production, and increases costs.

[0003] Therefore, how to quickly and accurately identify a structure and determine whether it is a periodic repeating structure is a technical problem that needs to be solved urgently by those skilled in the art. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide a method, device, equipment and storage medium for identifying periodic repeating structures, which can effectively and accurately identify periodic repeating structures, improve work efficiency, reduce costs and avoid repeated design. The specific scheme is as follows:

[0005] A method for identifying a periodic repeating structure, comprising:

[0006] Obtaining point cloud data of the structure to be identified;

[0007] Extracting a structural contour according to the point cloud data, and dividing the structural contour into a plurality of sub-structural contours;

[0008] Constructing a substructure three-dimensional model corresponding to each of the substructure contours;

[0009] Establishing a plurality of projection planes, and projecting the substructure three-dimensional model onto each of the projection planes respectively;

[0010] Calculating the similarity between the three-dimensional models of the substructures;

[0011] According to the proportion of similarities between the substructure three-dimensional models reaching a threshold, it is determined whether the structure to be identified is a periodic repeating structure.

[0012] Preferably, in the above-mentioned periodic repeating structure recognition method provided by the embodiment of the present invention, multiple projection planes are established, and the substructure three-dimensional model is projected onto each of the projection planes respectively, including:

[0013] Establish four projection planes; the four projection planes are respectively a first plane parallel to the upper surface, a second plane parallel to the bottom surface, a third plane passing through the center of the upper surface and perpendicular to the bottom surface, and a fourth plane passing through the center of the upper surface and perpendicular to the second plane and the third plane;

[0014] Projecting the substructure three-dimensional model onto the first plane to obtain a first comparison model;

[0015] Projecting the substructure three-dimensional model onto the second plane to obtain a second comparison model;

[0016] Projecting the substructure three-dimensional model onto the third plane to obtain a third comparison model;

[0017] The substructure three-dimensional model is projected onto the fourth plane to obtain a fourth comparison model.

[0018] Preferably, in the above-mentioned periodic repeating structure recognition method provided by the embodiment of the present invention, calculating the similarity between the three-dimensional models of the substructures includes:

[0019] Calculating a first similarity between each of the first comparison models;

[0020] Calculating a second similarity between each of the second comparison models;

[0021] Calculating a third similarity between the third comparison models;

[0022] Calculating a fourth similarity between the fourth comparison models;

[0023] The similarity between the substructure three-dimensional models is calculated according to the first similarity, the second similarity, the third similarity and the fourth similarity, and the weights in the substructure similarity.

[0024] Preferably, in the above-mentioned periodic repetitive structure recognition method provided by the embodiment of the present invention, extracting the structure contour according to the point cloud data includes:

[0025] The point cloud data is processed using a filtering algorithm to remove outliers and extract structure contours.

[0026] Preferably, in the above-mentioned periodic repetitive structure recognition method provided by an embodiment of the present invention, dividing the structure contour into a plurality of substructure contours comprises:

[0027] Extracting the interface according to the point cloud data;

[0028] The structure contour is divided into a plurality of sub-structure contours according to the interface.

[0029] Preferably, in the above-mentioned periodic repeating structure recognition method provided by the embodiment of the present invention, constructing a substructure three-dimensional model corresponding to each substructure contour includes:

[0030] Extracting characteristic points of each substructure contour;

[0031] A coordinate system is established with the extracted feature points as the coordinate origin, and each substructure outline is converted into a corresponding substructure three-dimensional model.

[0032] Preferably, in the above-mentioned periodic repeating structure recognition method provided by an embodiment of the present invention, judging whether the structure to be recognized is a periodic repeating structure according to the proportion of similarities between the three-dimensional models of the substructures reaching a threshold value includes:

[0033] Determine whether the proportion of the similarities between the three-dimensional models of the substructures reaching the threshold exceeds a set value;

[0034] If yes, it is determined that the structure to be identified is a periodic repeating structure;

[0035] If not, it is determined that the structure to be identified is not a periodic repeating structure.

[0036] The embodiment of the present invention further provides a device for identifying a periodic repetitive structure, comprising:

[0037] A data acquisition module, used to acquire point cloud data of the structure to be identified;

[0038] A data processing module, used for extracting a structural outline according to the point cloud data, and dividing the structural outline into a plurality of sub-structure outlines;

[0039] A model building module, used to build a substructure three-dimensional model corresponding to each substructure outline;

[0040] A projection module, used to establish multiple projection planes, and project the substructure three-dimensional model onto each of the projection planes respectively;

[0041] A similarity calculation module, used for calculating the similarity between the substructure three-dimensional models;

[0042] The structure recognition module is used to determine whether the structure to be recognized is a periodic repeating structure according to the proportion of similarities between the substructure three-dimensional models reaching a threshold.

[0043] An embodiment of the present invention further provides a device for identifying a periodic repetitive structure, comprising a processor and a memory, wherein when the processor executes a computer program stored in the memory, the method for identifying a periodic repetitive structure as provided in the embodiment of the present invention is implemented.

[0044] An embodiment of the present invention further provides a computer-readable storage medium for storing a computer program, wherein when the computer program is executed by a processor, the method for identifying a periodic repetitive structure as provided in the embodiment of the present invention is implemented.

[0045] It can be seen from the above technical scheme that a method for identifying a periodic repeating structure provided by the present invention includes: obtaining point cloud data of a structure to be identified; extracting a structure contour based on the point cloud data, and dividing the structure contour into a plurality of substructure contours; constructing a substructure three-dimensional model corresponding to each substructure contour; establishing a plurality of projection planes, and projecting the substructure three-dimensional model onto each projection plane respectively; calculating the similarity between each substructure three-dimensional model; and judging whether the structure to be identified is a periodic repeating structure based on the proportion of the similarities between each substructure three-dimensional model reaching a threshold.

[0046] The above-mentioned periodic repeating structure recognition method provided by the present invention extracts point cloud information of the structure and obtains structural information, and only uses one dimension as a calculation parameter. Compared with the traditional method, there is no need to calculate the color, texture and other characteristics of the structure, the calculation process is simple, and the amount of information processing is reduced; in addition, the structure is divided into substructures, and the similarity of the substructures is calculated based on the three-dimensional model of the substructure to determine whether the structure is a periodic repeating structure. This fully takes into account the characteristics of the structure, has a small amount of data processing, and a fast calculation speed. It can effectively and accurately identify periodic repeating structures, thereby guiding design and production, effectively improving work efficiency, reducing costs, and avoiding repeated design.

[0047] In addition, the present invention also provides corresponding devices, equipment and computer-readable storage media for the method of identifying periodic repetitive structures, further making the above method more practical. The device, equipment and computer-readable storage medium have corresponding advantages. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or related technologies, the drawings required for use in the embodiments or related technical descriptions are briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0049] Figure 1 A flowchart of a method for identifying a periodic repeating structure provided by an embodiment of the present invention;

[0050] Figure 2 A schematic diagram of a box-type structure provided by an embodiment of the present invention;

[0051] Figure 3 A schematic diagram of a three-dimensional model of a substructure provided in an embodiment of the present invention;

[0052] Figure 4 A schematic diagram of the structure of a device for identifying a periodic repeating structure provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] The present invention provides a method for identifying a periodic repeating structure. Figure 1 As shown, the following steps are included:

[0055] S101, obtaining point cloud data of a structure to be identified;

[0056] Specifically, the structure to be identified is scanned to obtain point cloud data of the structure. The point cloud data reflects the contour parameter information of the workpiece, and the parameter information can be stored in the control system. Figure 2 For example, when the structure to be identified is a box-type structure, the box-type structure is scanned in a certain order to obtain the point cloud information of the box-type structure.

[0057] S102, extracting a structural contour according to the point cloud data, and dividing the structural contour into a plurality of sub-structural contours;

[0058] It should be noted that a structure is often composed of many substructures, and there is a certain degree of connection between the substructures. In the present invention, the structure can be converted into substructures by edge detection and fitting, and the substructures can be compared for similarity to identify the structure.

[0059] S103, constructing a substructure three-dimensional model corresponding to each substructure outline;

[0060] S104, establishing multiple projection planes, and projecting the substructure three-dimensional model onto each projection plane respectively;

[0061] In practical applications, when the structure to be identified is a box-shaped structure, there can be four projection planes, and the substructure 3D model is projected onto the four projection planes respectively. If there are five projection planes, the substructure 3D model is projected onto the five projection planes respectively, and so on.

[0062] S105, calculating the similarity between the three-dimensional models of each substructure;

[0063] Specifically, the present invention only needs to compare multiple projections (such as four projections) of the substructure model to describe the similarity of the substructure, which greatly simplifies the amount of calculation.

[0064] S106 , judging whether the structure to be identified is a periodic repeating structure according to the proportion of similarities between the three-dimensional models of the substructures reaching the threshold, so as to complete the identification of the periodic repeating structure.

[0065] In the above-mentioned periodic repeating structure recognition method provided by an embodiment of the present invention, point cloud information of the structure is extracted to obtain structural information, and only one dimension is used as a calculation parameter. Compared with the traditional method, there is no need to calculate the color, texture and other characteristics of the structure, the calculation process is simple, and the amount of information processing is reduced; in addition, the structure is divided into substructures, and the similarity of the substructures is calculated based on the three-dimensional model of the substructure to determine whether the structure is a periodic repeating structure. This fully takes into account the characteristics of the structure, has a small amount of data processing, and a fast calculation speed. It can effectively and accurately identify periodic repeating structures, thereby guiding design and production, effectively improving work efficiency, reducing costs, and avoiding repeated design.

[0066] Since point cloud data contains a lot of noise, there are many interferences to the extraction of contours, and it must be processed to obtain the true contour of the structure. In specific implementation, in the above-mentioned periodic repetitive structure recognition method provided in an embodiment of the present invention, step S102 extracts the structural contour based on the point cloud data, which can specifically include: using a filtering algorithm (such as arithmetic mean filtering method) to process the point cloud data, remove outliers, and extract the structural contour. In this way, the interference signal can be removed and fitted into the structural contour.

[0067] In a specific implementation, in the above-mentioned periodic repetitive structure recognition method provided in an embodiment of the present invention, step S102 divides the structure contour into multiple sub-structure contours, which may specifically include: first, extracting the boundary surface based on the point cloud data; then, dividing the structure contour into multiple sub-structure contours based on the boundary surface.

[0068] Specifically, Figure 2 As shown in Figure 2, the interface can be extracted based on the point cloud data or the box-shaped structure contour; M 1 、M 2 、M 3 ……M n . According to the outline and interface of the structure, the structure is divided into substructures a 1 、a 2 、a 3 ……a n .

[0069] In specific implementation, in the above-mentioned periodic repetitive structure recognition method provided in an embodiment of the present invention, step S103 constructs a substructure three-dimensional model corresponding to each substructure contour, which may specifically include: extracting feature points of each substructure contour; establishing a coordinate system with the extracted feature points as the coordinate origin, and converting each substructure contour into a corresponding substructure three-dimensional model.

[0070] Specifically, Figure 2 As shown, according to the distribution characteristics of adjacent substructures, the feature points O of each substructure are extracted. 1 , O 2 , O 3 ...O n For example, the substructures of the embodiment of the present invention are linearly distributed in the structure, so the inner end point of the bottom surface of the substructure is taken as the feature point. 1 , O 2 , O 3 ...O n A coordinate system is established for the coordinate origin, and the substructure outline is converted into a substructure three-dimensional model; wherein, the establishment of each coordinate system should be unified.

[0071] In the specific implementation, in the above-mentioned periodic repeating structure recognition method provided by the embodiment of the present invention, step S104 establishes multiple projection planes, and projects the substructure three-dimensional model onto each projection plane respectively, which may specifically include: first, establishing four projection planes; Figure 3 As shown, the four projection planes are the first plane p parallel to the upper surface 1 , the second plane parallel to the bottom surface 4 , a third plane p passing through the center of the upper surface and perpendicular to the bottom surface 2 , passing through the center of the upper surface and perpendicular to the second plane p 4 and the third plane p 2 The fourth plane p 3 ; Then, the substructure three-dimensional model is projected onto the first plane p 1 , obtain the first comparison model; project the substructure three-dimensional model onto the second plane p 4 , get the second comparison model; project the substructure three-dimensional model onto the third plane p 2 , and obtain the third comparison model; project the substructure three-dimensional model onto the fourth plane p 3 Next, the similarity between the three-dimensional models of the substructures can be calculated based on the first comparison model, the second comparison model, the third comparison model and the fourth comparison model.

[0072] It should be noted that these four projection planes can already reflect the basic outline of the substructure, and there is no need to construct projection planes again, which increases the difficulty of comparison and the amount of calculation.

[0073] Further, in a specific implementation, in the above-mentioned periodic repetitive structure recognition method provided in an embodiment of the present invention, step S105 calculates the similarity between each substructure three-dimensional model, which may specifically include: first, calculating in sequence the first similarity between each first comparison model, the second similarity between each second comparison model, the third similarity between each third comparison model, and the fourth similarity between each fourth comparison model; then, calculating the similarity between each substructure three-dimensional model based on the first similarity, the second similarity, the third similarity and the fourth similarity, as well as the weights occupied in the substructure similarity.

[0074] Specifically, firstly, the first similarity between the first comparison models corresponding to each substructure three-dimensional model is calculated.

[0075]

[0076] Among them, a 12 For substructure a 1 The first comparison model with substructure a 2 The first similarity of the first comparison model, a 13 For substructure a 1 The first comparison model with substructure a 3 The first similarity of the first comparison model, a 1j For substructure a 1 The first comparison model with substructure a j The first similarity of the first comparison model, ..., a ij For substructure a i The first comparison model with substructure a j The first similarity of the first comparison model is constructed based on this. ij ).

[0077] Similarly, construct the similarity matrix g(b ij ), the similarity matrix g(c ij ), the similarity matrix g(d ij ).

[0078] Further, the similarity between each substructure is calculated based on the product of the comparison model similarity and the weight in the substructure model similarity. i ,a j ). In this way, the four projections of the substructure three-dimensional model are compared without comparing the entire structure, which greatly simplifies the calculation process and improves the efficiency of structure recognition.

[0079] In specific implementation, in the above-mentioned periodic repeating structure identification method provided in an embodiment of the present invention, step S106 determines whether the structure to be identified is a periodic repeating structure based on the proportion of the similarities between the three-dimensional models of each substructure reaching the threshold. Specifically, it may include: determining whether the proportion of the similarities between the three-dimensional models of each substructure reaching the threshold exceeds a set value; if so, determining that the structure to be identified is a periodic repeating structure; if not, determining that the structure to be identified is not a periodic repeating structure.

[0080] Specifically, according to the similarity of the substructures, the substructure similarity matrix F is constructed ij :

[0081]

[0082] A similarity threshold is set. If the ratio of the similarity of each substructure reaching the threshold to the total exceeds the set value, the overall structure is a periodic repeating structure; otherwise, the overall structure is not a periodic repeating structure.

[0083] It should be pointed out that the above-mentioned periodic repeating structure recognition method provided in the embodiment of the present invention is also applicable to the recognition of other structures, which will not be described in detail here.

[0084] Based on the same inventive concept, an embodiment of the present invention also provides a device for identifying a periodic repeating structure. Since the principle of solving the problem by the device is similar to that of the aforementioned method for identifying a periodic repeating structure, the implementation of the device can refer to the implementation of the method for identifying a periodic repeating structure, and the repeated parts will not be repeated here.

[0085] In specific implementation, the periodic repetitive structure recognition device provided by the embodiment of the present invention is as follows: Figure 4 As shown, specifically including:

[0086] A data acquisition module 11 is used to acquire point cloud data of the structure to be identified;

[0087] The data processing module 12 is used to extract the structure contour according to the point cloud data, and divide the structure contour into a plurality of sub-structure contours;

[0088] A model building module 13 is used to build a substructure three-dimensional model corresponding to each substructure outline;

[0089] A projection module 14 is used to establish multiple projection planes and project the substructure three-dimensional model onto each projection plane;

[0090] A similarity calculation module 15 is used to calculate the similarity between the three-dimensional models of each substructure;

[0091] The structure recognition module 16 is used to determine whether the structure to be recognized is a periodic repeating structure according to the proportion of similarities between the three-dimensional models of the substructures reaching a threshold.

[0092] It should be noted that the data acquisition module 11 can be an information acquisition system, including but not limited to cameras and laser sensors, for the purpose of collecting complete, clear and stable data, obtaining the characteristics of the structure to be identified, and providing parameter information for subsequent structure modeling and identification; the parameter information refers to the structural point cloud information obtained by the scanning system. The data processing module 12 and the model building module 13 can form an information processing system; the projection module 14, the similarity calculation module 15 and the structure recognition module 16 can form a control system.

[0093] In the above-mentioned periodic repeating structure identification device provided in the embodiment of the present invention, the point cloud information of the structure can be extracted and the structural information can be obtained through the interaction of the above-mentioned six modules. Only one dimension is used as a calculation parameter. Compared with the traditional method, there is no need to calculate the color, texture and other characteristics of the structure, the calculation process is simple, and the amount of information processing is reduced; in addition, the structure is divided into substructures, and the similarity of the substructures is calculated based on the three-dimensional model of the substructure to determine whether the structure is a periodic repeating structure. This fully takes into account the characteristics of the structure, has a small amount of data processing, and a fast calculation speed. It can effectively and accurately identify periodic repeating structures, thereby guiding design and production, effectively improving work efficiency, reducing costs, and avoiding repeated design.

[0094] Furthermore, in the above-mentioned periodic repetitive structure identification device provided by the embodiment of the present invention, the data processing module 12 may include:

[0095] An information preprocessing unit is used to process the point cloud data using a filtering algorithm, remove outliers, and obtain preprocessing information;

[0096] A feature extraction unit, used to fit the obtained preprocessing information and extract the structural contour;

[0097] The contour segmentation unit is used to extract the interface according to the point cloud data, and to segment the structure contour into multiple sub-structure contours according to the interface.

[0098] For more specific working processes of the above modules and units, please refer to the corresponding contents disclosed in the above embodiments, which will not be repeated here.

[0099] Correspondingly, an embodiment of the present invention further discloses a device for identifying a periodic repetitive structure, comprising a processor and a memory; wherein the processor implements the method for identifying a periodic repetitive structure disclosed in the above embodiment when executing a computer program stored in the memory.

[0100] For more specific processes of the above method, please refer to the corresponding contents disclosed in the aforementioned embodiments, which will not be repeated here.

[0101] Furthermore, the present invention also discloses a computer-readable storage medium for storing a computer program; when the computer program is executed by a processor, the method for identifying a periodic repetitive structure disclosed above is implemented.

[0102] For more specific processes of the above method, please refer to the corresponding contents disclosed in the aforementioned embodiments, which will not be repeated here.

[0103] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the devices, equipment, and storage media disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method part.

[0104] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0105] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0106] In summary, an embodiment of the present invention provides a method for identifying a periodic repeating structure, including: obtaining point cloud data of a structure to be identified; extracting a structure outline according to the point cloud data, and dividing the structure outline into a plurality of substructure outlines; constructing a substructure three-dimensional model corresponding to each substructure outline; establishing a plurality of projection planes, and projecting the substructure three-dimensional model onto each projection plane respectively; calculating the similarity between each substructure three-dimensional model; judging whether the structure to be identified is a periodic repeating structure according to the proportion of the similarity between each substructure three-dimensional model reaching a threshold. The present invention extracts point cloud information of the structure, obtains structural information, and only uses one dimension as a calculation parameter. Compared with the traditional method, there is no need to calculate the color, texture and other features of the structure, the calculation process is simple, and the amount of information processing is reduced; in addition, the structure is divided into substructures, and the similarity of the substructures is calculated from the substructure three-dimensional model to judge whether the structure is a periodic repeating structure. In this way, the characteristics of the structure are fully considered, the data processing amount is small, the calculation speed is fast, and the periodic repeating structure can be effectively and accurately identified, thereby guiding design and production, effectively improving work efficiency, reducing costs, and avoiding repeated design. In addition, the present invention also provides corresponding devices, equipment and computer-readable storage media for the method of identifying periodic repetitive structures, further making the above method more practical. The device, equipment and computer-readable storage medium have corresponding advantages.

[0107] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0108] The above is a detailed introduction to the periodic repetitive structure recognition method, device, equipment and storage medium provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for general technical personnel in this field, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A method for identifying periodic repeating structures. It is characterized in that include: Obtaining point cloud data of the structure to be identified; Extracting a structural contour according to the point cloud data, and dividing the structural contour into a plurality of sub-structural contours; Constructing a substructure three-dimensional model corresponding to each of the substructure contours; Establish four projection planes; the four projection planes are respectively a first plane parallel to the upper surface, a second plane parallel to the bottom surface, a third plane passing through the center of the upper surface and perpendicular to the bottom surface, and a fourth plane passing through the center of the upper surface and perpendicular to the second plane and the third plane; project the substructure three-dimensional model onto the first plane to obtain a first comparison model; project the substructure three-dimensional model onto the second plane to obtain a second comparison model; project the substructure three-dimensional model onto the third plane to obtain a third comparison model; project the substructure three-dimensional model onto the fourth plane to obtain a fourth comparison model; Calculating a first similarity between each of the first comparison models; calculating a second similarity between each of the second comparison models; calculating a third similarity between each of the third comparison models; calculating a fourth similarity between each of the fourth comparison models; calculating the similarity between each of the substructure three-dimensional models according to the first similarity, the second similarity, the third similarity and the fourth similarity, and the weights thereof in the substructure similarity; According to the proportion of similarities between the substructure three-dimensional models reaching a threshold, it is determined whether the structure to be identified is a periodic repeating structure.

2. The method for identifying a periodic repeating structure according to claim 1, It is characterized in that Extracting a structure contour according to the point cloud data includes: The point cloud data is processed using a filtering algorithm to remove outliers and extract structure contours.

3. The method for identifying a periodic repeating structure according to claim 1, It is characterized in that The structural contour is divided into a plurality of sub-structural contours, including: Extracting the interface according to the point cloud data; The structure contour is divided into a plurality of sub-structure contours according to the interface.

4. The method for identifying a periodic repeating structure according to claim 1, It is characterized in that Constructing a substructure three-dimensional model corresponding to each of the substructure contours, including: Extracting characteristic points of each substructure contour; A coordinate system is established with the extracted feature points as the coordinate origin, and each substructure outline is converted into a corresponding substructure three-dimensional model.

5. The method for identifying a periodic repeating structure according to claim 1, It is characterized in that According to the proportion of similarities between the three-dimensional models of the substructures reaching a threshold, judging whether the structure to be identified is a periodic repeating structure includes: Determine whether the proportion of the similarities between the three-dimensional models of the substructures reaching the threshold exceeds a set value; If yes, it is determined that the structure to be identified is a periodic repeating structure; If not, it is determined that the structure to be identified is not a periodic repeating structure.

6. A device for identifying a periodic repeating structure, It is characterized in that include: A data acquisition module, used to acquire point cloud data of the structure to be identified; A data processing module, used for extracting a structural outline according to the point cloud data, and dividing the structural outline into a plurality of sub-structure outlines; A model building module, used to build a substructure three-dimensional model corresponding to each substructure outline; A projection module is used to establish four projection planes; the four projection planes are respectively a first plane parallel to the upper surface, a second plane parallel to the bottom surface, a third plane passing through the center of the upper surface and perpendicular to the bottom surface, and a fourth plane passing through the center of the upper surface and perpendicular to the second plane and the third plane; the substructure three-dimensional model is projected onto the first plane to obtain a first comparison model; the substructure three-dimensional model is projected onto the second plane to obtain a second comparison model; the substructure three-dimensional model is projected onto the third plane to obtain a third comparison model; the substructure three-dimensional model is projected onto the fourth plane to obtain a fourth comparison model; A similarity calculation module, used for calculating the first similarity between the first comparison models; calculating the second similarity between the second comparison models; calculating the third similarity between the third comparison models; calculating the fourth similarity between the fourth comparison models; and calculating the similarity between the substructure three-dimensional models according to the first similarity, the second similarity, the third similarity and the fourth similarity, and the weights in the substructure similarity; The structure recognition module is used to determine whether the structure to be recognized is a periodic repeating structure according to the proportion of similarities between the substructure three-dimensional models reaching a threshold.

7. A device for identifying a periodic repeating structure, It is characterized in that The method comprises a processor and a memory, wherein the processor implements the method for identifying a periodic repetitive structure according to any one of claims 1 to 5 when executing a computer program stored in the memory.

8. A computer-readable storage medium, It is characterized in that Used to store a computer program, wherein when the computer program is executed by a processor, the method for identifying a periodic repetitive structure according to any one of claims 1 to 5 is implemented.

Citation Information

Patent Citations

  • Identification and space positioning method based on target two-dimensional contour model

    CN107622499A

  • A target recognition method based on the spatial relationship of contour segments

    CN109299720A